diff --git a/.github/workflows/cla.yml b/.github/workflows/cla.yml index a9b57b3a02..1edf59bb44 100644 --- a/.github/workflows/cla.yml +++ b/.github/workflows/cla.yml @@ -26,7 +26,7 @@ jobs: steps: - name: CLA Assistant if: (github.event.comment.body == 'recheck' || github.event.comment.body == 'I have read the CLA Document and I sign the CLA') || github.event_name == 'pull_request_target' - uses: contributor-assistant/github-action@v2.5.1 + uses: contributor-assistant/github-action@v2.5.2 env: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # Must be repository secret PAT diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml index 290122531e..02bc506a14 100644 --- a/.github/workflows/docs.yml +++ b/.github/workflows/docs.yml @@ -48,7 +48,7 @@ jobs: continue-on-error: true run: ruff check --fix --unsafe-fixes --select D --ignore=D100,D104,D203,D205,D212,D213,D401,D406,D407,D413 . - name: Update Docs Reference Section and Push Changes - if: github.event_name == 'pull_request_target' + continue-on-error: true run: | python docs/build_reference.py git pull origin ${{ github.head_ref || github.ref }} @@ -68,7 +68,7 @@ jobs: python docs/build_docs.py - name: Commit and Push Docs changes continue-on-error: true - if: always() && github.event_name == 'pull_request_target' + if: always() run: | git pull origin ${{ github.head_ref || github.ref }} git add --update # only add updated files diff --git a/docs/en/datasets/classify/caltech101.md b/docs/en/datasets/classify/caltech101.md index b50a51916b..51faa4957c 100644 --- a/docs/en/datasets/classify/caltech101.md +++ b/docs/en/datasets/classify/caltech101.md @@ -22,7 +22,7 @@ Unlike many other datasets, the Caltech-101 dataset is not formally split into t ## Applications -The Caltech-101 dataset is extensively used for training and evaluating deep learning models in object recognition tasks, such as Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and various other machine learning algorithms. Its wide variety of categories and high-quality images make it an excellent dataset for research and development in the field of machine learning and computer vision. +The Caltech-101 dataset is extensively used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in object recognition tasks, such as [Convolutional Neural Networks](https://www.ultralytics.com/glossary/convolutional-neural-network-cnn) (CNNs), Support Vector Machines (SVMs), and various other machine learning algorithms. Its wide variety of categories and high-quality images make it an excellent dataset for research and development in the field of machine learning and [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv). ## Usage @@ -84,11 +84,11 @@ We would like to acknowledge Li Fei-Fei, Rob Fergus, and Pietro Perona for creat ### What is the Caltech-101 dataset used for in machine learning? -The [Caltech-101](https://data.caltech.edu/records/mzrjq-6wc02) dataset is widely used in machine learning for object recognition tasks. It contains around 9,000 images across 101 categories, providing a challenging benchmark for evaluating object recognition algorithms. Researchers leverage it to train and test models, especially Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs), in computer vision. +The [Caltech-101](https://data.caltech.edu/records/mzrjq-6wc02) dataset is widely used in machine learning for object recognition tasks. It contains around 9,000 images across 101 categories, providing a challenging benchmark for evaluating object recognition algorithms. Researchers leverage it to train and test models, especially Convolutional [Neural Networks](https://www.ultralytics.com/glossary/neural-network-nn) (CNNs) and [Support Vector Machines](https://www.ultralytics.com/glossary/support-vector-machine-svm) (SVMs), in computer vision. ### How can I train an Ultralytics YOLO model on the Caltech-101 dataset? -To train an Ultralytics YOLO model on the Caltech-101 dataset, you can use the provided code snippets. For example, to train for 100 epochs: +To train an Ultralytics YOLO model on the Caltech-101 dataset, you can use the provided code snippets. For example, to train for 100 [epochs](https://www.ultralytics.com/glossary/epoch): !!! example "Train Example" @@ -122,7 +122,7 @@ The Caltech-101 dataset includes: - Variable number of images per category, typically between 40 and 800. - Variable image sizes, with most being medium resolution. -These features make it an excellent choice for training and evaluating object recognition models in machine learning and computer vision. +These features make it an excellent choice for training and evaluating object recognition models in [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and computer vision. ### Why should I cite the Caltech-101 dataset in my research? diff --git a/docs/en/datasets/classify/caltech256.md b/docs/en/datasets/classify/caltech256.md index c337721009..de7c2ea461 100644 --- a/docs/en/datasets/classify/caltech256.md +++ b/docs/en/datasets/classify/caltech256.md @@ -16,7 +16,7 @@ The [Caltech-256](https://data.caltech.edu/records/nyy15-4j048) dataset is an ex allowfullscreen>
- Watch: How to Train Image Classification Model using Caltech-256 Dataset with Ultralytics HUB + Watch: How to Train [Image Classification](https://www.ultralytics.com/glossary/image-classification) Model using Caltech-256 Dataset with Ultralytics HUB

## Key Features @@ -33,7 +33,7 @@ Like Caltech-101, the Caltech-256 dataset does not have a formal split between t ## Applications -The Caltech-256 dataset is extensively used for training and evaluating deep learning models in object recognition tasks, such as Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and various other machine learning algorithms. Its diverse set of categories and high-quality images make it an invaluable dataset for research and development in the field of machine learning and computer vision. +The Caltech-256 dataset is extensively used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in object recognition tasks, such as [Convolutional Neural Networks](https://www.ultralytics.com/glossary/convolutional-neural-network-cnn) (CNNs), Support Vector Machines (SVMs), and various other machine learning algorithms. Its diverse set of categories and high-quality images make it an invaluable dataset for research and development in the field of machine learning and [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv). ## Usage @@ -84,7 +84,7 @@ If you use the Caltech-256 dataset in your research or development work, please } ``` -We would like to acknowledge Gregory Griffin, Alex Holub, and Pietro Perona for creating and maintaining the Caltech-256 dataset as a valuable resource for the machine learning and computer vision research community. For more information about the +We would like to acknowledge Gregory Griffin, Alex Holub, and Pietro Perona for creating and maintaining the Caltech-256 dataset as a valuable resource for the [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and computer vision research community. For more information about the Caltech-256 dataset and its creators, visit the [Caltech-256 dataset website](https://data.caltech.edu/records/nyy15-4j048). @@ -96,7 +96,7 @@ The [Caltech-256](https://data.caltech.edu/records/nyy15-4j048) dataset is a lar ### How can I train a YOLO model on the Caltech-256 dataset using Python or CLI? -To train a YOLO model on the Caltech-256 dataset for 100 epochs, you can use the following code snippets. Refer to the model [Training](../../modes/train.md) page for additional options. +To train a YOLO model on the Caltech-256 dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch), you can use the following code snippets. Refer to the model [Training](../../modes/train.md) page for additional options. !!! example "Train Example" @@ -123,10 +123,10 @@ To train a YOLO model on the Caltech-256 dataset for 100 epochs, you can use the The Caltech-256 dataset is widely used for various object recognition tasks such as: -- Training Convolutional Neural Networks (CNNs) -- Evaluating the performance of Support Vector Machines (SVMs) +- Training Convolutional [Neural Networks](https://www.ultralytics.com/glossary/neural-network-nn) (CNNs) +- Evaluating the performance of [Support Vector Machines](https://www.ultralytics.com/glossary/support-vector-machine-svm) (SVMs) - Benchmarking new deep learning algorithms -- Developing object detection models using frameworks like Ultralytics YOLO +- Developing [object detection](https://www.ultralytics.com/glossary/object-detection) models using frameworks like Ultralytics YOLO Its diversity and comprehensive annotations make it ideal for research and development in machine learning and computer vision. @@ -141,6 +141,6 @@ Ultralytics YOLO models offer several advantages for training on the Caltech-256 - **High Accuracy**: YOLO models are known for their state-of-the-art performance in object detection tasks. - **Speed**: They provide real-time inference capabilities, making them suitable for applications requiring quick predictions. - **Ease of Use**: With Ultralytics HUB, users can train, validate, and deploy models without extensive coding. -- **Pretrained Models**: Starting from pretrained models, like `yolov8n-cls.pt`, can significantly reduce training time and improve model accuracy. +- **Pretrained Models**: Starting from pretrained models, like `yolov8n-cls.pt`, can significantly reduce training time and improve model [accuracy](https://www.ultralytics.com/glossary/accuracy). For more details, explore our [comprehensive training guide](../../modes/train.md). diff --git a/docs/en/datasets/classify/cifar10.md b/docs/en/datasets/classify/cifar10.md index 865c80865f..7bae78b38a 100644 --- a/docs/en/datasets/classify/cifar10.md +++ b/docs/en/datasets/classify/cifar10.md @@ -6,7 +6,7 @@ keywords: CIFAR-10, dataset, machine learning, computer vision, image classifica # CIFAR-10 Dataset -The [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html) (Canadian Institute For Advanced Research) dataset is a collection of images used widely for machine learning and computer vision algorithms. It was developed by researchers at the CIFAR institute and consists of 60,000 32x32 color images in 10 different classes. +The [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html) (Canadian Institute For Advanced Research) dataset is a collection of images used widely for [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and computer vision algorithms. It was developed by researchers at the CIFAR institute and consists of 60,000 32x32 color images in 10 different classes.


@@ -16,7 +16,7 @@ The [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html) (Canadian Institute allowfullscreen>
- Watch: How to Train an Image Classification Model with CIFAR-10 Dataset using Ultralytics YOLOv8 + Watch: How to Train an [Image Classification](https://www.ultralytics.com/glossary/image-classification) Model with CIFAR-10 Dataset using Ultralytics YOLOv8

## Key Features @@ -36,7 +36,7 @@ The CIFAR-10 dataset is split into two subsets: ## Applications -The CIFAR-10 dataset is widely used for training and evaluating deep learning models in image classification tasks, such as Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and various other machine learning algorithms. The diversity of the dataset in terms of classes and the presence of color images make it a well-rounded dataset for research and development in the field of machine learning and computer vision. +The CIFAR-10 dataset is widely used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in image classification tasks, such as [Convolutional Neural Networks](https://www.ultralytics.com/glossary/convolutional-neural-network-cnn) (CNNs), Support Vector Machines (SVMs), and various other machine learning algorithms. The diversity of the dataset in terms of classes and the presence of color images make it a well-rounded dataset for research and development in the field of machine learning and computer vision. ## Usage @@ -88,13 +88,13 @@ If you use the CIFAR-10 dataset in your research or development work, please cit } ``` -We would like to acknowledge Alex Krizhevsky for creating and maintaining the CIFAR-10 dataset as a valuable resource for the machine learning and computer vision research community. For more information about the CIFAR-10 dataset and its creator, visit the [CIFAR-10 dataset website](https://www.cs.toronto.edu/~kriz/cifar.html). +We would like to acknowledge Alex Krizhevsky for creating and maintaining the CIFAR-10 dataset as a valuable resource for the machine learning and [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) research community. For more information about the CIFAR-10 dataset and its creator, visit the [CIFAR-10 dataset website](https://www.cs.toronto.edu/~kriz/cifar.html). ## FAQ ### How can I train a YOLO model on the CIFAR-10 dataset? -To train a YOLO model on the CIFAR-10 dataset using Ultralytics, you can follow the examples provided for both Python and CLI. Here is a basic example to train your model for 100 epochs with an image size of 32x32 pixels: +To train a YOLO model on the CIFAR-10 dataset using Ultralytics, you can follow the examples provided for both Python and CLI. Here is a basic example to train your model for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 32x32 pixels: !!! example @@ -138,7 +138,7 @@ This diverse dataset is essential for training image classification models in fi ### Why use the CIFAR-10 dataset for image classification tasks? -The CIFAR-10 dataset is an excellent benchmark for image classification due to its diversity and structure. It contains a balanced mix of 60,000 labeled images across 10 different categories, which helps in training robust and generalized models. It is widely used for evaluating deep learning models, including Convolutional Neural Networks (CNNs) and other machine learning algorithms. The dataset is relatively small, making it suitable for quick experimentation and algorithm development. Explore its numerous applications in the [applications](#applications) section. +The CIFAR-10 dataset is an excellent benchmark for image classification due to its diversity and structure. It contains a balanced mix of 60,000 labeled images across 10 different categories, which helps in training robust and generalized models. It is widely used for evaluating deep learning models, including Convolutional [Neural Networks](https://www.ultralytics.com/glossary/neural-network-nn) (CNNs) and other machine learning algorithms. The dataset is relatively small, making it suitable for quick experimentation and algorithm development. Explore its numerous applications in the [applications](#applications) section. ### How is the CIFAR-10 dataset structured? @@ -170,4 +170,4 @@ Acknowledging the dataset's creators helps support continued research and develo ### What are some practical examples of using the CIFAR-10 dataset? -The CIFAR-10 dataset is often used for training image classification models, such as Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs). These models can be employed in various computer vision tasks including object detection, image recognition, and automated tagging. To see some practical examples, check the code snippets in the [usage](#usage) section. +The CIFAR-10 dataset is often used for training image classification models, such as Convolutional Neural Networks (CNNs) and [Support Vector Machines](https://www.ultralytics.com/glossary/support-vector-machine-svm) (SVMs). These models can be employed in various computer vision tasks including [object detection](https://www.ultralytics.com/glossary/object-detection), [image recognition](https://www.ultralytics.com/glossary/image-recognition), and automated tagging. To see some practical examples, check the code snippets in the [usage](#usage) section. diff --git a/docs/en/datasets/classify/cifar100.md b/docs/en/datasets/classify/cifar100.md index ca868240f7..a6735bbcc4 100644 --- a/docs/en/datasets/classify/cifar100.md +++ b/docs/en/datasets/classify/cifar100.md @@ -6,7 +6,7 @@ keywords: CIFAR-100, dataset, machine learning, computer vision, image classific # CIFAR-100 Dataset -The [CIFAR-100](https://www.cs.toronto.edu/~kriz/cifar.html) (Canadian Institute For Advanced Research) dataset is a significant extension of the CIFAR-10 dataset, composed of 60,000 32x32 color images in 100 different classes. It was developed by researchers at the CIFAR institute, offering a more challenging dataset for more complex machine learning and computer vision tasks. +The [CIFAR-100](https://www.cs.toronto.edu/~kriz/cifar.html) (Canadian Institute For Advanced Research) dataset is a significant extension of the CIFAR-10 dataset, composed of 60,000 32x32 color images in 100 different classes. It was developed by researchers at the CIFAR institute, offering a more challenging dataset for more complex machine learning and [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks. ## Key Features @@ -25,11 +25,11 @@ The CIFAR-100 dataset is split into two subsets: ## Applications -The CIFAR-100 dataset is extensively used for training and evaluating deep learning models in image classification tasks, such as Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and various other machine learning algorithms. The diversity of the dataset in terms of classes and the presence of color images make it a more challenging and comprehensive dataset for research and development in the field of machine learning and computer vision. +The CIFAR-100 dataset is extensively used for training and evaluating deep learning models in image classification tasks, such as [Convolutional Neural Networks](https://www.ultralytics.com/glossary/convolutional-neural-network-cnn) (CNNs), Support Vector Machines (SVMs), and various other machine learning algorithms. The diversity of the dataset in terms of classes and the presence of color images make it a more challenging and comprehensive dataset for research and development in the field of machine learning and computer vision. ## Usage -To train a YOLO model on the CIFAR-100 dataset for 100 epochs with an image size of 32x32, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLO model on the CIFAR-100 dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 32x32, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -54,7 +54,7 @@ To train a YOLO model on the CIFAR-100 dataset for 100 epochs with an image size ## Sample Images and Annotations -The CIFAR-100 dataset contains color images of various objects, providing a well-structured dataset for image classification tasks. Here are some examples of images from the dataset: +The CIFAR-100 dataset contains color images of various objects, providing a well-structured dataset for [image classification](https://www.ultralytics.com/glossary/image-classification) tasks. Here are some examples of images from the dataset: ![Dataset sample image](https://github.com/ultralytics/docs/releases/download/0/cifar100-sample-image.avif) @@ -77,13 +77,13 @@ If you use the CIFAR-100 dataset in your research or development work, please ci } ``` -We would like to acknowledge Alex Krizhevsky for creating and maintaining the CIFAR-100 dataset as a valuable resource for the machine learning and computer vision research community. For more information about the CIFAR-100 dataset and its creator, visit the [CIFAR-100 dataset website](https://www.cs.toronto.edu/~kriz/cifar.html). +We would like to acknowledge Alex Krizhevsky for creating and maintaining the CIFAR-100 dataset as a valuable resource for the [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and computer vision research community. For more information about the CIFAR-100 dataset and its creator, visit the [CIFAR-100 dataset website](https://www.cs.toronto.edu/~kriz/cifar.html). ## FAQ ### What is the CIFAR-100 dataset and why is it significant? -The [CIFAR-100 dataset](https://www.cs.toronto.edu/~kriz/cifar.html) is a large collection of 60,000 32x32 color images classified into 100 classes. Developed by the Canadian Institute For Advanced Research (CIFAR), it provides a challenging dataset ideal for complex machine learning and computer vision tasks. Its significance lies in the diversity of classes and the small size of the images, making it a valuable resource for training and testing deep learning models, like Convolutional Neural Networks (CNNs), using frameworks such as Ultralytics YOLO. +The [CIFAR-100 dataset](https://www.cs.toronto.edu/~kriz/cifar.html) is a large collection of 60,000 32x32 color images classified into 100 classes. Developed by the Canadian Institute For Advanced Research (CIFAR), it provides a challenging dataset ideal for complex machine learning and computer vision tasks. Its significance lies in the diversity of classes and the small size of the images, making it a valuable resource for training and testing deep learning models, like Convolutional [Neural Networks](https://www.ultralytics.com/glossary/neural-network-nn) (CNNs), using frameworks such as Ultralytics YOLO. ### How do I train a YOLO model on the CIFAR-100 dataset? @@ -114,7 +114,7 @@ For a comprehensive list of available arguments, please refer to the model [Trai ### What are the primary applications of the CIFAR-100 dataset? -The CIFAR-100 dataset is extensively used in training and evaluating deep learning models for image classification. Its diverse set of 100 classes, grouped into 20 coarse categories, provides a challenging environment for testing algorithms such as Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and various other machine learning approaches. This dataset is a key resource in research and development within machine learning and computer vision fields. +The CIFAR-100 dataset is extensively used in training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models for image classification. Its diverse set of 100 classes, grouped into 20 coarse categories, provides a challenging environment for testing algorithms such as Convolutional Neural Networks (CNNs), [Support Vector Machines](https://www.ultralytics.com/glossary/support-vector-machine-svm) (SVMs), and various other machine learning approaches. This dataset is a key resource in research and development within machine learning and computer vision fields. ### How is the CIFAR-100 dataset structured? diff --git a/docs/en/datasets/classify/fashion-mnist.md b/docs/en/datasets/classify/fashion-mnist.md index d1c87e2676..531cd2c1bd 100644 --- a/docs/en/datasets/classify/fashion-mnist.md +++ b/docs/en/datasets/classify/fashion-mnist.md @@ -6,7 +6,7 @@ keywords: Fashion-MNIST, image classification, Zalando dataset, machine learning # Fashion-MNIST Dataset -The [Fashion-MNIST](https://github.com/zalandoresearch/fashion-mnist) dataset is a database of Zalando's article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms. +The [Fashion-MNIST](https://github.com/zalandoresearch/fashion-mnist) dataset is a database of Zalando's article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) algorithms.


@@ -16,7 +16,7 @@ The [Fashion-MNIST](https://github.com/zalandoresearch/fashion-mnist) dataset is allowfullscreen>
- Watch: How to do Image Classification on Fashion MNIST Dataset using Ultralytics YOLOv8 + Watch: How to do [Image Classification](https://www.ultralytics.com/glossary/image-classification) on Fashion MNIST Dataset using Ultralytics YOLOv8

## Key Features @@ -50,11 +50,11 @@ Each training and test example is assigned to one of the following labels: ## Applications -The Fashion-MNIST dataset is widely used for training and evaluating deep learning models in image classification tasks, such as Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and various other machine learning algorithms. The dataset's simple and well-structured format makes it an essential resource for researchers and practitioners in the field of machine learning and computer vision. +The Fashion-MNIST dataset is widely used for training and evaluating deep learning models in image classification tasks, such as [Convolutional Neural Networks](https://www.ultralytics.com/glossary/convolutional-neural-network-cnn) (CNNs), [Support Vector Machines](https://www.ultralytics.com/glossary/support-vector-machine-svm) (SVMs), and various other machine learning algorithms. The dataset's simple and well-structured format makes it an essential resource for researchers and practitioners in the field of machine learning and computer vision. ## Usage -To train a CNN model on the Fashion-MNIST dataset for 100 epochs with an image size of 28x28, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a CNN model on the Fashion-MNIST dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 28x28, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -124,7 +124,7 @@ For more detailed training parameters, refer to the [Training page](../../modes/ ### Why should I use the Fashion-MNIST dataset for benchmarking my machine learning models? -The [Fashion-MNIST](https://github.com/zalandoresearch/fashion-mnist) dataset is widely recognized in the deep learning community as a robust alternative to MNIST. It offers a more complex and varied set of images, making it an excellent choice for benchmarking image classification models. The dataset's structure, comprising 60,000 training images and 10,000 testing images, each labeled with one of 10 classes, makes it ideal for evaluating the performance of different machine learning algorithms in a more challenging context. +The [Fashion-MNIST](https://github.com/zalandoresearch/fashion-mnist) dataset is widely recognized in the [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) community as a robust alternative to MNIST. It offers a more complex and varied set of images, making it an excellent choice for benchmarking image classification models. The dataset's structure, comprising 60,000 training images and 10,000 testing images, each labeled with one of 10 classes, makes it ideal for evaluating the performance of different machine learning algorithms in a more challenging context. ### Can I use Ultralytics YOLO for image classification tasks like Fashion-MNIST? @@ -132,7 +132,7 @@ Yes, Ultralytics YOLO models can be used for image classification tasks, includi ### What are the key features and structure of the Fashion-MNIST dataset? -The Fashion-MNIST dataset is divided into two main subsets: 60,000 training images and 10,000 testing images. Each image is a 28x28-pixel grayscale picture representing one of 10 fashion-related classes. The simplicity and well-structured format make it ideal for training and evaluating models in machine learning and computer vision tasks. For more details on the dataset structure, see the [Dataset Structure section](#dataset-structure). +The Fashion-MNIST dataset is divided into two main subsets: 60,000 training images and 10,000 testing images. Each image is a 28x28-pixel grayscale picture representing one of 10 fashion-related classes. The simplicity and well-structured format make it ideal for training and evaluating models in machine learning and [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks. For more details on the dataset structure, see the [Dataset Structure section](#dataset-structure). ### How can I acknowledge the use of the Fashion-MNIST dataset in my research? diff --git a/docs/en/datasets/classify/imagenet.md b/docs/en/datasets/classify/imagenet.md index 8c4102caf8..76e59b3f18 100644 --- a/docs/en/datasets/classify/imagenet.md +++ b/docs/en/datasets/classify/imagenet.md @@ -6,7 +6,7 @@ keywords: ImageNet, deep learning, visual recognition, computer vision, pretrain # ImageNet Dataset -[ImageNet](https://www.image-net.org/) is a large-scale database of annotated images designed for use in visual object recognition research. It contains over 14 million images, with each image annotated using WordNet synsets, making it one of the most extensive resources available for training deep learning models in computer vision tasks. +[ImageNet](https://www.image-net.org/) is a large-scale database of annotated images designed for use in visual object recognition research. It contains over 14 million images, with each image annotated using WordNet synsets, making it one of the most extensive resources available for training [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks. ## ImageNet Pretrained Models @@ -22,7 +22,7 @@ keywords: ImageNet, deep learning, visual recognition, computer vision, pretrain - ImageNet contains over 14 million high-resolution images spanning thousands of object categories. - The dataset is organized according to the WordNet hierarchy, with each synset representing a category. -- ImageNet is widely used for training and benchmarking in the field of computer vision, particularly for image classification and object detection tasks. +- ImageNet is widely used for training and benchmarking in the field of computer vision, particularly for [image classification](https://www.ultralytics.com/glossary/image-classification) and [object detection](https://www.ultralytics.com/glossary/object-detection) tasks. - The annual ImageNet Large Scale Visual Recognition Challenge (ILSVRC) has been instrumental in advancing computer vision research. ## Dataset Structure @@ -39,7 +39,7 @@ The ImageNet dataset is widely used for training and evaluating deep learning mo ## Usage -To train a deep learning model on the ImageNet dataset for 100 epochs with an image size of 224x224, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a deep learning model on the ImageNet dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 224x224, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -90,7 +90,7 @@ If you use the ImageNet dataset in your research or development work, please cit } ``` -We would like to acknowledge the ImageNet team, led by Olga Russakovsky, Jia Deng, and Li Fei-Fei, for creating and maintaining the ImageNet dataset as a valuable resource for the machine learning and computer vision research community. For more information about the ImageNet dataset and its creators, visit the [ImageNet website](https://www.image-net.org/). +We would like to acknowledge the ImageNet team, led by Olga Russakovsky, Jia Deng, and Li Fei-Fei, for creating and maintaining the ImageNet dataset as a valuable resource for the [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and computer vision research community. For more information about the ImageNet dataset and its creators, visit the [ImageNet website](https://www.image-net.org/). ## FAQ @@ -127,7 +127,7 @@ For more in-depth training instruction, refer to our [Training page](../../modes ### Why should I use the Ultralytics YOLOv8 pretrained models for my ImageNet dataset projects? -Ultralytics YOLOv8 pretrained models offer state-of-the-art performance in terms of speed and accuracy for various computer vision tasks. For example, the YOLOv8n-cls model, with a top-1 accuracy of 69.0% and a top-5 accuracy of 88.3%, is optimized for real-time applications. Pretrained models reduce the computational resources required for training from scratch and accelerate development cycles. Learn more about the performance metrics of YOLOv8 models in the [ImageNet Pretrained Models section](#imagenet-pretrained-models). +Ultralytics YOLOv8 pretrained models offer state-of-the-art performance in terms of speed and [accuracy](https://www.ultralytics.com/glossary/accuracy) for various computer vision tasks. For example, the YOLOv8n-cls model, with a top-1 accuracy of 69.0% and a top-5 accuracy of 88.3%, is optimized for real-time applications. Pretrained models reduce the computational resources required for training from scratch and accelerate development cycles. Learn more about the performance metrics of YOLOv8 models in the [ImageNet Pretrained Models section](#imagenet-pretrained-models). ### How is the ImageNet dataset structured, and why is it important? @@ -135,4 +135,4 @@ The ImageNet dataset is organized using the WordNet hierarchy, where each node i ### What role does the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) play in computer vision? -The annual [ImageNet Large Scale Visual Recognition Challenge (ILSVRC)](https://image-net.org/challenges/LSVRC/) has been pivotal in driving advancements in computer vision by providing a competitive platform for evaluating algorithms on a large-scale, standardized dataset. It offers standardized evaluation metrics, fostering innovation and development in areas such as image classification, object detection, and image segmentation. The challenge has continuously pushed the boundaries of what is possible with deep learning and computer vision technologies. +The annual [ImageNet Large Scale Visual Recognition Challenge (ILSVRC)](https://image-net.org/challenges/LSVRC/) has been pivotal in driving advancements in computer vision by providing a competitive platform for evaluating algorithms on a large-scale, standardized dataset. It offers standardized evaluation metrics, fostering innovation and development in areas such as image classification, object detection, and [image segmentation](https://www.ultralytics.com/glossary/image-segmentation). The challenge has continuously pushed the boundaries of what is possible with deep learning and computer vision technologies. diff --git a/docs/en/datasets/classify/imagenet10.md b/docs/en/datasets/classify/imagenet10.md index b74e2a7a62..4e40e6655f 100644 --- a/docs/en/datasets/classify/imagenet10.md +++ b/docs/en/datasets/classify/imagenet10.md @@ -12,7 +12,7 @@ The [ImageNet10](https://github.com/ultralytics/assets/releases/download/v0.0.0/ - ImageNet10 is a compact version of ImageNet, with 20 images representing the first 10 classes of the original dataset. - The dataset is organized according to the WordNet hierarchy, mirroring the structure of the full ImageNet dataset. -- It is ideally suited for CI tests, sanity checks, and rapid testing of training pipelines in computer vision tasks. +- It is ideally suited for CI tests, sanity checks, and rapid testing of training pipelines in [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks. - Although not designed for model benchmarking, it can provide a quick indication of a model's basic functionality and correctness. ## Dataset Structure @@ -74,7 +74,7 @@ If you use the ImageNet10 dataset in your research or development work, please c } ``` -We would like to acknowledge the ImageNet team, led by Olga Russakovsky, Jia Deng, and Li Fei-Fei, for creating and maintaining the ImageNet dataset. The ImageNet10 dataset, while a compact subset, is a valuable resource for quick testing and debugging in the machine learning and computer vision research community. For more information about the ImageNet dataset and its creators, visit the [ImageNet website](https://www.image-net.org/). +We would like to acknowledge the ImageNet team, led by Olga Russakovsky, Jia Deng, and Li Fei-Fei, for creating and maintaining the ImageNet dataset. The ImageNet10 dataset, while a compact subset, is a valuable resource for quick testing and debugging in the [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and computer vision research community. For more information about the ImageNet dataset and its creators, visit the [ImageNet website](https://www.image-net.org/). ## FAQ @@ -111,7 +111,7 @@ Refer to the [Training](../../modes/train.md) page for a comprehensive list of a ### Why should I use the ImageNet10 dataset for CI tests and sanity checks? -The ImageNet10 dataset is designed specifically for CI tests, sanity checks, and quick evaluations in deep learning pipelines. Its small size allows for rapid iteration and testing, making it perfect for continuous integration processes where speed is crucial. By maintaining the structural complexity and diversity of the original ImageNet dataset, ImageNet10 provides a reliable indication of a model's basic functionality and correctness without the overhead of processing a large dataset. +The ImageNet10 dataset is designed specifically for CI tests, sanity checks, and quick evaluations in [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) pipelines. Its small size allows for rapid iteration and testing, making it perfect for continuous integration processes where speed is crucial. By maintaining the structural complexity and diversity of the original ImageNet dataset, ImageNet10 provides a reliable indication of a model's basic functionality and correctness without the overhead of processing a large dataset. ### What are the main features of the ImageNet10 dataset? diff --git a/docs/en/datasets/classify/imagenette.md b/docs/en/datasets/classify/imagenette.md index 42368a672a..bf371502ad 100644 --- a/docs/en/datasets/classify/imagenette.md +++ b/docs/en/datasets/classify/imagenette.md @@ -23,7 +23,7 @@ The ImageNette dataset is split into two subsets: ## Applications -The ImageNette dataset is widely used for training and evaluating deep learning models in image classification tasks, such as Convolutional Neural Networks (CNNs), and various other machine learning algorithms. The dataset's straightforward format and well-chosen classes make it a handy resource for both beginner and experienced practitioners in the field of machine learning and computer vision. +The ImageNette dataset is widely used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in image classification tasks, such as [Convolutional Neural Networks](https://www.ultralytics.com/glossary/convolutional-neural-network-cnn) (CNNs), and various other machine learning algorithms. The dataset's straightforward format and well-chosen classes make it a handy resource for both beginner and experienced practitioners in the field of machine learning and computer vision. ## Usage @@ -52,7 +52,7 @@ To train a model on the ImageNette dataset for 100 epochs with a standard image ## Sample Images and Annotations -The ImageNette dataset contains colored images of various objects and scenes, providing a diverse dataset for image classification tasks. Here are some examples of images from the dataset: +The ImageNette dataset contains colored images of various objects and scenes, providing a diverse dataset for [image classification](https://www.ultralytics.com/glossary/image-classification) tasks. Here are some examples of images from the dataset: ![Dataset sample image](https://github.com/ultralytics/docs/releases/download/0/imagenette-sample-image.avif) @@ -116,11 +116,11 @@ If you use the ImageNette dataset in your research or development work, please a ### What is the ImageNette dataset? -The [ImageNette dataset](https://github.com/fastai/imagenette) is a simplified subset of the larger [ImageNet dataset](https://www.image-net.org/), featuring only 10 easily distinguishable classes such as tench, English springer, and French horn. It was created to offer a more manageable dataset for efficient training and evaluation of image classification models. This dataset is particularly useful for quick software development and educational purposes in machine learning and computer vision. +The [ImageNette dataset](https://github.com/fastai/imagenette) is a simplified subset of the larger [ImageNet dataset](https://www.image-net.org/), featuring only 10 easily distinguishable classes such as tench, English springer, and French horn. It was created to offer a more manageable dataset for efficient training and evaluation of image classification models. This dataset is particularly useful for quick software development and educational purposes in [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and computer vision. ### How can I use the ImageNette dataset for training a YOLO model? -To train a YOLO model on the ImageNette dataset for 100 epochs, you can use the following commands. Make sure to have the Ultralytics YOLO environment set up. +To train a YOLO model on the ImageNette dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch), you can use the following commands. Make sure to have the Ultralytics YOLO environment set up. !!! example "Train Example" @@ -186,8 +186,8 @@ For more information, refer to [Training with ImageNette160 and ImageNette320](# The ImageNette dataset is extensively used in: -- **Educational Settings**: To educate beginners in machine learning and computer vision. +- **Educational Settings**: To educate beginners in machine learning and [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv). - **Software Development**: For rapid prototyping and development of image classification models. -- **Deep Learning Research**: To evaluate and benchmark the performance of various deep learning models, especially Convolutional Neural Networks (CNNs). +- **Deep Learning Research**: To evaluate and benchmark the performance of various deep learning models, especially Convolutional [Neural Networks](https://www.ultralytics.com/glossary/neural-network-nn) (CNNs). Explore the [Applications](#applications) section for detailed use cases. diff --git a/docs/en/datasets/classify/imagewoof.md b/docs/en/datasets/classify/imagewoof.md index 54361abc60..2ed0273b60 100644 --- a/docs/en/datasets/classify/imagewoof.md +++ b/docs/en/datasets/classify/imagewoof.md @@ -6,7 +6,7 @@ keywords: ImageWoof dataset, ImageNet subset, dog breeds, image classification, # ImageWoof Dataset -The [ImageWoof](https://github.com/fastai/imagenette) dataset is a subset of the ImageNet consisting of 10 classes that are challenging to classify, since they're all dog breeds. It was created as a more difficult task for image classification algorithms to solve, aiming at encouraging development of more advanced models. +The [ImageWoof](https://github.com/fastai/imagenette) dataset is a subset of the ImageNet consisting of 10 classes that are challenging to classify, since they're all dog breeds. It was created as a more difficult task for [image classification](https://www.ultralytics.com/glossary/image-classification) algorithms to solve, aiming at encouraging development of more advanced models. ## Key Features @@ -24,7 +24,7 @@ The ImageWoof dataset is widely used for training and evaluating deep learning m ## Usage -To train a CNN model on the ImageWoof dataset for 100 epochs with an image size of 224x224, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a CNN model on the ImageWoof dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 224x224, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -97,7 +97,7 @@ The example showcases the subtle differences and similarities among the differen If you use the ImageWoof dataset in your research or development work, please make sure to acknowledge the creators of the dataset by linking to the [official dataset repository](https://github.com/fastai/imagenette). -We would like to acknowledge the FastAI team for creating and maintaining the ImageWoof dataset as a valuable resource for the machine learning and computer vision research community. For more information about the ImageWoof dataset, visit the [ImageWoof dataset repository](https://github.com/fastai/imagenette). +We would like to acknowledge the FastAI team for creating and maintaining the ImageWoof dataset as a valuable resource for the [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) research community. For more information about the ImageWoof dataset, visit the [ImageWoof dataset repository](https://github.com/fastai/imagenette). ## FAQ @@ -107,7 +107,7 @@ The [ImageWoof](https://github.com/fastai/imagenette) dataset is a challenging s ### How can I train a model using the ImageWoof dataset with Ultralytics YOLO? -To train a Convolutional Neural Network (CNN) model on the ImageWoof dataset using Ultralytics YOLO for 100 epochs at an image size of 224x224, you can use the following code: +To train a [Convolutional Neural Network](https://www.ultralytics.com/glossary/convolutional-neural-network-cnn) (CNN) model on the ImageWoof dataset using Ultralytics YOLO for 100 epochs at an image size of 224x224, you can use the following code: !!! example "Train Example" @@ -137,7 +137,7 @@ The ImageWoof dataset comes in three sizes: 2. **Medium Size (imagewoof320)**: Resized images with a maximum edge length of 320 pixels, suited for faster training. 3. **Small Size (imagewoof160)**: Resized images with a maximum edge length of 160 pixels, perfect for rapid prototyping. -Use these versions by replacing 'imagewoof' in the dataset argument accordingly. Note, however, that smaller images may yield lower classification accuracy but can be useful for quicker iterations. +Use these versions by replacing 'imagewoof' in the dataset argument accordingly. Note, however, that smaller images may yield lower classification [accuracy](https://www.ultralytics.com/glossary/accuracy) but can be useful for quicker iterations. ### How do noisy labels in the ImageWoof dataset benefit training? @@ -145,4 +145,4 @@ Noisy labels in the ImageWoof dataset simulate real-world conditions where label ### What are the key challenges of using the ImageWoof dataset? -The primary challenge of the ImageWoof dataset lies in the subtle differences among the dog breeds it includes. Since it focuses on 10 closely related breeds, distinguishing between them requires more advanced and fine-tuned image classification models. This makes ImageWoof an excellent benchmark to test the capabilities and improvements of deep learning models. +The primary challenge of the ImageWoof dataset lies in the subtle differences among the dog breeds it includes. Since it focuses on 10 closely related breeds, distinguishing between them requires more advanced and fine-tuned image classification models. This makes ImageWoof an excellent benchmark to test the capabilities and improvements of [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models. diff --git a/docs/en/datasets/classify/index.md b/docs/en/datasets/classify/index.md index 2b01824a96..3567d6a295 100644 --- a/docs/en/datasets/classify/index.md +++ b/docs/en/datasets/classify/index.md @@ -103,12 +103,12 @@ This structured approach ensures that the model can effectively learn from well- Ultralytics supports the following datasets with automatic download: -- [Caltech 101](caltech101.md): A dataset containing images of 101 object categories for image classification tasks. +- [Caltech 101](caltech101.md): A dataset containing images of 101 object categories for [image classification](https://www.ultralytics.com/glossary/image-classification) tasks. - [Caltech 256](caltech256.md): An extended version of Caltech 101 with 256 object categories and more challenging images. - [CIFAR-10](cifar10.md): A dataset of 60K 32x32 color images in 10 classes, with 6K images per class. - [CIFAR-100](cifar100.md): An extended version of CIFAR-10 with 100 object categories and 600 images per class. - [Fashion-MNIST](fashion-mnist.md): A dataset consisting of 70,000 grayscale images of 10 fashion categories for image classification tasks. -- [ImageNet](imagenet.md): A large-scale dataset for object detection and image classification with over 14 million images and 20,000 categories. +- [ImageNet](imagenet.md): A large-scale dataset for [object detection](https://www.ultralytics.com/glossary/object-detection) and image classification with over 14 million images and 20,000 categories. - [ImageNet-10](imagenet10.md): A smaller subset of ImageNet with 10 categories for faster experimentation and testing. - [Imagenette](imagenette.md): A smaller subset of ImageNet that contains 10 easily distinguishable classes for quicker training and testing. - [Imagewoof](imagewoof.md): A more challenging subset of ImageNet containing 10 dog breed categories for image classification tasks. @@ -184,7 +184,7 @@ Ultralytics YOLO offers several benefits for image classification, including: - **Pretrained Models**: Load pretrained models like `yolov8n-cls.pt` to jump-start your training process. - **Ease of Use**: Simple API and CLI commands for training and evaluation. -- **High Performance**: State-of-the-art accuracy and speed, ideal for real-time applications. +- **High Performance**: State-of-the-art [accuracy](https://www.ultralytics.com/glossary/accuracy) and speed, ideal for real-time applications. - **Support for Multiple Datasets**: Seamless integration with various popular datasets like CIFAR-10, ImageNet, and more. - **Community and Support**: Access to extensive documentation and an active community for troubleshooting and improvements. diff --git a/docs/en/datasets/classify/mnist.md b/docs/en/datasets/classify/mnist.md index 7ee4531392..07f0a70a1d 100644 --- a/docs/en/datasets/classify/mnist.md +++ b/docs/en/datasets/classify/mnist.md @@ -12,7 +12,7 @@ The [MNIST](http://yann.lecun.com/exdb/mnist/) (Modified National Institute of S - MNIST contains 60,000 training images and 10,000 testing images of handwritten digits. - The dataset comprises grayscale images of size 28x28 pixels. -- The images are normalized to fit into a 28x28 pixel bounding box and anti-aliased, introducing grayscale levels. +- The images are normalized to fit into a 28x28 pixel [bounding box](https://www.ultralytics.com/glossary/bounding-box) and anti-aliased, introducing grayscale levels. - MNIST is widely used for training and testing in the field of machine learning, especially for image classification tasks. ## Dataset Structure @@ -28,11 +28,11 @@ Extended MNIST (EMNIST) is a newer dataset developed and released by NIST to be ## Applications -The MNIST dataset is widely used for training and evaluating deep learning models in image classification tasks, such as Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and various other machine learning algorithms. The dataset's simple and well-structured format makes it an essential resource for researchers and practitioners in the field of machine learning and computer vision. +The MNIST dataset is widely used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in image classification tasks, such as [Convolutional Neural Networks](https://www.ultralytics.com/glossary/convolutional-neural-network-cnn) (CNNs), [Support Vector Machines](https://www.ultralytics.com/glossary/support-vector-machine-svm) (SVMs), and various other machine learning algorithms. The dataset's simple and well-structured format makes it an essential resource for researchers and practitioners in the field of machine learning and computer vision. ## Usage -To train a CNN model on the MNIST dataset for 100 epochs with an image size of 32x32, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a CNN model on the MNIST dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 32x32, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -57,7 +57,7 @@ To train a CNN model on the MNIST dataset for 100 epochs with an image size of 3 ## Sample Images and Annotations -The MNIST dataset contains grayscale images of handwritten digits, providing a well-structured dataset for image classification tasks. Here are some examples of images from the dataset: +The MNIST dataset contains grayscale images of handwritten digits, providing a well-structured dataset for [image classification](https://www.ultralytics.com/glossary/image-classification) tasks. Here are some examples of images from the dataset: ![Dataset sample image](https://upload.wikimedia.org/wikipedia/commons/2/27/MnistExamples.png) @@ -83,7 +83,7 @@ research or development work, please cite the following paper: } ``` -We would like to acknowledge Yann LeCun, Corinna Cortes, and Christopher J.C. Burges for creating and maintaining the MNIST dataset as a valuable resource for the machine learning and computer vision research community. For more information about the MNIST dataset and its creators, visit the [MNIST dataset website](http://yann.lecun.com/exdb/mnist/). +We would like to acknowledge Yann LeCun, Corinna Cortes, and Christopher J.C. Burges for creating and maintaining the MNIST dataset as a valuable resource for the [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) research community. For more information about the MNIST dataset and its creators, visit the [MNIST dataset website](http://yann.lecun.com/exdb/mnist/). ## FAQ diff --git a/docs/en/datasets/detect/african-wildlife.md b/docs/en/datasets/detect/african-wildlife.md index d0c86a0314..0d01372dbd 100644 --- a/docs/en/datasets/detect/african-wildlife.md +++ b/docs/en/datasets/detect/african-wildlife.md @@ -6,7 +6,7 @@ keywords: African Wildlife Dataset, South African animals, object detection, com # African Wildlife Dataset -This dataset showcases four common animal classes typically found in South African nature reserves. It includes images of African wildlife such as buffalo, elephant, rhino, and zebra, providing valuable insights into their characteristics. Essential for training computer vision algorithms, this dataset aids in identifying animals in various habitats, from zoos to forests, and supports wildlife research. +This dataset showcases four common animal classes typically found in South African nature reserves. It includes images of African wildlife such as buffalo, elephant, rhino, and zebra, providing valuable insights into their characteristics. Essential for training [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) algorithms, this dataset aids in identifying animals in various habitats, from zoos to forests, and supports wildlife research.


@@ -29,7 +29,7 @@ The African wildlife objects detection dataset is split into three subsets: ## Applications -This dataset can be applied in various computer vision tasks such as object detection, object tracking, and research. Specifically, it can be used to train and evaluate models for identifying African wildlife objects in images, which can have applications in wildlife conservation, ecological research, and monitoring efforts in natural reserves and protected areas. Additionally, it can serve as a valuable resource for educational purposes, enabling students and researchers to study and understand the characteristics and behaviors of different animal species. +This dataset can be applied in various computer vision tasks such as [object detection](https://www.ultralytics.com/glossary/object-detection), object tracking, and research. Specifically, it can be used to train and evaluate models for identifying African wildlife objects in images, which can have applications in wildlife conservation, ecological research, and monitoring efforts in natural reserves and protected areas. Additionally, it can serve as a valuable resource for educational purposes, enabling students and researchers to study and understand the characteristics and behaviors of different animal species. ## Dataset YAML @@ -43,7 +43,7 @@ A YAML (Yet Another Markup Language) file defines the dataset configuration, inc ## Usage -To train a YOLOv8n model on the African wildlife dataset for 100 epochs with an image size of 640, use the provided code samples. For a comprehensive list of available parameters, refer to the model's [Training](../../modes/train.md) page. +To train a YOLOv8n model on the African wildlife dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, use the provided code samples. For a comprehensive list of available parameters, refer to the model's [Training](../../modes/train.md) page. !!! example "Train Example" @@ -136,7 +136,7 @@ For additional training parameters and options, refer to the [Training](../../mo ### Where can I find the YAML configuration file for the African Wildlife Dataset? -The YAML configuration file for the African Wildlife Dataset, named `african-wildlife.yaml`, can be found at [this GitHub link](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/african-wildlife.yaml). This file defines the dataset configuration, including paths, classes, and other details crucial for training machine learning models. See the [Dataset YAML](#dataset-yaml) section for more details. +The YAML configuration file for the African Wildlife Dataset, named `african-wildlife.yaml`, can be found at [this GitHub link](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/african-wildlife.yaml). This file defines the dataset configuration, including paths, classes, and other details crucial for training [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models. See the [Dataset YAML](#dataset-yaml) section for more details. ### Can I see sample images and annotations from the African Wildlife Dataset? diff --git a/docs/en/datasets/detect/argoverse.md b/docs/en/datasets/detect/argoverse.md index 47ef822b08..a834be90ed 100644 --- a/docs/en/datasets/detect/argoverse.md +++ b/docs/en/datasets/detect/argoverse.md @@ -29,7 +29,7 @@ The Argoverse dataset is organized into three main subsets: ## Applications -The Argoverse dataset is widely used for training and evaluating deep learning models in autonomous driving tasks such as 3D object tracking, motion forecasting, and stereo depth estimation. The dataset's diverse set of sensor data, object annotations, and map information make it a valuable resource for researchers and practitioners in the field of autonomous driving. +The Argoverse dataset is widely used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in autonomous driving tasks such as 3D object tracking, motion forecasting, and stereo depth estimation. The dataset's diverse set of sensor data, object annotations, and map information make it a valuable resource for researchers and practitioners in the field of autonomous driving. ## Dataset YAML @@ -43,7 +43,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n model on the Argoverse dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n model on the Argoverse dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" diff --git a/docs/en/datasets/detect/brain-tumor.md b/docs/en/datasets/detect/brain-tumor.md index aa48c5f9e4..9f108e7388 100644 --- a/docs/en/datasets/detect/brain-tumor.md +++ b/docs/en/datasets/detect/brain-tumor.md @@ -6,7 +6,7 @@ keywords: brain tumor dataset, MRI scans, CT scans, brain tumor detection, medic # Brain Tumor Dataset -A brain tumor detection dataset consists of medical images from MRI or CT scans, containing information about brain tumor presence, location, and characteristics. This dataset is essential for training computer vision algorithms to automate brain tumor identification, aiding in early diagnosis and treatment planning. +A brain tumor detection dataset consists of medical images from MRI or CT scans, containing information about brain tumor presence, location, and characteristics. This dataset is essential for training [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) algorithms to automate brain tumor identification, aiding in early diagnosis and treatment planning.


@@ -42,7 +42,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n model on the brain tumor dataset for 100 epochs with an image size of 640, utilize the provided code snippets. For a detailed list of available arguments, consult the model's [Training](../../modes/train.md) page. +To train a YOLOv8n model on the brain tumor dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, utilize the provided code snippets. For a detailed list of available arguments, consult the model's [Training](../../modes/train.md) page. !!! example "Train Example" diff --git a/docs/en/datasets/detect/coco.md b/docs/en/datasets/detect/coco.md index 25878ed913..d090142838 100644 --- a/docs/en/datasets/detect/coco.md +++ b/docs/en/datasets/detect/coco.md @@ -6,7 +6,7 @@ keywords: COCO dataset, object detection, segmentation, benchmarking, computer v # COCO Dataset -The [COCO](https://cocodataset.org/#home) (Common Objects in Context) dataset is a large-scale object detection, segmentation, and captioning dataset. It is designed to encourage research on a wide variety of object categories and is commonly used for benchmarking computer vision models. It is an essential dataset for researchers and developers working on object detection, segmentation, and pose estimation tasks. +The [COCO](https://cocodataset.org/#home) (Common Objects in Context) dataset is a large-scale object detection, segmentation, and captioning dataset. It is designed to encourage research on a wide variety of object categories and is commonly used for benchmarking [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) models. It is an essential dataset for researchers and developers working on object detection, segmentation, and pose estimation tasks.


@@ -34,7 +34,7 @@ The [COCO](https://cocodataset.org/#home) (Common Objects in Context) dataset is - COCO contains 330K images, with 200K images having annotations for object detection, segmentation, and captioning tasks. - The dataset comprises 80 object categories, including common objects like cars, bicycles, and animals, as well as more specific categories such as umbrellas, handbags, and sports equipment. - Annotations include object bounding boxes, segmentation masks, and captions for each image. -- COCO provides standardized evaluation metrics like mean Average Precision (mAP) for object detection, and mean Average Recall (mAR) for segmentation tasks, making it suitable for comparing model performance. +- COCO provides standardized evaluation metrics like [mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP) for object detection, and mean Average [Recall](https://www.ultralytics.com/glossary/recall) (mAR) for segmentation tasks, making it suitable for comparing model performance. ## Dataset Structure @@ -46,7 +46,7 @@ The COCO dataset is split into three subsets: ## Applications -The COCO dataset is widely used for training and evaluating deep learning models in object detection (such as YOLO, Faster R-CNN, and SSD), instance segmentation (such as Mask R-CNN), and keypoint detection (such as OpenPose). The dataset's diverse set of object categories, large number of annotated images, and standardized evaluation metrics make it an essential resource for computer vision researchers and practitioners. +The COCO dataset is widely used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in object detection (such as YOLO, Faster R-CNN, and SSD), [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation) (such as Mask R-CNN), and keypoint detection (such as OpenPose). The dataset's diverse set of object categories, large number of annotated images, and standardized evaluation metrics make it an essential resource for computer vision researchers and practitioners. ## Dataset YAML @@ -60,7 +60,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n model on the COCO dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n model on the COCO dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -118,7 +118,7 @@ We would like to acknowledge the COCO Consortium for creating and maintaining th ### What is the COCO dataset and why is it important for computer vision? -The [COCO dataset](https://cocodataset.org/#home) (Common Objects in Context) is a large-scale dataset used for object detection, segmentation, and captioning. It contains 330K images with detailed annotations for 80 object categories, making it essential for benchmarking and training computer vision models. Researchers use COCO due to its diverse categories and standardized evaluation metrics like mean Average Precision (mAP). +The [COCO dataset](https://cocodataset.org/#home) (Common Objects in Context) is a large-scale dataset used for [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and captioning. It contains 330K images with detailed annotations for 80 object categories, making it essential for benchmarking and training computer vision models. Researchers use COCO due to its diverse categories and standardized evaluation metrics like mean Average [Precision](https://www.ultralytics.com/glossary/precision) (mAP). ### How can I train a YOLO model using the COCO dataset? diff --git a/docs/en/datasets/detect/coco8.md b/docs/en/datasets/detect/coco8.md index a0972693ea..4a8ad5a852 100644 --- a/docs/en/datasets/detect/coco8.md +++ b/docs/en/datasets/detect/coco8.md @@ -8,7 +8,7 @@ keywords: COCO8, Ultralytics, dataset, object detection, YOLOv8, training, valid ## Introduction -[Ultralytics](https://www.ultralytics.com/) COCO8 is a small, but versatile object detection dataset composed of the first 8 images of the COCO train 2017 set, 4 for training and 4 for validation. This dataset is ideal for testing and debugging object detection models, or for experimenting with new detection approaches. With 8 images, it is small enough to be easily manageable, yet diverse enough to test training pipelines for errors and act as a sanity check before training larger datasets. +[Ultralytics](https://www.ultralytics.com/) COCO8 is a small, but versatile [object detection](https://www.ultralytics.com/glossary/object-detection) dataset composed of the first 8 images of the COCO train 2017 set, 4 for training and 4 for validation. This dataset is ideal for testing and debugging object detection models, or for experimenting with new detection approaches. With 8 images, it is small enough to be easily manageable, yet diverse enough to test training pipelines for errors and act as a sanity check before training larger datasets.


@@ -35,7 +35,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n model on the COCO8 dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n model on the COCO8 dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -87,7 +87,7 @@ If you use the COCO dataset in your research or development work, please cite th } ``` -We would like to acknowledge the COCO Consortium for creating and maintaining this valuable resource for the computer vision community. For more information about the COCO dataset and its creators, visit the [COCO dataset website](https://cocodataset.org/#home). +We would like to acknowledge the COCO Consortium for creating and maintaining this valuable resource for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) community. For more information about the COCO dataset and its creators, visit the [COCO dataset website](https://cocodataset.org/#home). ## FAQ diff --git a/docs/en/datasets/detect/globalwheat2020.md b/docs/en/datasets/detect/globalwheat2020.md index 37b9759f36..ef7ff7ac31 100644 --- a/docs/en/datasets/detect/globalwheat2020.md +++ b/docs/en/datasets/detect/globalwheat2020.md @@ -24,7 +24,7 @@ The Global Wheat Head Dataset is organized into two main subsets: ## Applications -The Global Wheat Head Dataset is widely used for training and evaluating deep learning models in wheat head detection tasks. The dataset's diverse set of images, capturing a wide range of appearances, environments, and conditions, make it a valuable resource for researchers and practitioners in the field of plant phenotyping and crop management. +The Global Wheat Head Dataset is widely used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in wheat head detection tasks. The dataset's diverse set of images, capturing a wide range of appearances, environments, and conditions, make it a valuable resource for researchers and practitioners in the field of plant phenotyping and crop management. ## Dataset YAML @@ -38,7 +38,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n model on the Global Wheat Head Dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n model on the Global Wheat Head Dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -130,7 +130,7 @@ Key features of the Global Wheat Head Dataset include: - Over 3,000 training images from Europe (France, UK, Switzerland) and North America (Canada). - Approximately 1,000 test images from Australia, Japan, and China. - High variability in wheat head appearances due to different growing environments. -- Detailed annotations with wheat head bounding boxes to aid object detection models. +- Detailed annotations with wheat head bounding boxes to aid [object detection](https://www.ultralytics.com/glossary/object-detection) models. These features facilitate the development of robust models capable of generalization across multiple regions. diff --git a/docs/en/datasets/detect/index.md b/docs/en/datasets/detect/index.md index f76ba40bc2..61640480f6 100644 --- a/docs/en/datasets/detect/index.md +++ b/docs/en/datasets/detect/index.md @@ -6,7 +6,7 @@ keywords: Ultralytics, YOLO, object detection datasets, dataset formats, COCO, d # Object Detection Datasets Overview -Training a robust and accurate object detection model requires a comprehensive dataset. This guide introduces various formats of datasets that are compatible with the Ultralytics YOLO model and provides insights into their structure, usage, and how to convert between different formats. +Training a robust and accurate [object detection](https://www.ultralytics.com/glossary/object-detection) model requires a comprehensive dataset. This guide introduces various formats of datasets that are compatible with the Ultralytics YOLO model and provides insights into their structure, usage, and how to convert between different formats. ## Supported Dataset Formats diff --git a/docs/en/datasets/detect/lvis.md b/docs/en/datasets/detect/lvis.md index 8c06920fd6..c4a4ff76ed 100644 --- a/docs/en/datasets/detect/lvis.md +++ b/docs/en/datasets/detect/lvis.md @@ -6,7 +6,7 @@ keywords: LVIS dataset, object detection, instance segmentation, Facebook AI Res # LVIS Dataset -The [LVIS dataset](https://www.lvisdataset.org/) is a large-scale, fine-grained vocabulary-level annotation dataset developed and released by Facebook AI Research (FAIR). It is primarily used as a research benchmark for object detection and instance segmentation with a large vocabulary of categories, aiming to drive further advancements in computer vision field. +The [LVIS dataset](https://www.lvisdataset.org/) is a large-scale, fine-grained vocabulary-level annotation dataset developed and released by Facebook AI Research (FAIR). It is primarily used as a research benchmark for object detection and [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation) with a large vocabulary of categories, aiming to drive further advancements in computer vision field.


@@ -28,7 +28,7 @@ The [LVIS dataset](https://www.lvisdataset.org/) is a large-scale, fine-grained - LVIS contains 160k images and 2M instance annotations for object detection, segmentation, and captioning tasks. - The dataset comprises 1203 object categories, including common objects like cars, bicycles, and animals, as well as more specific categories such as umbrellas, handbags, and sports equipment. - Annotations include object bounding boxes, segmentation masks, and captions for each image. -- LVIS provides standardized evaluation metrics like mean Average Precision (mAP) for object detection, and mean Average Recall (mAR) for segmentation tasks, making it suitable for comparing model performance. +- LVIS provides standardized evaluation metrics like [mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP) for object detection, and mean Average [Recall](https://www.ultralytics.com/glossary/recall) (mAR) for segmentation tasks, making it suitable for comparing model performance. - LVIS uses exactly the same images as [COCO](./coco.md) dataset, but with different splits and different annotations. ## Dataset Structure @@ -42,7 +42,7 @@ The LVIS dataset is split into three subsets: ## Applications -The LVIS dataset is widely used for training and evaluating deep learning models in object detection (such as YOLO, Faster R-CNN, and SSD), instance segmentation (such as Mask R-CNN). The dataset's diverse set of object categories, large number of annotated images, and standardized evaluation metrics make it an essential resource for computer vision researchers and practitioners. +The LVIS dataset is widely used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in object detection (such as YOLO, Faster R-CNN, and SSD), instance segmentation (such as Mask R-CNN). The dataset's diverse set of object categories, large number of annotated images, and standardized evaluation metrics make it an essential resource for computer vision researchers and practitioners. ## Dataset YAML @@ -56,7 +56,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n model on the LVIS dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n model on the LVIS dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -106,7 +106,7 @@ If you use the LVIS dataset in your research or development work, please cite th } ``` -We would like to acknowledge the LVIS Consortium for creating and maintaining this valuable resource for the computer vision community. For more information about the LVIS dataset and its creators, visit the [LVIS dataset website](https://www.lvisdataset.org/). +We would like to acknowledge the LVIS Consortium for creating and maintaining this valuable resource for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) community. For more information about the LVIS dataset and its creators, visit the [LVIS dataset website](https://www.lvisdataset.org/). ## FAQ @@ -144,11 +144,11 @@ For detailed training configurations, refer to the [Training](../../modes/train. ### How does the LVIS dataset differ from the COCO dataset? -The images in the LVIS dataset are the same as those in the [COCO dataset](./coco.md), but the two differ in terms of splitting and annotations. LVIS provides a larger and more detailed vocabulary with 1203 object categories compared to COCO's 80 categories. Additionally, LVIS focuses on annotation completeness and diversity, aiming to push the limits of object detection and instance segmentation models by offering more nuanced and comprehensive data. +The images in the LVIS dataset are the same as those in the [COCO dataset](./coco.md), but the two differ in terms of splitting and annotations. LVIS provides a larger and more detailed vocabulary with 1203 object categories compared to COCO's 80 categories. Additionally, LVIS focuses on annotation completeness and diversity, aiming to push the limits of [object detection](https://www.ultralytics.com/glossary/object-detection) and instance segmentation models by offering more nuanced and comprehensive data. ### Why should I use Ultralytics YOLO for training on the LVIS dataset? -Ultralytics YOLO models, including the latest YOLOv8, are optimized for real-time object detection with state-of-the-art accuracy and speed. They support a wide range of annotations, such as the fine-grained ones provided by the LVIS dataset, making them ideal for advanced computer vision applications. Moreover, Ultralytics offers seamless integration with various [training](../../modes/train.md), [validation](../../modes/val.md), and [prediction](../../modes/predict.md) modes, ensuring efficient model development and deployment. +Ultralytics YOLO models, including the latest YOLOv8, are optimized for real-time object detection with state-of-the-art [accuracy](https://www.ultralytics.com/glossary/accuracy) and speed. They support a wide range of annotations, such as the fine-grained ones provided by the LVIS dataset, making them ideal for advanced computer vision applications. Moreover, Ultralytics offers seamless integration with various [training](../../modes/train.md), [validation](../../modes/val.md), and [prediction](../../modes/predict.md) modes, ensuring efficient model development and deployment. ### Can I see some sample annotations from the LVIS dataset? diff --git a/docs/en/datasets/detect/objects365.md b/docs/en/datasets/detect/objects365.md index f2b44f245a..49947617af 100644 --- a/docs/en/datasets/detect/objects365.md +++ b/docs/en/datasets/detect/objects365.md @@ -24,7 +24,7 @@ The Objects365 dataset is organized into a single set of images with correspondi ## Applications -The Objects365 dataset is widely used for training and evaluating deep learning models in object detection tasks. The dataset's diverse set of object categories and high-quality annotations make it a valuable resource for researchers and practitioners in the field of computer vision. +The Objects365 dataset is widely used for training and evaluating deep learning models in object detection tasks. The dataset's diverse set of object categories and high-quality annotations make it a valuable resource for researchers and practitioners in the field of [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv). ## Dataset YAML @@ -38,7 +38,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n model on the Objects365 dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n model on the Objects365 dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -63,7 +63,7 @@ To train a YOLOv8n model on the Objects365 dataset for 100 epochs with an image ## Sample Data and Annotations -The Objects365 dataset contains a diverse set of high-resolution images with objects from 365 categories, providing rich context for object detection tasks. Here are some examples of the images in the dataset: +The Objects365 dataset contains a diverse set of high-resolution images with objects from 365 categories, providing rich context for [object detection](https://www.ultralytics.com/glossary/object-detection) tasks. Here are some examples of the images in the dataset: ![Dataset sample image](https://github.com/ultralytics/docs/releases/download/0/objects365-sample-image.avif) @@ -95,7 +95,7 @@ We would like to acknowledge the team of researchers who created and maintain th ### What is the Objects365 dataset used for? -The [Objects365 dataset](https://www.objects365.org/) is designed for object detection tasks in machine learning and computer vision. It provides a large-scale, high-quality dataset with 2 million annotated images and 30 million bounding boxes across 365 categories. Leveraging such a diverse dataset helps improve the performance and generalization of object detection models, making it invaluable for research and development in the field. +The [Objects365 dataset](https://www.objects365.org/) is designed for object detection tasks in [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and computer vision. It provides a large-scale, high-quality dataset with 2 million annotated images and 30 million bounding boxes across 365 categories. Leveraging such a diverse dataset helps improve the performance and generalization of object detection models, making it invaluable for research and development in the field. ### How can I train a YOLOv8 model on the Objects365 dataset? @@ -138,4 +138,4 @@ The YAML configuration file for the Objects365 dataset is available at [Objects3 ### How does the dataset structure of Objects365 enhance object detection modeling? -The [Objects365 dataset](https://www.objects365.org/) is organized with 2 million high-resolution images and comprehensive annotations of over 30 million bounding boxes. This structure ensures a robust dataset for training deep learning models in object detection, offering a wide variety of objects and scenarios. Such diversity and volume help in developing models that are more accurate and capable of generalizing well to real-world applications. For more details on the dataset structure, refer to the [Dataset YAML](#dataset-yaml) section. +The [Objects365 dataset](https://www.objects365.org/) is organized with 2 million high-resolution images and comprehensive annotations of over 30 million bounding boxes. This structure ensures a robust dataset for training [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in object detection, offering a wide variety of objects and scenarios. Such diversity and volume help in developing models that are more accurate and capable of generalizing well to real-world applications. For more details on the dataset structure, refer to the [Dataset YAML](#dataset-yaml) section. diff --git a/docs/en/datasets/detect/open-images-v7.md b/docs/en/datasets/detect/open-images-v7.md index f6b0c63bc4..1e6f1f7e4f 100644 --- a/docs/en/datasets/detect/open-images-v7.md +++ b/docs/en/datasets/detect/open-images-v7.md @@ -6,7 +6,7 @@ keywords: Open Images V7, Google dataset, computer vision, YOLOv8 models, object # Open Images V7 Dataset -[Open Images V7](https://storage.googleapis.com/openimages/web/index.html) is a versatile and expansive dataset championed by Google. Aimed at propelling research in the realm of computer vision, it boasts a vast collection of images annotated with a plethora of data, including image-level labels, object bounding boxes, object segmentation masks, visual relationships, and localized narratives. +[Open Images V7](https://storage.googleapis.com/openimages/web/index.html) is a versatile and expansive dataset championed by Google. Aimed at propelling research in the realm of [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv), it boasts a vast collection of images annotated with a plethora of data, including image-level labels, object bounding boxes, object segmentation masks, visual relationships, and localized narratives.


@@ -16,7 +16,7 @@ keywords: Open Images V7, Google dataset, computer vision, YOLOv8 models, object allowfullscreen>
- Watch: Object Detection using OpenImagesV7 Pretrained Model + Watch: [Object Detection](https://www.ultralytics.com/glossary/object-detection) using OpenImagesV7 Pretrained Model

## Open Images V7 Pretrained Models @@ -34,13 +34,13 @@ keywords: Open Images V7, Google dataset, computer vision, YOLOv8 models, object ## Key Features - Encompasses ~9M images annotated in various ways to suit multiple computer vision tasks. -- Houses a staggering 16M bounding boxes across 600 object classes in 1.9M images. These boxes are primarily hand-drawn by experts ensuring high precision. +- Houses a staggering 16M bounding boxes across 600 object classes in 1.9M images. These boxes are primarily hand-drawn by experts ensuring high [precision](https://www.ultralytics.com/glossary/precision). - Visual relationship annotations totaling 3.3M are available, detailing 1,466 unique relationship triplets, object properties, and human activities. - V5 introduced segmentation masks for 2.8M objects across 350 classes. - V6 introduced 675k localized narratives that amalgamate voice, text, and mouse traces highlighting described objects. - V7 introduced 66.4M point-level labels on 1.4M images, spanning 5,827 classes. - Encompasses 61.4M image-level labels across a diverse set of 20,638 classes. -- Provides a unified platform for image classification, object detection, relationship detection, instance segmentation, and multimodal image descriptions. +- Provides a unified platform for image classification, object detection, relationship detection, [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation), and multimodal image descriptions. ## Dataset Structure @@ -51,7 +51,7 @@ Open Images V7 is structured in multiple components catering to varied computer - **Segmentation Masks**: These detail the exact boundary of 2.8M objects across 350 classes. - **Visual Relationships**: 3.3M annotations indicating object relationships, properties, and actions. - **Localized Narratives**: 675k descriptions combining voice, text, and mouse traces. -- **Point-Level Labels**: 66.4M labels across 1.4M images, suitable for zero/few-shot semantic segmentation. +- **Point-Level Labels**: 66.4M labels across 1.4M images, suitable for zero/few-shot [semantic segmentation](https://www.ultralytics.com/glossary/semantic-segmentation). ## Applications @@ -69,7 +69,7 @@ Typically, datasets come with a YAML (Yet Another Markup Language) file that del ## Usage -To train a YOLOv8n model on the Open Images V7 dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n model on the Open Images V7 dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! warning @@ -191,10 +191,10 @@ Ultralytics provides several YOLOv8 pretrained models for the Open Images V7 dat The Open Images V7 dataset supports a variety of computer vision tasks including: -- **Image Classification** +- **[Image Classification](https://www.ultralytics.com/glossary/image-classification)** - **Object Detection** - **Instance Segmentation** - **Visual Relationship Detection** - **Multimodal Image Descriptions** -Its comprehensive annotations and broad scope make it suitable for training and evaluating advanced machine learning models, as highlighted in practical use cases detailed in our [applications](#applications) section. +Its comprehensive annotations and broad scope make it suitable for training and evaluating advanced [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models, as highlighted in practical use cases detailed in our [applications](#applications) section. diff --git a/docs/en/datasets/detect/roboflow-100.md b/docs/en/datasets/detect/roboflow-100.md index 844326c381..6b3c540e03 100644 --- a/docs/en/datasets/detect/roboflow-100.md +++ b/docs/en/datasets/detect/roboflow-100.md @@ -35,7 +35,7 @@ This structure enables a diverse and extensive testing ground for object detecti ## Benchmarking -Dataset benchmarking evaluates machine learning model performance on specific datasets using standardized metrics like accuracy, mean average precision and F1-score. +Dataset benchmarking evaluates machine learning model performance on specific datasets using standardized metrics like [accuracy](https://www.ultralytics.com/glossary/accuracy), [mean average precision](https://www.ultralytics.com/glossary/mean-average-precision-map) and F1-score. !!! tip "Benchmarking" @@ -85,7 +85,7 @@ Dataset benchmarking evaluates machine learning model performance on specific da ## Applications -Roboflow 100 is invaluable for various applications related to computer vision and deep learning. Researchers and engineers can use this benchmark to: +Roboflow 100 is invaluable for various applications related to [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) and [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl). Researchers and engineers can use this benchmark to: - Evaluate the performance of object detection models in a multi-domain context. - Test the adaptability of models to real-world scenarios beyond common object recognition. @@ -127,7 +127,7 @@ If you use the Roboflow 100 dataset in your research or development work, please Our thanks go to the Roboflow team and all the contributors for their hard work in creating and sustaining the Roboflow 100 dataset. -If you are interested in exploring more datasets to enhance your object detection and machine learning projects, feel free to visit [our comprehensive dataset collection](../index.md). +If you are interested in exploring more datasets to enhance your object detection and [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) projects, feel free to visit [our comprehensive dataset collection](../index.md). ## FAQ @@ -183,7 +183,7 @@ To use the Roboflow 100 dataset for benchmarking, you can implement the RF100Ben ### Which domains are covered by the Roboflow 100 dataset? -The **Roboflow 100** dataset spans seven domains, each providing unique challenges and applications for object detection models: +The **Roboflow 100** dataset spans seven domains, each providing unique challenges and applications for [object detection](https://www.ultralytics.com/glossary/object-detection) models: 1. **Aerial**: 7 datasets, 9,683 images, 24 classes 2. **Video Games**: 7 datasets, 11,579 images, 88 classes diff --git a/docs/en/datasets/detect/signature.md b/docs/en/datasets/detect/signature.md index 0d76e11f50..5746d57e02 100644 --- a/docs/en/datasets/detect/signature.md +++ b/docs/en/datasets/detect/signature.md @@ -6,7 +6,7 @@ keywords: Signature Detection Dataset, document verification, fraud detection, c # Signature Detection Dataset -This dataset focuses on detecting human written signatures within documents. It includes a variety of document types with annotated signatures, providing valuable insights for applications in document verification and fraud detection. Essential for training computer vision algorithms, this dataset aids in identifying signatures in various document formats, supporting research and practical applications in document analysis. +This dataset focuses on detecting human written signatures within documents. It includes a variety of document types with annotated signatures, providing valuable insights for applications in document verification and fraud detection. Essential for training [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) algorithms, this dataset aids in identifying signatures in various document formats, supporting research and practical applications in document analysis. ## Dataset Structure @@ -31,7 +31,7 @@ A YAML (Yet Another Markup Language) file defines the dataset configuration, inc ## Usage -To train a YOLOv8n model on the signature detection dataset for 100 epochs with an image size of 640, use the provided code samples. For a comprehensive list of available parameters, refer to the model's [Training](../../modes/train.md) page. +To train a YOLOv8n model on the signature detection dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, use the provided code samples. For a comprehensive list of available parameters, refer to the model's [Training](../../modes/train.md) page. !!! example "Train Example" @@ -93,7 +93,7 @@ The dataset has been released available under the [AGPL-3.0 License](https://git ### What is the Signature Detection Dataset, and how can it be used? -The Signature Detection Dataset is a collection of annotated images aimed at detecting human signatures within various document types. It can be applied in computer vision tasks such as object detection and tracking, primarily for document verification, fraud detection, and archival research. This dataset helps train models to recognize signatures in different contexts, making it valuable for both research and practical applications. +The Signature Detection Dataset is a collection of annotated images aimed at detecting human signatures within various document types. It can be applied in computer vision tasks such as [object detection](https://www.ultralytics.com/glossary/object-detection) and tracking, primarily for document verification, fraud detection, and archival research. This dataset helps train models to recognize signatures in different contexts, making it valuable for both research and practical applications. ### How do I train a YOLOv8n model on the Signature Detection Dataset? @@ -131,7 +131,7 @@ The Signature Detection Dataset can be used for: 1. **Document Verification**: Automatically verifying the presence and authenticity of human signatures in documents. 2. **Fraud Detection**: Identifying forged or fraudulent signatures in legal and financial documents. 3. **Archival Research**: Assisting historians and archivists in the digital analysis and cataloging of historical documents. -4. **Education**: Supporting academic research and teaching in the fields of computer vision and machine learning. +4. **Education**: Supporting academic research and teaching in the fields of computer vision and [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml). ### How can I perform inference using a model trained on the Signature Detection Dataset? diff --git a/docs/en/datasets/detect/sku-110k.md b/docs/en/datasets/detect/sku-110k.md index 145468321e..c6cddc483f 100644 --- a/docs/en/datasets/detect/sku-110k.md +++ b/docs/en/datasets/detect/sku-110k.md @@ -6,7 +6,7 @@ keywords: SKU-110k, dataset, object detection, retail shelf images, deep learnin # SKU-110k Dataset -The [SKU-110k](https://github.com/eg4000/SKU110K_CVPR19) dataset is a collection of densely packed retail shelf images, designed to support research in object detection tasks. Developed by Eran Goldman et al., the dataset contains over 110,000 unique store keeping unit (SKU) categories with densely packed objects, often looking similar or even identical, positioned in close proximity. +The [SKU-110k](https://github.com/eg4000/SKU110K_CVPR19) dataset is a collection of densely packed retail shelf images, designed to support research in [object detection](https://www.ultralytics.com/glossary/object-detection) tasks. Developed by Eran Goldman et al., the dataset contains over 110,000 unique store keeping unit (SKU) categories with densely packed objects, often looking similar or even identical, positioned in close proximity.


@@ -37,7 +37,7 @@ The SKU-110k dataset is organized into three main subsets: ## Applications -The SKU-110k dataset is widely used for training and evaluating deep learning models in object detection tasks, especially in densely packed scenes such as retail shelf displays. The dataset's diverse set of SKU categories and densely packed object arrangements make it a valuable resource for researchers and practitioners in the field of computer vision. +The SKU-110k dataset is widely used for training and evaluating deep learning models in object detection tasks, especially in densely packed scenes such as retail shelf displays. The dataset's diverse set of SKU categories and densely packed object arrangements make it a valuable resource for researchers and practitioners in the field of [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv). ## Dataset YAML @@ -51,7 +51,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n model on the SKU-110K dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n model on the SKU-110K dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -151,7 +151,7 @@ Refer to the [Dataset Structure](#dataset-structure) section for more details. The SKU-110k dataset configuration is defined in a YAML file, which includes details about the dataset's paths, classes, and other relevant information. The `SKU-110K.yaml` file is maintained at [SKU-110K.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/SKU-110K.yaml). For example, you can train a model using this configuration as shown in our [Usage](#usage) section. -### What are the key features of the SKU-110k dataset in the context of deep learning? +### What are the key features of the SKU-110k dataset in the context of [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl)? The SKU-110k dataset features images of store shelves from around the world, showcasing densely packed objects that pose significant challenges for object detectors: diff --git a/docs/en/datasets/detect/visdrone.md b/docs/en/datasets/detect/visdrone.md index c1060e9989..99b182cb4e 100644 --- a/docs/en/datasets/detect/visdrone.md +++ b/docs/en/datasets/detect/visdrone.md @@ -6,7 +6,7 @@ keywords: VisDrone, drone dataset, computer vision, object detection, object tra # VisDrone Dataset -The [VisDrone Dataset](https://github.com/VisDrone/VisDrone-Dataset) is a large-scale benchmark created by the AISKYEYE team at the Lab of Machine Learning and Data Mining, Tianjin University, China. It contains carefully annotated ground truth data for various computer vision tasks related to drone-based image and video analysis. +The [VisDrone Dataset](https://github.com/VisDrone/VisDrone-Dataset) is a large-scale benchmark created by the AISKYEYE team at the Lab of [Machine Learning](https://www.ultralytics.com/glossary/machine-learning-ml) and Data Mining, Tianjin University, China. It contains carefully annotated ground truth data for various computer vision tasks related to drone-based image and video analysis.


@@ -33,7 +33,7 @@ The VisDrone dataset is organized into five main subsets, each focusing on a spe ## Applications -The VisDrone dataset is widely used for training and evaluating deep learning models in drone-based computer vision tasks such as object detection, object tracking, and crowd counting. The dataset's diverse set of sensor data, object annotations, and attributes make it a valuable resource for researchers and practitioners in the field of drone-based computer vision. +The VisDrone dataset is widely used for training and evaluating deep learning models in drone-based [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks such as object detection, object tracking, and crowd counting. The dataset's diverse set of sensor data, object annotations, and attributes make it a valuable resource for researchers and practitioners in the field of drone-based computer vision. ## Dataset YAML @@ -47,7 +47,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n model on the VisDrone dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n model on the VisDrone dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -76,7 +76,7 @@ The VisDrone dataset contains a diverse set of images and videos captured by dro ![Dataset sample image](https://github.com/ultralytics/docs/releases/download/0/visdrone-object-detection-sample.avif) -- **Task 1**: Object detection in images - This image demonstrates an example of object detection in images, where objects are annotated with bounding boxes. The dataset provides a wide variety of images taken from different locations, environments, and densities to facilitate the development of models for this task. +- **Task 1**: [Object detection](https://www.ultralytics.com/glossary/object-detection) in images - This image demonstrates an example of object detection in images, where objects are annotated with bounding boxes. The dataset provides a wide variety of images taken from different locations, environments, and densities to facilitate the development of models for this task. The example showcases the variety and complexity of the data in the VisDrone dataset and highlights the importance of high-quality sensor data for drone-based computer vision tasks. @@ -100,7 +100,7 @@ If you use the VisDrone dataset in your research or development work, please cit doi={10.1109/TPAMI.2021.3119563}} ``` -We would like to acknowledge the AISKYEYE team at the Lab of Machine Learning and Data Mining, Tianjin University, China, for creating and maintaining the VisDrone dataset as a valuable resource for the drone-based computer vision research community. For more information about the VisDrone dataset and its creators, visit the [VisDrone Dataset GitHub repository](https://github.com/VisDrone/VisDrone-Dataset). +We would like to acknowledge the AISKYEYE team at the Lab of Machine Learning and [Data Mining](https://www.ultralytics.com/glossary/data-mining), Tianjin University, China, for creating and maintaining the VisDrone dataset as a valuable resource for the drone-based computer vision research community. For more information about the VisDrone dataset and its creators, visit the [VisDrone Dataset GitHub repository](https://github.com/VisDrone/VisDrone-Dataset). ## FAQ @@ -150,7 +150,7 @@ The VisDrone dataset is divided into five main subsets, each tailored for a spec 4. **Task 4**: Multi-object tracking. 5. **Task 5**: Crowd counting. -These subsets are widely used for training and evaluating deep learning models in drone-based applications such as surveillance, traffic monitoring, and public safety. +These subsets are widely used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in drone-based applications such as surveillance, traffic monitoring, and public safety. ### Where can I find the configuration file for the VisDrone dataset in Ultralytics? diff --git a/docs/en/datasets/detect/voc.md b/docs/en/datasets/detect/voc.md index 0afc920529..7dc67fb5a4 100644 --- a/docs/en/datasets/detect/voc.md +++ b/docs/en/datasets/detect/voc.md @@ -13,7 +13,7 @@ The [PASCAL VOC](http://host.robots.ox.ac.uk/pascal/VOC/) (Visual Object Classes - VOC dataset includes two main challenges: VOC2007 and VOC2012. - The dataset comprises 20 object categories, including common objects like cars, bicycles, and animals, as well as more specific categories such as boats, sofas, and dining tables. - Annotations include object bounding boxes and class labels for object detection and classification tasks, and segmentation masks for the segmentation tasks. -- VOC provides standardized evaluation metrics like mean Average Precision (mAP) for object detection and classification, making it suitable for comparing model performance. +- VOC provides standardized evaluation metrics like [mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP) for object detection and classification, making it suitable for comparing model performance. ## Dataset Structure @@ -25,7 +25,7 @@ The VOC dataset is split into three subsets: ## Applications -The VOC dataset is widely used for training and evaluating deep learning models in object detection (such as YOLO, Faster R-CNN, and SSD), instance segmentation (such as Mask R-CNN), and image classification. The dataset's diverse set of object categories, large number of annotated images, and standardized evaluation metrics make it an essential resource for computer vision researchers and practitioners. +The VOC dataset is widely used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in object detection (such as YOLO, Faster R-CNN, and SSD), [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation) (such as Mask R-CNN), and [image classification](https://www.ultralytics.com/glossary/image-classification). The dataset's diverse set of object categories, large number of annotated images, and standardized evaluation metrics make it an essential resource for computer vision researchers and practitioners. ## Dataset YAML @@ -39,7 +39,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n model on the VOC dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n model on the VOC dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -91,13 +91,13 @@ If you use the VOC dataset in your research or development work, please cite the } ``` -We would like to acknowledge the PASCAL VOC Consortium for creating and maintaining this valuable resource for the computer vision community. For more information about the VOC dataset and its creators, visit the [PASCAL VOC dataset website](http://host.robots.ox.ac.uk/pascal/VOC/). +We would like to acknowledge the PASCAL VOC Consortium for creating and maintaining this valuable resource for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) community. For more information about the VOC dataset and its creators, visit the [PASCAL VOC dataset website](http://host.robots.ox.ac.uk/pascal/VOC/). ## FAQ ### What is the PASCAL VOC dataset and why is it important for computer vision tasks? -The [PASCAL VOC](http://host.robots.ox.ac.uk/pascal/VOC/) (Visual Object Classes) dataset is a renowned benchmark for object detection, segmentation, and classification in computer vision. It includes comprehensive annotations like bounding boxes, class labels, and segmentation masks across 20 different object categories. Researchers use it widely to evaluate the performance of models like Faster R-CNN, YOLO, and Mask R-CNN due to its standardized evaluation metrics such as mean Average Precision (mAP). +The [PASCAL VOC](http://host.robots.ox.ac.uk/pascal/VOC/) (Visual Object Classes) dataset is a renowned benchmark for [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and classification in computer vision. It includes comprehensive annotations like bounding boxes, class labels, and segmentation masks across 20 different object categories. Researchers use it widely to evaluate the performance of models like Faster R-CNN, YOLO, and Mask R-CNN due to its standardized evaluation metrics such as mean Average Precision (mAP). ### How do I train a YOLOv8 model using the VOC dataset? @@ -130,8 +130,8 @@ The VOC dataset includes two main challenges: VOC2007 and VOC2012. These challen ### How does the PASCAL VOC dataset enhance model benchmarking and evaluation? -The PASCAL VOC dataset enhances model benchmarking and evaluation through its detailed annotations and standardized metrics like mean Average Precision (mAP). These metrics are crucial for assessing the performance of object detection and classification models. The dataset's diverse and complex images ensure comprehensive model evaluation across various real-world scenarios. +The PASCAL VOC dataset enhances model benchmarking and evaluation through its detailed annotations and standardized metrics like mean Average [Precision](https://www.ultralytics.com/glossary/precision) (mAP). These metrics are crucial for assessing the performance of object detection and classification models. The dataset's diverse and complex images ensure comprehensive model evaluation across various real-world scenarios. -### How do I use the VOC dataset for semantic segmentation in YOLO models? +### How do I use the VOC dataset for [semantic segmentation](https://www.ultralytics.com/glossary/semantic-segmentation) in YOLO models? To use the VOC dataset for semantic segmentation tasks with YOLO models, you need to configure the dataset properly in a YAML file. The YAML file defines paths and classes needed for training segmentation models. Check the VOC dataset YAML configuration file at [VOC.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/VOC.yaml) for detailed setups. diff --git a/docs/en/datasets/detect/xview.md b/docs/en/datasets/detect/xview.md index e7e2f3d3f7..df8e493357 100644 --- a/docs/en/datasets/detect/xview.md +++ b/docs/en/datasets/detect/xview.md @@ -6,7 +6,7 @@ keywords: xView dataset, overhead imagery, satellite images, object detection, h # xView Dataset -The [xView](http://xviewdataset.org/) dataset is one of the largest publicly available datasets of overhead imagery, containing images from complex scenes around the world annotated using bounding boxes. The goal of the xView dataset is to accelerate progress in four computer vision frontiers: +The [xView](http://xviewdataset.org/) dataset is one of the largest publicly available datasets of overhead imagery, containing images from complex scenes around the world annotated using bounding boxes. The goal of the xView dataset is to accelerate progress in four [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) frontiers: 1. Reduce minimum resolution for detection. 2. Improve learning efficiency. @@ -19,8 +19,8 @@ xView builds on the success of challenges like Common Objects in Context (COCO) - xView contains over 1 million object instances across 60 classes. - The dataset has a resolution of 0.3 meters, providing higher resolution imagery than most public satellite imagery datasets. -- xView features a diverse collection of small, rare, fine-grained, and multi-type objects with bounding box annotation. -- Comes with a pre-trained baseline model using the TensorFlow object detection API and an example for PyTorch. +- xView features a diverse collection of small, rare, fine-grained, and multi-type objects with [bounding box](https://www.ultralytics.com/glossary/bounding-box) annotation. +- Comes with a pre-trained baseline model using the TensorFlow object detection API and an example for [PyTorch](https://www.ultralytics.com/glossary/pytorch). ## Dataset Structure @@ -42,7 +42,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a model on the xView dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a model on the xView dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -71,7 +71,7 @@ The xView dataset contains high-resolution satellite images with a diverse set o ![Dataset sample image](https://github.com/ultralytics/docs/releases/download/0/overhead-imagery-object-detection.avif) -- **Overhead Imagery**: This image demonstrates an example of object detection in overhead imagery, where objects are annotated with bounding boxes. The dataset provides high-resolution satellite images to facilitate the development of models for this task. +- **Overhead Imagery**: This image demonstrates an example of [object detection](https://www.ultralytics.com/glossary/object-detection) in overhead imagery, where objects are annotated with bounding boxes. The dataset provides high-resolution satellite images to facilitate the development of models for this task. The example showcases the variety and complexity of the data in the xView dataset and highlights the importance of high-quality satellite imagery for object detection tasks. @@ -137,11 +137,11 @@ The xView dataset stands out due to its comprehensive set of features: - Over 1 million object instances across 60 distinct classes. - High-resolution imagery at 0.3 meters. - Diverse object types including small, rare, and fine-grained objects, all annotated with bounding boxes. -- Availability of a pre-trained baseline model and examples in TensorFlow and PyTorch. +- Availability of a pre-trained baseline model and examples in [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) and PyTorch. ### What is the dataset structure of xView, and how is it annotated? -The xView dataset comprises high-resolution satellite images collected from WorldView-3 satellites at a 0.3m ground sample distance. It encompasses over 1 million objects across 60 classes in approximately 1,400 km² of imagery. Each object within the dataset is annotated with bounding boxes, making it ideal for training and evaluating deep learning models for object detection in overhead imagery. For a detailed overview, you can look at the dataset structure section [here](#dataset-structure). +The xView dataset comprises high-resolution satellite images collected from WorldView-3 satellites at a 0.3m ground sample distance. It encompasses over 1 million objects across 60 classes in approximately 1,400 km² of imagery. Each object within the dataset is annotated with bounding boxes, making it ideal for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models for object detection in overhead imagery. For a detailed overview, you can look at the dataset structure section [here](#dataset-structure). ### How do I cite the xView dataset in my research? diff --git a/docs/en/datasets/explorer/api.md b/docs/en/datasets/explorer/api.md index 905142efa7..6c716c14c5 100644 --- a/docs/en/datasets/explorer/api.md +++ b/docs/en/datasets/explorer/api.md @@ -50,7 +50,7 @@ dataframe = explorer.get_similar(idx=0) !!! note - Embeddings table for a given dataset and model pair is only created once and reused. These use [LanceDB](https://lancedb.github.io/lancedb/) under the hood, which scales on-disk, so you can create and reuse embeddings for large datasets like COCO without running out of memory. + [Embeddings](https://www.ultralytics.com/glossary/embeddings) table for a given dataset and model pair is only created once and reused. These use [LanceDB](https://lancedb.github.io/lancedb/) under the hood, which scales on-disk, so you can create and reuse embeddings for large datasets like COCO without running out of memory. In case you want to force update the embeddings table, you can pass `force=True` to `create_embeddings_table` method. @@ -339,7 +339,7 @@ Try our GUI Demo based on Explorer API ### What is the Ultralytics Explorer API used for? -The Ultralytics Explorer API is designed for comprehensive dataset exploration. It allows users to filter and search datasets using SQL queries, vector similarity search, and semantic search. This powerful Python API can handle large datasets, making it ideal for various computer vision tasks using Ultralytics models. +The Ultralytics Explorer API is designed for comprehensive dataset exploration. It allows users to filter and search datasets using SQL queries, vector similarity search, and semantic search. This powerful Python API can handle large datasets, making it ideal for various [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks using Ultralytics models. ### How do I install the Ultralytics Explorer API? diff --git a/docs/en/datasets/explorer/dashboard.md b/docs/en/datasets/explorer/dashboard.md index 160d2b7abe..3bc3a21e46 100644 --- a/docs/en/datasets/explorer/dashboard.md +++ b/docs/en/datasets/explorer/dashboard.md @@ -36,7 +36,7 @@ pip install ultralytics[explorer] ## Vector Semantic Similarity Search -Semantic search is a technique for finding similar images to a given image. It is based on the idea that similar images will have similar embeddings. In the UI, you can select one of more images and search for the images similar to them. This can be useful when you want to find images similar to a given image or a set of images that don't perform as expected. +Semantic search is a technique for finding similar images to a given image. It is based on the idea that similar images will have similar [embeddings](https://www.ultralytics.com/glossary/embeddings). In the UI, you can select one of more images and search for the images similar to them. This can be useful when you want to find images similar to a given image or a set of images that don't perform as expected. For example: In this VOC Exploration dashboard, user selects a couple airplane images like this: @@ -79,7 +79,7 @@ This is a Demo build using the Explorer API. You can use the API to build your o ### What is Ultralytics Explorer GUI and how do I install it? -Ultralytics Explorer GUI is a powerful interface that unlocks advanced data exploration capabilities using the [Ultralytics Explorer API](api.md). It allows you to run semantic/vector similarity search, SQL queries, and natural language queries using the Ask AI feature powered by Large Language Models (LLMs). +Ultralytics Explorer GUI is a powerful interface that unlocks advanced data exploration capabilities using the [Ultralytics Explorer API](api.md). It allows you to run semantic/vector similarity search, SQL queries, and natural language queries using the Ask AI feature powered by [Large Language Models](https://www.ultralytics.com/glossary/large-language-model-llm) (LLMs). To install the Explorer GUI, you can use pip: @@ -91,7 +91,7 @@ Note: To use the Ask AI feature, you'll need to set the OpenAI API key: `yolo se ### How does the semantic search feature in Ultralytics Explorer GUI work? -The semantic search feature in Ultralytics Explorer GUI allows you to find images similar to a given image based on their embeddings. This technique is useful for identifying and exploring images that share visual similarities. To use this feature, select one or more images in the UI and execute a search for similar images. The result will display images that closely resemble the selected ones, facilitating efficient dataset exploration and anomaly detection. +The semantic search feature in Ultralytics Explorer GUI allows you to find images similar to a given image based on their embeddings. This technique is useful for identifying and exploring images that share visual similarities. To use this feature, select one or more images in the UI and execute a search for similar images. The result will display images that closely resemble the selected ones, facilitating efficient dataset exploration and [anomaly detection](https://www.ultralytics.com/glossary/anomaly-detection). Learn more about semantic search and other features by visiting the [Feature Overview](#vector-semantic-similarity-search) section. diff --git a/docs/en/datasets/explorer/index.md b/docs/en/datasets/explorer/index.md index d1092a7625..d7e7ab66d4 100644 --- a/docs/en/datasets/explorer/index.md +++ b/docs/en/datasets/explorer/index.md @@ -44,7 +44,7 @@ Learn more about the Explorer API [here](api.md). ## GUI Explorer Usage -The GUI demo runs in your browser allowing you to create embeddings for your dataset and search for similar images, run SQL queries and perform semantic search. It can be run using the following command: +The GUI demo runs in your browser allowing you to create [embeddings](https://www.ultralytics.com/glossary/embeddings) for your dataset and search for similar images, run SQL queries and perform semantic search. It can be run using the following command: ```bash yolo explorer @@ -63,7 +63,7 @@ yolo explorer ### What is Ultralytics Explorer and how can it help with CV datasets? -Ultralytics Explorer is a powerful tool designed for exploring computer vision (CV) datasets through semantic search, SQL queries, vector similarity search, and even natural language. This versatile tool provides both a GUI and a Python API, allowing users to seamlessly interact with their datasets. By leveraging technologies like LanceDB, Ultralytics Explorer ensures efficient, scalable access to large datasets without excessive memory usage. Whether you're performing detailed dataset analysis or exploring data patterns, Ultralytics Explorer streamlines the entire process. +Ultralytics Explorer is a powerful tool designed for exploring [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) (CV) datasets through semantic search, SQL queries, vector similarity search, and even natural language. This versatile tool provides both a GUI and a Python API, allowing users to seamlessly interact with their datasets. By leveraging technologies like LanceDB, Ultralytics Explorer ensures efficient, scalable access to large datasets without excessive memory usage. Whether you're performing detailed dataset analysis or exploring data patterns, Ultralytics Explorer streamlines the entire process. Learn more about the [Explorer API](api.md). diff --git a/docs/en/datasets/index.md b/docs/en/datasets/index.md index 0a85ce15d0..19e395307b 100644 --- a/docs/en/datasets/index.md +++ b/docs/en/datasets/index.md @@ -6,7 +6,7 @@ keywords: Ultralytics, datasets, computer vision, object detection, instance seg # Datasets Overview -Ultralytics provides support for various datasets to facilitate computer vision tasks such as detection, instance segmentation, pose estimation, classification, and multi-object tracking. Below is a list of the main Ultralytics datasets, followed by a summary of each computer vision task and the respective datasets. +Ultralytics provides support for various datasets to facilitate computer vision tasks such as detection, [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation), pose estimation, classification, and multi-object tracking. Below is a list of the main Ultralytics datasets, followed by a summary of each computer vision task and the respective datasets.


@@ -21,7 +21,7 @@ Ultralytics provides support for various datasets to facilitate computer vision ## NEW 🚀 Ultralytics Explorer -Create embeddings for your dataset, search for similar images, run SQL queries, perform semantic search and even search using natural language! You can get started with our GUI app or build your own using the API. Learn more [here](explorer/index.md). +Create [embeddings](https://www.ultralytics.com/glossary/embeddings) for your dataset, search for similar images, run SQL queries, perform semantic search and even search using natural language! You can get started with our GUI app or build your own using the API. Learn more [here](explorer/index.md).

Ultralytics Explorer Screenshot @@ -32,7 +32,7 @@ Create embeddings for your dataset, search for similar images, run SQL queries, ## [Object Detection](detect/index.md) -Bounding box object detection is a computer vision technique that involves detecting and localizing objects in an image by drawing a bounding box around each object. +[Bounding box](https://www.ultralytics.com/glossary/bounding-box) object detection is a computer vision technique that involves detecting and localizing objects in an image by drawing a bounding box around each object. - [Argoverse](detect/argoverse.md): A dataset containing 3D tracking and motion forecasting data from urban environments with rich annotations. - [COCO](detect/coco.md): Common Objects in Context (COCO) is a large-scale object detection, segmentation, and captioning dataset with 80 object categories. @@ -72,7 +72,7 @@ Pose estimation is a technique used to determine the pose of the object relative ## [Classification](classify/index.md) -Image classification is a computer vision task that involves categorizing an image into one or more predefined classes or categories based on its visual content. +[Image classification](https://www.ultralytics.com/glossary/image-classification) is a computer vision task that involves categorizing an image into one or more predefined classes or categories based on its visual content. - [Caltech 101](classify/caltech101.md): A dataset containing images of 101 object categories for image classification tasks. - [Caltech 256](classify/caltech256.md): An extended version of Caltech 101 with 256 object categories and more challenging images. @@ -152,7 +152,7 @@ By following these steps, you can contribute a new dataset that integrates well ## FAQ -### What datasets does Ultralytics support for object detection? +### What datasets does Ultralytics support for [object detection](https://www.ultralytics.com/glossary/object-detection)? Ultralytics supports a wide variety of datasets for object detection, including: @@ -190,7 +190,7 @@ Ultralytics Explorer offers powerful features for dataset analysis, including: Explore the [Ultralytics Explorer](explorer/index.md) for more information and to try the [GUI Demo](explorer/index.md). -### What are the unique features of Ultralytics YOLO models for computer vision? +### What are the unique features of Ultralytics YOLO models for [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv)? Ultralytics YOLO models provide several unique features: diff --git a/docs/en/datasets/obb/dota-v2.md b/docs/en/datasets/obb/dota-v2.md index 66b3ac5f21..76024cac10 100644 --- a/docs/en/datasets/obb/dota-v2.md +++ b/docs/en/datasets/obb/dota-v2.md @@ -6,7 +6,7 @@ keywords: DOTA dataset, object detection, aerial images, oriented bounding boxes # DOTA Dataset with OBB -[DOTA](https://captain-whu.github.io/DOTA/index.html) stands as a specialized dataset, emphasizing object detection in aerial images. Originating from the DOTA series of datasets, it offers annotated images capturing a diverse array of aerial scenes with Oriented Bounding Boxes (OBB). +[DOTA](https://captain-whu.github.io/DOTA/index.html) stands as a specialized dataset, emphasizing [object detection](https://www.ultralytics.com/glossary/object-detection) in aerial images. Originating from the DOTA series of datasets, it offers annotated images capturing a diverse array of aerial scenes with Oriented Bounding Boxes (OBB). ![DOTA classes visual](https://github.com/ultralytics/docs/releases/download/0/dota-classes-visual.avif) @@ -128,7 +128,7 @@ Having a glance at the dataset illustrates its depth: ![Dataset sample image](https://github.com/ultralytics/docs/releases/download/0/instances-DOTA.avif) -- **DOTA examples**: This snapshot underlines the complexity of aerial scenes and the significance of Oriented Bounding Box annotations, capturing objects in their natural orientation. +- **DOTA examples**: This snapshot underlines the complexity of aerial scenes and the significance of Oriented [Bounding Box](https://www.ultralytics.com/glossary/bounding-box) annotations, capturing objects in their natural orientation. The dataset's richness offers invaluable insights into object detection challenges exclusive to aerial imagery. diff --git a/docs/en/datasets/obb/dota8.md b/docs/en/datasets/obb/dota8.md index 0188c31785..f24ea5bce2 100644 --- a/docs/en/datasets/obb/dota8.md +++ b/docs/en/datasets/obb/dota8.md @@ -8,7 +8,7 @@ keywords: DOTA8 dataset, Ultralytics, YOLOv8, object detection, debugging, train ## Introduction -[Ultralytics](https://www.ultralytics.com/) DOTA8 is a small, but versatile oriented object detection dataset composed of the first 8 images of 8 images of the split DOTAv1 set, 4 for training and 4 for validation. This dataset is ideal for testing and debugging object detection models, or for experimenting with new detection approaches. With 8 images, it is small enough to be easily manageable, yet diverse enough to test training pipelines for errors and act as a sanity check before training larger datasets. +[Ultralytics](https://www.ultralytics.com/) DOTA8 is a small, but versatile oriented [object detection](https://www.ultralytics.com/glossary/object-detection) dataset composed of the first 8 images of 8 images of the split DOTAv1 set, 4 for training and 4 for validation. This dataset is ideal for testing and debugging object detection models, or for experimenting with new detection approaches. With 8 images, it is small enough to be easily manageable, yet diverse enough to test training pipelines for errors and act as a sanity check before training larger datasets. This dataset is intended for use with Ultralytics [HUB](https://hub.ultralytics.com/) and [YOLOv8](https://github.com/ultralytics/ultralytics). @@ -24,7 +24,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n-obb model on the DOTA8 dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n-obb model on the DOTA8 dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -121,4 +121,4 @@ Mosaicing combines multiple images into one during training, increasing the vari ### Why should I use Ultralytics YOLOv8 for object detection tasks? -Ultralytics YOLOv8 provides state-of-the-art real-time object detection capabilities, including features like oriented bounding boxes (OBB), instance segmentation, and a highly versatile training pipeline. It's suitable for various applications and offers pretrained models for efficient fine-tuning. Explore further about the advantages and usage in the [Ultralytics YOLOv8 documentation](https://github.com/ultralytics/ultralytics). +Ultralytics YOLOv8 provides state-of-the-art real-time object detection capabilities, including features like oriented bounding boxes (OBB), [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation), and a highly versatile training pipeline. It's suitable for various applications and offers pretrained models for efficient fine-tuning. Explore further about the advantages and usage in the [Ultralytics YOLOv8 documentation](https://github.com/ultralytics/ultralytics). diff --git a/docs/en/datasets/obb/index.md b/docs/en/datasets/obb/index.md index 4ca53497be..edeffb83af 100644 --- a/docs/en/datasets/obb/index.md +++ b/docs/en/datasets/obb/index.md @@ -6,7 +6,7 @@ keywords: Oriented Bounding Box, OBB Datasets, YOLO, Ultralytics, Object Detecti # Oriented Bounding Box (OBB) Datasets Overview -Training a precise object detection model with oriented bounding boxes (OBB) requires a thorough dataset. This guide explains the various OBB dataset formats compatible with Ultralytics YOLO models, offering insights into their structure, application, and methods for format conversions. +Training a precise [object detection](https://www.ultralytics.com/glossary/object-detection) model with oriented bounding boxes (OBB) requires a thorough dataset. This guide explains the various OBB dataset formats compatible with Ultralytics YOLO models, offering insights into their structure, application, and methods for format conversions. ## Supported OBB Dataset Formats @@ -18,7 +18,7 @@ The YOLO OBB format designates bounding boxes by their four corner points with c class_index x1 y1 x2 y2 x3 y3 x4 y4 ``` -Internally, YOLO processes losses and outputs in the `xywhr` format, which represents the bounding box's center point (xy), width, height, and rotation. +Internally, YOLO processes losses and outputs in the `xywhr` format, which represents the [bounding box](https://www.ultralytics.com/glossary/bounding-box)'s center point (xy), width, height, and rotation.

OBB format examples

@@ -129,7 +129,7 @@ Training a YOLOv8 model with OBBs involves ensuring your dataset is in the YOLO yolo obb train data=your_dataset.yaml model=yolov8n-obb.yaml epochs=100 imgsz=640 ``` -This ensures your model leverages the detailed OBB annotations for improved detection accuracy. +This ensures your model leverages the detailed OBB annotations for improved detection [accuracy](https://www.ultralytics.com/glossary/accuracy). ### What datasets are currently supported for OBB training in Ultralytics YOLO models? diff --git a/docs/en/datasets/pose/coco.md b/docs/en/datasets/pose/coco.md index 8addbd96e3..20042b40e2 100644 --- a/docs/en/datasets/pose/coco.md +++ b/docs/en/datasets/pose/coco.md @@ -37,7 +37,7 @@ The COCO-Pose dataset is split into three subsets: ## Applications -The COCO-Pose dataset is specifically used for training and evaluating deep learning models in keypoint detection and pose estimation tasks, such as OpenPose. The dataset's large number of annotated images and standardized evaluation metrics make it an essential resource for computer vision researchers and practitioners focused on pose estimation. +The COCO-Pose dataset is specifically used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in keypoint detection and pose estimation tasks, such as OpenPose. The dataset's large number of annotated images and standardized evaluation metrics make it an essential resource for [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) researchers and practitioners focused on pose estimation. ## Dataset YAML @@ -51,7 +51,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n-pose model on the COCO-Pose dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n-pose model on the COCO-Pose dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -140,7 +140,7 @@ For more details on the training process and available arguments, check the [tra ### What are the different metrics provided by the COCO-Pose dataset for evaluating model performance? -The COCO-Pose dataset provides several standardized evaluation metrics for pose estimation tasks, similar to the original COCO dataset. Key metrics include the Object Keypoint Similarity (OKS), which evaluates the accuracy of predicted keypoints against ground truth annotations. These metrics allow for thorough performance comparisons between different models. For instance, the COCO-Pose pretrained models such as YOLOv8n-pose, YOLOv8s-pose, and others have specific performance metrics listed in the documentation, like mAPpose50-95 and mAPpose50. +The COCO-Pose dataset provides several standardized evaluation metrics for pose estimation tasks, similar to the original COCO dataset. Key metrics include the Object Keypoint Similarity (OKS), which evaluates the [accuracy](https://www.ultralytics.com/glossary/accuracy) of predicted keypoints against ground truth annotations. These metrics allow for thorough performance comparisons between different models. For instance, the COCO-Pose pretrained models such as YOLOv8n-pose, YOLOv8s-pose, and others have specific performance metrics listed in the documentation, like mAPpose50-95 and mAPpose50. ### How is the dataset structured and split for the COCO-Pose dataset? diff --git a/docs/en/datasets/pose/coco8-pose.md b/docs/en/datasets/pose/coco8-pose.md index c5847e1129..95157b794e 100644 --- a/docs/en/datasets/pose/coco8-pose.md +++ b/docs/en/datasets/pose/coco8-pose.md @@ -8,7 +8,7 @@ keywords: COCO8-Pose, Ultralytics, pose detection dataset, object detection, YOL ## Introduction -[Ultralytics](https://www.ultralytics.com/) COCO8-Pose is a small, but versatile pose detection dataset composed of the first 8 images of the COCO train 2017 set, 4 for training and 4 for validation. This dataset is ideal for testing and debugging object detection models, or for experimenting with new detection approaches. With 8 images, it is small enough to be easily manageable, yet diverse enough to test training pipelines for errors and act as a sanity check before training larger datasets. +[Ultralytics](https://www.ultralytics.com/) COCO8-Pose is a small, but versatile pose detection dataset composed of the first 8 images of the COCO train 2017 set, 4 for training and 4 for validation. This dataset is ideal for testing and debugging [object detection](https://www.ultralytics.com/glossary/object-detection) models, or for experimenting with new detection approaches. With 8 images, it is small enough to be easily manageable, yet diverse enough to test training pipelines for errors and act as a sanity check before training larger datasets. This dataset is intended for use with Ultralytics [HUB](https://hub.ultralytics.com/) and [YOLOv8](https://github.com/ultralytics/ultralytics). @@ -24,7 +24,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n-pose model on the COCO8-Pose dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n-pose model on the COCO8-Pose dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -76,7 +76,7 @@ If you use the COCO dataset in your research or development work, please cite th } ``` -We would like to acknowledge the COCO Consortium for creating and maintaining this valuable resource for the computer vision community. For more information about the COCO dataset and its creators, visit the [COCO dataset website](https://cocodataset.org/#home). +We would like to acknowledge the COCO Consortium for creating and maintaining this valuable resource for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) community. For more information about the COCO dataset and its creators, visit the [COCO dataset website](https://cocodataset.org/#home). ## FAQ diff --git a/docs/en/datasets/pose/index.md b/docs/en/datasets/pose/index.md index 4288497174..9a6b6d930f 100644 --- a/docs/en/datasets/pose/index.md +++ b/docs/en/datasets/pose/index.md @@ -34,7 +34,7 @@ Format with Dim = 3 ``` -In this format, `` is the index of the class for the object,` ` are coordinates of bounding box, and ` ... ` are the pixel coordinates of the keypoints. The coordinates are separated by spaces. +In this format, `` is the index of the class for the object,` ` are coordinates of [bounding box](https://www.ultralytics.com/glossary/bounding-box), and ` ... ` are the pixel coordinates of the keypoints. The coordinates are separated by spaces. ### Dataset YAML format @@ -91,7 +91,7 @@ This section outlines the datasets that are compatible with Ultralytics YOLO for ### COCO-Pose -- **Description**: COCO-Pose is a large-scale object detection, segmentation, and pose estimation dataset. It is a subset of the popular COCO dataset and focuses on human pose estimation. COCO-Pose includes multiple keypoints for each human instance. +- **Description**: COCO-Pose is a large-scale [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and pose estimation dataset. It is a subset of the popular COCO dataset and focuses on human pose estimation. COCO-Pose includes multiple keypoints for each human instance. - **Label Format**: Same as Ultralytics YOLO format as described above, with keypoints for human poses. - **Number of Classes**: 1 (Human). - **Keypoints**: 17 keypoints including nose, eyes, ears, shoulders, elbows, wrists, hips, knees, and ankles. diff --git a/docs/en/datasets/pose/tiger-pose.md b/docs/en/datasets/pose/tiger-pose.md index 13f62232d6..06333b345b 100644 --- a/docs/en/datasets/pose/tiger-pose.md +++ b/docs/en/datasets/pose/tiger-pose.md @@ -37,7 +37,7 @@ A YAML (Yet Another Markup Language) file serves as the means to specify the con ## Usage -To train a YOLOv8n-pose model on the Tiger-Pose dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n-pose model on the Tiger-Pose dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -161,4 +161,4 @@ To perform inference using a YOLOv8 model trained on the Tiger-Pose dataset, you ### What are the benefits of using the Tiger-Pose dataset for pose estimation? -The Tiger-Pose dataset, despite its manageable size of 210 images for training, provides a diverse collection of images that are ideal for testing pose estimation pipelines. The dataset helps identify potential errors and acts as a preliminary step before working with larger datasets. Additionally, the dataset supports the training and refinement of pose estimation algorithms using advanced tools like [Ultralytics HUB](https://hub.ultralytics.com/) and [YOLOv8](https://github.com/ultralytics/ultralytics), enhancing model performance and accuracy. +The Tiger-Pose dataset, despite its manageable size of 210 images for training, provides a diverse collection of images that are ideal for testing pose estimation pipelines. The dataset helps identify potential errors and acts as a preliminary step before working with larger datasets. Additionally, the dataset supports the training and refinement of pose estimation algorithms using advanced tools like [Ultralytics HUB](https://hub.ultralytics.com/) and [YOLOv8](https://github.com/ultralytics/ultralytics), enhancing model performance and [accuracy](https://www.ultralytics.com/glossary/accuracy). diff --git a/docs/en/datasets/segment/carparts-seg.md b/docs/en/datasets/segment/carparts-seg.md index 6283cae8ce..b798cacad1 100644 --- a/docs/en/datasets/segment/carparts-seg.md +++ b/docs/en/datasets/segment/carparts-seg.md @@ -6,7 +6,7 @@ keywords: Carparts Segmentation Dataset, Roboflow, computer vision, automotive A # Roboflow Universe Carparts Segmentation Dataset -The [Roboflow](https://roboflow.com/?ref=ultralytics) [Carparts Segmentation Dataset](https://universe.roboflow.com/gianmarco-russo-vt9xr/car-seg-un1pm?ref=ultralytics) is a curated collection of images and videos designed for computer vision applications, specifically focusing on segmentation tasks related to car parts. This dataset provides a diverse set of visuals captured from multiple perspectives, offering valuable annotated examples for training and testing segmentation models. +The [Roboflow](https://roboflow.com/?ref=ultralytics) [Carparts Segmentation Dataset](https://universe.roboflow.com/gianmarco-russo-vt9xr/car-seg-un1pm?ref=ultralytics) is a curated collection of images and videos designed for [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) applications, specifically focusing on segmentation tasks related to car parts. This dataset provides a diverse set of visuals captured from multiple perspectives, offering valuable annotated examples for training and testing segmentation models. Whether you're working on automotive research, developing AI solutions for vehicle maintenance, or exploring computer vision applications, the Carparts Segmentation Dataset serves as a valuable resource for enhancing accuracy and efficiency in your projects. @@ -18,7 +18,7 @@ Whether you're working on automotive research, developing AI solutions for vehic allowfullscreen>
- Watch: Carparts Instance Segmentation Using Ultralytics HUB + Watch: Carparts [Instance Segmentation](https://www.ultralytics.com/glossary/instance-segmentation) Using Ultralytics HUB

## Dataset Structure @@ -45,7 +45,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train Ultralytics YOLOv8n model on the Carparts Segmentation dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train Ultralytics YOLOv8n model on the Carparts Segmentation dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -156,6 +156,6 @@ The dataset configuration file for the Carparts Segmentation dataset, `carparts- ### Why should I use the Carparts Segmentation Dataset? -The Carparts Segmentation Dataset provides rich, annotated data essential for developing high-accuracy segmentation models in automotive computer vision. This dataset's diversity and detailed annotations improve model training, making it ideal for applications like vehicle maintenance automation, enhancing vehicle safety systems, and supporting autonomous driving technologies. Partnering with a robust dataset accelerates AI development and ensures better model performance. +The Carparts Segmentation Dataset provides rich, annotated data essential for developing high-[accuracy](https://www.ultralytics.com/glossary/accuracy) segmentation models in automotive computer vision. This dataset's diversity and detailed annotations improve model training, making it ideal for applications like vehicle maintenance automation, enhancing vehicle safety systems, and supporting autonomous driving technologies. Partnering with a robust dataset accelerates AI development and ensures better model performance. For more details, visit the [CarParts Segmentation Dataset Page](https://universe.roboflow.com/gianmarco-russo-vt9xr/car-seg-un1pm?ref=ultralytics). diff --git a/docs/en/datasets/segment/coco.md b/docs/en/datasets/segment/coco.md index 5c6b56402d..0f403c69af 100644 --- a/docs/en/datasets/segment/coco.md +++ b/docs/en/datasets/segment/coco.md @@ -6,7 +6,7 @@ keywords: COCO-Seg, dataset, YOLO models, instance segmentation, object detectio # COCO-Seg Dataset -The [COCO-Seg](https://cocodataset.org/#home) dataset, an extension of the COCO (Common Objects in Context) dataset, is specially designed to aid research in object instance segmentation. It uses the same images as COCO but introduces more detailed segmentation annotations. This dataset is a crucial resource for researchers and developers working on instance segmentation tasks, especially for training YOLO models. +The [COCO-Seg](https://cocodataset.org/#home) dataset, an extension of the COCO (Common Objects in Context) dataset, is specially designed to aid research in object [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation). It uses the same images as COCO but introduces more detailed segmentation annotations. This dataset is a crucial resource for researchers and developers working on instance segmentation tasks, especially for training YOLO models. ## COCO-Seg Pretrained Models @@ -23,7 +23,7 @@ The [COCO-Seg](https://cocodataset.org/#home) dataset, an extension of the COCO - COCO-Seg retains the original 330K images from COCO. - The dataset consists of the same 80 object categories found in the original COCO dataset. - Annotations now include more detailed instance segmentation masks for each object in the images. -- COCO-Seg provides standardized evaluation metrics like mean Average Precision (mAP) for object detection, and mean Average Recall (mAR) for instance segmentation tasks, enabling effective comparison of model performance. +- COCO-Seg provides standardized evaluation metrics like [mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP) for object detection, and mean Average [Recall](https://www.ultralytics.com/glossary/recall) (mAR) for instance segmentation tasks, enabling effective comparison of model performance. ## Dataset Structure @@ -35,7 +35,7 @@ The COCO-Seg dataset is partitioned into three subsets: ## Applications -COCO-Seg is widely used for training and evaluating deep learning models in instance segmentation, such as the YOLO models. The large number of annotated images, the diversity of object categories, and the standardized evaluation metrics make it an indispensable resource for computer vision researchers and practitioners. +COCO-Seg is widely used for training and evaluating [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models in instance segmentation, such as the YOLO models. The large number of annotated images, the diversity of object categories, and the standardized evaluation metrics make it an indispensable resource for computer vision researchers and practitioners. ## Dataset YAML @@ -49,7 +49,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n-seg model on the COCO-Seg dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n-seg model on the COCO-Seg dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -101,7 +101,7 @@ If you use the COCO-Seg dataset in your research or development work, please cit } ``` -We extend our thanks to the COCO Consortium for creating and maintaining this invaluable resource for the computer vision community. For more information about the COCO dataset and its creators, visit the [COCO dataset website](https://cocodataset.org/#home). +We extend our thanks to the COCO Consortium for creating and maintaining this invaluable resource for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) community. For more information about the COCO dataset and its creators, visit the [COCO dataset website](https://cocodataset.org/#home). ## FAQ @@ -141,7 +141,7 @@ The COCO-Seg dataset includes several key features: - Retains the original 330K images from the COCO dataset. - Annotates the same 80 object categories found in the original COCO. - Provides more detailed instance segmentation masks for each object. -- Uses standardized evaluation metrics such as mean Average Precision (mAP) for object detection and mean Average Recall (mAR) for instance segmentation tasks. +- Uses standardized evaluation metrics such as mean Average [Precision](https://www.ultralytics.com/glossary/precision) (mAP) for [object detection](https://www.ultralytics.com/glossary/object-detection) and mean Average Recall (mAR) for instance segmentation tasks. ### What pretrained models are available for COCO-Seg, and what are their performance metrics? diff --git a/docs/en/datasets/segment/coco8-seg.md b/docs/en/datasets/segment/coco8-seg.md index 50a7f41af9..21abf3d802 100644 --- a/docs/en/datasets/segment/coco8-seg.md +++ b/docs/en/datasets/segment/coco8-seg.md @@ -8,7 +8,7 @@ keywords: COCO8-Seg, Ultralytics, segmentation dataset, YOLOv8, COCO 2017, model ## Introduction -[Ultralytics](https://www.ultralytics.com/) COCO8-Seg is a small, but versatile instance segmentation dataset composed of the first 8 images of the COCO train 2017 set, 4 for training and 4 for validation. This dataset is ideal for testing and debugging segmentation models, or for experimenting with new detection approaches. With 8 images, it is small enough to be easily manageable, yet diverse enough to test training pipelines for errors and act as a sanity check before training larger datasets. +[Ultralytics](https://www.ultralytics.com/) COCO8-Seg is a small, but versatile [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation) dataset composed of the first 8 images of the COCO train 2017 set, 4 for training and 4 for validation. This dataset is ideal for testing and debugging segmentation models, or for experimenting with new detection approaches. With 8 images, it is small enough to be easily manageable, yet diverse enough to test training pipelines for errors and act as a sanity check before training larger datasets. This dataset is intended for use with Ultralytics [HUB](https://hub.ultralytics.com/) and [YOLOv8](https://github.com/ultralytics/ultralytics). @@ -24,7 +24,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train a YOLOv8n-seg model on the COCO8-Seg dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train a YOLOv8n-seg model on the COCO8-Seg dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -76,7 +76,7 @@ If you use the COCO dataset in your research or development work, please cite th } ``` -We would like to acknowledge the COCO Consortium for creating and maintaining this valuable resource for the computer vision community. For more information about the COCO dataset and its creators, visit the [COCO dataset website](https://cocodataset.org/#home). +We would like to acknowledge the COCO Consortium for creating and maintaining this valuable resource for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) community. For more information about the COCO dataset and its creators, visit the [COCO dataset website](https://cocodataset.org/#home). ## FAQ @@ -121,4 +121,4 @@ The YAML configuration file for the **COCO8-Seg dataset** is available in the Ul ### What are some benefits of using mosaicing during training with the COCO8-Seg dataset? -Using **mosaicing** during training helps increase the diversity and variety of objects and scenes in each training batch. This technique combines multiple images into a single composite image, enhancing the model's ability to generalize to different object sizes, aspect ratios, and contexts within the scene. Mosaicing is beneficial for improving a model's robustness and accuracy, especially when working with small datasets like COCO8-Seg. For an example of mosaiced images, see the [Sample Images and Annotations](#sample-images-and-annotations) section. +Using **mosaicing** during training helps increase the diversity and variety of objects and scenes in each training batch. This technique combines multiple images into a single composite image, enhancing the model's ability to generalize to different object sizes, aspect ratios, and contexts within the scene. Mosaicing is beneficial for improving a model's robustness and [accuracy](https://www.ultralytics.com/glossary/accuracy), especially when working with small datasets like COCO8-Seg. For an example of mosaiced images, see the [Sample Images and Annotations](#sample-images-and-annotations) section. diff --git a/docs/en/datasets/segment/crack-seg.md b/docs/en/datasets/segment/crack-seg.md index ed66d7cf94..f5ffbe92e0 100644 --- a/docs/en/datasets/segment/crack-seg.md +++ b/docs/en/datasets/segment/crack-seg.md @@ -6,9 +6,9 @@ keywords: Roboflow, Crack Segmentation Dataset, Ultralytics, transportation safe # Roboflow Universe Crack Segmentation Dataset -The [Roboflow](https://roboflow.com/?ref=ultralytics) [Crack Segmentation Dataset](https://universe.roboflow.com/university-bswxt/crack-bphdr?ref=ultralytics) stands out as an extensive resource designed specifically for individuals involved in transportation and public safety studies. It is equally beneficial for those working on the development of self-driving car models or simply exploring computer vision applications for recreational purposes. +The [Roboflow](https://roboflow.com/?ref=ultralytics) [Crack Segmentation Dataset](https://universe.roboflow.com/university-bswxt/crack-bphdr?ref=ultralytics) stands out as an extensive resource designed specifically for individuals involved in transportation and public safety studies. It is equally beneficial for those working on the development of self-driving car models or simply exploring [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) applications for recreational purposes. -Comprising a total of 4029 static images captured from diverse road and wall scenarios, this dataset emerges as a valuable asset for tasks related to crack segmentation. Whether you are delving into the intricacies of transportation research or seeking to enhance the accuracy of your self-driving car models, this dataset provides a rich and varied collection of images to support your endeavors. +Comprising a total of 4029 static images captured from diverse road and wall scenarios, this dataset emerges as a valuable asset for tasks related to crack segmentation. Whether you are delving into the intricacies of transportation research or seeking to enhance the [accuracy](https://www.ultralytics.com/glossary/accuracy) of your self-driving car models, this dataset provides a rich and varied collection of images to support your endeavors. ## Dataset Structure @@ -34,7 +34,7 @@ A YAML (Yet Another Markup Language) file is employed to outline the configurati ## Usage -To train Ultralytics YOLOv8n model on the Crack Segmentation dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train Ultralytics YOLOv8n model on the Crack Segmentation dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -129,7 +129,7 @@ The Crack Segmentation Dataset is exceptionally suited for self-driving car proj ### What unique features does Ultralytics YOLO offer for crack segmentation? -Ultralytics YOLO offers advanced real-time object detection, segmentation, and classification capabilities that make it ideal for crack segmentation tasks. Its ability to handle large datasets and complex scenarios ensures high accuracy and efficiency. For example, the model [Training](../../modes/train.md), [Predict](../../modes/predict.md), and [Export](../../modes/export.md) modes cover comprehensive functionalities from training to deployment. +Ultralytics YOLO offers advanced real-time [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and classification capabilities that make it ideal for crack segmentation tasks. Its ability to handle large datasets and complex scenarios ensures high accuracy and efficiency. For example, the model [Training](../../modes/train.md), [Predict](../../modes/predict.md), and [Export](../../modes/export.md) modes cover comprehensive functionalities from training to deployment. ### How do I cite the Roboflow Crack Segmentation Dataset in my research paper? diff --git a/docs/en/datasets/segment/index.md b/docs/en/datasets/segment/index.md index 4d39fc124c..52b1978164 100644 --- a/docs/en/datasets/segment/index.md +++ b/docs/en/datasets/segment/index.md @@ -91,9 +91,9 @@ The `train` and `val` fields specify the paths to the directories containing the ## Supported Datasets -- [COCO](coco.md): A comprehensive dataset for object detection, segmentation, and captioning, featuring over 200K labeled images across a wide range of categories. +- [COCO](coco.md): A comprehensive dataset for [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and captioning, featuring over 200K labeled images across a wide range of categories. - [COCO8-seg](coco8-seg.md): A compact, 8-image subset of COCO designed for quick testing of segmentation model training, ideal for CI checks and workflow validation in the `ultralytics` repository. -- [COCO128-seg](coco.md): A smaller dataset for instance segmentation tasks, containing a subset of 128 COCO images with segmentation annotations. +- [COCO128-seg](coco.md): A smaller dataset for [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation) tasks, containing a subset of 128 COCO images with segmentation annotations. - [Carparts-seg](carparts-seg.md): A specialized dataset focused on the segmentation of car parts, ideal for automotive applications. It includes a variety of vehicles with detailed annotations of individual car components. - [Crack-seg](crack-seg.md): A dataset tailored for the segmentation of cracks in various surfaces. Essential for infrastructure maintenance and quality control, it provides detailed imagery for training models to identify structural weaknesses. - [Package-seg](package-seg.md): A dataset dedicated to the segmentation of different types of packaging materials and shapes. It's particularly useful for logistics and warehouse automation, aiding in the development of systems for package handling and sorting. diff --git a/docs/en/datasets/segment/package-seg.md b/docs/en/datasets/segment/package-seg.md index db5f62be5f..477072fb57 100644 --- a/docs/en/datasets/segment/package-seg.md +++ b/docs/en/datasets/segment/package-seg.md @@ -6,7 +6,7 @@ keywords: Roboflow, Package Segmentation Dataset, computer vision, package ident # Roboflow Universe Package Segmentation Dataset -The [Roboflow](https://roboflow.com/?ref=ultralytics) [Package Segmentation Dataset](https://universe.roboflow.com/factorypackage/factory_package?ref=ultralytics) is a curated collection of images specifically tailored for tasks related to package segmentation in the field of computer vision. This dataset is designed to assist researchers, developers, and enthusiasts working on projects related to package identification, sorting, and handling. +The [Roboflow](https://roboflow.com/?ref=ultralytics) [Package Segmentation Dataset](https://universe.roboflow.com/factorypackage/factory_package?ref=ultralytics) is a curated collection of images specifically tailored for tasks related to package segmentation in the field of [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv). This dataset is designed to assist researchers, developers, and enthusiasts working on projects related to package identification, sorting, and handling. Containing a diverse set of images showcasing various packages in different contexts and environments, the dataset serves as a valuable resource for training and evaluating segmentation models. Whether you are engaged in logistics, warehouse automation, or any application requiring precise package analysis, the Package Segmentation Dataset provides a targeted and comprehensive set of images to enhance the performance of your computer vision algorithms. @@ -34,7 +34,7 @@ A YAML (Yet Another Markup Language) file is used to define the dataset configur ## Usage -To train Ultralytics YOLOv8n model on the Package Segmentation dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. +To train Ultralytics YOLOv8n model on the Package Segmentation dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model [Training](../../modes/train.md) page. !!! example "Train Example" @@ -63,7 +63,7 @@ The Package Segmentation dataset comprises a varied collection of images and vid ![Dataset sample image](https://github.com/ultralytics/docs/releases/download/0/dataset-sample-image-1.avif) -- This image displays an instance of image object detection, featuring annotated bounding boxes with masks outlining recognized objects. The dataset incorporates a diverse collection of images taken in different locations, environments, and densities. It serves as a comprehensive resource for developing models specific to this task. +- This image displays an instance of image [object detection](https://www.ultralytics.com/glossary/object-detection), featuring annotated bounding boxes with masks outlining recognized objects. The dataset incorporates a diverse collection of images taken in different locations, environments, and densities. It serves as a comprehensive resource for developing models specific to this task. - The example emphasizes the diversity and complexity present in the VisDrone dataset, underscoring the significance of high-quality sensor data for computer vision tasks involving drones. ## Citations and Acknowledgments @@ -136,7 +136,7 @@ This structure ensures a balanced dataset for thorough model training, validatio ### Why should I use Ultralytics YOLOv8 with the Package Segmentation Dataset? -Ultralytics YOLOv8 provides state-of-the-art accuracy and speed for real-time object detection and segmentation tasks. Using it with the Package Segmentation Dataset allows you to leverage YOLOv8's capabilities for precise package segmentation. This combination is especially beneficial for industries like logistics and warehouse automation, where accurate package identification is critical. For more information, check out our [page on YOLOv8 segmentation](https://docs.ultralytics.com/models/yolov8/). +Ultralytics YOLOv8 provides state-of-the-art [accuracy](https://www.ultralytics.com/glossary/accuracy) and speed for real-time object detection and segmentation tasks. Using it with the Package Segmentation Dataset allows you to leverage YOLOv8's capabilities for precise package segmentation. This combination is especially beneficial for industries like logistics and warehouse automation, where accurate package identification is critical. For more information, check out our [page on YOLOv8 segmentation](https://docs.ultralytics.com/models/yolov8/). ### How can I access and use the package-seg.yaml file for the Package Segmentation Dataset? diff --git a/docs/en/datasets/track/index.md b/docs/en/datasets/track/index.md index a2e5c13107..f9a8b4f81b 100644 --- a/docs/en/datasets/track/index.md +++ b/docs/en/datasets/track/index.md @@ -52,7 +52,7 @@ To use Multi-Object Tracking with Ultralytics YOLO, you can start by using the P yolo track model=yolov8n.pt source="https://youtu.be/LNwODJXcvt4" conf=0.3 iou=0.5 show ``` -These commands load the YOLOv8 model and use it for tracking objects in the given video source with specific confidence (`conf`) and Intersection over Union (`iou`) thresholds. For more details, refer to the [track mode documentation](../../modes/track.md). +These commands load the YOLOv8 model and use it for tracking objects in the given video source with specific confidence (`conf`) and [Intersection over Union](https://www.ultralytics.com/glossary/intersection-over-union-iou) (`iou`) thresholds. For more details, refer to the [track mode documentation](../../modes/track.md). ### What are the upcoming features for training trackers in Ultralytics? @@ -60,7 +60,7 @@ Ultralytics is continuously enhancing its AI models. An upcoming feature will en ### Why should I use Ultralytics YOLO for multi-object tracking? -Ultralytics YOLO is a state-of-the-art object detection model known for its real-time performance and high accuracy. Using YOLO for multi-object tracking provides several advantages: +Ultralytics YOLO is a state-of-the-art [object detection](https://www.ultralytics.com/glossary/object-detection) model known for its real-time performance and high [accuracy](https://www.ultralytics.com/glossary/accuracy). Using YOLO for multi-object tracking provides several advantages: - **Real-time tracking:** Achieve efficient and high-speed tracking ideal for dynamic environments. - **Flexibility with pre-trained models:** No need to train from scratch; simply use pre-trained detection, segmentation, or Pose models. diff --git a/docs/en/guides/analytics.md b/docs/en/guides/analytics.md index 8da149d3f3..7519f0324f 100644 --- a/docs/en/guides/analytics.md +++ b/docs/en/guides/analytics.md @@ -8,7 +8,7 @@ keywords: Ultralytics, YOLOv8, data visualization, line graphs, bar plots, pie c ## Introduction -This guide provides a comprehensive overview of three fundamental types of data visualizations: line graphs, bar plots, and pie charts. Each section includes step-by-step instructions and code snippets on how to create these visualizations using Python. +This guide provides a comprehensive overview of three fundamental types of [data visualizations](https://www.ultralytics.com/glossary/data-visualization): line graphs, bar plots, and pie charts. Each section includes step-by-step instructions and code snippets on how to create these visualizations using Python. ### Visual Samples @@ -361,7 +361,7 @@ For further details on configuring the `Analytics` class, visit the [Analytics u Using Ultralytics YOLOv8 for creating bar plots offers several benefits: -1. **Real-time Data Visualization**: Seamlessly integrate object detection results into bar plots for dynamic updates. +1. **Real-time Data Visualization**: Seamlessly integrate [object detection](https://www.ultralytics.com/glossary/object-detection) results into bar plots for dynamic updates. 2. **Ease of Use**: Simple API and functions make it straightforward to implement and visualize data. 3. **Customization**: Customize titles, labels, colors, and more to fit your specific requirements. 4. **Efficiency**: Efficiently handle large amounts of data and update plots in real-time during video processing. @@ -472,11 +472,11 @@ cv2.destroyAllWindows() To learn about the complete functionality, see the [Tracking](../modes/track.md) section. -### What makes Ultralytics YOLOv8 different from other object detection solutions like OpenCV and TensorFlow? +### What makes Ultralytics YOLOv8 different from other object detection solutions like [OpenCV](https://www.ultralytics.com/glossary/opencv) and [TensorFlow](https://www.ultralytics.com/glossary/tensorflow)? Ultralytics YOLOv8 stands out from other object detection solutions like OpenCV and TensorFlow for multiple reasons: -1. **State-of-the-art Accuracy**: YOLOv8 provides superior accuracy in object detection, segmentation, and classification tasks. +1. **State-of-the-art [Accuracy](https://www.ultralytics.com/glossary/accuracy)**: YOLOv8 provides superior accuracy in object detection, segmentation, and classification tasks. 2. **Ease of Use**: User-friendly API allows for quick implementation and integration without extensive coding. 3. **Real-time Performance**: Optimized for high-speed inference, suitable for real-time applications. 4. **Diverse Applications**: Supports various tasks including multi-object tracking, custom model training, and exporting to different formats like ONNX, TensorRT, and CoreML. diff --git a/docs/en/guides/azureml-quickstart.md b/docs/en/guides/azureml-quickstart.md index 92e3d83787..a769eee10d 100644 --- a/docs/en/guides/azureml-quickstart.md +++ b/docs/en/guides/azureml-quickstart.md @@ -8,7 +8,7 @@ keywords: YOLOv8, AzureML, machine learning, cloud computing, quickstart, termin ## What is Azure? -[Azure](https://azure.microsoft.com/) is Microsoft's cloud computing platform, designed to help organizations move their workloads to the cloud from on-premises data centers. With the full spectrum of cloud services including those for computing, databases, analytics, machine learning, and networking, users can pick and choose from these services to develop and scale new applications, or run existing applications, in the public cloud. +[Azure](https://azure.microsoft.com/) is Microsoft's [cloud computing](https://www.ultralytics.com/glossary/cloud-computing) platform, designed to help organizations move their workloads to the cloud from on-premises data centers. With the full spectrum of cloud services including those for computing, databases, analytics, [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml), and networking, users can pick and choose from these services to develop and scale new applications, or run existing applications, in the public cloud. ## What is Azure Machine Learning (AzureML)? @@ -71,7 +71,7 @@ Predict: yolo predict model=yolov8n.pt source='https://ultralytics.com/images/bus.jpg' ``` -Train a detection model for 10 epochs with an initial learning_rate of 0.01: +Train a detection model for 10 [epochs](https://www.ultralytics.com/glossary/epoch) with an initial learning_rate of 0.01: ```bash yolo train data=coco8.yaml model=yolov8n.pt epochs=10 lr0=0.01 @@ -216,12 +216,12 @@ Yes, AzureML allows you to use both the Ultralytics CLI and the Python interface Refer to the quickstart guides for more detailed instructions [here](../quickstart.md#use-ultralytics-with-cli) and [here](../quickstart.md#use-ultralytics-with-python). -### What is the advantage of using Ultralytics YOLOv8 over other object detection models? +### What is the advantage of using Ultralytics YOLOv8 over other [object detection](https://www.ultralytics.com/glossary/object-detection) models? Ultralytics YOLOv8 offers several unique advantages over competing object detection models: - **Speed**: Faster inference and training times compared to models like Faster R-CNN and SSD. -- **Accuracy**: High accuracy in detection tasks with features like anchor-free design and enhanced augmentation strategies. +- **[Accuracy](https://www.ultralytics.com/glossary/accuracy)**: High accuracy in detection tasks with features like anchor-free design and enhanced augmentation strategies. - **Ease of Use**: Intuitive API and CLI for quick setup, making it accessible both to beginners and experts. To explore more about YOLOv8's features, visit the [Ultralytics YOLO](https://www.ultralytics.com/yolo) page for detailed insights. diff --git a/docs/en/guides/conda-quickstart.md b/docs/en/guides/conda-quickstart.md index 7afb202b2a..6b52339260 100644 --- a/docs/en/guides/conda-quickstart.md +++ b/docs/en/guides/conda-quickstart.md @@ -10,7 +10,7 @@ keywords: Ultralytics, Conda, setup, installation, environment, guide, machine l Ultralytics Conda Package Visual

-This guide provides a comprehensive introduction to setting up a Conda environment for your Ultralytics projects. Conda is an open-source package and environment management system that offers an excellent alternative to pip for installing packages and dependencies. Its isolated environments make it particularly well-suited for data science and machine learning endeavors. For more details, visit the Ultralytics Conda package on [Anaconda](https://anaconda.org/conda-forge/ultralytics) and check out the Ultralytics feedstock repository for package updates on [GitHub](https://github.com/conda-forge/ultralytics-feedstock/). +This guide provides a comprehensive introduction to setting up a Conda environment for your Ultralytics projects. Conda is an open-source package and environment management system that offers an excellent alternative to pip for installing packages and dependencies. Its isolated environments make it particularly well-suited for data science and [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) endeavors. For more details, visit the Ultralytics Conda package on [Anaconda](https://anaconda.org/conda-forge/ultralytics) and check out the Ultralytics feedstock repository for package updates on [GitHub](https://github.com/conda-forge/ultralytics-feedstock/). [![Conda Version](https://img.shields.io/conda/vn/conda-forge/ultralytics?logo=condaforge)](https://anaconda.org/conda-forge/ultralytics) [![Conda Downloads](https://img.shields.io/conda/dn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics) @@ -68,7 +68,7 @@ conda install -c pytorch -c nvidia -c conda-forge pytorch torchvision pytorch-cu ## Using Ultralytics -With Ultralytics installed, you can now start using its robust features for object detection, instance segmentation, and more. For example, to predict an image, you can run: +With Ultralytics installed, you can now start using its robust features for [object detection](https://www.ultralytics.com/glossary/object-detection), [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation), and more. For example, to predict an image, you can run: ```python from ultralytics import YOLO @@ -162,7 +162,7 @@ Yes, you can enhance performance by utilizing a CUDA-enabled environment. Ensure conda install -c pytorch -c nvidia -c conda-forge pytorch torchvision pytorch-cuda=11.8 ultralytics ``` -This setup enables GPU acceleration, crucial for intensive tasks like deep learning model training and inference. For more information, visit the [Ultralytics installation guide](../quickstart.md). +This setup enables GPU acceleration, crucial for intensive tasks like [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) model training and inference. For more information, visit the [Ultralytics installation guide](../quickstart.md). ### What are the benefits of using Ultralytics Docker images with a Conda environment? diff --git a/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md b/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md index 8f8f076746..db61c08196 100644 --- a/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md +++ b/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md @@ -12,7 +12,7 @@ keywords: Coral Edge TPU, Raspberry Pi, YOLOv8, Ultralytics, TensorFlow Lite, ML ## What is a Coral Edge TPU? -The Coral Edge TPU is a compact device that adds an Edge TPU coprocessor to your system. It enables low-power, high-performance ML inference for TensorFlow Lite models. Read more at the [Coral Edge TPU home page](https://coral.ai/products/accelerator). +The Coral Edge TPU is a compact device that adds an Edge TPU coprocessor to your system. It enables low-power, high-performance ML inference for [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) Lite models. Read more at the [Coral Edge TPU home page](https://coral.ai/products/accelerator).


@@ -38,7 +38,7 @@ The [existing guide](https://coral.ai/docs/accelerator/get-started/) by Coral on - [Raspberry Pi 4B](https://www.raspberrypi.com/products/raspberry-pi-4-model-b/) (2GB or more recommended) or [Raspberry Pi 5](https://www.raspberrypi.com/products/raspberry-pi-5/) (Recommended) - [Raspberry Pi OS](https://www.raspberrypi.com/software/) Bullseye/Bookworm (64-bit) with desktop (Recommended) - [Coral USB Accelerator](https://coral.ai/products/accelerator/) -- A non-ARM based platform for exporting an Ultralytics PyTorch model +- A non-ARM based platform for exporting an Ultralytics [PyTorch](https://www.ultralytics.com/glossary/pytorch) model ## Installation Walkthrough @@ -154,7 +154,7 @@ Find comprehensive information on the [Predict](../modes/predict.md) page for fu ### What is a Coral Edge TPU and how does it enhance Raspberry Pi's performance with Ultralytics YOLOv8? -The Coral Edge TPU is a compact device designed to add an Edge TPU coprocessor to your system. This coprocessor enables low-power, high-performance machine learning inference, particularly optimized for TensorFlow Lite models. When using a Raspberry Pi, the Edge TPU accelerates ML model inference, significantly boosting performance, especially for Ultralytics YOLOv8 models. You can read more about the Coral Edge TPU on their [home page](https://coral.ai/products/accelerator). +The Coral Edge TPU is a compact device designed to add an Edge TPU coprocessor to your system. This coprocessor enables low-power, high-performance [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) inference, particularly optimized for TensorFlow Lite models. When using a Raspberry Pi, the Edge TPU accelerates ML model inference, significantly boosting performance, especially for Ultralytics YOLOv8 models. You can read more about the Coral Edge TPU on their [home page](https://coral.ai/products/accelerator). ### How do I install the Coral Edge TPU runtime on a Raspberry Pi? diff --git a/docs/en/guides/data-collection-and-annotation.md b/docs/en/guides/data-collection-and-annotation.md index 7939d12a42..6ca205260e 100644 --- a/docs/en/guides/data-collection-and-annotation.md +++ b/docs/en/guides/data-collection-and-annotation.md @@ -35,7 +35,7 @@ You can use public datasets or gather your own custom data. Public datasets like Custom data collection, on the other hand, allows you to customize your dataset to your specific needs. You might capture images and videos with cameras or drones, scrape the web for images, or use existing internal data from your organization. Custom data gives you more control over its quality and relevance. Combining both public and custom data sources helps create a diverse and comprehensive dataset. -### Avoiding Bias in Data Collection +### Avoiding [Bias in](https://www.ultralytics.com/glossary/bias-in-ai) Data Collection Bias occurs when certain groups or scenarios are underrepresented or overrepresented in your dataset. It leads to a model that performs well on some data but poorly on others. It's crucial to avoid bias so that your computer vision model can perform well in a variety of scenarios. @@ -44,20 +44,20 @@ Here is how you can avoid bias while collecting data: - **Diverse Sources**: Collect data from many sources to capture different perspectives and scenarios. - **Balanced Representation**: Include balanced representation from all relevant groups. For example, consider different ages, genders, and ethnicities. - **Continuous Monitoring**: Regularly review and update your dataset to identify and address any emerging biases. -- **Bias Mitigation Techniques**: Use methods like oversampling underrepresented classes, data augmentation, and fairness-aware algorithms. +- **Bias Mitigation Techniques**: Use methods like oversampling underrepresented classes, [data augmentation](https://www.ultralytics.com/glossary/data-augmentation), and fairness-aware algorithms. Following these practices helps create a more robust and fair model that can generalize well in real-world applications. ## What is Data Annotation? -Data annotation is the process of labeling data to make it usable for training machine learning models. In computer vision, this means labeling images or videos with the information that a model needs to learn from. Without properly annotated data, models cannot accurately learn the relationships between inputs and outputs. +Data annotation is the process of labeling data to make it usable for training [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models. In computer vision, this means labeling images or videos with the information that a model needs to learn from. Without properly annotated data, models cannot accurately learn the relationships between inputs and outputs. ### Types of Data Annotation Depending on the specific requirements of a [computer vision task](../tasks/index.md), there are different types of data annotation. Here are some examples: - **Bounding Boxes**: Rectangular boxes drawn around objects in an image, used primarily for object detection tasks. These boxes are defined by their top-left and bottom-right coordinates. -- **Polygons**: Detailed outlines for objects, allowing for more precise annotation than bounding boxes. Polygons are used in tasks like instance segmentation, where the shape of the object is important. +- **Polygons**: Detailed outlines for objects, allowing for more precise annotation than bounding boxes. Polygons are used in tasks like [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation), where the shape of the object is important. - **Masks**: Binary masks where each pixel is either part of an object or the background. Masks are used in semantic segmentation tasks to provide pixel-level detail. - **Keypoints**: Specific points marked within an image to identify locations of interest. Keypoints are used in tasks like pose estimation and facial landmark detection. @@ -69,11 +69,11 @@ Depending on the specific requirements of a [computer vision task](../tasks/inde After selecting a type of annotation, it's important to choose the appropriate format for storing and sharing annotations. -Commonly used formats include [COCO](../datasets/detect/coco.md), which supports various annotation types like object detection, keypoint detection, stuff segmentation, panoptic segmentation, and image captioning, stored in JSON. [Pascal VOC](../datasets/detect/voc.md) uses XML files and is popular for object detection tasks. YOLO, on the other hand, creates a .txt file for each image, containing annotations like object class, coordinates, height, and width, making it suitable for object detection. +Commonly used formats include [COCO](../datasets/detect/coco.md), which supports various annotation types like [object detection](https://www.ultralytics.com/glossary/object-detection), keypoint detection, stuff segmentation, [panoptic segmentation](https://www.ultralytics.com/glossary/panoptic-segmentation), and image captioning, stored in JSON. [Pascal VOC](../datasets/detect/voc.md) uses XML files and is popular for object detection tasks. YOLO, on the other hand, creates a .txt file for each image, containing annotations like object class, coordinates, height, and width, making it suitable for object detection. ### Techniques of Annotation -Now, assuming you've chosen a type of annotation and format, it's time to establish clear and objective labeling rules. These rules are like a roadmap for consistency and accuracy throughout the annotation process. Key aspects of these rules include: +Now, assuming you've chosen a type of annotation and format, it's time to establish clear and objective labeling rules. These rules are like a roadmap for consistency and [accuracy](https://www.ultralytics.com/glossary/accuracy) throughout the annotation process. Key aspects of these rules include: - **Clarity and Detail**: Make sure your instructions are clear. Use examples and illustrations to understand what's expected. - **Consistency**: Keep your annotations uniform. Set standard criteria for annotating different types of data, so all annotations follow the same rules. @@ -98,11 +98,11 @@ These open-source tools are budget-friendly and provide a range of features to m ### Some More Things to Consider Before Annotating Data -Before you dive into annotating your data, there are a few more things to keep in mind. You should be aware of accuracy, precision, outliers, and quality control to avoid labeling your data in a counterproductive manner. +Before you dive into annotating your data, there are a few more things to keep in mind. You should be aware of accuracy, [precision](https://www.ultralytics.com/glossary/precision), outliers, and quality control to avoid labeling your data in a counterproductive manner. #### Understanding Accuracy and Precision -It's important to understand the difference between accuracy and precision and how it relates to annotation. Accuracy refers to how close the annotated data is to the true values. It helps us measure how closely the labels reflect real-world scenarios. Precision indicates the consistency of annotations. It checks if you are giving the same label to the same object or feature throughout the dataset. High accuracy and precision lead to better-trained models by reducing noise and improving the model's ability to generalize from the training data. +It's important to understand the difference between accuracy and precision and how it relates to annotation. Accuracy refers to how close the annotated data is to the true values. It helps us measure how closely the labels reflect real-world scenarios. Precision indicates the consistency of annotations. It checks if you are giving the same label to the same object or feature throughout the dataset. High accuracy and precision lead to better-trained models by reducing noise and improving the model's ability to generalize from the [training data](https://www.ultralytics.com/glossary/training-data).

Example of Precision @@ -114,9 +114,9 @@ Outliers are data points that deviate quite a bit from other observations in the You can use various methods to detect and correct outliers: -- **Statistical Techniques**: To detect outliers in numerical features like pixel values, bounding box coordinates, or object sizes, you can use methods such as box plots, histograms, or z-scores. +- **Statistical Techniques**: To detect outliers in numerical features like pixel values, [bounding box](https://www.ultralytics.com/glossary/bounding-box) coordinates, or object sizes, you can use methods such as box plots, histograms, or z-scores. - **Visual Techniques**: To spot anomalies in categorical features like object classes, colors, or shapes, use visual methods like plotting images, labels, or heat maps. -- **Algorithmic Methods**: Use tools like clustering (e.g., K-means clustering, DBSCAN) and anomaly detection algorithms to identify outliers based on data distribution patterns. +- **Algorithmic Methods**: Use tools like clustering (e.g., K-means clustering, DBSCAN) and [anomaly detection](https://www.ultralytics.com/glossary/anomaly-detection) algorithms to identify outliers based on data distribution patterns. #### Quality Control of Annotated Data @@ -132,7 +132,7 @@ While reviewing, if you find errors, correct them and update the guidelines to a ## Share Your Thoughts with the Community -Bouncing your ideas and queries off other computer vision enthusiasts can help accelerate your projects. Here are some great ways to learn, troubleshoot, and network: +Bouncing your ideas and queries off other [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) enthusiasts can help accelerate your projects. Here are some great ways to learn, troubleshoot, and network: ### Where to Find Help and Support @@ -159,7 +159,7 @@ Ensuring high consistency and accuracy in data annotation involves establishing ### How many images do I need for training Ultralytics YOLO models? -For effective transfer learning and object detection with Ultralytics YOLO models, start with a minimum of a few hundred annotated objects per class. If training for just one class, begin with at least 100 annotated images and train for approximately 100 epochs. More complex tasks might require thousands of images per class to achieve high reliability and performance. Quality annotations are crucial, so ensure your data collection and annotation processes are rigorous and aligned with your project's specific goals. Explore detailed training strategies in the [YOLOv8 training guide](../modes/train.md). +For effective [transfer learning](https://www.ultralytics.com/glossary/transfer-learning) and object detection with Ultralytics YOLO models, start with a minimum of a few hundred annotated objects per class. If training for just one class, begin with at least 100 annotated images and train for approximately 100 [epochs](https://www.ultralytics.com/glossary/epoch). More complex tasks might require thousands of images per class to achieve high reliability and performance. Quality annotations are crucial, so ensure your data collection and annotation processes are rigorous and aligned with your project's specific goals. Explore detailed training strategies in the [YOLOv8 training guide](../modes/train.md). ### What are some popular tools for data annotation? @@ -177,7 +177,7 @@ Different types of data annotation cater to various computer vision tasks: - **Bounding Boxes**: Used primarily for object detection, these are rectangular boxes around objects in an image. - **Polygons**: Provide more precise object outlines suitable for instance segmentation tasks. -- **Masks**: Offer pixel-level detail, used in semantic segmentation to differentiate objects from the background. +- **Masks**: Offer pixel-level detail, used in [semantic segmentation](https://www.ultralytics.com/glossary/semantic-segmentation) to differentiate objects from the background. - **Keypoints**: Identify specific points of interest within an image, useful for tasks like pose estimation and facial landmark detection. Selecting the appropriate annotation type depends on your project's requirements. Learn more about how to implement these annotations and their formats in our [data annotation guide](#what-is-data-annotation). diff --git a/docs/en/guides/deepstream-nvidia-jetson.md b/docs/en/guides/deepstream-nvidia-jetson.md index cd114b8690..ab15009b99 100644 --- a/docs/en/guides/deepstream-nvidia-jetson.md +++ b/docs/en/guides/deepstream-nvidia-jetson.md @@ -27,7 +27,7 @@ This comprehensive guide provides a detailed walkthrough for deploying Ultralyti ## What is NVIDIA DeepStream? -[NVIDIA's DeepStream SDK](https://developer.nvidia.com/deepstream-sdk) is a complete streaming analytics toolkit based on GStreamer for AI-based multi-sensor processing, video, audio, and image understanding. It's ideal for vision AI developers, software partners, startups, and OEMs building IVA (Intelligent Video Analytics) apps and services. You can now create stream-processing pipelines that incorporate neural networks and other complex processing tasks like tracking, video encoding/decoding, and video rendering. These pipelines enable real-time analytics on video, image, and sensor data. DeepStream's multi-platform support gives you a faster, easier way to develop vision AI applications and services on-premise, at the edge, and in the cloud. +[NVIDIA's DeepStream SDK](https://developer.nvidia.com/deepstream-sdk) is a complete streaming analytics toolkit based on GStreamer for AI-based multi-sensor processing, video, audio, and image understanding. It's ideal for vision AI developers, software partners, startups, and OEMs building IVA (Intelligent Video Analytics) apps and services. You can now create stream-processing pipelines that incorporate [neural networks](https://www.ultralytics.com/glossary/neural-network-nn) and other complex processing tasks like tracking, video encoding/decoding, and video rendering. These pipelines enable real-time analytics on video, image, and sensor data. DeepStream's multi-platform support gives you a faster, easier way to develop vision AI applications and services on-premise, at the edge, and in the cloud. ## Prerequisites @@ -183,7 +183,7 @@ deepstream-app -c deepstream_app_config.txt !!! tip - If you want to convert the model to FP16 precision, simply set `model-engine-file=model_b1_gpu0_fp16.engine` and `network-mode=2` inside `config_infer_primary_yoloV8.txt` + If you want to convert the model to FP16 [precision](https://www.ultralytics.com/glossary/precision), simply set `model-engine-file=model_b1_gpu0_fp16.engine` and `network-mode=2` inside `config_infer_primary_yoloV8.txt` ## INT8 Calibration @@ -219,7 +219,7 @@ If you want to use INT8 precision for inference, you need to follow the steps be !!! note - NVIDIA recommends at least 500 images to get a good accuracy. On this example, 1000 images are chosen to get better accuracy (more images = more accuracy). You can set it from **head -1000**. For example, for 2000 images, **head -2000**. This process can take a long time. + NVIDIA recommends at least 500 images to get a good [accuracy](https://www.ultralytics.com/glossary/accuracy). On this example, 1000 images are chosen to get better accuracy (more images = more accuracy). You can set it from **head -1000**. For example, for 2000 images, **head -2000**. This process can take a long time. 6. Create the `calibration.txt` file with all selected images @@ -323,7 +323,7 @@ To set up Ultralytics YOLOv8 on an [NVIDIA Jetson](https://www.nvidia.com/en-us/ ### What is the benefit of using TensorRT with YOLOv8 on NVIDIA Jetson? -Using TensorRT with YOLOv8 optimizes the model for inference, significantly reducing latency and improving throughput on NVIDIA Jetson devices. TensorRT provides high-performance, low-latency deep learning inference through layer fusion, precision calibration, and kernel auto-tuning. This leads to faster and more efficient execution, particularly useful for real-time applications like video analytics and autonomous machines. +Using TensorRT with YOLOv8 optimizes the model for inference, significantly reducing latency and improving throughput on NVIDIA Jetson devices. TensorRT provides high-performance, low-latency [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) inference through layer fusion, precision calibration, and kernel auto-tuning. This leads to faster and more efficient execution, particularly useful for real-time applications like video analytics and autonomous machines. ### Can I run Ultralytics YOLOv8 with DeepStream SDK across different NVIDIA Jetson hardware? diff --git a/docs/en/guides/defining-project-goals.md b/docs/en/guides/defining-project-goals.md index fcd32f12f2..c5e3c58cf3 100644 --- a/docs/en/guides/defining-project-goals.md +++ b/docs/en/guides/defining-project-goals.md @@ -4,7 +4,7 @@ description: Learn how to define clear goals and objectives for your computer vi keywords: computer vision, project planning, problem statement, measurable objectives, dataset preparation, model selection, YOLOv8, Ultralytics --- -# A Practical Guide for Defining Your Computer Vision Project +# A Practical Guide for Defining Your [Computer Vision](https://www.ultralytics.com/glossary/computer-vision-cv) Project ## Introduction @@ -33,7 +33,7 @@ Consider a computer vision project where you want to [estimate the speed of vehi Speed Estimation Using YOLOv8

-Primary users include traffic management authorities and law enforcement, while secondary stakeholders are highway planners and the public benefiting from safer roads. Key requirements involve evaluating budget, time, and personnel, as well as addressing technical needs like high-resolution cameras and real-time data processing. Additionally, regulatory constraints on privacy and data security must be considered. +Primary users include traffic management authorities and law enforcement, while secondary stakeholders are highway planners and the public benefiting from safer roads. Key requirements involve evaluating budget, time, and personnel, as well as addressing technical needs like high-resolution cameras and real-time data processing. Additionally, regulatory constraints on privacy and [data security](https://www.ultralytics.com/glossary/data-security) must be considered. ### Setting Measurable Objectives @@ -41,7 +41,7 @@ Setting measurable objectives is key to the success of a computer vision project For example, if you are developing a system to estimate vehicle speeds on a highway. You could consider the following measurable objectives: -- To achieve at least 95% accuracy in speed detection within six months, using a dataset of 10,000 vehicle images. +- To achieve at least 95% [accuracy](https://www.ultralytics.com/glossary/accuracy) in speed detection within six months, using a dataset of 10,000 vehicle images. - The system should be able to process real-time video feeds at 30 frames per second with minimal delay. By setting specific and quantifiable goals, you can effectively track progress, identify areas for improvement, and ensure the project stays on course. @@ -68,7 +68,7 @@ The order of model selection, dataset preparation, and training approach depends - **Unique or Limited Data**: If your project is constrained by unique or limited data, begin with dataset preparation. For instance, if you have a rare dataset of medical images, annotate and prepare the data first. Then, select a model that performs well on such data, followed by choosing a suitable training approach. - - **Example**: Prepare the data first for a facial recognition system with a small dataset. Annotate it, then select a model that works well with limited data, such as a pre-trained model for transfer learning. Finally, decide on a training approach, including data augmentation, to expand the dataset. + - **Example**: Prepare the data first for a facial recognition system with a small dataset. Annotate it, then select a model that works well with limited data, such as a pre-trained model for [transfer learning](https://www.ultralytics.com/glossary/transfer-learning). Finally, decide on a training approach, including [data augmentation](https://www.ultralytics.com/glossary/data-augmentation), to expand the dataset. - **Need for Experimentation**: In projects where experimentation is crucial, start with the training approach. This is common in research projects where you might initially test different training techniques. Refine your model selection after identifying a promising method and prepare the dataset based on your findings. - **Example**: In a project exploring new methods for detecting manufacturing defects, start with experimenting on a small data subset. Once you find a promising technique, select a model tailored to those findings and prepare a comprehensive dataset. @@ -79,7 +79,7 @@ Next, let's look at a few common discussion points in the community regarding co ### What Are the Different Computer Vision Tasks? -The most popular computer vision tasks include image classification, object detection, and image segmentation. +The most popular computer vision tasks include [image classification](https://www.ultralytics.com/glossary/image-classification), [object detection](https://www.ultralytics.com/glossary/object-detection), and [image segmentation](https://www.ultralytics.com/glossary/image-segmentation).

Overview of Computer Vision Tasks @@ -103,7 +103,7 @@ If you want to use the classes the model was pre-trained on, a practical approac - **Edge Devices**: Deploying on edge devices like smartphones or IoT devices requires lightweight models due to their limited computational resources. Example technologies include [TensorFlow Lite](../integrations/tflite.md) and [ONNX Runtime](../integrations/onnx.md), which are optimized for such environments. - **Cloud Servers**: Cloud deployments can handle more complex models with larger computational demands. Cloud platforms like [AWS](../integrations/amazon-sagemaker.md), Google Cloud, and Azure offer robust hardware options that can scale based on the project's needs. -- **On-Premise Servers**: For scenarios requiring high data privacy and security, deploying on-premise might be necessary. This involves significant upfront hardware investment but allows full control over the data and infrastructure. +- **On-Premise Servers**: For scenarios requiring high [data privacy](https://www.ultralytics.com/glossary/data-privacy) and security, deploying on-premise might be necessary. This involves significant upfront hardware investment but allows full control over the data and infrastructure. - **Hybrid Solutions**: Some projects might benefit from a hybrid approach, where some processing is done on the edge, while more complex analyses are offloaded to the cloud. This can balance performance needs with cost and latency considerations. Each deployment option offers different benefits and challenges, and the choice depends on specific project requirements like performance, cost, and security. @@ -158,7 +158,7 @@ For example, "Achieve 95% accuracy in speed detection within six months using a Deployment options critically impact the performance of your Ultralytics YOLO models. Here are key options: -- **Edge Devices:** Use lightweight models like TensorFlow Lite or ONNX Runtime for deployment on devices with limited resources. +- **Edge Devices:** Use lightweight models like [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) Lite or ONNX Runtime for deployment on devices with limited resources. - **Cloud Servers:** Utilize robust cloud platforms like AWS, Google Cloud, or Azure for handling complex models. - **On-Premise Servers:** High data privacy and security needs may require on-premise deployments. - **Hybrid Solutions:** Combine edge and cloud approaches for balanced performance and cost-efficiency. diff --git a/docs/en/guides/distance-calculation.md b/docs/en/guides/distance-calculation.md index a805b95e6e..443b208b70 100644 --- a/docs/en/guides/distance-calculation.md +++ b/docs/en/guides/distance-calculation.md @@ -8,7 +8,7 @@ keywords: Ultralytics, YOLOv8, distance calculation, computer vision, object tra ## What is Distance Calculation? -Measuring the gap between two objects is known as distance calculation within a specified space. In the case of [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics), the bounding box centroid is employed to calculate the distance for bounding boxes highlighted by the user. +Measuring the gap between two objects is known as distance calculation within a specified space. In the case of [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics), the [bounding box](https://www.ultralytics.com/glossary/bounding-box) centroid is employed to calculate the distance for bounding boxes highlighted by the user.


@@ -29,7 +29,7 @@ Measuring the gap between two objects is known as distance calculation within a ## Advantages of Distance Calculation? -- **Localization Precision:** Enhances accurate spatial positioning in computer vision tasks. +- **Localization [Precision](https://www.ultralytics.com/glossary/precision):** Enhances accurate spatial positioning in [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks. - **Size Estimation:** Allows estimation of object size for better contextual understanding. ???+ tip "Distance Calculation" @@ -112,7 +112,7 @@ Using distance calculation with Ultralytics YOLOv8 offers several advantages: ### Can I perform distance calculation in real-time video streams with Ultralytics YOLOv8? -Yes, you can perform distance calculation in real-time video streams with Ultralytics YOLOv8. The process involves capturing video frames using OpenCV, running YOLOv8 object detection, and using the `DistanceCalculation` class to calculate distances between objects in successive frames. For a detailed implementation, see the [video stream example](#distance-calculation-using-ultralytics-yolov8). +Yes, you can perform distance calculation in real-time video streams with Ultralytics YOLOv8. The process involves capturing video frames using [OpenCV](https://www.ultralytics.com/glossary/opencv), running YOLOv8 [object detection](https://www.ultralytics.com/glossary/object-detection), and using the `DistanceCalculation` class to calculate distances between objects in successive frames. For a detailed implementation, see the [video stream example](#distance-calculation-using-ultralytics-yolov8). ### How do I delete points drawn during distance calculation using Ultralytics YOLOv8? diff --git a/docs/en/guides/docker-quickstart.md b/docs/en/guides/docker-quickstart.md index 6d08fac0b5..3ee48946c9 100644 --- a/docs/en/guides/docker-quickstart.md +++ b/docs/en/guides/docker-quickstart.md @@ -237,7 +237,7 @@ sudo docker pull ultralytics/ultralytics:latest For detailed steps, refer to our [Docker Quickstart Guide](../quickstart.md). -### What are the benefits of using Ultralytics Docker images for machine learning projects? +### What are the benefits of using Ultralytics Docker images for [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) projects? Using Ultralytics Docker images ensures a consistent environment across different machines, replicating the same software and dependencies. This is particularly useful for collaborating across teams, running models on various hardware, and maintaining reproducibility. For GPU-based training, Ultralytics provides optimized Docker images such as `Dockerfile` for general GPU usage and `Dockerfile-jetson` for NVIDIA Jetson devices. Explore [Ultralytics Docker Hub](https://hub.docker.com/r/ultralytics/ultralytics) for more details. diff --git a/docs/en/guides/heatmaps.md b/docs/en/guides/heatmaps.md index 02f99c0d5c..d2ebd4b14b 100644 --- a/docs/en/guides/heatmaps.md +++ b/docs/en/guides/heatmaps.md @@ -4,7 +4,7 @@ description: Transform complex data into insightful heatmaps using Ultralytics Y keywords: Ultralytics, YOLOv8, heatmaps, data visualization, data analysis, complex data, patterns, trends, anomalies --- -# Advanced Data Visualization: Heatmaps using Ultralytics YOLOv8 🚀 +# Advanced [Data Visualization](https://www.ultralytics.com/glossary/data-visualization): Heatmaps using Ultralytics YOLOv8 🚀 ## Introduction to Heatmaps @@ -359,9 +359,9 @@ cv2.destroyAllWindows() For further guidance, check the [Tracking Mode](../modes/track.md) page. -### What makes Ultralytics YOLOv8 heatmaps different from other data visualization tools like those from OpenCV or Matplotlib? +### What makes Ultralytics YOLOv8 heatmaps different from other data visualization tools like those from [OpenCV](https://www.ultralytics.com/glossary/opencv) or Matplotlib? -Ultralytics YOLOv8 heatmaps are specifically designed for integration with its object detection and tracking models, providing an end-to-end solution for real-time data analysis. Unlike generic visualization tools like OpenCV or Matplotlib, YOLOv8 heatmaps are optimized for performance and automated processing, supporting features like persistent tracking, decay factor adjustment, and real-time video overlay. For more information on YOLOv8's unique features, visit the [Ultralytics YOLOv8 Introduction](https://www.ultralytics.com/blog/introducing-ultralytics-yolov8). +Ultralytics YOLOv8 heatmaps are specifically designed for integration with its [object detection](https://www.ultralytics.com/glossary/object-detection) and tracking models, providing an end-to-end solution for real-time data analysis. Unlike generic visualization tools like OpenCV or Matplotlib, YOLOv8 heatmaps are optimized for performance and automated processing, supporting features like persistent tracking, decay factor adjustment, and real-time video overlay. For more information on YOLOv8's unique features, visit the [Ultralytics YOLOv8 Introduction](https://www.ultralytics.com/blog/introducing-ultralytics-yolov8). ### How can I visualize only specific object classes in heatmaps using Ultralytics YOLOv8? @@ -393,4 +393,4 @@ cv2.destroyAllWindows() ### Why should businesses choose Ultralytics YOLOv8 for heatmap generation in data analysis? -Ultralytics YOLOv8 offers seamless integration of advanced object detection and real-time heatmap generation, making it an ideal choice for businesses looking to visualize data more effectively. The key advantages include intuitive data distribution visualization, efficient pattern detection, and enhanced spatial analysis for better decision-making. Additionally, YOLOv8's cutting-edge features such as persistent tracking, customizable colormaps, and support for various export formats make it superior to other tools like TensorFlow and OpenCV for comprehensive data analysis. Learn more about business applications at [Ultralytics Plans](https://www.ultralytics.com/plans). +Ultralytics YOLOv8 offers seamless integration of advanced object detection and real-time heatmap generation, making it an ideal choice for businesses looking to visualize data more effectively. The key advantages include intuitive data distribution visualization, efficient pattern detection, and enhanced spatial analysis for better decision-making. Additionally, YOLOv8's cutting-edge features such as persistent tracking, customizable colormaps, and support for various export formats make it superior to other tools like [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) and OpenCV for comprehensive data analysis. Learn more about business applications at [Ultralytics Plans](https://www.ultralytics.com/plans). diff --git a/docs/en/guides/hyperparameter-tuning.md b/docs/en/guides/hyperparameter-tuning.md index b9b1723d32..d715820f24 100644 --- a/docs/en/guides/hyperparameter-tuning.md +++ b/docs/en/guides/hyperparameter-tuning.md @@ -4,19 +4,19 @@ description: Master hyperparameter tuning for Ultralytics YOLO to optimize model keywords: Ultralytics YOLO, hyperparameter tuning, machine learning, model optimization, genetic algorithms, learning rate, batch size, epochs --- -# Ultralytics YOLO Hyperparameter Tuning Guide +# Ultralytics YOLO [Hyperparameter Tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning) Guide ## Introduction -Hyperparameter tuning is not just a one-time set-up but an iterative process aimed at optimizing the machine learning model's performance metrics, such as accuracy, precision, and recall. In the context of Ultralytics YOLO, these hyperparameters could range from learning rate to architectural details, such as the number of layers or types of activation functions used. +Hyperparameter tuning is not just a one-time set-up but an iterative process aimed at optimizing the [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) model's performance metrics, such as accuracy, precision, and recall. In the context of Ultralytics YOLO, these hyperparameters could range from learning rate to architectural details, such as the number of layers or types of activation functions used. ### What are Hyperparameters? Hyperparameters are high-level, structural settings for the algorithm. They are set prior to the training phase and remain constant during it. Here are some commonly tuned hyperparameters in Ultralytics YOLO: -- **Learning Rate** `lr0`: Determines the step size at each iteration while moving towards a minimum in the loss function. -- **Batch Size** `batch`: Number of images processed simultaneously in a forward pass. -- **Number of Epochs** `epochs`: An epoch is one complete forward and backward pass of all the training examples. +- **Learning Rate** `lr0`: Determines the step size at each iteration while moving towards a minimum in the [loss function](https://www.ultralytics.com/glossary/loss-function). +- **[Batch Size](https://www.ultralytics.com/glossary/batch-size)** `batch`: Number of images processed simultaneously in a forward pass. +- **Number of [Epochs](https://www.ultralytics.com/glossary/epoch)** `epochs`: An epoch is one complete forward and backward pass of all the training examples. - **Architecture Specifics**: Such as channel counts, number of layers, types of activation functions, etc.

@@ -162,7 +162,7 @@ This is a plot displaying fitness (typically a performance metric like AP50) aga #### tune_results.csv -A CSV file containing detailed results of each iteration during the tuning. Each row in the file represents one iteration, and it includes metrics like fitness score, precision, recall, as well as the hyperparameters used. +A CSV file containing detailed results of each iteration during the tuning. Each row in the file represents one iteration, and it includes metrics like fitness score, [precision](https://www.ultralytics.com/glossary/precision), [recall](https://www.ultralytics.com/glossary/recall), as well as the hyperparameters used. - **Format**: CSV - **Usage**: Per-iteration results tracking. @@ -187,7 +187,7 @@ This file contains scatter plots generated from `tune_results.csv`, helping you #### weights/ -This directory contains the saved PyTorch models for the last and the best iterations during the hyperparameter tuning process. +This directory contains the saved [PyTorch](https://www.ultralytics.com/glossary/pytorch) models for the last and the best iterations during the hyperparameter tuning process. - **`last.pt`**: The last.pt are the weights from the last epoch of training. - **`best.pt`**: The best.pt weights for the iteration that achieved the best fitness score. @@ -208,7 +208,7 @@ For deeper insights, you can explore the `Tuner` class source code and accompany ## FAQ -### How do I optimize the learning rate for Ultralytics YOLO during hyperparameter tuning? +### How do I optimize the [learning rate](https://www.ultralytics.com/glossary/learning-rate) for Ultralytics YOLO during hyperparameter tuning? To optimize the learning rate for Ultralytics YOLO, start by setting an initial learning rate using the `lr0` parameter. Common values range from `0.001` to `0.01`. During the hyperparameter tuning process, this value will be mutated to find the optimal setting. You can utilize the `model.tune()` method to automate this process. For example: @@ -250,7 +250,7 @@ When evaluating model performance during hyperparameter tuning in YOLO, you can - **AP50**: The average precision at IoU threshold of 0.50. - **F1-Score**: The harmonic mean of precision and recall. -- **Precision and Recall**: Individual metrics indicating the model's accuracy in identifying true positives versus false positives and false negatives. +- **Precision and Recall**: Individual metrics indicating the model's [accuracy](https://www.ultralytics.com/glossary/accuracy) in identifying true positives versus false positives and false negatives. These metrics help you understand different aspects of your model's performance. Refer to the [Ultralytics YOLO performance metrics](../guides/yolo-performance-metrics.md) guide for a comprehensive overview. diff --git a/docs/en/guides/index.md b/docs/en/guides/index.md index e1cb5341c0..1ad70434ab 100644 --- a/docs/en/guides/index.md +++ b/docs/en/guides/index.md @@ -6,9 +6,9 @@ keywords: Ultralytics, YOLO, tutorials, guides, object detection, deep learning, # Comprehensive Tutorials to Ultralytics YOLO -Welcome to the Ultralytics' YOLO 🚀 Guides! Our comprehensive tutorials cover various aspects of the YOLO object detection model, ranging from training and prediction to deployment. Built on PyTorch, YOLO stands out for its exceptional speed and accuracy in real-time object detection tasks. +Welcome to the Ultralytics' YOLO 🚀 Guides! Our comprehensive tutorials cover various aspects of the YOLO [object detection](https://www.ultralytics.com/glossary/object-detection) model, ranging from training and prediction to deployment. Built on [PyTorch](https://www.ultralytics.com/glossary/pytorch), YOLO stands out for its exceptional speed and [accuracy](https://www.ultralytics.com/glossary/accuracy) in real-time object detection tasks. -Whether you're a beginner or an expert in deep learning, our tutorials offer valuable insights into the implementation and optimization of YOLO for your computer vision projects. Let's dive in! +Whether you're a beginner or an expert in [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl), our tutorials offer valuable insights into the implementation and optimization of YOLO for your [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) projects. Let's dive in!


@@ -26,12 +26,12 @@ Whether you're a beginner or an expert in deep learning, our tutorials offer val Here's a compilation of in-depth guides to help you master different aspects of Ultralytics YOLO. - [YOLO Common Issues](yolo-common-issues.md) ⭐ RECOMMENDED: Practical solutions and troubleshooting tips to the most frequently encountered issues when working with Ultralytics YOLO models. -- [YOLO Performance Metrics](yolo-performance-metrics.md) ⭐ ESSENTIAL: Understand the key metrics like mAP, IoU, and F1 score used to evaluate the performance of your YOLO models. Includes practical examples and tips on how to improve detection accuracy and speed. -- [Model Deployment Options](model-deployment-options.md): Overview of YOLO model deployment formats like ONNX, OpenVINO, and TensorRT, with pros and cons for each to inform your deployment strategy. +- [YOLO Performance Metrics](yolo-performance-metrics.md) ⭐ ESSENTIAL: Understand the key metrics like mAP, IoU, and [F1 score](https://www.ultralytics.com/glossary/f1-score) used to evaluate the performance of your YOLO models. Includes practical examples and tips on how to improve detection accuracy and speed. +- [Model Deployment Options](model-deployment-options.md): Overview of YOLO [model deployment](https://www.ultralytics.com/glossary/model-deployment) formats like ONNX, OpenVINO, and TensorRT, with pros and cons for each to inform your deployment strategy. - [K-Fold Cross Validation](kfold-cross-validation.md) 🚀 NEW: Learn how to improve model generalization using K-Fold cross-validation technique. - [Hyperparameter Tuning](hyperparameter-tuning.md) 🚀 NEW: Discover how to optimize your YOLO models by fine-tuning hyperparameters using the Tuner class and genetic evolution algorithms. - [SAHI Tiled Inference](sahi-tiled-inference.md) 🚀 NEW: Comprehensive guide on leveraging SAHI's sliced inference capabilities with YOLOv8 for object detection in high-resolution images. -- [AzureML Quickstart](azureml-quickstart.md) 🚀 NEW: Get up and running with Ultralytics YOLO models on Microsoft's Azure Machine Learning platform. Learn how to train, deploy, and scale your object detection projects in the cloud. +- [AzureML Quickstart](azureml-quickstart.md) 🚀 NEW: Get up and running with Ultralytics YOLO models on Microsoft's Azure [Machine Learning](https://www.ultralytics.com/glossary/machine-learning-ml) platform. Learn how to train, deploy, and scale your object detection projects in the cloud. - [Conda Quickstart](conda-quickstart.md) 🚀 NEW: Step-by-step guide to setting up a [Conda](https://anaconda.org/conda-forge/ultralytics) environment for Ultralytics. Learn how to install and start using the Ultralytics package efficiently with Conda. - [Docker Quickstart](docker-quickstart.md) 🚀 NEW: Complete guide to setting up and using Ultralytics YOLO models with [Docker](https://hub.docker.com/r/ultralytics/ultralytics). Learn how to install Docker, manage GPU support, and run YOLO models in isolated containers for consistent development and deployment. - [Raspberry Pi](raspberry-pi.md) 🚀 NEW: Quickstart tutorial to run YOLO models to the latest Raspberry Pi hardware. @@ -47,7 +47,7 @@ Here's a compilation of in-depth guides to help you master different aspects of - [Defining A Computer Vision Project's Goals](defining-project-goals.md) 🚀 NEW: Walk through how to effectively define clear and measurable goals for your computer vision project. Learn the importance of a well-defined problem statement and how it creates a roadmap for your project. - [Data Collection and Annotation](data-collection-and-annotation.md) 🚀 NEW: Explore the tools, techniques, and best practices for collecting and annotating data to create high-quality inputs for your computer vision models. - [Preprocessing Annotated Data](preprocessing_annotated_data.md) 🚀 NEW: Learn about preprocessing and augmenting image data in computer vision projects using YOLOv8, including normalization, dataset augmentation, splitting, and exploratory data analysis (EDA). -- [Tips for Model Training](model-training-tips.md) 🚀 NEW: Explore tips on optimizing batch sizes, using mixed precision, applying pre-trained weights, and more to make training your computer vision model a breeze. +- [Tips for Model Training](model-training-tips.md) 🚀 NEW: Explore tips on optimizing [batch sizes](https://www.ultralytics.com/glossary/batch-size), using [mixed precision](https://www.ultralytics.com/glossary/mixed-precision), applying pre-trained weights, and more to make training your computer vision model a breeze. - [Insights on Model Evaluation and Fine-Tuning](model-evaluation-insights.md) 🚀 NEW: Gain insights into the strategies and best practices for evaluating and fine-tuning your computer vision models. Learn about the iterative process of refining models to achieve optimal results. - [A Guide on Model Testing](model-testing.md) 🚀 NEW: A thorough guide on testing your computer vision models in realistic settings. Learn how to verify accuracy, reliability, and performance in line with project goals. - [Best Practices for Model Deployment](model-deployment-practices.md) 🚀 NEW: Walk through tips and best practices for efficiently deploying models in computer vision projects, with a focus on optimization, troubleshooting, and security. @@ -89,7 +89,7 @@ For detailed dataset formatting and additional options, refer to our [Tips for M ### What performance metrics should I use to evaluate my YOLO model? -Evaluating your YOLO model performance is crucial to understanding its efficacy. Key metrics include Mean Average Precision (mAP), Intersection over Union (IoU), and F1 score. These metrics help assess the accuracy and precision of object detection tasks. You can learn more about these metrics and how to improve your model in our [YOLO Performance Metrics](yolo-performance-metrics.md) guide. +Evaluating your YOLO model performance is crucial to understanding its efficacy. Key metrics include [Mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP), [Intersection over Union](https://www.ultralytics.com/glossary/intersection-over-union-iou) (IoU), and F1 score. These metrics help assess the accuracy and [precision](https://www.ultralytics.com/glossary/precision) of object detection tasks. You can learn more about these metrics and how to improve your model in our [YOLO Performance Metrics](yolo-performance-metrics.md) guide. ### Why should I use Ultralytics HUB for my computer vision projects? @@ -97,7 +97,7 @@ Ultralytics HUB is a no-code platform that simplifies managing, training, and de ### What are the common issues faced during YOLO model training, and how can I resolve them? -Common issues during YOLO model training include data formatting errors, model architecture mismatches, and insufficient training data. To address these, ensure your dataset is correctly formatted, check for compatible model versions, and augment your training data. For a comprehensive list of solutions, refer to our [YOLO Common Issues](yolo-common-issues.md) guide. +Common issues during YOLO model training include data formatting errors, model architecture mismatches, and insufficient [training data](https://www.ultralytics.com/glossary/training-data). To address these, ensure your dataset is correctly formatted, check for compatible model versions, and augment your training data. For a comprehensive list of solutions, refer to our [YOLO Common Issues](yolo-common-issues.md) guide. ### How can I deploy my YOLO model for real-time object detection on edge devices? diff --git a/docs/en/guides/instance-segmentation-and-tracking.md b/docs/en/guides/instance-segmentation-and-tracking.md index 52a11a3ae0..95e91a8caf 100644 --- a/docs/en/guides/instance-segmentation-and-tracking.md +++ b/docs/en/guides/instance-segmentation-and-tracking.md @@ -6,9 +6,9 @@ keywords: instance segmentation, tracking, YOLOv8, Ultralytics, object detection # Instance Segmentation and Tracking using Ultralytics YOLOv8 🚀 -## What is Instance Segmentation? +## What is [Instance Segmentation](https://www.ultralytics.com/glossary/instance-segmentation)? -[Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) instance segmentation involves identifying and outlining individual objects in an image, providing a detailed understanding of spatial distribution. Unlike semantic segmentation, it uniquely labels and precisely delineates each object, crucial for tasks like object detection and medical imaging. +[Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) instance segmentation involves identifying and outlining individual objects in an image, providing a detailed understanding of spatial distribution. Unlike [semantic segmentation](https://www.ultralytics.com/glossary/semantic-segmentation), it uniquely labels and precisely delineates each object, crucial for tasks like [object detection](https://www.ultralytics.com/glossary/object-detection) and medical imaging. There are two types of instance segmentation tracking available in the Ultralytics package: @@ -194,7 +194,7 @@ Instance segmentation identifies and outlines individual objects within an image ### Why should I use Ultralytics YOLOv8 for instance segmentation and tracking over other models like Mask R-CNN or Faster R-CNN? -Ultralytics YOLOv8 offers real-time performance, superior accuracy, and ease of use compared to other models like Mask R-CNN or Faster R-CNN. YOLOv8 provides a seamless integration with Ultralytics HUB, allowing users to manage models, datasets, and training pipelines efficiently. Discover more about the benefits of YOLOv8 in the [Ultralytics blog](https://www.ultralytics.com/blog/introducing-ultralytics-yolov8). +Ultralytics YOLOv8 offers real-time performance, superior [accuracy](https://www.ultralytics.com/glossary/accuracy), and ease of use compared to other models like Mask R-CNN or Faster R-CNN. YOLOv8 provides a seamless integration with Ultralytics HUB, allowing users to manage models, datasets, and training pipelines efficiently. Discover more about the benefits of YOLOv8 in the [Ultralytics blog](https://www.ultralytics.com/blog/introducing-ultralytics-yolov8). ### How can I implement object tracking using Ultralytics YOLOv8? diff --git a/docs/en/guides/isolating-segmentation-objects.md b/docs/en/guides/isolating-segmentation-objects.md index 0954dc1954..737510e984 100644 --- a/docs/en/guides/isolating-segmentation-objects.md +++ b/docs/en/guides/isolating-segmentation-objects.md @@ -96,7 +96,7 @@ After performing the [Segment Task](../tasks/segment.md), it's sometimes desirab 1. For more info on `c.masks.xy` see [Masks Section from Predict Mode](../modes/predict.md#masks). - 2. Here the values are cast into `np.int32` for compatibility with `drawContours()` function from OpenCV. + 2. Here the values are cast into `np.int32` for compatibility with `drawContours()` function from [OpenCV](https://www.ultralytics.com/glossary/opencv). 3. The OpenCV `drawContours()` function expects contours to have a shape of `[N, 1, 2]` expand section below for more details. @@ -178,7 +178,7 @@ After performing the [Segment Task](../tasks/segment.md), it's sometimes desirab iso_crop = isolated[y1:y2, x1:x2] ``` - 1. For more information on bounding box results, see [Boxes Section from Predict Mode](../modes/predict.md/#boxes) + 1. For more information on [bounding box](https://www.ultralytics.com/glossary/bounding-box) results, see [Boxes Section from Predict Mode](../modes/predict.md/#boxes) ??? question "What does this code do?" @@ -253,7 +253,7 @@ After performing the [Segment Task](../tasks/segment.md), it's sometimes desirab _ = cv2.imwrite(f"{img_name}_{label}-{ci}.png", iso_crop) ``` - - In this example, the `img_name` is the base-name of the source image file, `label` is the detected class-name, and `ci` is the index of the object detection (in case of multiple instances with the same class name). + - In this example, the `img_name` is the base-name of the source image file, `label` is the detected class-name, and `ci` is the index of the [object detection](https://www.ultralytics.com/glossary/object-detection) (in case of multiple instances with the same class name). ## Full Example code diff --git a/docs/en/guides/kfold-cross-validation.md b/docs/en/guides/kfold-cross-validation.md index a0a345339a..381aef0e2a 100644 --- a/docs/en/guides/kfold-cross-validation.md +++ b/docs/en/guides/kfold-cross-validation.md @@ -8,13 +8,13 @@ keywords: Ultralytics, YOLO, K-Fold Cross Validation, object detection, sklearn, ## Introduction -This comprehensive guide illustrates the implementation of K-Fold Cross Validation for object detection datasets within the Ultralytics ecosystem. We'll leverage the YOLO detection format and key Python libraries such as sklearn, pandas, and PyYaml to guide you through the necessary setup, the process of generating feature vectors, and the execution of a K-Fold dataset split. +This comprehensive guide illustrates the implementation of K-Fold Cross Validation for [object detection](https://www.ultralytics.com/glossary/object-detection) datasets within the Ultralytics ecosystem. We'll leverage the YOLO detection format and key Python libraries such as sklearn, pandas, and PyYaml to guide you through the necessary setup, the process of generating feature vectors, and the execution of a K-Fold dataset split.

K-Fold Cross Validation Overview

-Whether your project involves the Fruit Detection dataset or a custom data source, this tutorial aims to help you comprehend and apply K-Fold Cross Validation to bolster the reliability and robustness of your machine learning models. While we're applying `k=5` folds for this tutorial, keep in mind that the optimal number of folds can vary depending on your dataset and the specifics of your project. +Whether your project involves the Fruit Detection dataset or a custom data source, this tutorial aims to help you comprehend and apply K-Fold Cross Validation to bolster the reliability and robustness of your [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models. While we're applying `k=5` folds for this tutorial, keep in mind that the optimal number of folds can vary depending on your dataset and the specifics of your project. Without further ado, let's dive in! @@ -285,7 +285,7 @@ Remember that although we used YOLO in this guide, these steps are mostly transf ### What is K-Fold Cross Validation and why is it useful in object detection? -K-Fold Cross Validation is a technique where the dataset is divided into 'k' subsets (folds) to evaluate model performance more reliably. Each fold serves as both training and validation data. In the context of object detection, using K-Fold Cross Validation helps to ensure your Ultralytics YOLO model's performance is robust and generalizable across different data splits, enhancing its reliability. For detailed instructions on setting up K-Fold Cross Validation with Ultralytics YOLO, refer to [K-Fold Cross Validation with Ultralytics](#introduction). +K-Fold Cross Validation is a technique where the dataset is divided into 'k' subsets (folds) to evaluate model performance more reliably. Each fold serves as both training and [validation data](https://www.ultralytics.com/glossary/validation-data). In the context of object detection, using K-Fold Cross Validation helps to ensure your Ultralytics YOLO model's performance is robust and generalizable across different data splits, enhancing its reliability. For detailed instructions on setting up K-Fold Cross Validation with Ultralytics YOLO, refer to [K-Fold Cross Validation with Ultralytics](#introduction). ### How do I implement K-Fold Cross Validation using Ultralytics YOLO? @@ -301,11 +301,11 @@ For a comprehensive guide, see the [K-Fold Dataset Split](#k-fold-dataset-split) ### Why should I use Ultralytics YOLO for object detection? -Ultralytics YOLO offers state-of-the-art, real-time object detection with high accuracy and efficiency. It's versatile, supporting multiple computer vision tasks such as detection, segmentation, and classification. Additionally, it integrates seamlessly with tools like Ultralytics HUB for no-code model training and deployment. For more details, explore the benefits and features on our [Ultralytics YOLO page](https://www.ultralytics.com/yolo). +Ultralytics YOLO offers state-of-the-art, real-time object detection with high [accuracy](https://www.ultralytics.com/glossary/accuracy) and efficiency. It's versatile, supporting multiple [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks such as detection, segmentation, and classification. Additionally, it integrates seamlessly with tools like Ultralytics HUB for no-code model training and deployment. For more details, explore the benefits and features on our [Ultralytics YOLO page](https://www.ultralytics.com/yolo). ### How can I ensure my annotations are in the correct format for Ultralytics YOLO? -Your annotations should follow the YOLO detection format. Each annotation file must list the object class, alongside its bounding box coordinates in the image. The YOLO format ensures streamlined and standardized data processing for training object detection models. For more information on proper annotation formatting, visit the [YOLO detection format guide](../datasets/detect/index.md). +Your annotations should follow the YOLO detection format. Each annotation file must list the object class, alongside its [bounding box](https://www.ultralytics.com/glossary/bounding-box) coordinates in the image. The YOLO format ensures streamlined and standardized data processing for training object detection models. For more information on proper annotation formatting, visit the [YOLO detection format guide](../datasets/detect/index.md). ### Can I use K-Fold Cross Validation with custom datasets other than Fruit Detection? diff --git a/docs/en/guides/model-deployment-options.md b/docs/en/guides/model-deployment-options.md index 635716e581..c2ecf8b649 100644 --- a/docs/en/guides/model-deployment-options.md +++ b/docs/en/guides/model-deployment-options.md @@ -24,7 +24,7 @@ Let's walk through the different YOLOv8 deployment options. For a detailed walkt #### PyTorch -PyTorch is an open-source machine learning library widely used for applications in deep learning and artificial intelligence. It provides a high level of flexibility and speed, which has made it a favorite among researchers and developers. +PyTorch is an open-source machine learning library widely used for applications in [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) and [artificial intelligence](https://www.ultralytics.com/glossary/artificial-intelligence-ai). It provides a high level of flexibility and speed, which has made it a favorite among researchers and developers. - **Performance Benchmarks**: PyTorch is known for its ease of use and flexibility, which may result in a slight trade-off in raw performance when compared to other frameworks that are more specialized and optimized. @@ -60,7 +60,7 @@ TorchScript extends PyTorch's capabilities by allowing the exportation of models #### ONNX -The Open Neural Network Exchange (ONNX) is a format that allows for model interoperability across different frameworks, which can be critical when deploying to various platforms. +The Open [Neural Network](https://www.ultralytics.com/glossary/neural-network-nn) Exchange (ONNX) is a format that allows for model interoperability across different frameworks, which can be critical when deploying to various platforms. - **Performance Benchmarks**: ONNX models may experience a variable performance depending on the specific runtime they are deployed on. @@ -84,9 +84,9 @@ OpenVINO is an Intel toolkit designed to facilitate the deployment of deep learn - **Compatibility and Integration**: Works best within the Intel ecosystem but also supports a range of other platforms. -- **Community Support and Ecosystem**: Backed by Intel, with a solid user base especially in the computer vision domain. +- **Community Support and Ecosystem**: Backed by Intel, with a solid user base especially in the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) domain. -- **Case Studies**: Often utilized in IoT and edge computing scenarios where Intel hardware is prevalent. +- **Case Studies**: Often utilized in IoT and [edge computing](https://www.ultralytics.com/glossary/edge-computing) scenarios where Intel hardware is prevalent. - **Maintenance and Updates**: Intel regularly updates OpenVINO to support the latest deep learning models and Intel hardware. @@ -128,7 +128,7 @@ CoreML is Apple's machine learning framework, optimized for on-device performanc - **Maintenance and Updates**: Regularly updated by Apple to support the latest machine learning advancements and Apple hardware. -- **Security Considerations**: Benefits from Apple's focus on user privacy and data security. +- **Security Considerations**: Benefits from Apple's focus on user privacy and [data security](https://www.ultralytics.com/glossary/data-security). - **Hardware Acceleration**: Takes full advantage of Apple's neural engine and GPU for accelerated machine learning tasks. @@ -236,7 +236,7 @@ PaddlePaddle is an open-source deep learning framework developed by Baidu. It is - **Maintenance and Updates**: Regularly updated with a focus on serving Chinese language AI applications and services. -- **Security Considerations**: Emphasizes data privacy and security, catering to Chinese data governance standards. +- **Security Considerations**: Emphasizes [data privacy](https://www.ultralytics.com/glossary/data-privacy) and security, catering to Chinese data governance standards. - **Hardware Acceleration**: Supports various hardware accelerations, including Baidu's own Kunlun chips. @@ -329,7 +329,7 @@ For more insights, check out our [blog post](https://www.ultralytics.com/blog/ac ### Can I deploy YOLOv8 models on mobile devices? -Yes, YOLOv8 models can be deployed on mobile devices using TensorFlow Lite (TF Lite) for both Android and iOS platforms. TF Lite is designed for mobile and embedded devices, providing efficient on-device inference. +Yes, YOLOv8 models can be deployed on mobile devices using [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) Lite (TF Lite) for both Android and iOS platforms. TF Lite is designed for mobile and embedded devices, providing efficient on-device inference. !!! example @@ -356,13 +356,13 @@ When choosing a deployment format for YOLOv8, consider the following factors: - **Performance**: Some formats like TensorRT provide exceptional speeds on NVIDIA GPUs, while OpenVINO is optimized for Intel hardware. - **Compatibility**: ONNX offers broad compatibility across different platforms. - **Ease of Integration**: Formats like CoreML or TF Lite are tailored for specific ecosystems like iOS and Android, respectively. -- **Community Support**: Formats like PyTorch and TensorFlow have extensive community resources and support. +- **Community Support**: Formats like [PyTorch](https://www.ultralytics.com/glossary/pytorch) and TensorFlow have extensive community resources and support. For a comparative analysis, refer to our [export formats documentation](../modes/export.md#export-formats). ### How can I deploy YOLOv8 models in a web application? -To deploy YOLOv8 models in a web application, you can use TensorFlow.js (TF.js), which allows for running machine learning models directly in the browser. This approach eliminates the need for backend infrastructure and provides real-time performance. +To deploy YOLOv8 models in a web application, you can use TensorFlow.js (TF.js), which allows for running [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models directly in the browser. This approach eliminates the need for backend infrastructure and provides real-time performance. 1. Export the YOLOv8 model to the TF.js format. 2. Integrate the exported model into your web application. diff --git a/docs/en/guides/model-deployment-practices.md b/docs/en/guides/model-deployment-practices.md index df485abd45..f259779ceb 100644 --- a/docs/en/guides/model-deployment-practices.md +++ b/docs/en/guides/model-deployment-practices.md @@ -4,7 +4,7 @@ description: Learn essential tips, insights, and best practices for deploying co keywords: Model Deployment, Machine Learning Model Deployment, ML Model Deployment, AI Model Deployment, How to Deploy a Machine Learning Model, How to Deploy ML Models --- -# Best Practices for Model Deployment +# Best Practices for [Model Deployment](https://www.ultralytics.com/glossary/model-deployment) ## Introduction @@ -31,13 +31,13 @@ With respect to YOLOv8, you can [export your model](../modes/export.md) to diffe ### Choosing a Deployment Environment -Choosing where to deploy your computer vision model depends on multiple factors. Different environments have unique benefits and challenges, so it's essential to pick the one that best fits your needs. +Choosing where to deploy your [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) model depends on multiple factors. Different environments have unique benefits and challenges, so it's essential to pick the one that best fits your needs. #### Cloud Deployment Cloud deployment is great for applications that need to scale up quickly and handle large amounts of data. Platforms like AWS, [Google Cloud](../yolov5/environments/google_cloud_quickstart_tutorial.md), and Azure make it easy to manage your models from training to deployment. They offer services like [AWS SageMaker](../integrations/amazon-sagemaker.md), Google AI Platform, and [Azure Machine Learning](./azureml-quickstart.md) to help you throughout the process. -However, using the cloud can be expensive, especially with high data usage, and you might face latency issues if your users are far from the data centers. To manage costs and performance, it's important to optimize resource use and ensure compliance with data privacy rules. +However, using the cloud can be expensive, especially with high data usage, and you might face latency issues if your users are far from the data centers. To manage costs and performance, it's important to optimize resource use and ensure compliance with [data privacy](https://www.ultralytics.com/glossary/data-privacy) rules. #### Edge Deployment @@ -65,7 +65,7 @@ Pruning reduces the size of the model by removing weights that contribute little ### Model Quantization -Quantization converts the model's weights and activations from high precision (like 32-bit floats) to lower precision (like 8-bit integers). By reducing the model size, it speeds up inference. Quantization-aware training (QAT) is a method where the model is trained with quantization in mind, preserving accuracy better than post-training quantization. By handling quantization during the training phase, the model learns to adjust to lower precision, maintaining performance while reducing computational demands. +Quantization converts the model's weights and activations from high [precision](https://www.ultralytics.com/glossary/precision) (like 32-bit floats) to lower precision (like 8-bit integers). By reducing the model size, it speeds up inference. Quantization-aware training (QAT) is a method where the model is trained with quantization in mind, preserving accuracy better than post-training quantization. By handling quantization during the training phase, the model learns to adjust to lower precision, maintaining performance while reducing computational demands.

Model Quantization Overview @@ -73,7 +73,7 @@ Quantization converts the model's weights and activations from high precision (l ### Knowledge Distillation -Knowledge distillation involves training a smaller, simpler model (the student) to mimic the outputs of a larger, more complex model (the teacher). The student model learns to approximate the teacher's predictions, resulting in a compact model that retains much of the teacher's accuracy. This technique is beneficial for creating efficient models suitable for deployment on edge devices with constrained resources. +Knowledge distillation involves training a smaller, simpler model (the student) to mimic the outputs of a larger, more complex model (the teacher). The student model learns to approximate the teacher's predictions, resulting in a compact model that retains much of the teacher's [accuracy](https://www.ultralytics.com/glossary/accuracy). This technique is beneficial for creating efficient models suitable for deployment on edge devices with constrained resources.

Knowledge Distillation Overview @@ -98,7 +98,7 @@ When deploying YOLOv8, several factors can affect model accuracy. Converting mod ### Inferences Are Taking Longer Than You Expected -When deploying machine learning models, it's important that they run efficiently. If inferences are taking longer than expected, it can affect the user experience and the effectiveness of your application. Here are some steps to help you identify and resolve the problem: +When deploying [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models, it's important that they run efficiently. If inferences are taking longer than expected, it can affect the user experience and the effectiveness of your application. Here are some steps to help you identify and resolve the problem: - **Implement Warm-Up Runs**: Initial runs often include setup overhead, which can skew latency measurements. Perform a few warm-up inferences before measuring latency. Excluding these initial runs provides a more accurate measurement of the model's performance. - **Optimize the Inference Engine:** Double-check that the inference engine is fully optimized for your specific GPU architecture. Use the latest drivers and software versions tailored to your hardware to ensure maximum performance and compatibility. @@ -124,7 +124,7 @@ It's essential to control who can access your model and its data to prevent unau ### Model Obfuscation -Protecting your model from being reverse-engineered or misuse can be done through model obfuscation. It involves encrypting model parameters, such as weights and biases in neural networks, to make it difficult for unauthorized individuals to understand or alter the model. You can also obfuscate the model's architecture by renaming layers and parameters or adding dummy layers, making it harder for attackers to reverse-engineer it. You can also serve the model in a secure environment, like a secure enclave or using a trusted execution environment (TEE), can provide an extra layer of protection during inference. +Protecting your model from being reverse-engineered or misuse can be done through model obfuscation. It involves encrypting model parameters, such as weights and biases in [neural networks](https://www.ultralytics.com/glossary/neural-network-nn), to make it difficult for unauthorized individuals to understand or alter the model. You can also obfuscate the model's architecture by renaming layers and parameters or adding dummy layers, making it harder for attackers to reverse-engineer it. You can also serve the model in a secure environment, like a secure enclave or using a trusted execution environment (TEE), can provide an extra layer of protection during inference. ## Share Ideas With Your Peers diff --git a/docs/en/guides/model-evaluation-insights.md b/docs/en/guides/model-evaluation-insights.md index 22c44e5df0..ef9389c266 100644 --- a/docs/en/guides/model-evaluation-insights.md +++ b/docs/en/guides/model-evaluation-insights.md @@ -24,19 +24,19 @@ _Quick Tip:_ When running inferences, if you aren't seeing any predictions and y ### Intersection over Union -Intersection over Union (IoU) is a metric in object detection that measures how well the predicted bounding box overlaps with the ground truth bounding box. IoU values range from 0 to 1, where one stands for a perfect match. IoU is essential because it measures how closely the predicted boundaries match the actual object boundaries. +[Intersection over Union](https://www.ultralytics.com/glossary/intersection-over-union-iou) (IoU) is a metric in [object detection](https://www.ultralytics.com/glossary/object-detection) that measures how well the predicted [bounding box](https://www.ultralytics.com/glossary/bounding-box) overlaps with the ground truth bounding box. IoU values range from 0 to 1, where one stands for a perfect match. IoU is essential because it measures how closely the predicted boundaries match the actual object boundaries.

Intersection over Union Overview

-### Mean Average Precision +### Mean Average [Precision](https://www.ultralytics.com/glossary/precision) -Mean Average Precision (mAP) is a way to measure how well an object detection model performs. It looks at the precision of detecting each object class, averages these scores, and gives an overall number that shows how accurately the model can identify and classify objects. +[Mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP) is a way to measure how well an object detection model performs. It looks at the precision of detecting each object class, averages these scores, and gives an overall number that shows how accurately the model can identify and classify objects. Let's focus on two specific mAP metrics: -- *mAP@.5:* Measures the average precision at a single IoU (Intersection over Union) threshold of 0.5. This metric checks if the model can correctly find objects with a looser accuracy requirement. It focuses on whether the object is roughly in the right place, not needing perfect placement. It helps see if the model is generally good at spotting objects. +- *mAP@.5:* Measures the average precision at a single IoU (Intersection over Union) threshold of 0.5. This metric checks if the model can correctly find objects with a looser [accuracy](https://www.ultralytics.com/glossary/accuracy) requirement. It focuses on whether the object is roughly in the right place, not needing perfect placement. It helps see if the model is generally good at spotting objects. - *mAP@.5:.95:* Averages the mAP values calculated at multiple IoU thresholds, from 0.5 to 0.95 in 0.05 increments. This metric is more detailed and strict. It gives a fuller picture of how accurately the model can find objects at different levels of strictness and is especially useful for applications that need precise object detection. Other mAP metrics include mAP@0.75, which uses a stricter IoU threshold of 0.75, and mAP@small, medium, and large, which evaluate precision across objects of different sizes. @@ -111,9 +111,9 @@ Fine-tuning involves taking a pre-trained model and adjusting its parameters to Fine-tuning a model means paying close attention to several vital parameters and techniques to achieve optimal performance. Here are some essential tips to guide you through the process. -### Starting With a Higher Learning Rate +### Starting With a Higher [Learning Rate](https://www.ultralytics.com/glossary/learning-rate) -Usually, during the initial training epochs, the learning rate starts low and gradually increases to stabilize the training process. However, since your model has already learned some features from the previous dataset, starting with a higher learning rate right away can be more beneficial. +Usually, during the initial training [epochs](https://www.ultralytics.com/glossary/epoch), the learning rate starts low and gradually increases to stabilize the training process. However, since your model has already learned some features from the previous dataset, starting with a higher learning rate right away can be more beneficial. When evaluating your YOLOv8 model, you can set the `warmup_epochs` validation parameter to `warmup_epochs=0` to prevent the learning rate from starting too high. By following this process, the training will continue from the provided weights, adjusting to the nuances of your new data. @@ -123,7 +123,7 @@ Image tiling can improve detection accuracy for small objects. By dividing large ## Engage with the Community -Sharing your ideas and questions with other computer vision enthusiasts can inspire creative solutions to roadblocks in your projects. Here are some excellent ways to learn, troubleshoot, and connect. +Sharing your ideas and questions with other [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) enthusiasts can inspire creative solutions to roadblocks in your projects. Here are some excellent ways to learn, troubleshoot, and connect. ### Finding Help and Support @@ -136,7 +136,7 @@ Sharing your ideas and questions with other computer vision enthusiasts can insp ## Final Thoughts -Evaluating and fine-tuning your computer vision model are important steps for successful model deployment. These steps help make sure that your model is accurate, efficient, and suited to your overall application. The key to training the best model possible is continuous experimentation and learning. Don't hesitate to tweak parameters, try new techniques, and explore different datasets. Keep experimenting and pushing the boundaries of what's possible! +Evaluating and fine-tuning your computer vision model are important steps for successful [model deployment](https://www.ultralytics.com/glossary/model-deployment). These steps help make sure that your model is accurate, efficient, and suited to your overall application. The key to training the best model possible is continuous experimentation and learning. Don't hesitate to tweak parameters, try new techniques, and explore different datasets. Keep experimenting and pushing the boundaries of what's possible! ## FAQ @@ -156,8 +156,8 @@ To handle variable image sizes during evaluation, use the `rect=true` parameter Improving mean average precision (mAP) for a YOLOv8 model involves several steps: -1. **Tuning Hyperparameters**: Experiment with different learning rates, batch sizes, and image augmentations. -2. **Data Augmentation**: Use techniques like Mosaic and MixUp to create diverse training samples. +1. **Tuning Hyperparameters**: Experiment with different learning rates, [batch sizes](https://www.ultralytics.com/glossary/batch-size), and image augmentations. +2. **[Data Augmentation](https://www.ultralytics.com/glossary/data-augmentation)**: Use techniques like Mosaic and MixUp to create diverse training samples. 3. **Image Tiling**: Split larger images into smaller tiles to improve detection accuracy for small objects. Refer to our detailed guide on [model fine-tuning](#tips-for-fine-tuning-your-model) for specific strategies. diff --git a/docs/en/guides/model-monitoring-and-maintenance.md b/docs/en/guides/model-monitoring-and-maintenance.md index ab5e417a3b..2aedc8e3a3 100644 --- a/docs/en/guides/model-monitoring-and-maintenance.md +++ b/docs/en/guides/model-monitoring-and-maintenance.md @@ -34,8 +34,8 @@ Here are some best practices to keep in mind while monitoring your computer visi You can use automated monitoring tools to make it easier to monitor models after deployment. Many tools offer real-time insights and alerting capabilities. Here are some examples of open-source model monitoring tools that can work together: - **[Prometheus](https://prometheus.io/)**: Prometheus is an open-source monitoring tool that collects and stores metrics for detailed performance tracking. It integrates easily with Kubernetes and Docker, collecting data at set intervals and storing it in a time-series database. Prometheus can also scrape HTTP endpoints to gather real-time metrics. Collected data can be queried using the PromQL language. -- **[Grafana](https://grafana.com/)**: Grafana is an open-source data visualization and monitoring tool that allows you to query, visualize, alert on, and understand your metrics no matter where they are stored. It works well with Prometheus and offers advanced data visualization features. You can create custom dashboards to show important metrics for your computer vision models, like inference latency, error rates, and resource usage. Grafana turns collected data into easy-to-read dashboards with line graphs, heat maps, and histograms. It also supports alerts, which can be sent through channels like Slack to quickly notify teams of any issues. -- **[Evidently AI](https://www.evidentlyai.com/)**: Evidently AI is an open-source tool designed for monitoring and debugging machine learning models in production. It generates interactive reports from pandas DataFrames, helping analyze machine learning models. Evidently AI can detect data drift, model performance degradation, and other issues that may arise with your deployed models. +- **[Grafana](https://grafana.com/)**: Grafana is an open-source [data visualization](https://www.ultralytics.com/glossary/data-visualization) and monitoring tool that allows you to query, visualize, alert on, and understand your metrics no matter where they are stored. It works well with Prometheus and offers advanced data visualization features. You can create custom dashboards to show important metrics for your computer vision models, like inference latency, error rates, and resource usage. Grafana turns collected data into easy-to-read dashboards with line graphs, heat maps, and histograms. It also supports alerts, which can be sent through channels like Slack to quickly notify teams of any issues. +- **[Evidently AI](https://www.evidentlyai.com/)**: Evidently AI is an open-source tool designed for monitoring and debugging [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models in production. It generates interactive reports from pandas DataFrames, helping analyze machine learning models. Evidently AI can detect data drift, model performance degradation, and other issues that may arise with your deployed models. The three tools introduced above, Evidently AI, Prometheus, and Grafana, can work together seamlessly as a fully open-source ML monitoring solution that is ready for production. Evidently AI is used to collect and calculate metrics, Prometheus stores these metrics, and Grafana displays them and sets up alerts. While there are many other tools available, this setup is an exciting open-source option that provides robust capabilities for monitoring and maintaining your models. @@ -45,7 +45,7 @@ The three tools introduced above, Evidently AI, Prometheus, and Grafana, can wor ### Anomaly Detection and Alert Systems -An anomaly is any data point or pattern that deviates quite a bit from what is expected. With respect to computer vision models, anomalies can be images that are very different from the ones the model was trained on. These unexpected images can be signs of issues like changes in data distribution, outliers, or behaviors that might reduce model performance. Setting up alert systems to detect these anomalies is an important part of model monitoring. +An anomaly is any data point or pattern that deviates quite a bit from what is expected. With respect to [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) models, anomalies can be images that are very different from the ones the model was trained on. These unexpected images can be signs of issues like changes in data distribution, outliers, or behaviors that might reduce model performance. Setting up alert systems to detect these anomalies is an important part of model monitoring. By setting standard performance levels and limits for key metrics, you can catch problems early. When performance goes outside these limits, alerts are triggered, prompting quick fixes. Regularly updating and retraining models with new data keeps them relevant and accurate as the data changes. @@ -69,7 +69,7 @@ Here are several methods to detect data drift: **Continuous Monitoring**: Regularly monitor the model's input data and outputs for signs of drift. Track key metrics and compare them against historical data to identify significant changes. -**Statistical Techniques**: Use methods like the Kolmogorov-Smirnov test or Population Stability Index (PSI) to detect changes in data distributions. These tests compare the distribution of new data with the training data to identify significant differences. +**Statistical Techniques**: Use methods like the Kolmogorov-Smirnov test or Population Stability Index (PSI) to detect changes in data distributions. These tests compare the distribution of new data with the [training data](https://www.ultralytics.com/glossary/training-data) to identify significant differences. **Feature Drift**: Monitor individual features for drift. Sometimes, the overall data distribution may remain stable, but individual features may drift. Identifying which features are drifting helps in fine-tuning the retraining process. @@ -91,7 +91,7 @@ Regardless of the method, validation and testing are a must after updates. It is ### Deciding When to Retrain Your Model -The frequency of retraining your computer vision model depends on data changes and model performance. Retrain your model whenever you observe a significant performance drop or detect data drift. Regular evaluations can help determine the right retraining schedule by testing the model against new data. Monitoring performance metrics and data patterns lets you decide if your model needs more frequent updates to maintain accuracy. +The frequency of retraining your computer vision model depends on data changes and model performance. Retrain your model whenever you observe a significant performance drop or detect data drift. Regular evaluations can help determine the right retraining schedule by testing the model against new data. Monitoring performance metrics and data patterns lets you decide if your model needs more frequent updates to maintain [accuracy](https://www.ultralytics.com/glossary/accuracy).

When to Retrain Overview @@ -108,8 +108,8 @@ These are some of the key elements that should be included in project documentat - **[Project Overview](./steps-of-a-cv-project.md)**: Provide a high-level summary of the project, including the problem statement, solution approach, expected outcomes, and project scope. Explain the role of computer vision in addressing the problem and outline the stages and deliverables. - **Model Architecture**: Detail the structure and design of the model, including its components, layers, and connections. Explain the chosen hyperparameters and the rationale behind these choices. - **[Data Preparation](./data-collection-and-annotation.md)**: Describe the data sources, types, formats, sizes, and preprocessing steps. Discuss data quality, reliability, and any transformations applied before training the model. -- **[Training Process](./model-training-tips.md)**: Document the training procedure, including the datasets used, training parameters, and loss functions. Explain how the model was trained and any challenges encountered during training. -- **[Evaluation Metrics](./model-evaluation-insights.md)**: Specify the metrics used to evaluate the model's performance, such as accuracy, precision, recall, and F1-score. Include performance results and an analysis of these metrics. +- **[Training Process](./model-training-tips.md)**: Document the training procedure, including the datasets used, training parameters, and [loss functions](https://www.ultralytics.com/glossary/loss-function). Explain how the model was trained and any challenges encountered during training. +- **[Evaluation Metrics](./model-evaluation-insights.md)**: Specify the metrics used to evaluate the model's performance, such as accuracy, [precision](https://www.ultralytics.com/glossary/precision), [recall](https://www.ultralytics.com/glossary/recall), and F1-score. Include performance results and an analysis of these metrics. - **[Deployment Steps](./model-deployment-options.md)**: Outline the steps taken to deploy the model, including the tools and platforms used, deployment configurations, and any specific challenges or considerations. - **Monitoring and Maintenance Procedure**: Provide a detailed plan for monitoring the model's performance post-deployment. Include methods for detecting and addressing data and model drift, and describe the process for regular updates and retraining. @@ -155,7 +155,7 @@ Maintaining computer vision models involves regular updates, retraining, and mon Data drift detection is essential because it helps identify when the statistical properties of the input data change over time, which can degrade model performance. Techniques like continuous monitoring, statistical tests (e.g., Kolmogorov-Smirnov test), and feature drift analysis can help spot issues early. Addressing data drift ensures that your model remains accurate and relevant in changing environments. Learn more about data drift detection in our [Data Drift Detection](#data-drift-detection) section. -### What tools can I use for anomaly detection in computer vision models? +### What tools can I use for [anomaly detection](https://www.ultralytics.com/glossary/anomaly-detection) in computer vision models? For anomaly detection in computer vision models, tools like [Prometheus](https://prometheus.io/), [Grafana](https://grafana.com/), and [Evidently AI](https://www.evidentlyai.com/) are highly effective. These tools can help you set up alert systems to detect unusual data points or patterns that deviate from expected behavior. Configurable alerts and standardized messages can help you respond quickly to potential issues. Explore more in our [Anomaly Detection and Alert Systems](#anomaly-detection-and-alert-systems) section. @@ -168,5 +168,5 @@ Effective documentation of a computer vision project should include: - **Data Preparation**: Information on data sources, preprocessing steps, and transformations. - **Training Process**: Description of the training procedure, datasets used, and challenges encountered. - **Evaluation Metrics**: Metrics used for performance evaluation and analysis. -- **Deployment Steps**: Steps taken for model deployment and any specific challenges. +- **Deployment Steps**: Steps taken for [model deployment](https://www.ultralytics.com/glossary/model-deployment) and any specific challenges. - **Monitoring and Maintenance Procedure**: Plan for ongoing monitoring and maintenance. For more comprehensive guidelines, refer to our [Documentation](#documentation) section. diff --git a/docs/en/guides/model-testing.md b/docs/en/guides/model-testing.md index 71ff69b0be..8d32467955 100644 --- a/docs/en/guides/model-testing.md +++ b/docs/en/guides/model-testing.md @@ -10,19 +10,19 @@ keywords: Overfitting and Underfitting in Machine Learning, Model Testing, Data After [training](./model-training-tips.md) and [evaluating](./model-evaluation-insights.md) your model, it's time to test it. Model testing involves assessing how well it performs in real-world scenarios. Testing considers factors like accuracy, reliability, fairness, and how easy it is to understand the model's decisions. The goal is to make sure the model performs as intended, delivers the expected results, and fits into the [overall objective of your application](./defining-project-goals.md) or project. -Model testing is quite similar to model evaluation, but they are two distinct [steps in a computer vision project](./steps-of-a-cv-project.md). Model evaluation involves metrics and plots to assess the model's accuracy. On the other hand, model testing checks if the model's learned behavior is the same as expectations. In this guide, we'll explore strategies for testing your computer vision models. +Model testing is quite similar to model evaluation, but they are two distinct [steps in a computer vision project](./steps-of-a-cv-project.md). Model evaluation involves metrics and plots to assess the model's accuracy. On the other hand, model testing checks if the model's learned behavior is the same as expectations. In this guide, we'll explore strategies for testing your [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) models. ## Model Testing Vs. Model Evaluation First, let's understand the difference between model evaluation and testing with an example. -Suppose you have trained a computer vision model to recognize cats and dogs, and you want to deploy this model at a pet store to monitor the animals. During the model evaluation phase, you use a labeled dataset to calculate metrics like accuracy, precision, recall, and F1 score. For instance, the model might have an accuracy of 98% in distinguishing between cats and dogs in a given dataset. +Suppose you have trained a computer vision model to recognize cats and dogs, and you want to deploy this model at a pet store to monitor the animals. During the model evaluation phase, you use a labeled dataset to calculate metrics like accuracy, [precision](https://www.ultralytics.com/glossary/precision), [recall](https://www.ultralytics.com/glossary/recall), and F1 score. For instance, the model might have an accuracy of 98% in distinguishing between cats and dogs in a given dataset. After evaluation, you test the model using images from a pet store to see how well it identifies cats and dogs in more varied and realistic conditions. You check if it can correctly label cats and dogs when they are moving, in different lighting conditions, or partially obscured by objects like toys or furniture. Model testing checks that the model behaves as expected outside the controlled evaluation environment. ## Preparing for Model Testing -Computer vision models learn from datasets by detecting patterns, making predictions, and evaluating their performance. These [datasets](./preprocessing_annotated_data.md) are usually divided into training and testing sets to simulate real-world conditions. Training data teaches the model while testing data verifies its accuracy. +Computer vision models learn from datasets by detecting patterns, making predictions, and evaluating their performance. These [datasets](./preprocessing_annotated_data.md) are usually divided into training and testing sets to simulate real-world conditions. [Training data](https://www.ultralytics.com/glossary/training-data) teaches the model while testing data verifies its accuracy. Here are two points to keep in mind before testing your model: @@ -61,7 +61,7 @@ If you want to test your trained YOLOv8 model on multiple images stored in a fol If you are interested in testing the basic YOLOv8 model to understand whether it can be used for your application without custom training, you can use the prediction mode. While the model is pre-trained on datasets like COCO, running predictions on your own dataset can give you a quick sense of how well it might perform in your specific context. -## Overfitting and Underfitting in Machine Learning +## Overfitting and [Underfitting](https://www.ultralytics.com/glossary/underfitting) in [Machine Learning](https://www.ultralytics.com/glossary/machine-learning-ml) When testing a machine learning model, especially in computer vision, it's important to watch out for overfitting and underfitting. These issues can significantly affect how well your model works with new data. @@ -71,7 +71,7 @@ Overfitting happens when your model learns the training data too well, including #### Signs of Overfitting -- **High Training Accuracy, Low Validation Accuracy:** If your model performs very well on training data but poorly on validation or test data, it's likely overfitting. +- **High Training Accuracy, Low Validation Accuracy:** If your model performs very well on training data but poorly on validation or [test data](https://www.ultralytics.com/glossary/test-data), it's likely overfitting. - **Visual Inspection:** Sometimes, you can see overfitting if your model is too sensitive to minor changes or irrelevant details in images. ### Underfitting @@ -102,7 +102,7 @@ Data leakage can be tricky to spot and often comes from hidden biases in the tra - **Camera Bias:** Different angles, lighting, shadows, and camera movements can introduce unwanted patterns. - **Overlay Bias:** Logos, timestamps, or other overlays in images can mislead the model. - **Font and Object Bias:** Specific fonts or objects that frequently appear in certain classes can skew the model's learning. -- **Spatial Bias:** Imbalances in foreground-background, bounding box distributions, and object locations can affect training. +- **Spatial Bias:** Imbalances in foreground-background, [bounding box](https://www.ultralytics.com/glossary/bounding-box) distributions, and object locations can affect training. - **Label and Domain Bias:** Incorrect labels or shifts in data types can lead to leakage. ### Detecting Data Leakage @@ -139,13 +139,13 @@ These resources will help you navigate challenges and remain updated on the late ## In Summary -Building trustworthy computer vision models relies on rigorous model testing. By testing the model with previously unseen data, we can analyze it and spot weaknesses like overfitting and data leakage. Addressing these issues before deployment helps the model perform well in real-world applications. It's important to remember that model testing is just as crucial as model evaluation in guaranteeing the model's long-term success and effectiveness. +Building trustworthy computer vision models relies on rigorous model testing. By testing the model with previously unseen data, we can analyze it and spot weaknesses like [overfitting](https://www.ultralytics.com/glossary/overfitting) and data leakage. Addressing these issues before deployment helps the model perform well in real-world applications. It's important to remember that model testing is just as crucial as model evaluation in guaranteeing the model's long-term success and effectiveness. ## FAQ ### What are the key differences between model evaluation and model testing in computer vision? -Model evaluation and model testing are distinct steps in a computer vision project. Model evaluation involves using a labeled dataset to compute metrics such as accuracy, precision, recall, and F1 score, providing insights into the model's performance with a controlled dataset. Model testing, on the other hand, assesses the model's performance in real-world scenarios by applying it to new, unseen data, ensuring the model's learned behavior aligns with expectations outside the evaluation environment. For a detailed guide, refer to the [steps in a computer vision project](./steps-of-a-cv-project.md). +Model evaluation and model testing are distinct steps in a computer vision project. Model evaluation involves using a labeled dataset to compute metrics such as [accuracy](https://www.ultralytics.com/glossary/accuracy), precision, recall, and [F1 score](https://www.ultralytics.com/glossary/f1-score), providing insights into the model's performance with a controlled dataset. Model testing, on the other hand, assesses the model's performance in real-world scenarios by applying it to new, unseen data, ensuring the model's learned behavior aligns with expectations outside the evaluation environment. For a detailed guide, refer to the [steps in a computer vision project](./steps-of-a-cv-project.md). ### How can I test my Ultralytics YOLOv8 model on multiple images? @@ -155,7 +155,7 @@ To test your Ultralytics YOLOv8 model on multiple images, you can use the [predi To address **overfitting**: -- Regularization techniques like dropout. +- [Regularization](https://www.ultralytics.com/glossary/regularization) techniques like dropout. - Increase the size of the training dataset. - Simplify the model architecture. @@ -163,7 +163,7 @@ To address **underfitting**: - Use a more complex model. - Provide more relevant features. -- Increase training iterations or epochs. +- Increase training iterations or [epochs](https://www.ultralytics.com/glossary/epoch). Review misclassified images, perform thorough error analysis, and regularly track performance metrics to maintain a balance. For more information on these concepts, explore our section on [Overfitting and Underfitting](#overfitting-and-underfitting-in-machine-learning). @@ -190,7 +190,7 @@ Post-testing, if the model performance meets the project goals, proceed with dep - Error analysis. - Gathering more diverse and high-quality data. -- Hyperparameter tuning. +- [Hyperparameter tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning). - Retraining the model. Gain insights from the [Model Testing Vs. Model Evaluation](#model-testing-vs-model-evaluation) section to refine and enhance model effectiveness in real-world applications. diff --git a/docs/en/guides/model-training-tips.md b/docs/en/guides/model-training-tips.md index 932a412ffb..725081a244 100644 --- a/docs/en/guides/model-training-tips.md +++ b/docs/en/guides/model-training-tips.md @@ -18,22 +18,22 @@ One of the most important steps when working on a [computer vision project](./st allowfullscreen>
- Watch: Model Training Tips | How to Handle Large Datasets | Batch Size, GPU Utilization and Mixed Precision + Watch: Model Training Tips | How to Handle Large Datasets | Batch Size, GPU Utilization and [Mixed Precision](https://www.ultralytics.com/glossary/mixed-precision)

So, what is [model training](../modes/train.md)? Model training is the process of teaching your model to recognize visual patterns and make predictions based on your data. It directly impacts the performance and accuracy of your application. In this guide, we'll cover best practices, optimization techniques, and troubleshooting tips to help you train your computer vision models effectively. -## How to Train a Machine Learning Model +## How to Train a [Machine Learning](https://www.ultralytics.com/glossary/machine-learning-ml) Model A computer vision model is trained by adjusting its internal parameters to minimize errors. Initially, the model is fed a large set of labeled images. It makes predictions about what is in these images, and the predictions are compared to the actual labels or contents to calculate errors. These errors show how far off the model's predictions are from the true values. -During training, the model iteratively makes predictions, calculates errors, and updates its parameters through a process called backpropagation. In this process, the model adjusts its internal parameters (weights and biases) to reduce the errors. By repeating this cycle many times, the model gradually improves its accuracy. Over time, it learns to recognize complex patterns such as shapes, colors, and textures. +During training, the model iteratively makes predictions, calculates errors, and updates its parameters through a process called [backpropagation](https://www.ultralytics.com/glossary/backpropagation). In this process, the model adjusts its internal parameters (weights and biases) to reduce the errors. By repeating this cycle many times, the model gradually improves its accuracy. Over time, it learns to recognize complex patterns such as shapes, colors, and textures.

What is Backpropagation?

-This learning process makes it possible for the computer vision model to perform various [tasks](../tasks/index.md), including [object detection](../tasks/detect.md), [instance segmentation](../tasks/segment.md), and [image classification](../tasks/classify.md). The ultimate goal is to create a model that can generalize its learning to new, unseen images so that it can accurately understand visual data in real-world applications. +This learning process makes it possible for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) model to perform various [tasks](../tasks/index.md), including [object detection](../tasks/detect.md), [instance segmentation](../tasks/segment.md), and [image classification](../tasks/classify.md). The ultimate goal is to create a model that can generalize its learning to new, unseen images so that it can accurately understand visual data in real-world applications. Now that we know what is happening behind the scenes when we train a model, let's look at points to consider when training a model. @@ -46,7 +46,7 @@ There are a few different aspects to think about when you are planning on using When training models on large datasets, efficiently utilizing your GPU is key. Batch size is an important factor. It is the number of data samples that a machine learning model processes in a single training iteration. Using the maximum batch size supported by your GPU, you can fully take advantage of its capabilities and reduce the time model training takes. However, you want to avoid running out of GPU memory. If you encounter memory errors, reduce the batch size incrementally until the model trains smoothly. -With respect to YOLOv8, you can set the `batch_size` parameter in the [training configuration](../modes/train.md) to match your GPU capacity. Also, setting `batch=-1` in your training script will automatically determine the batch size that can be efficiently processed based on your device's capabilities. By fine-tuning the batch size, you can make the most of your GPU resources and improve the overall training process. +With respect to YOLOv8, you can set the `batch_size` parameter in the [training configuration](../modes/train.md) to match your GPU capacity. Also, setting `batch=-1` in your training script will automatically determine the [batch size](https://www.ultralytics.com/glossary/batch-size) that can be efficiently processed based on your device's capabilities. By fine-tuning the batch size, you can make the most of your GPU resources and improve the overall training process. ### Subset Training @@ -72,19 +72,19 @@ Caching can be controlled when training YOLOv8 using the `cache` parameter: ### Mixed Precision Training -Mixed precision training uses both 16-bit (FP16) and 32-bit (FP32) floating-point types. The strengths of both FP16 and FP32 are leveraged by using FP16 for faster computation and FP32 to maintain precision where needed. Most of the neural network's operations are done in FP16 to benefit from faster computation and lower memory usage. However, a master copy of the model's weights is kept in FP32 to ensure accuracy during the weight update steps. You can handle larger models or larger batch sizes within the same hardware constraints. +Mixed precision training uses both 16-bit (FP16) and 32-bit (FP32) floating-point types. The strengths of both FP16 and FP32 are leveraged by using FP16 for faster computation and FP32 to maintain precision where needed. Most of the [neural network](https://www.ultralytics.com/glossary/neural-network-nn)'s operations are done in FP16 to benefit from faster computation and lower memory usage. However, a master copy of the model's weights is kept in FP32 to ensure accuracy during the weight update steps. You can handle larger models or larger batch sizes within the same hardware constraints.

Mixed Precision Training Overview

-To implement mixed precision training, you'll need to modify your training scripts and ensure your hardware (like GPUs) supports it. Many modern deep learning frameworks, such as Tensorflow, offer built-in support for mixed precision. +To implement mixed precision training, you'll need to modify your training scripts and ensure your hardware (like GPUs) supports it. Many modern [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) frameworks, such as [Tensorflow](https://www.ultralytics.com/glossary/tensorflow), offer built-in support for mixed precision. Mixed precision training is straightforward when working with YOLOv8. You can use the `amp` flag in your training configuration. Setting `amp=True` enables Automatic Mixed Precision (AMP) training. Mixed precision training is a simple yet effective way to optimize your model training process. ### Pre-trained Weights -Using pretrained weights is a smart way to speed up your model's training process. Pretrained weights come from models already trained on large datasets, giving your model a head start. Transfer learning adapts pretrained models to new, related tasks. Fine-tuning a pre-trained model involves starting with these weights and then continuing training on your specific dataset. This method of training results in faster training times and often better performance because the model starts with a solid understanding of basic features. +Using pretrained weights is a smart way to speed up your model's training process. Pretrained weights come from models already trained on large datasets, giving your model a head start. [Transfer learning](https://www.ultralytics.com/glossary/transfer-learning) adapts pretrained models to new, related tasks. Fine-tuning a pre-trained model involves starting with these weights and then continuing training on your specific dataset. This method of training results in faster training times and often better performance because the model starts with a solid understanding of basic features. The `pretrained` parameter makes transfer learning easy with YOLOv8. Setting `pretrained=True` will use default pre-trained weights, or you can specify a path to a custom pre-trained model. Using pre-trained weights and transfer learning effectively boosts your model's capabilities and reduces training costs. @@ -92,14 +92,14 @@ The `pretrained` parameter makes transfer learning easy with YOLOv8. Setting `pr There are a couple of other techniques to consider when handling a large dataset: -- **Learning Rate Schedulers**: Implementing learning rate schedulers dynamically adjusts the learning rate during training. A well-tuned learning rate can prevent the model from overshooting minima and improve stability. When training YOLOv8, the `lrf` parameter helps manage learning rate scheduling by setting the final learning rate as a fraction of the initial rate. +- **[Learning Rate](https://www.ultralytics.com/glossary/learning-rate) Schedulers**: Implementing learning rate schedulers dynamically adjusts the learning rate during training. A well-tuned learning rate can prevent the model from overshooting minima and improve stability. When training YOLOv8, the `lrf` parameter helps manage learning rate scheduling by setting the final learning rate as a fraction of the initial rate. - **Distributed Training**: For handling large datasets, distributed training can be a game-changer. You can reduce the training time by spreading the training workload across multiple GPUs or machines. ## The Number of Epochs To Train For When training a model, an epoch refers to one complete pass through the entire training dataset. During an epoch, the model processes each example in the training set once and updates its parameters based on the learning algorithm. Multiple epochs are usually needed to allow the model to learn and refine its parameters over time. -A common question that comes up is how to determine the number of epochs to train the model for. A good starting point is 300 epochs. If the model overfits early, you can reduce the number of epochs. If overfitting does not occur after 300 epochs, you can extend the training to 600, 1200, or more epochs. +A common question that comes up is how to determine the number of epochs to train the model for. A good starting point is 300 epochs. If the model overfits early, you can reduce the number of epochs. If [overfitting](https://www.ultralytics.com/glossary/overfitting) does not occur after 300 epochs, you can extend the training to 600, 1200, or more epochs. However, the ideal number of epochs can vary based on your dataset's size and project goals. Larger datasets might require more epochs for the model to learn effectively, while smaller datasets might need fewer epochs to avoid overfitting. With respect to YOLOv8, you can set the `epochs` parameter in your training script. @@ -107,7 +107,7 @@ However, the ideal number of epochs can vary based on your dataset's size and pr Early stopping is a valuable technique for optimizing model training. By monitoring validation performance, you can halt training once the model stops improving. You can save computational resources and prevent overfitting. -The process involves setting a patience parameter that determines how many epochs to wait for an improvement in validation metrics before stopping training. If the model's performance does not improve within these epochs, training is stopped to avoid wasting time and resources. +The process involves setting a patience parameter that determines how many [epochs](https://www.ultralytics.com/glossary/epoch) to wait for an improvement in validation metrics before stopping training. If the model's performance does not improve within these epochs, training is stopped to avoid wasting time and resources.

Early Stopping Overview @@ -125,7 +125,7 @@ Local training provides greater control and customization, letting you tailor yo ## Selecting an Optimizer -An optimizer is an algorithm that adjusts the weights of your neural network to minimize the loss function, which measures how well the model is performing. In simpler terms, the optimizer helps the model learn by tweaking its parameters to reduce errors. Choosing the right optimizer directly affects how quickly and accurately the model learns. +An optimizer is an algorithm that adjusts the weights of your neural network to minimize the [loss function](https://www.ultralytics.com/glossary/loss-function), which measures how well the model is performing. In simpler terms, the optimizer helps the model learn by tweaking its parameters to reduce errors. Choosing the right optimizer directly affects how quickly and accurately the model learns. You can also fine-tune optimizer parameters to improve model performance. Adjusting the learning rate sets the size of the steps when updating parameters. For stability, you might start with a moderate learning rate and gradually decrease it over time to improve long-term learning. Additionally, setting the momentum determines how much influence past updates have on current updates. A common value for momentum is around 0.9. It generally provides a good balance. @@ -147,7 +147,7 @@ Different optimizers have various strengths and weaknesses. Let's take a glimpse - **RMSProp (Root Mean Square Propagation)**: - Adjusts the learning rate for each parameter by dividing the gradient by a running average of the magnitudes of recent gradients. - - Helps in handling the vanishing gradient problem and is effective for recurrent neural networks. + - Helps in handling the vanishing gradient problem and is effective for [recurrent neural networks](https://www.ultralytics.com/glossary/recurrent-neural-network-rnn). For YOLOv8, the `optimizer` parameter lets you choose from various optimizers, including SGD, Adam, AdamW, NAdam, RAdam, and RMSProp, or you can set it to `auto` for automatic selection based on model configuration. @@ -168,7 +168,7 @@ Using these resources will help you solve challenges and stay up-to-date with th ## Key Takeaways -Training computer vision models involves following good practices, optimizing your strategies, and solving problems as they arise. Techniques like adjusting batch sizes, mixed precision training, and starting with pre-trained weights can make your models work better and train faster. Methods like subset training and early stopping help you save time and resources. Staying connected with the community and keeping up with new trends will help you keep improving your model training skills. +Training computer vision models involves following good practices, optimizing your strategies, and solving problems as they arise. Techniques like adjusting batch sizes, mixed [precision](https://www.ultralytics.com/glossary/precision) training, and starting with pre-trained weights can make your models work better and train faster. Methods like subset training and early stopping help you save time and resources. Staying connected with the community and keeping up with new trends will help you keep improving your model training skills. ## FAQ @@ -178,7 +178,7 @@ To improve GPU utilization, set the `batch_size` parameter in your training conf ### What is mixed precision training, and how do I enable it in YOLOv8? -Mixed precision training utilizes both 16-bit (FP16) and 32-bit (FP32) floating-point types to balance computational speed and precision. This approach speeds up training and reduces memory usage without sacrificing model accuracy. To enable mixed precision training in YOLOv8, set the `amp` parameter to `True` in your training configuration. This activates Automatic Mixed Precision (AMP) training. For more details on this optimization technique, see the [training configuration](../modes/train.md). +Mixed precision training utilizes both 16-bit (FP16) and 32-bit (FP32) floating-point types to balance computational speed and precision. This approach speeds up training and reduces memory usage without sacrificing model [accuracy](https://www.ultralytics.com/glossary/accuracy). To enable mixed precision training in YOLOv8, set the `amp` parameter to `True` in your training configuration. This activates Automatic Mixed Precision (AMP) training. For more details on this optimization technique, see the [training configuration](../modes/train.md). ### How does multiscale training enhance YOLOv8 model performance? diff --git a/docs/en/guides/nvidia-jetson.md b/docs/en/guides/nvidia-jetson.md index db1b9b79f4..f352c76b8c 100644 --- a/docs/en/guides/nvidia-jetson.md +++ b/docs/en/guides/nvidia-jetson.md @@ -27,7 +27,7 @@ This comprehensive guide provides a detailed walkthrough for deploying Ultralyti ## What is NVIDIA Jetson? -NVIDIA Jetson is a series of embedded computing boards designed to bring accelerated AI (artificial intelligence) computing to edge devices. These compact and powerful devices are built around NVIDIA's GPU architecture and are capable of running complex AI algorithms and deep learning models directly on the device, without needing to rely on cloud computing resources. Jetson boards are often used in robotics, autonomous vehicles, industrial automation, and other applications where AI inference needs to be performed locally with low latency and high efficiency. Additionally, these boards are based on the ARM64 architecture and runs on lower power compared to traditional GPU computing devices. +NVIDIA Jetson is a series of embedded computing boards designed to bring accelerated AI (artificial intelligence) computing to edge devices. These compact and powerful devices are built around NVIDIA's GPU architecture and are capable of running complex AI algorithms and [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models directly on the device, without needing to rely on [cloud computing](https://www.ultralytics.com/glossary/cloud-computing) resources. Jetson boards are often used in robotics, autonomous vehicles, industrial automation, and other applications where AI inference needs to be performed locally with low latency and high efficiency. Additionally, these boards are based on the ARM64 architecture and runs on lower power compared to traditional GPU computing devices. ## NVIDIA Jetson Series Comparison @@ -46,7 +46,7 @@ For a more detailed comparison table, please visit the **Technical Specification ## What is NVIDIA JetPack? -[NVIDIA JetPack SDK](https://developer.nvidia.com/embedded/jetpack) powering the Jetson modules is the most comprehensive solution and provides full development environment for building end-to-end accelerated AI applications and shortens time to market. JetPack includes Jetson Linux with bootloader, Linux kernel, Ubuntu desktop environment, and a complete set of libraries for acceleration of GPU computing, multimedia, graphics, and computer vision. It also includes samples, documentation, and developer tools for both host computer and developer kit, and supports higher level SDKs such as DeepStream for streaming video analytics, Isaac for robotics, and Riva for conversational AI. +[NVIDIA JetPack SDK](https://developer.nvidia.com/embedded/jetpack) powering the Jetson modules is the most comprehensive solution and provides full development environment for building end-to-end accelerated AI applications and shortens time to market. JetPack includes Jetson Linux with bootloader, Linux kernel, Ubuntu desktop environment, and a complete set of libraries for acceleration of GPU computing, multimedia, graphics, and [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv). It also includes samples, documentation, and developer tools for both host computer and developer kit, and supports higher level SDKs such as DeepStream for streaming video analytics, Isaac for robotics, and Riva for conversational AI. ## Flash JetPack to NVIDIA Jetson @@ -110,7 +110,7 @@ For a native installation without Docker, please refer to the steps below. #### Install Ultralytics Package -Here we will install Ultralytics package on the Jetson with optional dependencies so that we can export the PyTorch models to other different formats. We will mainly focus on [NVIDIA TensorRT exports](../integrations/tensorrt.md) because TensorRT will make sure we can get the maximum performance out of the Jetson devices. +Here we will install Ultralytics package on the Jetson with optional dependencies so that we can export the [PyTorch](https://www.ultralytics.com/glossary/pytorch) models to other different formats. We will mainly focus on [NVIDIA TensorRT exports](../integrations/tensorrt.md) because TensorRT will make sure we can get the maximum performance out of the Jetson devices. 1. Update packages list, install pip and upgrade to latest @@ -280,7 +280,7 @@ The YOLOv8n model in PyTorch format is converted to TensorRT to run inference wi ## NVIDIA Jetson Orin YOLOv8 Benchmarks -YOLOv8 benchmarks were run by the Ultralytics team on 10 different model formats measuring speed and accuracy: PyTorch, TorchScript, ONNX, OpenVINO, TensorRT, TF SavedModel, TF GraphDef, TF Lite, PaddlePaddle, NCNN. Benchmarks were run on Seeed Studio reComputer J4012 powered by Jetson Orin NX 16GB device at FP32 precision with default input image size of 640. +YOLOv8 benchmarks were run by the Ultralytics team on 10 different model formats measuring speed and [accuracy](https://www.ultralytics.com/glossary/accuracy): PyTorch, TorchScript, ONNX, OpenVINO, TensorRT, TF SavedModel, TF GraphDef, TF Lite, PaddlePaddle, NCNN. Benchmarks were run on Seeed Studio reComputer J4012 powered by Jetson Orin NX 16GB device at FP32 [precision](https://www.ultralytics.com/glossary/precision) with default input image size of 640. ### Comparison Chart diff --git a/docs/en/guides/object-blurring.md b/docs/en/guides/object-blurring.md index 709ca1bd60..315bcd76ea 100644 --- a/docs/en/guides/object-blurring.md +++ b/docs/en/guides/object-blurring.md @@ -92,7 +92,7 @@ Object blurring with [Ultralytics YOLOv8](https://github.com/ultralytics/ultraly ### How can I implement real-time object blurring using YOLOv8? -To implement real-time object blurring with YOLOv8, follow the provided Python example. This involves using YOLOv8 for object detection and OpenCV for applying the blur effect. Here's a simplified version: +To implement real-time object blurring with YOLOv8, follow the provided Python example. This involves using YOLOv8 for [object detection](https://www.ultralytics.com/glossary/object-detection) and OpenCV for applying the blur effect. Here's a simplified version: ```python import cv2 @@ -132,7 +132,7 @@ For more detailed applications, check the [advantages of object blurring section ### Can I use Ultralytics YOLOv8 to blur faces in a video for privacy reasons? -Yes, Ultralytics YOLOv8 can be configured to detect and blur faces in videos to protect privacy. By training or using a pre-trained model to specifically recognize faces, the detection results can be processed with OpenCV to apply a blur effect. Refer to our guide on [object detection with YOLOv8](https://docs.ultralytics.com/models/yolov8/) and modify the code to target face detection. +Yes, Ultralytics YOLOv8 can be configured to detect and blur faces in videos to protect privacy. By training or using a pre-trained model to specifically recognize faces, the detection results can be processed with [OpenCV](https://www.ultralytics.com/glossary/opencv) to apply a blur effect. Refer to our guide on [object detection with YOLOv8](https://docs.ultralytics.com/models/yolov8/) and modify the code to target face detection. ### How does YOLOv8 compare to other object detection models like Faster R-CNN for object blurring? diff --git a/docs/en/guides/object-counting.md b/docs/en/guides/object-counting.md index 749ffbe8fa..bdec66e42d 100644 --- a/docs/en/guides/object-counting.md +++ b/docs/en/guides/object-counting.md @@ -8,7 +8,7 @@ keywords: object counting, YOLOv8, Ultralytics, real-time object detection, AI, ## What is Object Counting? -Object counting with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) involves accurate identification and counting of specific objects in videos and camera streams. YOLOv8 excels in real-time applications, providing efficient and precise object counting for various scenarios like crowd analysis and surveillance, thanks to its state-of-the-art algorithms and deep learning capabilities. +Object counting with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) involves accurate identification and counting of specific objects in videos and camera streams. YOLOv8 excels in real-time applications, providing efficient and precise object counting for various scenarios like crowd analysis and surveillance, thanks to its state-of-the-art algorithms and [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) capabilities. @@ -340,12 +340,12 @@ count_specific_classes("path/to/video.mp4", "output_specific_classes.avi", "yolo In this example, `classes_to_count=[0, 2]`, which means it counts objects of class `0` and `2` (e.g., person and car). -### Why should I use YOLOv8 over other object detection models for real-time applications? +### Why should I use YOLOv8 over other [object detection](https://www.ultralytics.com/glossary/object-detection) models for real-time applications? Ultralytics YOLOv8 provides several advantages over other object detection models like Faster R-CNN, SSD, and previous YOLO versions: 1. **Speed and Efficiency:** YOLOv8 offers real-time processing capabilities, making it ideal for applications requiring high-speed inference, such as surveillance and autonomous driving. -2. **Accuracy:** It provides state-of-the-art accuracy for object detection and tracking tasks, reducing the number of false positives and improving overall system reliability. +2. **[Accuracy](https://www.ultralytics.com/glossary/accuracy):** It provides state-of-the-art accuracy for object detection and tracking tasks, reducing the number of false positives and improving overall system reliability. 3. **Ease of Integration:** YOLOv8 offers seamless integration with various platforms and devices, including mobile and edge devices, which is crucial for modern AI applications. 4. **Flexibility:** Supports various tasks like object detection, segmentation, and tracking with configurable models to meet specific use-case requirements. diff --git a/docs/en/guides/object-cropping.md b/docs/en/guides/object-cropping.md index 09adb625d3..f4b50ed027 100644 --- a/docs/en/guides/object-cropping.md +++ b/docs/en/guides/object-cropping.md @@ -25,7 +25,7 @@ Object cropping with [Ultralytics YOLOv8](https://github.com/ultralytics/ultraly - **Focused Analysis**: YOLOv8 facilitates targeted object cropping, allowing for in-depth examination or processing of individual items within a scene. - **Reduced Data Volume**: By extracting only relevant objects, object cropping helps in minimizing data size, making it efficient for storage, transmission, or subsequent computational tasks. -- **Enhanced Precision**: YOLOv8's object detection accuracy ensures that the cropped objects maintain their spatial relationships, preserving the integrity of the visual information for detailed analysis. +- **Enhanced Precision**: YOLOv8's [object detection](https://www.ultralytics.com/glossary/object-detection) [accuracy](https://www.ultralytics.com/glossary/accuracy) ensures that the cropped objects maintain their spatial relationships, preserving the integrity of the visual information for detailed analysis. ## Visuals @@ -100,7 +100,7 @@ Object cropping with [Ultralytics YOLOv8](https://github.com/ultralytics/ultraly ### What is object cropping in Ultralytics YOLOv8 and how does it work? -Object cropping using [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) involves isolating and extracting specific objects from an image or video based on YOLOv8's detection capabilities. This process allows for focused analysis, reduced data volume, and enhanced precision by leveraging YOLOv8 to identify objects with high accuracy and crop them accordingly. For an in-depth tutorial, refer to the [object cropping example](#object-cropping-using-ultralytics-yolov8). +Object cropping using [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) involves isolating and extracting specific objects from an image or video based on YOLOv8's detection capabilities. This process allows for focused analysis, reduced data volume, and enhanced [precision](https://www.ultralytics.com/glossary/precision) by leveraging YOLOv8 to identify objects with high accuracy and crop them accordingly. For an in-depth tutorial, refer to the [object cropping example](#object-cropping-using-ultralytics-yolov8). ### Why should I use Ultralytics YOLOv8 for object cropping over other solutions? diff --git a/docs/en/guides/optimizing-openvino-latency-vs-throughput-modes.md b/docs/en/guides/optimizing-openvino-latency-vs-throughput-modes.md index 63fbb7a904..154ec7a893 100644 --- a/docs/en/guides/optimizing-openvino-latency-vs-throughput-modes.md +++ b/docs/en/guides/optimizing-openvino-latency-vs-throughput-modes.md @@ -10,7 +10,7 @@ keywords: Ultralytics YOLO, OpenVINO optimization, deep learning, model inferenc ## Introduction -When deploying deep learning models, particularly those for object detection such as Ultralytics YOLO models, achieving optimal performance is crucial. This guide delves into leveraging Intel's OpenVINO toolkit to optimize inference, focusing on latency and throughput. Whether you're working on consumer-grade applications or large-scale deployments, understanding and applying these optimization strategies will ensure your models run efficiently on various devices. +When deploying [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models, particularly those for [object detection](https://www.ultralytics.com/glossary/object-detection) such as Ultralytics YOLO models, achieving optimal performance is crucial. This guide delves into leveraging Intel's OpenVINO toolkit to optimize inference, focusing on latency and throughput. Whether you're working on consumer-grade applications or large-scale deployments, understanding and applying these optimization strategies will ensure your models run efficiently on various devices. ## Optimizing for Latency @@ -123,6 +123,6 @@ Yes, Ultralytics YOLO models are highly versatile and can be integrated with var - **TensorRT:** For NVIDIA GPU optimization, follow the [TensorRT integration guide](https://docs.ultralytics.com/integrations/tensorrt/). - **CoreML:** For Apple devices, refer to our [CoreML export instructions](https://docs.ultralytics.com/integrations/coreml/). -- **TensorFlow.js:** For web and Node.js apps, see the [TF.js conversion guide](https://docs.ultralytics.com/integrations/tfjs/). +- **[TensorFlow](https://www.ultralytics.com/glossary/tensorflow).js:** For web and Node.js apps, see the [TF.js conversion guide](https://docs.ultralytics.com/integrations/tfjs/). Explore more integrations on the [Ultralytics Integrations page](https://docs.ultralytics.com/integrations/). diff --git a/docs/en/guides/parking-management.md b/docs/en/guides/parking-management.md index 84a88f5753..78686bd061 100644 --- a/docs/en/guides/parking-management.md +++ b/docs/en/guides/parking-management.md @@ -74,9 +74,6 @@ Parking management with [Ultralytics YOLOv8](https://github.com/ultralytics/ultr from ultralytics import solutions - # Path to json file, that created with above point selection app - polygon_json_path = "bounding_boxes.json" - # Video capture cap = cv2.VideoCapture("Path/to/video/file.mp4") assert cap.isOpened(), "Error reading video file" @@ -86,22 +83,16 @@ Parking management with [Ultralytics YOLOv8](https://github.com/ultralytics/ultr video_writer = cv2.VideoWriter("parking management.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h)) # Initialize parking management object - management = solutions.ParkingManagement(model_path="yolov8n.pt") + parking_manager = solutions.ParkingManagement( + model="yolov8n.pt", # path to model file + json_file="bounding_boxes.json", # path to parking annotations file + ) while cap.isOpened(): ret, im0 = cap.read() if not ret: break - - json_data = management.parking_regions_extraction(polygon_json_path) - results = management.model.track(im0, persist=True, show=False) - - if results[0].boxes.id is not None: - boxes = results[0].boxes.xyxy.cpu().tolist() - clss = results[0].boxes.cls.cpu().tolist() - management.process_data(json_data, im0, boxes, clss) - - management.display_frames(im0) + im0 = parking_manager.process_data(im0) video_writer.write(im0) cap.release() @@ -111,14 +102,12 @@ Parking management with [Ultralytics YOLOv8](https://github.com/ultralytics/ultr ### Optional Arguments `ParkingManagement` -| Name | Type | Default | Description | -| ------------------------ | ------- | ----------------- | -------------------------------------- | -| `model_path` | `str` | `None` | Path to the YOLOv8 model. | -| `txt_color` | `tuple` | `(0, 0, 0)` | RGB color tuple for text. | -| `bg_color` | `tuple` | `(255, 255, 255)` | RGB color tuple for background. | -| `occupied_region_color` | `tuple` | `(0, 255, 0)` | RGB color tuple for occupied regions. | -| `available_region_color` | `tuple` | `(0, 0, 255)` | RGB color tuple for available regions. | -| `margin` | `int` | `10` | Margin for text display. | +| Name | Type | Default | Description | +| ------------------------ | ------- | ------------- | -------------------------------------------------------------- | +| `model` | `str` | `None` | Path to the YOLOv8 model. | +| `json_file` | `str` | `None` | Path to the JSON file, that have all parking coordinates data. | +| `occupied_region_color` | `tuple` | `(0, 0, 255)` | RGB color for occupied regions. | +| `available_region_color` | `tuple` | `(0, 255, 0)` | RGB color for available regions. | ### Arguments `model.track` diff --git a/docs/en/guides/preprocessing_annotated_data.md b/docs/en/guides/preprocessing_annotated_data.md index 36fcf9f9c1..fcd329c743 100644 --- a/docs/en/guides/preprocessing_annotated_data.md +++ b/docs/en/guides/preprocessing_annotated_data.md @@ -4,7 +4,7 @@ description: Learn essential data preprocessing techniques for annotated compute keywords: data preprocessing, computer vision, image resizing, normalization, data augmentation, training dataset, validation dataset, test dataset, YOLOv8 --- -# Data Preprocessing Techniques for Annotated Computer Vision Data +# Data Preprocessing Techniques for Annotated [Computer Vision](https://www.ultralytics.com/glossary/computer-vision-cv) Data ## Introduction @@ -33,7 +33,7 @@ You can resize your images using the following methods: To make resizing a simpler task, you can use the following tools: -- **OpenCV**: A popular computer vision library with extensive functions for image processing. +- **[OpenCV](https://www.ultralytics.com/glossary/opencv)**: A popular computer vision library with extensive functions for image processing. - **PIL (Pillow)**: A Python Imaging Library for opening, manipulating, and saving image files. With respect to YOLOv8, the 'imgsz' parameter during [model training](../modes/train.md) allows for flexible input sizes. When set to a specific size, such as 640, the model will resize input images so their largest dimension is 640 pixels while maintaining the original aspect ratio. @@ -65,7 +65,7 @@ The most commonly discussed data preprocessing step is data augmentation. Data a Here are some other benefits of data augmentation: - **Creates a More Robust Dataset**: Data augmentation can make the model more robust to variations and distortions in the input data. This includes changes in lighting, orientation, and scale. -- **Cost-Effective**: Data augmentation is a cost-effective way to increase the amount of training data without collecting and labeling new data. +- **Cost-Effective**: Data augmentation is a cost-effective way to increase the amount of [training data](https://www.ultralytics.com/glossary/training-data) without collecting and labeling new data. - **Better Use of Data**: Every available data point is used to its maximum potential by creating new variations #### Data Augmentation Methods @@ -96,7 +96,7 @@ Here's what each step of preprocessing would look like for this project: - Resizing Images: Since YOLOv8 handles flexible input sizes and performs resizing automatically, manual resizing is not required. The model will adjust the image size according to the specified 'imgsz' parameter during training. - Normalizing Pixel Values: YOLOv8 automatically normalizes pixel values to a range of 0 to 1 during preprocessing, so it's not required. - Splitting the Dataset: Divide the dataset into training (70%), validation (20%), and test (10%) sets using tools like scikit-learn. -- Data Augmentation: Modify the dataset configuration file (.yaml) to include data augmentation techniques such as random crops, horizontal flips, and brightness adjustments. +- [Data Augmentation](https://www.ultralytics.com/glossary/data-augmentation): Modify the dataset configuration file (.yaml) to include data augmentation techniques such as random crops, horizontal flips, and brightness adjustments. These steps make sure the dataset is prepared without any potential issues and is ready for Exploratory Data Analysis (EDA). @@ -120,7 +120,7 @@ Common tools for visualizations include: ### Using Ultralytics Explorer for EDA -For a more advanced approach to EDA, you can use the Ultralytics Explorer tool. It offers robust capabilities for exploring computer vision datasets. By supporting semantic search, SQL queries, and vector similarity search, the tool makes it easy to analyze and understand your data. With Ultralytics Explorer, you can create embeddings for your dataset to find similar images, run SQL queries for detailed analysis, and perform semantic searches, all through a user-friendly graphical interface. +For a more advanced approach to EDA, you can use the Ultralytics Explorer tool. It offers robust capabilities for exploring computer vision datasets. By supporting semantic search, SQL queries, and vector similarity search, the tool makes it easy to analyze and understand your data. With Ultralytics Explorer, you can create [embeddings](https://www.ultralytics.com/glossary/embeddings) for your dataset to find similar images, run SQL queries for detailed analysis, and perform semantic searches, all through a user-friendly graphical interface.

Overview of Ultralytics Explorer @@ -151,7 +151,7 @@ Data preprocessing is essential in computer vision projects because it ensures t ### How can I use Ultralytics YOLO for data augmentation? -For data augmentation with Ultralytics YOLOv8, you need to modify the dataset configuration file (.yaml). In this file, you can specify various augmentation techniques such as random crops, horizontal flips, and brightness adjustments. This can be effectively done using the training configurations [explained here](../modes/train.md). Data augmentation helps create a more robust dataset, reduce overfitting, and improve model generalization. +For data augmentation with Ultralytics YOLOv8, you need to modify the dataset configuration file (.yaml). In this file, you can specify various augmentation techniques such as random crops, horizontal flips, and brightness adjustments. This can be effectively done using the training configurations [explained here](../modes/train.md). Data augmentation helps create a more robust dataset, reduce [overfitting](https://www.ultralytics.com/glossary/overfitting), and improve model generalization. ### What are the best data normalization techniques for computer vision data? @@ -164,7 +164,7 @@ For YOLOv8, normalization is handled automatically, including conversion to RGB ### How should I split my annotated dataset for training? -To split your dataset, a common practice is to divide it into 70% for training, 20% for validation, and 10% for testing. It is important to maintain the data distribution of classes across these splits and avoid data leakage by performing augmentation only on the training set. Use tools like scikit-learn or TensorFlow for efficient dataset splitting. See the detailed guide on [dataset preparation](../guides/data-collection-and-annotation.md). +To split your dataset, a common practice is to divide it into 70% for training, 20% for validation, and 10% for testing. It is important to maintain the data distribution of classes across these splits and avoid data leakage by performing augmentation only on the training set. Use tools like scikit-learn or [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) for efficient dataset splitting. See the detailed guide on [dataset preparation](../guides/data-collection-and-annotation.md). ### Can I handle varying image sizes in YOLOv8 without manual resizing? diff --git a/docs/en/guides/queue-management.md b/docs/en/guides/queue-management.md index 993d414102..9fb4897edf 100644 --- a/docs/en/guides/queue-management.md +++ b/docs/en/guides/queue-management.md @@ -187,7 +187,7 @@ Using Ultralytics YOLOv8 for queue management offers several benefits: For more details, explore our [Queue Management](https://docs.ultralytics.com/reference/solutions/queue_management/) solutions. -### Why should I choose Ultralytics YOLOv8 over competitors like TensorFlow or Detectron2 for queue management? +### Why should I choose Ultralytics YOLOv8 over competitors like [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) or Detectron2 for queue management? Ultralytics YOLOv8 has several advantages over TensorFlow and Detectron2 for queue management: diff --git a/docs/en/guides/raspberry-pi.md b/docs/en/guides/raspberry-pi.md index 25d45068a8..c25557e8a3 100644 --- a/docs/en/guides/raspberry-pi.md +++ b/docs/en/guides/raspberry-pi.md @@ -49,7 +49,7 @@ The first thing to do after getting your hands on a Raspberry Pi is to flash a m ## Set Up Ultralytics -There are two ways of setting up Ultralytics package on Raspberry Pi to build your next Computer Vision project. You can use either of them. +There are two ways of setting up Ultralytics package on Raspberry Pi to build your next [Computer Vision](https://www.ultralytics.com/glossary/computer-vision-cv) project. You can use either of them. - [Start with Docker](#start-with-docker) - [Start without Docker](#start-without-docker) @@ -70,7 +70,7 @@ After this is done, skip to [Use NCNN on Raspberry Pi section](#use-ncnn-on-rasp #### Install Ultralytics Package -Here we will install Ultralytics package on the Raspberry Pi with optional dependencies so that we can export the PyTorch models to other different formats. +Here we will install Ultralytics package on the Raspberry Pi with optional dependencies so that we can export the [PyTorch](https://www.ultralytics.com/glossary/pytorch) models to other different formats. 1. Update packages list, install pip and upgrade to latest @@ -136,7 +136,7 @@ The YOLOv8n model in PyTorch format is converted to NCNN to run inference with t ## Raspberry Pi 5 vs Raspberry Pi 4 YOLOv8 Benchmarks -YOLOv8 benchmarks were run by the Ultralytics team on nine different model formats measuring speed and accuracy: PyTorch, TorchScript, ONNX, OpenVINO, TF SavedModel, TF GraphDef, TF Lite, PaddlePaddle, NCNN. Benchmarks were run on both Raspberry Pi 5 and Raspberry Pi 4 at FP32 precision with default input image size of 640. +YOLOv8 benchmarks were run by the Ultralytics team on nine different model formats measuring speed and [accuracy](https://www.ultralytics.com/glossary/accuracy): PyTorch, TorchScript, ONNX, OpenVINO, TF SavedModel, TF GraphDef, TF Lite, PaddlePaddle, NCNN. Benchmarks were run on both Raspberry Pi 5 and Raspberry Pi 4 at FP32 [precision](https://www.ultralytics.com/glossary/precision) with default input image size of 640. !!! note diff --git a/docs/en/guides/region-counting.md b/docs/en/guides/region-counting.md index f2be9d4574..a27c2b4e53 100644 --- a/docs/en/guides/region-counting.md +++ b/docs/en/guides/region-counting.md @@ -8,7 +8,7 @@ keywords: object counting, regions, YOLOv8, computer vision, Ultralytics, effici ## What is Object Counting in Regions? -[Object counting](../guides/object-counting.md) in regions with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) involves precisely determining the number of objects within specified areas using advanced computer vision. This approach is valuable for optimizing processes, enhancing security, and improving efficiency in various applications. +[Object counting](../guides/object-counting.md) in regions with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) involves precisely determining the number of objects within specified areas using advanced [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv). This approach is valuable for optimizing processes, enhancing security, and improving efficiency in various applications.


@@ -23,7 +23,7 @@ keywords: object counting, regions, YOLOv8, computer vision, Ultralytics, effici ## Advantages of Object Counting in Regions? -- **Precision and Accuracy:** Object counting in regions with advanced computer vision ensures precise and accurate counts, minimizing errors often associated with manual counting. +- **[Precision](https://www.ultralytics.com/glossary/precision) and Accuracy:** Object counting in regions with advanced computer vision ensures precise and accurate counts, minimizing errors often associated with manual counting. - **Efficiency Improvement:** Automated object counting enhances operational efficiency, providing real-time results and streamlining processes across different applications. - **Versatility and Application:** The versatility of object counting in regions makes it applicable across various domains, from manufacturing and surveillance to traffic monitoring, contributing to its widespread utility and effectiveness. @@ -75,21 +75,21 @@ python yolov8_region_counter.py --source "path/to/video.mp4" --view-img ### Optional Arguments -| Name | Type | Default | Description | -| -------------------- | ------ | ------------ | ------------------------------------------ | -| `--source` | `str` | `None` | Path to video file, for webcam 0 | -| `--line_thickness` | `int` | `2` | Bounding Box thickness | -| `--save-img` | `bool` | `False` | Save the predicted video/image | -| `--weights` | `str` | `yolov8n.pt` | Weights file path | -| `--classes` | `list` | `None` | Detect specific classes i.e. --classes 0 2 | -| `--region-thickness` | `int` | `2` | Region Box thickness | -| `--track-thickness` | `int` | `2` | Tracking line thickness | +| Name | Type | Default | Description | +| -------------------- | ------ | ------------ | --------------------------------------------------------------------------- | +| `--source` | `str` | `None` | Path to video file, for webcam 0 | +| `--line_thickness` | `int` | `2` | [Bounding Box](https://www.ultralytics.com/glossary/bounding-box) thickness | +| `--save-img` | `bool` | `False` | Save the predicted video/image | +| `--weights` | `str` | `yolov8n.pt` | Weights file path | +| `--classes` | `list` | `None` | Detect specific classes i.e. --classes 0 2 | +| `--region-thickness` | `int` | `2` | Region Box thickness | +| `--track-thickness` | `int` | `2` | Tracking line thickness | ## FAQ ### What is object counting in specified regions using Ultralytics YOLOv8? -Object counting in specified regions with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) involves detecting and tallying the number of objects within defined areas using advanced computer vision. This precise method enhances efficiency and accuracy across various applications like manufacturing, surveillance, and traffic monitoring. +Object counting in specified regions with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) involves detecting and tallying the number of objects within defined areas using advanced computer vision. This precise method enhances efficiency and [accuracy](https://www.ultralytics.com/glossary/accuracy) across various applications like manufacturing, surveillance, and traffic monitoring. ### How do I run the object counting script with Ultralytics YOLOv8? diff --git a/docs/en/guides/ros-quickstart.md b/docs/en/guides/ros-quickstart.md index 227286de0d..27371131dd 100644 --- a/docs/en/guides/ros-quickstart.md +++ b/docs/en/guides/ros-quickstart.md @@ -69,7 +69,7 @@ Apart from the ROS environment, you will need to install the following dependenc ## Use Ultralytics with ROS `sensor_msgs/Image` -The `sensor_msgs/Image` [message type](https://docs.ros.org/en/api/sensor_msgs/html/msg/Image.html) is commonly used in ROS for representing image data. It contains fields for encoding, height, width, and pixel data, making it suitable for transmitting images captured by cameras or other sensors. Image messages are widely used in robotic applications for tasks such as visual perception, object detection, and navigation. +The `sensor_msgs/Image` [message type](https://docs.ros.org/en/api/sensor_msgs/html/msg/Image.html) is commonly used in ROS for representing image data. It contains fields for encoding, height, width, and pixel data, making it suitable for transmitting images captured by cameras or other sensors. Image messages are widely used in robotic applications for tasks such as visual perception, [object detection](https://www.ultralytics.com/glossary/object-detection), and navigation.

Detection and Segmentation in ROS Gazebo @@ -360,7 +360,7 @@ A point cloud is a collection of data points defined within a three-dimensional Point Clouds can be obtained using various sensors: - 1. **LIDAR (Light Detection and Ranging)**: Uses laser pulses to measure distances to objects and create high-precision 3D maps. + 1. **LIDAR (Light Detection and Ranging)**: Uses laser pulses to measure distances to objects and create high-[precision](https://www.ultralytics.com/glossary/precision) 3D maps. 2. **Depth Cameras**: Capture depth information for each pixel, allowing for 3D reconstruction of the scene. 3. **Stereo Cameras**: Utilize two or more cameras to obtain depth information through triangulation. 4. **Structured Light Scanners**: Project a known pattern onto a surface and measure the deformation to calculate depth. diff --git a/docs/en/guides/sahi-tiled-inference.md b/docs/en/guides/sahi-tiled-inference.md index 6b23b21c7f..1137d6b84f 100644 --- a/docs/en/guides/sahi-tiled-inference.md +++ b/docs/en/guides/sahi-tiled-inference.md @@ -6,7 +6,7 @@ keywords: YOLOv8, SAHI, Sliced Inference, Object Detection, Ultralytics, High-re # Ultralytics Docs: Using YOLOv8 with SAHI for Sliced Inference -Welcome to the Ultralytics documentation on how to use YOLOv8 with [SAHI](https://github.com/obss/sahi) (Slicing Aided Hyper Inference). This comprehensive guide aims to furnish you with all the essential knowledge you'll need to implement SAHI alongside YOLOv8. We'll deep-dive into what SAHI is, why sliced inference is critical for large-scale applications, and how to integrate these functionalities with YOLOv8 for enhanced object detection performance. +Welcome to the Ultralytics documentation on how to use YOLOv8 with [SAHI](https://github.com/obss/sahi) (Slicing Aided Hyper Inference). This comprehensive guide aims to furnish you with all the essential knowledge you'll need to implement SAHI alongside YOLOv8. We'll deep-dive into what SAHI is, why sliced inference is critical for large-scale applications, and how to integrate these functionalities with YOLOv8 for enhanced [object detection](https://www.ultralytics.com/glossary/object-detection) performance.

SAHI Sliced Inference Overview @@ -31,7 +31,7 @@ SAHI (Slicing Aided Hyper Inference) is an innovative library designed to optimi - **Seamless Integration**: SAHI integrates effortlessly with YOLO models, meaning you can start slicing and detecting without a lot of code modification. - **Resource Efficiency**: By breaking down large images into smaller parts, SAHI optimizes the memory usage, allowing you to run high-quality detection on hardware with limited resources. -- **High Accuracy**: SAHI maintains the detection accuracy by employing smart algorithms to merge overlapping detection boxes during the stitching process. +- **High [Accuracy](https://www.ultralytics.com/glossary/accuracy)**: SAHI maintains the detection accuracy by employing smart algorithms to merge overlapping detection boxes during the stitching process. ## What is Sliced Inference? @@ -202,7 +202,7 @@ If you use SAHI in your research or development work, please cite the original S } ``` -We extend our thanks to the SAHI research group for creating and maintaining this invaluable resource for the computer vision community. For more information about SAHI and its creators, visit the [SAHI GitHub repository](https://github.com/obss/sahi). +We extend our thanks to the SAHI research group for creating and maintaining this invaluable resource for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) community. For more information about SAHI and its creators, visit the [SAHI GitHub repository](https://github.com/obss/sahi). ## FAQ diff --git a/docs/en/guides/security-alarm-system.md b/docs/en/guides/security-alarm-system.md index 4b5cdeebd2..d90e44a583 100644 --- a/docs/en/guides/security-alarm-system.md +++ b/docs/en/guides/security-alarm-system.md @@ -8,10 +8,10 @@ keywords: YOLOv8, Security Alarm System, real-time object detection, Ultralytics Security Alarm System -The Security Alarm System Project utilizing Ultralytics YOLOv8 integrates advanced computer vision capabilities to enhance security measures. YOLOv8, developed by Ultralytics, provides real-time object detection, allowing the system to identify and respond to potential security threats promptly. This project offers several advantages: +The Security Alarm System Project utilizing Ultralytics YOLOv8 integrates advanced [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) capabilities to enhance security measures. YOLOv8, developed by Ultralytics, provides real-time object detection, allowing the system to identify and respond to potential security threats promptly. This project offers several advantages: - **Real-time Detection:** YOLOv8's efficiency enables the Security Alarm System to detect and respond to security incidents in real-time, minimizing response time. -- **Accuracy:** YOLOv8 is known for its accuracy in object detection, reducing false positives and enhancing the reliability of the security alarm system. +- **[Accuracy](https://www.ultralytics.com/glossary/accuracy):** YOLOv8 is known for its accuracy in object detection, reducing false positives and enhancing the reliability of the security alarm system. - **Integration Capabilities:** The project can be seamlessly integrated with existing security infrastructure, providing an upgraded layer of intelligent surveillance.

@@ -22,7 +22,7 @@ The Security Alarm System Project utilizing Ultralytics YOLOv8 integrates advanc allowfullscreen>
- Watch: Security Alarm System Project with Ultralytics YOLOv8 Object Detection + Watch: Security Alarm System Project with Ultralytics YOLOv8 [Object Detection](https://www.ultralytics.com/glossary/object-detection)

### Code @@ -193,8 +193,8 @@ Running Ultralytics YOLOv8 on a standard setup typically requires around 5GB of ### What makes Ultralytics YOLOv8 different from other object detection models like Faster R-CNN or SSD? -Ultralytics YOLOv8 provides an edge over models like Faster R-CNN or SSD with its real-time detection capabilities and higher accuracy. Its unique architecture allows it to process images much faster without compromising on precision, making it ideal for time-sensitive applications like security alarm systems. For a comprehensive comparison of object detection models, you can explore our [guide](https://docs.ultralytics.com/models/). +Ultralytics YOLOv8 provides an edge over models like Faster R-CNN or SSD with its real-time detection capabilities and higher accuracy. Its unique architecture allows it to process images much faster without compromising on [precision](https://www.ultralytics.com/glossary/precision), making it ideal for time-sensitive applications like security alarm systems. For a comprehensive comparison of object detection models, you can explore our [guide](https://docs.ultralytics.com/models/). ### How can I reduce the frequency of false positives in my security system using Ultralytics YOLOv8? -To reduce false positives, ensure your Ultralytics YOLOv8 model is adequately trained with a diverse and well-annotated dataset. Fine-tuning hyperparameters and regularly updating the model with new data can significantly improve detection accuracy. Detailed hyperparameter tuning techniques can be found in our [hyperparameter tuning guide](../guides/hyperparameter-tuning.md). +To reduce false positives, ensure your Ultralytics YOLOv8 model is adequately trained with a diverse and well-annotated dataset. Fine-tuning hyperparameters and regularly updating the model with new data can significantly improve detection accuracy. Detailed [hyperparameter tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning) techniques can be found in our [hyperparameter tuning guide](../guides/hyperparameter-tuning.md). diff --git a/docs/en/guides/speed-estimation.md b/docs/en/guides/speed-estimation.md index 9b76d0a3a0..6f3726c921 100644 --- a/docs/en/guides/speed-estimation.md +++ b/docs/en/guides/speed-estimation.md @@ -8,7 +8,7 @@ keywords: Ultralytics YOLOv8, speed estimation, object tracking, computer vision ## What is Speed Estimation? -[Speed estimation](https://www.ultralytics.com/blog/ultralytics-yolov8-for-speed-estimation-in-computer-vision-projects) is the process of calculating the rate of movement of an object within a given context, often employed in computer vision applications. Using [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) you can now calculate the speed of object using [object tracking](../modes/track.md) alongside distance and time data, crucial for tasks like traffic and surveillance. The accuracy of speed estimation directly influences the efficiency and reliability of various applications, making it a key component in the advancement of intelligent systems and real-time decision-making processes. +[Speed estimation](https://www.ultralytics.com/blog/ultralytics-yolov8-for-speed-estimation-in-computer-vision-projects) is the process of calculating the rate of movement of an object within a given context, often employed in [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) applications. Using [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) you can now calculate the speed of object using [object tracking](../modes/track.md) alongside distance and time data, crucial for tasks like traffic and surveillance. The accuracy of speed estimation directly influences the efficiency and reliability of various applications, making it a key component in the advancement of intelligent systems and real-time decision-making processes.


@@ -104,7 +104,7 @@ keywords: Ultralytics YOLOv8, speed estimation, object tracking, computer vision ### How do I estimate object speed using Ultralytics YOLOv8? -Estimating object speed with Ultralytics YOLOv8 involves combining object detection and tracking techniques. First, you need to detect objects in each frame using the YOLOv8 model. Then, track these objects across frames to calculate their movement over time. Finally, use the distance traveled by the object between frames and the frame rate to estimate its speed. +Estimating object speed with Ultralytics YOLOv8 involves combining [object detection](https://www.ultralytics.com/glossary/object-detection) and tracking techniques. First, you need to detect objects in each frame using the YOLOv8 model. Then, track these objects across frames to calculate their movement over time. Finally, use the distance traveled by the object between frames and the frame rate to estimate its speed. **Example**: @@ -152,7 +152,7 @@ Using Ultralytics YOLOv8 for speed estimation offers significant advantages in t For more applications, see [advantages of speed estimation](#advantages-of-speed-estimation). -### Can YOLOv8 be integrated with other AI frameworks like TensorFlow or PyTorch? +### Can YOLOv8 be integrated with other AI frameworks like [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) or [PyTorch](https://www.ultralytics.com/glossary/pytorch)? Yes, YOLOv8 can be integrated with other AI frameworks like TensorFlow and PyTorch. Ultralytics provides support for exporting YOLOv8 models to various formats like ONNX, TensorRT, and CoreML, ensuring smooth interoperability with other ML frameworks. @@ -166,7 +166,7 @@ Learn more about exporting models in our [guide on export](../modes/export.md). ### How accurate is the speed estimation using Ultralytics YOLOv8? -The accuracy of speed estimation using Ultralytics YOLOv8 depends on several factors, including the quality of the object tracking, the resolution and frame rate of the video, and environmental variables. While the speed estimator provides reliable estimates, it may not be 100% accurate due to variances in frame processing speed and object occlusion. +The [accuracy](https://www.ultralytics.com/glossary/accuracy) of speed estimation using Ultralytics YOLOv8 depends on several factors, including the quality of the object tracking, the resolution and frame rate of the video, and environmental variables. While the speed estimator provides reliable estimates, it may not be 100% accurate due to variances in frame processing speed and object occlusion. **Note**: Always consider margin of error and validate the estimates with ground truth data when possible. diff --git a/docs/en/guides/steps-of-a-cv-project.md b/docs/en/guides/steps-of-a-cv-project.md index ec9b84ff2f..bbdbef5f35 100644 --- a/docs/en/guides/steps-of-a-cv-project.md +++ b/docs/en/guides/steps-of-a-cv-project.md @@ -8,7 +8,7 @@ keywords: Computer Vision, AI, Object Detection, Image Classification, Instance ## Introduction -Computer vision is a subfield of artificial intelligence (AI) that helps computers see and understand the world like humans do. It processes and analyzes images or videos to extract information, recognize patterns, and make decisions based on that data. +Computer vision is a subfield of [artificial intelligence](https://www.ultralytics.com/glossary/artificial-intelligence-ai) (AI) that helps computers see and understand the world like humans do. It processes and analyzes images or videos to extract information, recognize patterns, and make decisions based on that data.


@@ -18,7 +18,7 @@ Computer vision is a subfield of artificial intelligence (AI) that helps compute allowfullscreen>
- Watch: How to Do Computer Vision Projects | A Step-by-Step Guide + Watch: How to Do [Computer Vision](https://www.ultralytics.com/glossary/computer-vision-cv) Projects | A Step-by-Step Guide

Computer vision techniques like [object detection](../tasks/detect.md), [image classification](../tasks/classify.md), and [instance segmentation](../tasks/segment.md) can be applied across various industries, from [autonomous driving](https://www.ultralytics.com/solutions/ai-in-self-driving) to [medical imaging](https://www.ultralytics.com/solutions/ai-in-healthcare) to gain valuable insights. @@ -60,7 +60,7 @@ Here are some examples of project objectives and the computer vision tasks that - **Computer Vision Task:** Image segmentation is suitable for medical imaging because it provides accurate and detailed boundaries of tumors that are crucial for assessing size, shape, and treatment planning. - **Objective:** To create a digital system that categorizes various documents (e.g., invoices, receipts, legal paperwork) to improve organizational efficiency and document retrieval. - - **Computer Vision Task:** Image classification is ideal here as it handles one document at a time, without needing to consider the document's position in the image. This approach simplifies and accelerates the sorting process. + - **Computer Vision Task:** [Image classification](https://www.ultralytics.com/glossary/image-classification) is ideal here as it handles one document at a time, without needing to consider the document's position in the image. This approach simplifies and accelerates the sorting process. ### Step 1.5: Selecting the Right Model and Training Approach @@ -68,13 +68,13 @@ After understanding the project objective and suitable computer vision tasks, an Depending on the objective, you might choose to select the model first or after seeing what data you are able to collect in Step 2. For example, suppose your project is highly dependent on the availability of specific types of data. In that case, it may be more practical to gather and analyze the data first before selecting a model. On the other hand, if you have a clear understanding of the model requirements, you can choose the model first and then collect data that fits those specifications. -Choosing between training from scratch or using transfer learning affects how you prepare your data. Training from scratch requires a diverse dataset to build the model's understanding from the ground up. Transfer learning, on the other hand, allows you to use a pre-trained model and adapt it with a smaller, more specific dataset. Also, choosing a specific model to train will determine how you need to prepare your data, such as resizing images or adding annotations, according to the model's specific requirements. +Choosing between training from scratch or using [transfer learning](https://www.ultralytics.com/glossary/transfer-learning) affects how you prepare your data. Training from scratch requires a diverse dataset to build the model's understanding from the ground up. Transfer learning, on the other hand, allows you to use a pre-trained model and adapt it with a smaller, more specific dataset. Also, choosing a specific model to train will determine how you need to prepare your data, such as resizing images or adding annotations, according to the model's specific requirements.

Training From Scratch Vs. Using Transfer Learning

-Note: When choosing a model, consider its [deployment](./model-deployment-options.md) to ensure compatibility and performance. For example, lightweight models are ideal for edge computing due to their efficiency on resource-constrained devices. To learn more about the key points related to defining your project, read [our guide](./defining-project-goals.md) on defining your project's goals and selecting the right model. +Note: When choosing a model, consider its [deployment](./model-deployment-options.md) to ensure compatibility and performance. For example, lightweight models are ideal for [edge computing](https://www.ultralytics.com/glossary/edge-computing) due to their efficiency on resource-constrained devices. To learn more about the key points related to defining your project, read [our guide](./defining-project-goals.md) on defining your project's goals and selecting the right model. Before getting into the hands-on work of a computer vision project, it's important to have a clear understanding of these details. Double-check that you've considered the following before moving on to Step 2: @@ -93,8 +93,8 @@ Some libraries, like Ultralytics, provide [built-in support for various datasets However, if you choose to collect images or take your own pictures, you'll need to annotate your data. Data annotation is the process of labeling your data to impart knowledge to your model. The type of data annotation you'll work with depends on your specific computer vision technique. Here are some examples: - **Image Classification:** You'll label the entire image as a single class. -- **Object Detection:** You'll draw bounding boxes around each object in the image and label each box. -- **Image Segmentation:** You'll label each pixel in the image according to the object it belongs to, creating detailed object boundaries. +- **[Object Detection](https://www.ultralytics.com/glossary/object-detection):** You'll draw bounding boxes around each object in the image and label each box. +- **[Image Segmentation](https://www.ultralytics.com/glossary/image-segmentation):** You'll label each pixel in the image according to the object it belongs to, creating detailed object boundaries.

Different Types of Image Annotation @@ -102,14 +102,14 @@ However, if you choose to collect images or take your own pictures, you'll need [Data collection and annotation](./data-collection-and-annotation.md) can be a time-consuming manual effort. Annotation tools can help make this process easier. Here are some useful open annotation tools: [LabeI Studio](https://github.com/HumanSignal/label-studio), [CVAT](https://github.com/cvat-ai/cvat), and [Labelme](https://github.com/labelmeai/labelme). -## Step 3: Data Augmentation and Splitting Your Dataset +## Step 3: [Data Augmentation](https://www.ultralytics.com/glossary/data-augmentation) and Splitting Your Dataset After collecting and annotating your image data, it's important to first split your dataset into training, validation, and test sets before performing data augmentation. Splitting your dataset before augmentation is crucial to test and validate your model on original, unaltered data. It helps accurately assess how well the model generalizes to new, unseen data. Here's how to split your data: - **Training Set:** It is the largest portion of your data, typically 70-80% of the total, used to train your model. -- **Validation Set:** Usually around 10-15% of your data; this set is used to tune hyperparameters and validate the model during training, helping to prevent overfitting. +- **Validation Set:** Usually around 10-15% of your data; this set is used to tune hyperparameters and validate the model during training, helping to prevent [overfitting](https://www.ultralytics.com/glossary/overfitting). - **Test Set:** The remaining 10-15% of your data is set aside as the test set. It is used to evaluate the model's performance on unseen data after training is complete. After splitting your data, you can perform data augmentation by applying transformations like rotating, scaling, and flipping images to artificially increase the size of your dataset. Data augmentation makes your model more robust to variations and improves its performance on unseen images. @@ -118,7 +118,7 @@ After splitting your data, you can perform data augmentation by applying transfo Examples of Data Augmentations

-Libraries like OpenCV, Albumentations, and TensorFlow offer flexible augmentation functions that you can use. Additionally, some libraries, such as Ultralytics, have [built-in augmentation settings](../modes/train.md) directly within its model training function, simplifying the process. +Libraries like [OpenCV](https://www.ultralytics.com/glossary/opencv), Albumentations, and [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) offer flexible augmentation functions that you can use. Additionally, some libraries, such as Ultralytics, have [built-in augmentation settings](../modes/train.md) directly within its model training function, simplifying the process. To understand your data better, you can use tools like [Matplotlib](https://matplotlib.org/) or [Seaborn](https://seaborn.pydata.org/) to visualize the images and analyze their distribution and characteristics. Visualizing your data helps identify patterns, anomalies, and the effectiveness of your augmentation techniques. You can also use [Ultralytics Explorer](../datasets/explorer/index.md), a tool for exploring computer vision datasets with semantic search, SQL queries, and vector similarity search. @@ -134,23 +134,23 @@ Once your dataset is ready for training, you can focus on setting up the necessa First, you'll need to make sure your environment is configured correctly. Typically, this includes the following: -- Installing essential libraries and frameworks like TensorFlow, PyTorch, or [Ultralytics](../quickstart.md). +- Installing essential libraries and frameworks like TensorFlow, [PyTorch](https://www.ultralytics.com/glossary/pytorch), or [Ultralytics](../quickstart.md). - If you are using a GPU, installing libraries like CUDA and cuDNN will help enable GPU acceleration and speed up the training process. -Then, you can load your training and validation datasets into your environment. Normalize and preprocess the data through resizing, format conversion, or augmentation. With your model selected, configure the layers and specify hyperparameters. Compile the model by setting the loss function, optimizer, and performance metrics. +Then, you can load your training and validation datasets into your environment. Normalize and preprocess the data through resizing, format conversion, or augmentation. With your model selected, configure the layers and specify hyperparameters. Compile the model by setting the [loss function](https://www.ultralytics.com/glossary/loss-function), optimizer, and performance metrics. -Libraries like Ultralytics simplify the training process. You can [start training](../modes/train.md) by feeding data into the model with minimal code. These libraries handle weight adjustments, backpropagation, and validation automatically. They also offer tools to monitor progress and adjust hyperparameters easily. After training, save the model and its weights with a few commands. +Libraries like Ultralytics simplify the training process. You can [start training](../modes/train.md) by feeding data into the model with minimal code. These libraries handle weight adjustments, [backpropagation](https://www.ultralytics.com/glossary/backpropagation), and validation automatically. They also offer tools to monitor progress and adjust hyperparameters easily. After training, save the model and its weights with a few commands. It's important to keep in mind that proper dataset management is vital for efficient training. Use version control for datasets to track changes and ensure reproducibility. Tools like [DVC (Data Version Control)](../integrations/dvc.md) can help manage large datasets. -## Step 5: Model Evaluation and Model Finetuning +## Step 5: Model Evaluation and Model [Finetuning](https://www.ultralytics.com/glossary/fine-tuning) -It's important to assess your model's performance using various metrics and refine it to improve accuracy. [Evaluating](../modes/val.md) helps identify areas where the model excels and where it may need improvement. Fine-tuning ensures the model is optimized for the best possible performance. +It's important to assess your model's performance using various metrics and refine it to improve [accuracy](https://www.ultralytics.com/glossary/accuracy). [Evaluating](../modes/val.md) helps identify areas where the model excels and where it may need improvement. Fine-tuning ensures the model is optimized for the best possible performance. -- **[Performance Metrics](./yolo-performance-metrics.md):** Use metrics like accuracy, precision, recall, and F1-score to evaluate your model's performance. These metrics provide insights into how well your model is making predictions. +- **[Performance Metrics](./yolo-performance-metrics.md):** Use metrics like accuracy, [precision](https://www.ultralytics.com/glossary/precision), recall, and F1-score to evaluate your model's performance. These metrics provide insights into how well your model is making predictions. - **[Hyperparameter Tuning](./hyperparameter-tuning.md):** Adjust hyperparameters to optimize model performance. Techniques like grid search or random search can help find the best hyperparameter values. -- Fine-Tuning: Make small adjustments to the model architecture or training process to enhance performance. This might involve tweaking learning rates, batch sizes, or other model parameters. +- Fine-Tuning: Make small adjustments to the model architecture or training process to enhance performance. This might involve tweaking [learning rates](https://www.ultralytics.com/glossary/learning-rate), [batch sizes](https://www.ultralytics.com/glossary/batch-size), or other model parameters. ## Step 6: Model Testing @@ -158,9 +158,9 @@ In this step, you can make sure that your model performs well on completely unse It's important to thoroughly test and debug any common issues that may arise. Test your model on a separate test dataset that was not used during training or validation. This dataset should represent real-world scenarios to ensure the model's performance is consistent and reliable. -Also, address common problems such as overfitting, underfitting, and data leakage. Use techniques like cross-validation and anomaly detection to identify and fix these issues. +Also, address common problems such as overfitting, [underfitting](https://www.ultralytics.com/glossary/underfitting), and data leakage. Use techniques like cross-validation and [anomaly detection](https://www.ultralytics.com/glossary/anomaly-detection) to identify and fix these issues. -## Step 7: Model Deployment +## Step 7: [Model Deployment](https://www.ultralytics.com/glossary/model-deployment) Once your model has been thoroughly tested, it's time to deploy it. Deployment involves making your model available for use in a production environment. Here are the steps to deploy a computer vision model: @@ -222,7 +222,7 @@ Tools like [Label Studio](https://github.com/HumanSignal/label-studio), [CVAT](h Splitting your dataset before augmentation helps validate model performance on original, unaltered data. Follow these steps: - **Training Set**: 70-80% of your data. -- **Validation Set**: 10-15% for hyperparameter tuning. +- **Validation Set**: 10-15% for [hyperparameter tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning). - **Test Set**: Remaining 10-15% for final evaluation. After splitting, apply data augmentation techniques like rotation, scaling, and flipping to increase dataset diversity. Libraries such as Albumentations and OpenCV can help. Ultralytics also offers [built-in augmentation settings](../modes/train.md) for convenience. diff --git a/docs/en/guides/streamlit-live-inference.md b/docs/en/guides/streamlit-live-inference.md index 84e1bce8ee..e8fb5c9165 100644 --- a/docs/en/guides/streamlit-live-inference.md +++ b/docs/en/guides/streamlit-live-inference.md @@ -8,7 +8,7 @@ keywords: Streamlit, YOLOv8, Real-time Object Detection, Streamlit Application, ## Introduction -Streamlit makes it simple to build and deploy interactive web applications. Combining this with Ultralytics YOLOv8 allows for real-time object detection and analysis directly in your browser. YOLOv8 high accuracy and speed ensure seamless performance for live video streams, making it ideal for applications in security, retail, and beyond. +Streamlit makes it simple to build and deploy interactive web applications. Combining this with Ultralytics YOLOv8 allows for real-time [object detection](https://www.ultralytics.com/glossary/object-detection) and analysis directly in your browser. YOLOv8 high accuracy and speed ensure seamless performance for live video streams, making it ideal for applications in security, retail, and beyond.


@@ -18,7 +18,7 @@ Streamlit makes it simple to build and deploy interactive web applications. Comb allowfullscreen>
- Watch: How to Use Streamlit with Ultralytics for Real-Time Computer Vision in Your Browser + Watch: How to Use Streamlit with Ultralytics for Real-Time [Computer Vision](https://www.ultralytics.com/glossary/computer-vision-cv) in Your Browser

| Aquaculture | Animals husbandry | @@ -128,7 +128,7 @@ For more details on the practical setup, refer to the [Streamlit Application Cod Using Ultralytics YOLOv8 with Streamlit for real-time object detection offers several advantages: -- **Seamless Real-Time Detection**: Achieve high-accuracy, real-time object detection directly from webcam feeds. +- **Seamless Real-Time Detection**: Achieve high-[accuracy](https://www.ultralytics.com/glossary/accuracy), real-time object detection directly from webcam feeds. - **User-Friendly Interface**: Streamlit's intuitive interface allows easy use and deployment without extensive technical knowledge. - **Resource Efficiency**: YOLOv8's optimized algorithms ensure high-speed processing with minimal computational resources. diff --git a/docs/en/guides/triton-inference-server.md b/docs/en/guides/triton-inference-server.md index 05edf54f43..1233ba9ae1 100644 --- a/docs/en/guides/triton-inference-server.md +++ b/docs/en/guides/triton-inference-server.md @@ -6,7 +6,7 @@ keywords: Triton Inference Server, YOLOv8, Ultralytics, NVIDIA, deep learning, A # Triton Inference Server with Ultralytics YOLOv8 -The [Triton Inference Server](https://developer.nvidia.com/triton-inference-server) (formerly known as TensorRT Inference Server) is an open-source software solution developed by NVIDIA. It provides a cloud inference solution optimized for NVIDIA GPUs. Triton simplifies the deployment of AI models at scale in production. Integrating Ultralytics YOLOv8 with Triton Inference Server allows you to deploy scalable, high-performance deep learning inference workloads. This guide provides steps to set up and test the integration. +The [Triton Inference Server](https://developer.nvidia.com/triton-inference-server) (formerly known as TensorRT Inference Server) is an open-source software solution developed by NVIDIA. It provides a cloud inference solution optimized for NVIDIA GPUs. Triton simplifies the deployment of AI models at scale in production. Integrating Ultralytics YOLOv8 with Triton Inference Server allows you to deploy scalable, high-performance [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) inference workloads. This guide provides steps to set up and test the integration.


@@ -21,7 +21,7 @@ The [Triton Inference Server](https://developer.nvidia.com/triton-inference-serv ## What is Triton Inference Server? -Triton Inference Server is designed to deploy a variety of AI models in production. It supports a wide range of deep learning and machine learning frameworks, including TensorFlow, PyTorch, ONNX Runtime, and many others. Its primary use cases are: +Triton Inference Server is designed to deploy a variety of AI models in production. It supports a wide range of deep learning and [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) frameworks, including TensorFlow, [PyTorch](https://www.ultralytics.com/glossary/pytorch), ONNX Runtime, and many others. Its primary use cases are: - Serving multiple models from a single server instance. - Dynamic model loading and unloading without server restart. @@ -216,7 +216,7 @@ This setup can help you efficiently deploy YOLOv8 models at scale on Triton Infe Integrating [Ultralytics YOLOv8](../models/yolov8.md) with [NVIDIA Triton Inference Server](https://developer.nvidia.com/triton-inference-server) provides several advantages: - **Scalable AI Inference**: Triton allows serving multiple models from a single server instance, supporting dynamic model loading and unloading, making it highly scalable for diverse AI workloads. -- **High Performance**: Optimized for NVIDIA GPUs, Triton Inference Server ensures high-speed inference operations, perfect for real-time applications such as object detection. +- **High Performance**: Optimized for NVIDIA GPUs, Triton Inference Server ensures high-speed inference operations, perfect for real-time applications such as [object detection](https://www.ultralytics.com/glossary/object-detection). - **Ensemble and Model Versioning**: Triton's ensemble mode enables combining multiple models to improve results, and its model versioning supports A/B testing and rolling updates. For detailed instructions on setting up and running YOLOv8 with Triton, you can refer to the [setup guide](#setting-up-triton-model-repository). @@ -256,11 +256,11 @@ results = model("path/to/image.jpg") For an in-depth guide on setting up and running Triton Server with YOLOv8, refer to the [running triton inference server](#running-triton-inference-server) section. -### How does Ultralytics YOLOv8 compare to TensorFlow and PyTorch models for deployment? +### How does Ultralytics YOLOv8 compare to [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) and PyTorch models for deployment? [Ultralytics YOLOv8](https://docs.ultralytics.com/models/yolov8/) offers several unique advantages compared to TensorFlow and PyTorch models for deployment: -- **Real-time Performance**: Optimized for real-time object detection tasks, YOLOv8 provides state-of-the-art accuracy and speed, making it ideal for applications requiring live video analytics. +- **Real-time Performance**: Optimized for real-time object detection tasks, YOLOv8 provides state-of-the-art [accuracy](https://www.ultralytics.com/glossary/accuracy) and speed, making it ideal for applications requiring live video analytics. - **Ease of Use**: YOLOv8 integrates seamlessly with Triton Inference Server and supports diverse export formats (ONNX, TensorRT, CoreML), making it flexible for various deployment scenarios. - **Advanced Features**: YOLOv8 includes features like dynamic model loading, model versioning, and ensemble inference, which are crucial for scalable and reliable AI deployments. diff --git a/docs/en/guides/view-results-in-terminal.md b/docs/en/guides/view-results-in-terminal.md index c599f6643a..cb6ce1c087 100644 --- a/docs/en/guides/view-results-in-terminal.md +++ b/docs/en/guides/view-results-in-terminal.md @@ -58,7 +58,7 @@ The VSCode compatible protocols for viewing images using the integrated terminal 1. See [plot method parameters](../modes/predict.md#plot-method-parameters) to see possible arguments to use. -4. Now, use OpenCV to convert the `numpy.ndarray` to `bytes` data. Then use `io.BytesIO` to make a "file-like" object. +4. Now, use [OpenCV](https://www.ultralytics.com/glossary/opencv) to convert the `numpy.ndarray` to `bytes` data. Then use `io.BytesIO` to make a "file-like" object. ```{ .py .annotate } import io diff --git a/docs/en/guides/vision-eye.md b/docs/en/guides/vision-eye.md index 891a589b24..48cff2746d 100644 --- a/docs/en/guides/vision-eye.md +++ b/docs/en/guides/vision-eye.md @@ -8,7 +8,7 @@ keywords: VisionEye, YOLOv8, Ultralytics, object mapping, object tracking, dista ## What is VisionEye Object Mapping? -[Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) VisionEye offers the capability for computers to identify and pinpoint objects, simulating the observational precision of the human eye. This functionality enables computers to discern and focus on specific objects, much like the way the human eye observes details from a particular viewpoint. +[Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) VisionEye offers the capability for computers to identify and pinpoint objects, simulating the observational [precision](https://www.ultralytics.com/glossary/precision) of the human eye. This functionality enables computers to discern and focus on specific objects, much like the way the human eye observes details from a particular viewpoint. ## Samples @@ -182,7 +182,7 @@ For any inquiries, feel free to post your questions in the [Ultralytics Issue Se ### How do I start using VisionEye Object Mapping with Ultralytics YOLOv8? -To start using VisionEye Object Mapping with Ultralytics YOLOv8, first, you'll need to install the Ultralytics YOLO package via pip. Then, you can use the sample code provided in the documentation to set up object detection with VisionEye. Here's a simple example to get you started: +To start using VisionEye Object Mapping with Ultralytics YOLOv8, first, you'll need to install the Ultralytics YOLO package via pip. Then, you can use the sample code provided in the documentation to set up [object detection](https://www.ultralytics.com/glossary/object-detection) with VisionEye. Here's a simple example to get you started: ```python import cv2 @@ -292,7 +292,7 @@ For detailed instructions, refer to the [VisionEye with Distance Calculation](#s ### Why should I use Ultralytics YOLOv8 for object mapping and tracking? -Ultralytics YOLOv8 is renowned for its speed, accuracy, and ease of integration, making it a top choice for object mapping and tracking. Key advantages include: +Ultralytics YOLOv8 is renowned for its speed, [accuracy](https://www.ultralytics.com/glossary/accuracy), and ease of integration, making it a top choice for object mapping and tracking. Key advantages include: 1. **State-of-the-art Performance**: Delivers high accuracy in real-time object detection. 2. **Flexibility**: Supports various tasks such as detection, tracking, and distance calculation. @@ -301,7 +301,7 @@ Ultralytics YOLOv8 is renowned for its speed, accuracy, and ease of integration, For more information on applications and benefits, check out the [Ultralytics YOLOv8 documentation](https://docs.ultralytics.com/models/yolov8/). -### How can I integrate VisionEye with other machine learning tools like Comet or ClearML? +### How can I integrate VisionEye with other [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) tools like Comet or ClearML? Ultralytics YOLOv8 can integrate seamlessly with various machine learning tools like Comet and ClearML, enhancing experiment tracking, collaboration, and reproducibility. Follow the detailed guides on [how to use YOLOv5 with Comet](https://www.ultralytics.com/blog/how-to-use-yolov5-with-comet) and [integrate YOLOv8 with ClearML](https://docs.ultralytics.com/integrations/clearml/) to get started. diff --git a/docs/en/guides/workouts-monitoring.md b/docs/en/guides/workouts-monitoring.md index e042acfa75..4585631683 100644 --- a/docs/en/guides/workouts-monitoring.md +++ b/docs/en/guides/workouts-monitoring.md @@ -179,7 +179,7 @@ You can watch a [YouTube video demonstration](https://www.youtube.com/watch?v=LG ### How accurate is Ultralytics YOLOv8 in detecting and tracking exercises? -Ultralytics YOLOv8 is highly accurate in detecting and tracking exercises due to its state-of-the-art pose estimation capabilities. It can accurately track key body landmarks and joints, providing real-time feedback on exercise form and performance metrics. The model's pretrained weights and robust architecture ensure high precision and reliability. For real-world examples, check out the [real-world applications](#real-world-applications) section in the documentation, which showcases pushups and pullups counting. +Ultralytics YOLOv8 is highly accurate in detecting and tracking exercises due to its state-of-the-art pose estimation capabilities. It can accurately track key body landmarks and joints, providing real-time feedback on exercise form and performance metrics. The model's pretrained weights and robust architecture ensure high [precision](https://www.ultralytics.com/glossary/precision) and reliability. For real-world examples, check out the [real-world applications](#real-world-applications) section in the documentation, which showcases pushups and pullups counting. ### Can I use Ultralytics YOLOv8 for custom workout routines? diff --git a/docs/en/guides/yolo-common-issues.md b/docs/en/guides/yolo-common-issues.md index 77351eaa06..6da5d164e9 100644 --- a/docs/en/guides/yolo-common-issues.md +++ b/docs/en/guides/yolo-common-issues.md @@ -33,7 +33,7 @@ Installation errors can arise due to various reasons, such as incompatible versi - You're using Python 3.8 or later as recommended. -- Ensure that you have the correct version of PyTorch (1.8 or later) installed. +- Ensure that you have the correct version of [PyTorch](https://www.ultralytics.com/glossary/pytorch) (1.8 or later) installed. - Consider using virtual environments to avoid conflicts. @@ -86,7 +86,7 @@ model.train(data="/path/to/your/data.yaml", batch=4) **Issue**: Training is slow on a single GPU, and you want to speed up the process using multiple GPUs. -**Solution**: Increasing the batch size can accelerate training, but it's essential to consider GPU memory capacity. To speed up training with multiple GPUs, follow these steps: +**Solution**: Increasing the [batch size](https://www.ultralytics.com/glossary/batch-size) can accelerate training, but it's essential to consider GPU memory capacity. To speed up training with multiple GPUs, follow these steps: - Ensure that you have multiple GPUs available. @@ -109,7 +109,7 @@ model.train(data="/path/to/your/data.yaml", batch=32, multi_scale=True) - Precision - Recall -- Mean Average Precision (mAP) +- [Mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP) You can access these metrics from the training logs or by using tools like TensorBoard or wandb for visualization. Implementing early stopping based on these metrics can help you achieve better results. @@ -119,7 +119,7 @@ You can access these metrics from the training logs or by using tools like Tenso **Solution**: To track and visualize training progress, you can consider using the following tools: -- [TensorBoard](https://www.tensorflow.org/tensorboard): TensorBoard is a popular choice for visualizing training metrics, including loss, accuracy, and more. You can integrate it with your YOLOv8 training process. +- [TensorBoard](https://www.tensorflow.org/tensorboard): TensorBoard is a popular choice for visualizing training metrics, including loss, [accuracy](https://www.ultralytics.com/glossary/accuracy), and more. You can integrate it with your YOLOv8 training process. - [Comet](https://bit.ly/yolov8-readme-comet): Comet provides an extensive toolkit for experiment tracking and comparison. It allows you to track metrics, hyperparameters, and even model weights. Integration with YOLO models is also straightforward, providing you with a complete overview of your experiment cycle. - [Ultralytics HUB](https://hub.ultralytics.com/): Ultralytics HUB offers a specialized environment for tracking YOLO models, giving you a one-stop platform to manage metrics, datasets, and even collaborate with your team. Given its tailored focus on YOLO, it offers more customized tracking options. @@ -145,17 +145,17 @@ Here are some things to keep in mind, if you are facing issues related to model **Dataset Format and Labels** -- Importance: The foundation of any machine learning model lies in the quality and format of the data it is trained on. +- Importance: The foundation of any [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) model lies in the quality and format of the data it is trained on. - Recommendation: Ensure that your custom dataset and its associated labels adhere to the expected format. It's crucial to verify that annotations are accurate and of high quality. Incorrect or subpar annotations can derail the model's learning process, leading to unpredictable outcomes. **Model Convergence** -- Importance: Achieving model convergence ensures that the model has sufficiently learned from the training data. +- Importance: Achieving model convergence ensures that the model has sufficiently learned from the [training data](https://www.ultralytics.com/glossary/training-data). -- Recommendation: When training a model 'from scratch', it's vital to ensure that the model reaches a satisfactory level of convergence. This might necessitate a longer training duration, with more epochs, compared to when you're fine-tuning an existing model. +- Recommendation: When training a model 'from scratch', it's vital to ensure that the model reaches a satisfactory level of convergence. This might necessitate a longer training duration, with more [epochs](https://www.ultralytics.com/glossary/epoch), compared to when you're fine-tuning an existing model. -**Learning Rate and Batch Size** +**[Learning Rate](https://www.ultralytics.com/glossary/learning-rate) and Batch Size** - Importance: These hyperparameters play a pivotal role in determining how the model updates its weights during training. @@ -207,9 +207,9 @@ yolo task=detect mode=segment model=yolov8n-seg.pt source='path/to/car.mp4' show #### Understanding Precision Metrics in YOLOv8 -**Issue**: Confusion regarding the difference between box precision, mask precision, and confusion matrix precision in YOLOv8. +**Issue**: Confusion regarding the difference between box precision, mask precision, and [confusion matrix](https://www.ultralytics.com/glossary/confusion-matrix) precision in YOLOv8. -**Solution**: Box precision measures the accuracy of predicted bounding boxes compared to the actual ground truth boxes using IoU (Intersection over Union) as the metric. Mask precision assesses the agreement between predicted segmentation masks and ground truth masks in pixel-wise object classification. Confusion matrix precision, on the other hand, focuses on overall classification accuracy across all classes and does not consider the geometric accuracy of predictions. It's important to note that a bounding box can be geometrically accurate (true positive) even if the class prediction is wrong, leading to differences between box precision and confusion matrix precision. These metrics evaluate distinct aspects of a model's performance, reflecting the need for different evaluation metrics in various tasks. +**Solution**: Box precision measures the accuracy of predicted bounding boxes compared to the actual ground truth boxes using IoU (Intersection over Union) as the metric. Mask precision assesses the agreement between predicted segmentation masks and ground truth masks in pixel-wise object classification. Confusion matrix precision, on the other hand, focuses on overall classification accuracy across all classes and does not consider the geometric accuracy of predictions. It's important to note that a [bounding box](https://www.ultralytics.com/glossary/bounding-box) can be geometrically accurate (true positive) even if the class prediction is wrong, leading to differences between box precision and confusion matrix precision. These metrics evaluate distinct aspects of a model's performance, reflecting the need for different evaluation metrics in various tasks. #### Extracting Object Dimensions in YOLOv8 @@ -280,7 +280,7 @@ These resources should provide a solid foundation for troubleshooting and improv ## Conclusion -Troubleshooting is an integral part of any development process, and being equipped with the right knowledge can significantly reduce the time and effort spent in resolving issues. This guide aimed to address the most common challenges faced by users of the YOLOv8 model within the Ultralytics ecosystem. By understanding and addressing these common issues, you can ensure smoother project progress and achieve better results with your computer vision tasks. +Troubleshooting is an integral part of any development process, and being equipped with the right knowledge can significantly reduce the time and effort spent in resolving issues. This guide aimed to address the most common challenges faced by users of the YOLOv8 model within the Ultralytics ecosystem. By understanding and addressing these common issues, you can ensure smoother project progress and achieve better results with your [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks. Remember, the Ultralytics community is a valuable resource. Engaging with fellow developers and experts can provide additional insights and solutions that might not be covered in standard documentation. Always keep learning, experimenting, and sharing your experiences to contribute to the collective knowledge of the community. @@ -312,7 +312,7 @@ This sets the training process to the first GPU. Consult the `nvidia-smi` comman ### How can I monitor and track my YOLOv8 model training progress? -Tracking and visualizing training progress can be efficiently managed through tools like [TensorBoard](https://www.tensorflow.org/tensorboard), [Comet](https://bit.ly/yolov8-readme-comet), and [Ultralytics HUB](https://hub.ultralytics.com/). These tools allow you to log and visualize metrics such as loss, precision, recall, and mAP. Implementing [early stopping](#continuous-monitoring-parameters) based on these metrics can also help achieve better training outcomes. +Tracking and visualizing training progress can be efficiently managed through tools like [TensorBoard](https://www.tensorflow.org/tensorboard), [Comet](https://bit.ly/yolov8-readme-comet), and [Ultralytics HUB](https://hub.ultralytics.com/). These tools allow you to log and visualize metrics such as loss, [precision](https://www.ultralytics.com/glossary/precision), [recall](https://www.ultralytics.com/glossary/recall), and mAP. Implementing [early stopping](#continuous-monitoring-parameters) based on these metrics can also help achieve better training outcomes. ### What should I do if YOLOv8 is not recognizing my dataset format? diff --git a/docs/en/guides/yolo-performance-metrics.md b/docs/en/guides/yolo-performance-metrics.md index d885b9eab3..aeed82355d 100644 --- a/docs/en/guides/yolo-performance-metrics.md +++ b/docs/en/guides/yolo-performance-metrics.md @@ -8,7 +8,7 @@ keywords: YOLOv8 performance metrics, mAP, IoU, F1 Score, Precision, Recall, obj ## Introduction -Performance metrics are key tools to evaluate the accuracy and efficiency of object detection models. They shed light on how effectively a model can identify and localize objects within images. Additionally, they help in understanding the model's handling of false positives and false negatives. These insights are crucial for evaluating and enhancing the model's performance. In this guide, we will explore various performance metrics associated with YOLOv8, their significance, and how to interpret them. +Performance metrics are key tools to evaluate the [accuracy](https://www.ultralytics.com/glossary/accuracy) and efficiency of [object detection](https://www.ultralytics.com/glossary/object-detection) models. They shed light on how effectively a model can identify and localize objects within images. Additionally, they help in understanding the model's handling of false positives and false negatives. These insights are crucial for evaluating and enhancing the model's performance. In this guide, we will explore various performance metrics associated with YOLOv8, their significance, and how to interpret them.


@@ -18,14 +18,14 @@ Performance metrics are key tools to evaluate the accuracy and efficiency of obj allowfullscreen>
- Watch: Ultralytics YOLOv8 Performance Metrics | MAP, F1 Score, Precision, IoU & Accuracy + Watch: Ultralytics YOLOv8 Performance Metrics | MAP, F1 Score, [Precision](https://www.ultralytics.com/glossary/precision), IoU & Accuracy

## Object Detection Metrics Let's start by discussing some metrics that are not only important to YOLOv8 but are broadly applicable across different object detection models. -- **Intersection over Union (IoU):** IoU is a measure that quantifies the overlap between a predicted bounding box and a ground truth bounding box. It plays a fundamental role in evaluating the accuracy of object localization. +- **[Intersection over Union](https://www.ultralytics.com/glossary/intersection-over-union-iou) (IoU):** IoU is a measure that quantifies the overlap between a predicted [bounding box](https://www.ultralytics.com/glossary/bounding-box) and a ground truth bounding box. It plays a fundamental role in evaluating the accuracy of object localization. - **Average Precision (AP):** AP computes the area under the precision-recall curve, providing a single value that encapsulates the model's precision and recall performance. @@ -77,15 +77,15 @@ For users validating on the COCO dataset, additional metrics are calculated usin The model.val() function, apart from producing numeric metrics, also yields visual outputs that can provide a more intuitive understanding of the model's performance. Here's a breakdown of the visual outputs you can expect: -- **F1 Score Curve (`F1_curve.png`)**: This curve represents the F1 score across various thresholds. Interpreting this curve can offer insights into the model's balance between false positives and false negatives over different thresholds. +- **F1 Score Curve (`F1_curve.png`)**: This curve represents the [F1 score](https://www.ultralytics.com/glossary/f1-score) across various thresholds. Interpreting this curve can offer insights into the model's balance between false positives and false negatives over different thresholds. -- **Precision-Recall Curve (`PR_curve.png`)**: An integral visualization for any classification problem, this curve showcases the trade-offs between precision and recall at varied thresholds. It becomes especially significant when dealing with imbalanced classes. +- **Precision-Recall Curve (`PR_curve.png`)**: An integral visualization for any classification problem, this curve showcases the trade-offs between precision and [recall](https://www.ultralytics.com/glossary/recall) at varied thresholds. It becomes especially significant when dealing with imbalanced classes. - **Precision Curve (`P_curve.png`)**: A graphical representation of precision values at different thresholds. This curve helps in understanding how precision varies as the threshold changes. - **Recall Curve (`R_curve.png`)**: Correspondingly, this graph illustrates how the recall values change across different thresholds. -- **Confusion Matrix (`confusion_matrix.png`)**: The confusion matrix provides a detailed view of the outcomes, showcasing the counts of true positives, true negatives, false positives, and false negatives for each class. +- **[Confusion Matrix](https://www.ultralytics.com/glossary/confusion-matrix) (`confusion_matrix.png`)**: The confusion matrix provides a detailed view of the outcomes, showcasing the counts of true positives, true negatives, false positives, and false negatives for each class. - **Normalized Confusion Matrix (`confusion_matrix_normalized.png`)**: This visualization is a normalized version of the confusion matrix. It represents the data in proportions rather than raw counts. This format makes it simpler to compare the performance across classes. @@ -123,7 +123,7 @@ It's important to understand the metrics. Here's what some of the commonly obser - **Low Precision:** The model may be detecting too many non-existent objects. Adjusting confidence thresholds might reduce this. -- **Low Recall:** The model could be missing real objects. Improving feature extraction or using more data might help. +- **Low Recall:** The model could be missing real objects. Improving [feature extraction](https://www.ultralytics.com/glossary/feature-extraction) or using more data might help. - **Imbalanced F1 Score:** There's a disparity between precision and recall. @@ -177,7 +177,7 @@ Happy object detecting! ## FAQ -### What is the significance of Mean Average Precision (mAP) in evaluating YOLOv8 model performance? +### What is the significance of [Mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP) in evaluating YOLOv8 model performance? Mean Average Precision (mAP) is crucial for evaluating YOLOv8 models as it provides a single metric encapsulating precision and recall across multiple classes. mAP@0.50 measures precision at an IoU threshold of 0.50, focusing on the model's ability to detect objects correctly. mAP@0.50:0.95 averages precision across a range of IoU thresholds, offering a comprehensive assessment of detection performance. High mAP scores indicate that the model effectively balances precision and recall, essential for applications like autonomous driving and surveillance. diff --git a/docs/en/help/FAQ.md b/docs/en/help/FAQ.md index 24472e77f4..234fb9e82f 100644 --- a/docs/en/help/FAQ.md +++ b/docs/en/help/FAQ.md @@ -12,7 +12,7 @@ This FAQ section addresses common questions and issues users might encounter whi ### What is Ultralytics and what does it offer? -Ultralytics is a computer vision AI company specializing in state-of-the-art object detection and image segmentation models, with a focus on the YOLO (You Only Look Once) family. Their offerings include: +Ultralytics is a [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) AI company specializing in state-of-the-art object detection and [image segmentation](https://www.ultralytics.com/glossary/image-segmentation) models, with a focus on the YOLO (You Only Look Once) family. Their offerings include: - Open-source implementations of [YOLOv5](https://docs.ultralytics.com/models/yolov5/) and [YOLOv8](https://docs.ultralytics.com/models/yolov8/) - A wide range of [pre-trained models](https://docs.ultralytics.com/models/) for various computer vision tasks @@ -41,7 +41,7 @@ Detailed installation instructions can be found in the [quickstart guide](https: Minimum requirements: - Python 3.7+ -- PyTorch 1.7+ +- [PyTorch](https://www.ultralytics.com/glossary/pytorch) 1.7+ - CUDA-compatible GPU (for GPU acceleration) Recommended setup: @@ -80,10 +80,10 @@ For a more in-depth guide, including data preparation and advanced training opti Ultralytics offers a diverse range of pretrained YOLOv8 models for various tasks: - Object Detection: YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, YOLOv8x -- Instance Segmentation: YOLOv8n-seg, YOLOv8s-seg, YOLOv8m-seg, YOLOv8l-seg, YOLOv8x-seg +- [Instance Segmentation](https://www.ultralytics.com/glossary/instance-segmentation): YOLOv8n-seg, YOLOv8s-seg, YOLOv8m-seg, YOLOv8l-seg, YOLOv8x-seg - Classification: YOLOv8n-cls, YOLOv8s-cls, YOLOv8m-cls, YOLOv8l-cls, YOLOv8x-cls -These models vary in size and complexity, offering different trade-offs between speed and accuracy. Explore the full range of [pretrained models](https://docs.ultralytics.com/models/yolov8/) to find the best fit for your project. +These models vary in size and complexity, offering different trade-offs between speed and [accuracy](https://www.ultralytics.com/glossary/accuracy). Explore the full range of [pretrained models](https://docs.ultralytics.com/models/yolov8/) to find the best fit for your project. ### How do I perform inference using a trained Ultralytics model? @@ -113,7 +113,7 @@ Absolutely! Ultralytics models are designed for versatile deployment across vari - Edge devices: Optimize inference on devices like NVIDIA Jetson or Intel Neural Compute Stick using TensorRT, ONNX, or OpenVINO. - Mobile: Deploy on Android or iOS devices by converting models to TFLite or Core ML. -- Cloud: Leverage frameworks like TensorFlow Serving or PyTorch Serve for scalable cloud deployments. +- Cloud: Leverage frameworks like [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) Serving or PyTorch Serve for scalable cloud deployments. - Web: Implement in-browser inference using ONNX.js or TensorFlow.js. Ultralytics provides export functions to convert models to various formats for deployment. Explore the wide range of [deployment options](https://docs.ultralytics.com/guides/model-deployment-options/) to find the best solution for your use case. @@ -124,7 +124,7 @@ Key distinctions include: - Architecture: YOLOv8 features an improved backbone and head design for enhanced performance. - Performance: YOLOv8 generally offers superior accuracy and speed compared to YOLOv5. -- Tasks: YOLOv8 natively supports object detection, instance segmentation, and classification in a unified framework. +- Tasks: YOLOv8 natively supports [object detection](https://www.ultralytics.com/glossary/object-detection), instance segmentation, and classification in a unified framework. - Codebase: YOLOv8 is implemented with a more modular and extensible architecture, facilitating easier customization and extension. - Training: YOLOv8 incorporates advanced training techniques like multi-dataset training and hyperparameter evolution for improved results. @@ -174,9 +174,9 @@ Explore the [YOLO models page](https://docs.ultralytics.com/models/yolov8/) for Enhancing your YOLO model's performance can be achieved through several techniques: -1. Hyperparameter Tuning: Experiment with different hyperparameters using the [Hyperparameter Tuning Guide](https://docs.ultralytics.com/guides/hyperparameter-tuning/) to optimize model performance. -2. Data Augmentation: Implement techniques like flip, scale, rotate, and color adjustments to enhance your training dataset and improve model generalization. -3. Transfer Learning: Leverage pre-trained models and fine-tune them on your specific dataset using the [Train YOLOv8](https://docs.ultralytics.com/modes/train/) guide. +1. [Hyperparameter Tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning): Experiment with different hyperparameters using the [Hyperparameter Tuning Guide](https://docs.ultralytics.com/guides/hyperparameter-tuning/) to optimize model performance. +2. [Data Augmentation](https://www.ultralytics.com/glossary/data-augmentation): Implement techniques like flip, scale, rotate, and color adjustments to enhance your training dataset and improve model generalization. +3. [Transfer Learning](https://www.ultralytics.com/glossary/transfer-learning): Leverage pre-trained models and fine-tune them on your specific dataset using the [Train YOLOv8](https://docs.ultralytics.com/modes/train/) guide. 4. Export to Efficient Formats: Convert your model to optimized formats like TensorRT or ONNX for faster inference using the [Export guide](../modes/export.md). 5. Benchmarking: Utilize the [Benchmark Mode](https://docs.ultralytics.com/modes/benchmark/) to measure and improve inference speed and accuracy systematically. diff --git a/docs/en/help/contributing.md b/docs/en/help/contributing.md index 4078a6ce30..1dad4f5314 100644 --- a/docs/en/help/contributing.md +++ b/docs/en/help/contributing.md @@ -135,7 +135,7 @@ We encourage all contributors to familiarize themselves with the terms of the AG Thank you for your interest in contributing to [Ultralytics](https://www.ultralytics.com/) [open-source](https://github.com/ultralytics) YOLO projects. Your participation is essential in shaping the future of our software and building a vibrant community of innovation and collaboration. Whether you're enhancing code, reporting bugs, or suggesting new features, your contributions are invaluable. -We're excited to see your ideas come to life and appreciate your commitment to advancing object detection technology. Together, let's continue to grow and innovate in this exciting open-source journey. Happy coding! 🚀🌟 +We're excited to see your ideas come to life and appreciate your commitment to advancing [object detection](https://www.ultralytics.com/glossary/object-detection) technology. Together, let's continue to grow and innovate in this exciting open-source journey. Happy coding! 🚀🌟 ## FAQ diff --git a/docs/en/help/index.md b/docs/en/help/index.md index 9d9aa851b9..e8f2eecd7a 100644 --- a/docs/en/help/index.md +++ b/docs/en/help/index.md @@ -20,9 +20,9 @@ We encourage you to review these resources for a seamless and productive experie ## FAQ -### What is Ultralytics YOLO and how does it benefit my machine learning projects? +### What is Ultralytics YOLO and how does it benefit my [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) projects? -Ultralytics YOLO (You Only Look Once) is a state-of-the-art, real-time object detection model. Its latest version, YOLOv8, enhances speed, accuracy, and versatility, making it ideal for a wide range of applications, from real-time video analytics to advanced machine learning research. YOLO's efficiency in detecting objects in images and videos has made it the go-to solution for businesses and researchers looking to integrate robust computer vision capabilities into their projects. +Ultralytics YOLO (You Only Look Once) is a state-of-the-art, real-time [object detection](https://www.ultralytics.com/glossary/object-detection) model. Its latest version, YOLOv8, enhances speed, [accuracy](https://www.ultralytics.com/glossary/accuracy), and versatility, making it ideal for a wide range of applications, from real-time video analytics to advanced machine learning research. YOLO's efficiency in detecting objects in images and videos has made it the go-to solution for businesses and researchers looking to integrate robust [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) capabilities into their projects. For more details on YOLOv8, visit the [YOLOv8 documentation](../tasks/detect.md). @@ -32,7 +32,7 @@ Contributing to Ultralytics YOLO repositories is straightforward. Start by revie ### Why should I use Ultralytics HUB for my machine learning projects? -Ultralytics HUB offers a seamless, no-code solution for managing your machine learning projects. It enables you to generate, train, and deploy AI models like YOLOv8 effortlessly. Unique features include cloud training, real-time tracking, and intuitive dataset management. Ultralytics HUB simplifies the entire workflow, from data processing to model deployment, making it an indispensable tool for both beginners and advanced users. +Ultralytics HUB offers a seamless, no-code solution for managing your machine learning projects. It enables you to generate, train, and deploy AI models like YOLOv8 effortlessly. Unique features include cloud training, real-time tracking, and intuitive dataset management. Ultralytics HUB simplifies the entire workflow, from data processing to [model deployment](https://www.ultralytics.com/glossary/model-deployment), making it an indispensable tool for both beginners and advanced users. To get started, visit [Ultralytics HUB Quickstart](../hub/quickstart.md). @@ -42,7 +42,7 @@ Continuous Integration (CI) in Ultralytics involves automated processes that ens Learn more in the [Continuous Integration (CI) Guide](../help/CI.md). -### How is data privacy handled by Ultralytics? +### How is [data privacy](https://www.ultralytics.com/glossary/data-privacy) handled by Ultralytics? Ultralytics takes data privacy seriously. Our [Privacy Policy](../help/privacy.md) outlines how we collect and use anonymized data to improve the YOLO package while prioritizing user privacy and control. We adhere to strict data protection regulations to ensure your information is secure at all times. diff --git a/docs/en/help/privacy.md b/docs/en/help/privacy.md index 3683b1aea5..567a72aea5 100644 --- a/docs/en/help/privacy.md +++ b/docs/en/help/privacy.md @@ -19,7 +19,7 @@ keywords: Ultralytics, data collection, YOLO, Python package, Google Analytics, - **System Information**: We collect general non-identifiable information about your computing environment to ensure our package performs well across various systems. - **Performance Data**: Understanding the performance of our models during training, validation, and inference helps us in identifying optimization opportunities. -For more information about Google Analytics and data privacy, visit [Google Analytics Privacy](https://support.google.com/analytics/answer/6004245). +For more information about Google Analytics and [data privacy](https://www.ultralytics.com/glossary/data-privacy), visit [Google Analytics Privacy](https://support.google.com/analytics/answer/6004245). ### How We Use This Data diff --git a/docs/en/hub/app/android.md b/docs/en/hub/app/android.md index 0f3f0b820f..bca298fa9d 100644 --- a/docs/en/hub/app/android.md +++ b/docs/en/hub/app/android.md @@ -4,7 +4,7 @@ description: Experience real-time object detection on Android with Ultralytics. keywords: Ultralytics, Android app, real-time object detection, YOLO models, TensorFlow Lite, FP16 quantization, INT8 quantization, hardware delegates, mobile AI, download app --- -# Ultralytics Android App: Real-time Object Detection with YOLO Models +# Ultralytics Android App: Real-time [Object Detection](https://www.ultralytics.com/glossary/object-detection) with YOLO Models Ultralytics HUB preview image @@ -29,7 +29,7 @@ keywords: Ultralytics, Android app, real-time object detection, YOLO models, Ten Google Play store  -The Ultralytics Android App is a powerful tool that allows you to run YOLO models directly on your Android device for real-time object detection. This app utilizes TensorFlow Lite for model optimization and various hardware delegates for acceleration, enabling fast and efficient object detection. +The Ultralytics Android App is a powerful tool that allows you to run YOLO models directly on your Android device for real-time object detection. This app utilizes [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) Lite for model optimization and various hardware delegates for acceleration, enabling fast and efficient object detection.


@@ -44,7 +44,7 @@ The Ultralytics Android App is a powerful tool that allows you to run YOLO model ## Quantization and Acceleration -To achieve real-time performance on your Android device, YOLO models are quantized to either FP16 or INT8 precision. Quantization is a process that reduces the numerical precision of the model's weights and biases, thus reducing the model's size and the amount of computation required. This results in faster inference times without significantly affecting the model's accuracy. +To achieve real-time performance on your Android device, YOLO models are quantized to either FP16 or INT8 [precision](https://www.ultralytics.com/glossary/precision). Quantization is a process that reduces the numerical precision of the model's weights and biases, thus reducing the model's size and the amount of computation required. This results in faster inference times without significantly affecting the model's [accuracy](https://www.ultralytics.com/glossary/accuracy). ### FP16 Quantization @@ -52,7 +52,7 @@ FP16 (or half-precision) quantization converts the model's 32-bit floating-point ### INT8 Quantization -INT8 (or 8-bit integer) quantization further reduces the model's size and computation requirements by converting its 32-bit floating-point numbers to 8-bit integers. This quantization method can result in a significant speedup, but it may lead to a slight reduction in mean average precision (mAP) due to the lower numerical precision. +INT8 (or 8-bit integer) quantization further reduces the model's size and computation requirements by converting its 32-bit floating-point numbers to 8-bit integers. This quantization method can result in a significant speedup, but it may lead to a slight reduction in [mean average precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP) due to the lower numerical precision. !!! tip "mAP Reduction in INT8 Models" @@ -65,7 +65,7 @@ Different delegates are available on Android devices to accelerate model inferen 1. **CPU**: The default option, with reasonable performance on most devices. 2. **GPU**: Utilizes the device's GPU for faster inference. It can provide a significant performance boost on devices with powerful GPUs. 3. **Hexagon**: Leverages Qualcomm's Hexagon DSP for faster and more efficient processing. This option is available on devices with Qualcomm Snapdragon processors. -4. **NNAPI**: The Android Neural Networks API (NNAPI) serves as an abstraction layer for running ML models on Android devices. NNAPI can utilize various hardware accelerators, such as CPU, GPU, and dedicated AI chips (e.g., Google's Edge TPU, or the Pixel Neural Core). +4. **NNAPI**: The Android [Neural Networks](https://www.ultralytics.com/glossary/neural-network-nn) API (NNAPI) serves as an abstraction layer for running ML models on Android devices. NNAPI can utilize various hardware accelerators, such as CPU, GPU, and dedicated AI chips (e.g., Google's Edge TPU, or the Pixel Neural Core). Here's a table showing the primary vendors, their product lines, popular devices, and supported delegates: diff --git a/docs/en/hub/app/index.md b/docs/en/hub/app/index.md index 9266a0bd4d..e812d68678 100644 --- a/docs/en/hub/app/index.md +++ b/docs/en/hub/app/index.md @@ -31,11 +31,11 @@ keywords: Ultralytics HUB, YOLO models, mobile app, iOS, Android, hardware accel Google Play store  -Welcome to the Ultralytics HUB App! We are excited to introduce this powerful mobile app that allows you to run YOLOv5 and YOLOv8 models directly on your [iOS](https://apps.apple.com/xk/app/ultralytics/id1583935240) and [Android](https://play.google.com/store/apps/details?id=com.ultralytics.ultralytics_app) devices. With the HUB App, you can utilize hardware acceleration features like Apple's Neural Engine (ANE) or Android GPU and Neural Network API (NNAPI) delegates to achieve impressive performance on your mobile device. +Welcome to the Ultralytics HUB App! We are excited to introduce this powerful mobile app that allows you to run YOLOv5 and YOLOv8 models directly on your [iOS](https://apps.apple.com/xk/app/ultralytics/id1583935240) and [Android](https://play.google.com/store/apps/details?id=com.ultralytics.ultralytics_app) devices. With the HUB App, you can utilize hardware acceleration features like Apple's Neural Engine (ANE) or Android GPU and [Neural Network](https://www.ultralytics.com/glossary/neural-network-nn) API (NNAPI) delegates to achieve impressive performance on your mobile device. ## Features -- **Run YOLOv5 and YOLOv8 models**: Experience the power of YOLO models on your mobile device for real-time object detection and image recognition tasks. +- **Run YOLOv5 and YOLOv8 models**: Experience the power of YOLO models on your mobile device for real-time [object detection](https://www.ultralytics.com/glossary/object-detection) and [image recognition](https://www.ultralytics.com/glossary/image-recognition) tasks. - **Hardware Acceleration**: Benefit from Apple ANE on iOS devices or Android GPU and NNAPI delegates for optimized performance. - **Custom Model Training**: Train custom models with the Ultralytics HUB platform and preview them live using the HUB App. - **Mobile Compatibility**: The HUB App supports both iOS and Android devices, bringing the power of YOLO models to a wide range of users. diff --git a/docs/en/hub/app/ios.md b/docs/en/hub/app/ios.md index 5468633f5d..be896fe80b 100644 --- a/docs/en/hub/app/ios.md +++ b/docs/en/hub/app/ios.md @@ -4,7 +4,7 @@ description: Discover the Ultralytics iOS App for running YOLO models on your iP keywords: Ultralytics, iOS App, YOLO models, real-time object detection, Apple Neural Engine, Core ML, FP16 quantization, INT8 quantization, machine learning --- -# Ultralytics iOS App: Real-time Object Detection with YOLO Models +# Ultralytics iOS App: Real-time [Object Detection](https://www.ultralytics.com/glossary/object-detection) with YOLO Models Ultralytics HUB preview image @@ -44,7 +44,7 @@ The Ultralytics iOS App is a powerful tool that allows you to run YOLO models di ## Quantization and Acceleration -To achieve real-time performance on your iOS device, YOLO models are quantized to either FP16 or INT8 precision. Quantization is a process that reduces the numerical precision of the model's weights and biases, thus reducing the model's size and the amount of computation required. This results in faster inference times without significantly affecting the model's accuracy. +To achieve real-time performance on your iOS device, YOLO models are quantized to either FP16 or INT8 [precision](https://www.ultralytics.com/glossary/precision). Quantization is a process that reduces the numerical precision of the model's weights and biases, thus reducing the model's size and the amount of computation required. This results in faster inference times without significantly affecting the model's [accuracy](https://www.ultralytics.com/glossary/accuracy). ### FP16 Quantization @@ -56,7 +56,7 @@ INT8 (or 8-bit integer) quantization further reduces the model's size and comput ## Apple Neural Engine -The Apple Neural Engine (ANE) is a dedicated hardware component integrated into Apple's A-series and M-series chips. It's designed to accelerate machine learning tasks, particularly for neural networks, allowing for faster and more efficient execution of your YOLO models. +The Apple Neural Engine (ANE) is a dedicated hardware component integrated into Apple's A-series and M-series chips. It's designed to accelerate [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) tasks, particularly for [neural networks](https://www.ultralytics.com/glossary/neural-network-nn), allowing for faster and more efficient execution of your YOLO models. By combining quantized YOLO models with the Apple Neural Engine, the Ultralytics iOS App achieves real-time object detection on your iOS device without compromising on accuracy or performance. diff --git a/docs/en/hub/cloud-training.md b/docs/en/hub/cloud-training.md index 557e2847d8..f030367311 100644 --- a/docs/en/hub/cloud-training.md +++ b/docs/en/hub/cloud-training.md @@ -44,7 +44,7 @@ Most of the times, you will use the Epochs training. The number of epochs can be !!! note - When using the Epochs training, the [account balance](./pro.md#account-balance) is deducted after every epoch. + When using the Epochs training, the [account balance](./pro.md#account-balance) is deducted after every [epoch](https://www.ultralytics.com/glossary/epoch). Also, after every epoch, we check if you have enough [account balance](./pro.md#account-balance) for the next epoch. In case you don't have enough [account balance](./pro.md#account-balance) for the next epoch, we will stop the training session, allowing you to resume training your model from the last checkpoint saved. diff --git a/docs/en/hub/index.md b/docs/en/hub/index.md index 77b98b61ce..24dbdd3f57 100644 --- a/docs/en/hub/index.md +++ b/docs/en/hub/index.md @@ -49,7 +49,7 @@ We hope that the resources here will help you get the most out of HUB. Please br ## Introduction -[Ultralytics HUB](https://www.ultralytics.com/hub) is designed to be user-friendly and intuitive, allowing users to quickly upload their datasets and train new YOLO models. It also offers a range of pre-trained models to choose from, making it extremely easy for users to get started. Once a model is trained, it can be effortlessly previewed in the [Ultralytics HUB App](app/index.md) before being deployed for real-time classification, object detection, and instance segmentation tasks. +[Ultralytics HUB](https://www.ultralytics.com/hub) is designed to be user-friendly and intuitive, allowing users to quickly upload their datasets and train new YOLO models. It also offers a range of pre-trained models to choose from, making it extremely easy for users to get started. Once a model is trained, it can be effortlessly previewed in the [Ultralytics HUB App](app/index.md) before being deployed for real-time classification, [object detection](https://www.ultralytics.com/glossary/object-detection), and [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation) tasks.

+
+ Watch: How to Export Ultralytics YOLOv8 Models to PaddlePaddle Format | Key Features of PaddlePaddle Format +

The ability to export to PaddlePaddle model format allows you to optimize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for use within the PaddlePaddle framework. PaddlePaddle is known for facilitating industrial deployments and is a good choice for deploying computer vision applications in real-world settings across various domains. @@ -16,9 +27,9 @@ The ability to export to PaddlePaddle model format allows you to optimize your [ PaddlePaddle Logo

-Developed by Baidu, [PaddlePaddle](https://www.paddlepaddle.org.cn/en) (**PA**rallel **D**istributed **D**eep **LE**arning) is China's first open-source deep learning platform. Unlike some frameworks built mainly for research, PaddlePaddle prioritizes ease of use and smooth integration across industries. +Developed by Baidu, [PaddlePaddle](https://www.paddlepaddle.org.cn/en) (**PA**rallel **D**istributed **D**eep **LE**arning) is China's first open-source [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) platform. Unlike some frameworks built mainly for research, PaddlePaddle prioritizes ease of use and smooth integration across industries. -It offers tools and resources similar to popular frameworks like TensorFlow and PyTorch, making it accessible for developers of all experience levels. From farming and factories to service businesses, PaddlePaddle's large developer community of over 4.77 million is helping create and deploy AI applications. +It offers tools and resources similar to popular frameworks like [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) and [PyTorch](https://www.ultralytics.com/glossary/pytorch), making it accessible for developers of all experience levels. From farming and factories to service businesses, PaddlePaddle's large developer community of over 4.77 million is helping create and deploy AI applications. By exporting your Ultralytics YOLOv8 models to PaddlePaddle format, you can tap into PaddlePaddle's strengths in performance optimization. PaddlePaddle prioritizes efficient model execution and reduced memory usage. As a result, your YOLOv8 models can potentially achieve even better performance, delivering top-notch results in practical scenarios. @@ -159,14 +170,14 @@ Exporting Ultralytics YOLOv8 models to PaddlePaddle format is straightforward. Y For more detailed setup and troubleshooting, check the [Ultralytics Installation Guide](../quickstart.md) and [Common Issues Guide](../guides/yolo-common-issues.md). -### What are the advantages of using PaddlePaddle for model deployment? +### What are the advantages of using PaddlePaddle for [model deployment](https://www.ultralytics.com/glossary/model-deployment)? PaddlePaddle offers several key advantages for model deployment: - **Performance Optimization**: PaddlePaddle excels in efficient model execution and reduced memory usage. - **Dynamic-to-Static Graph Compilation**: It supports dynamic-to-static compilation, allowing for runtime optimizations. - **Operator Fusion**: By merging compatible operations, it reduces computational overhead. -- **Quantization Techniques**: Supports both post-training and quantization-aware training, enabling lower-precision data representations for improved performance. +- **Quantization Techniques**: Supports both post-training and quantization-aware training, enabling lower-[precision](https://www.ultralytics.com/glossary/precision) data representations for improved performance. You can achieve enhanced results by exporting your Ultralytics YOLOv8 models to PaddlePaddle, ensuring flexibility and high performance across various applications and hardware platforms. Learn more about PaddlePaddle's features [here](https://www.paddlepaddle.org.cn/en). @@ -186,7 +197,7 @@ PaddlePaddle employs several advanced techniques to optimize model performance: - **Dynamic-to-Static Graph**: Converts models into a static computational graph for runtime optimizations. - **Operator Fusion**: Combines compatible operations to minimize memory transfer and increase inference speed. -- **Quantization**: Reduces model size and increases efficiency using lower-precision data while maintaining accuracy. +- **Quantization**: Reduces model size and increases efficiency using lower-precision data while maintaining [accuracy](https://www.ultralytics.com/glossary/accuracy). These techniques prioritize efficient model execution, making PaddlePaddle an excellent option for deploying high-performance YOLOv8 models. For more on optimization, see the [PaddlePaddle official documentation](https://www.paddlepaddle.org.cn/documentation/docs/en/guides/index_en.html). diff --git a/docs/en/integrations/paperspace.md b/docs/en/integrations/paperspace.md index 447898509c..7c67d9bbff 100644 --- a/docs/en/integrations/paperspace.md +++ b/docs/en/integrations/paperspace.md @@ -8,7 +8,7 @@ keywords: YOLOv8, Paperspace Gradient, MLOps, machine learning, training, GPUs, Training computer vision models like [YOLOv8](https://github.com/ultralytics/ultralytics) can be complicated. It involves managing large datasets, using different types of computer hardware like GPUs, TPUs, and CPUs, and making sure data flows smoothly during the training process. Typically, developers end up spending a lot of time managing their computer systems and environments. It can be frustrating when you just want to focus on building the best model. -This is where a platform like Paperspace Gradient can make things simpler. Paperspace Gradient is a MLOps platform that lets you build, train, and deploy machine learning models all in one place. With Gradient, developers can focus on training their YOLOv8 models without the hassle of managing infrastructure and environments. +This is where a platform like Paperspace Gradient can make things simpler. Paperspace Gradient is a MLOps platform that lets you build, train, and deploy [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models all in one place. With Gradient, developers can focus on training their YOLOv8 models without the hassle of managing infrastructure and environments. ## Paperspace @@ -61,7 +61,7 @@ As you explore the Paperspace console, you'll see how each step of the machine-l - **Dataset Management:** Efficiently manage your datasets directly within Gradient. Upload, version, and pre-process data with ease, streamlining the data preparation phase of your project. -- **Model Serving:** Deploy your trained YOLOv8 models as REST APIs with just a few clicks. Gradient handles the infrastructure, allowing you to easily integrate your object detection models into your applications. +- **Model Serving:** Deploy your trained YOLOv8 models as REST APIs with just a few clicks. Gradient handles the infrastructure, allowing you to easily integrate your [object detection](https://www.ultralytics.com/glossary/object-detection) models into your applications. - **Real-time Monitoring:** Monitor the performance and health of your deployed models through Gradient's intuitive dashboard. Gain insights into inference speed, resource utilization, and potential errors. @@ -83,7 +83,7 @@ This guide explored the Paperspace Gradient integration for training YOLOv8 mode For further exploration, visit [PaperSpace's official documentation](https://docs.digitalocean.com/products/paperspace/). -Also, visit the [Ultralytics integration guide page](index.md) to learn more about different YOLOv8 integrations. It's full of insights and tips to take your computer vision projects to the next level. +Also, visit the [Ultralytics integration guide page](index.md) to learn more about different YOLOv8 integrations. It's full of insights and tips to take your [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) projects to the next level. ## FAQ @@ -104,7 +104,7 @@ Paperspace Gradient offers several unique advantages for training and deploying ### Why should I choose Ultralytics YOLOv8 over other object detection models? -Ultralytics YOLOv8 stands out for its real-time object detection capabilities and high accuracy. Its seamless integration with platforms like Paperspace Gradient enhances productivity by simplifying the training and deployment process. YOLOv8 supports various use cases, from security systems to retail inventory management. Explore more about YOLOv8's advantages [here](https://www.ultralytics.com/yolo). +Ultralytics YOLOv8 stands out for its real-time object detection capabilities and high [accuracy](https://www.ultralytics.com/glossary/accuracy). Its seamless integration with platforms like Paperspace Gradient enhances productivity by simplifying the training and deployment process. YOLOv8 supports various use cases, from security systems to retail inventory management. Explore more about YOLOv8's advantages [here](https://www.ultralytics.com/yolo). ### Can I deploy my YOLOv8 model on edge devices using Paperspace Gradient? diff --git a/docs/en/integrations/ray-tune.md b/docs/en/integrations/ray-tune.md index d216cf38e9..3dec5efeb6 100644 --- a/docs/en/integrations/ray-tune.md +++ b/docs/en/integrations/ray-tune.md @@ -4,7 +4,7 @@ description: Optimize YOLOv8 model performance with Ray Tune. Learn efficient hy keywords: YOLOv8, Ray Tune, hyperparameter tuning, model optimization, machine learning, deep learning, AI, Ultralytics, Weights & Biases --- -# Efficient Hyperparameter Tuning with Ray Tune and YOLOv8 +# Efficient [Hyperparameter Tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning) with Ray Tune and YOLOv8 Hyperparameter tuning is vital in achieving peak model performance by discovering the optimal set of hyperparameters. This involves running trials with different hyperparameters and evaluating each trial's performance. @@ -18,7 +18,7 @@ Hyperparameter tuning is vital in achieving peak model performance by discoverin Ray Tune Overview

-[Ray Tune](https://docs.ray.io/en/latest/tune/index.html) is a hyperparameter tuning library designed for efficiency and flexibility. It supports various search strategies, parallelism, and early stopping strategies, and seamlessly integrates with popular machine learning frameworks, including Ultralytics YOLOv8. +[Ray Tune](https://docs.ray.io/en/latest/tune/index.html) is a hyperparameter tuning library designed for efficiency and flexibility. It supports various search strategies, parallelism, and early stopping strategies, and seamlessly integrates with popular [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) frameworks, including Ultralytics YOLOv8. ### Integration with Weights & Biases @@ -60,14 +60,14 @@ To install the required packages, run: The `tune()` method in YOLOv8 provides an easy-to-use interface for hyperparameter tuning with Ray Tune. It accepts several arguments that allow you to customize the tuning process. Below is a detailed explanation of each parameter: -| Parameter | Type | Description | Default Value | -| --------------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------- | -| `data` | `str` | The dataset configuration file (in YAML format) to run the tuner on. This file should specify the training and validation data paths, as well as other dataset-specific settings. | | -| `space` | `dict, optional` | A dictionary defining the hyperparameter search space for Ray Tune. Each key corresponds to a hyperparameter name, and the value specifies the range of values to explore during tuning. If not provided, YOLOv8 uses a default search space with various hyperparameters. | | -| `grace_period` | `int, optional` | The grace period in epochs for the [ASHA scheduler](https://docs.ray.io/en/latest/tune/api/schedulers.html) in Ray Tune. The scheduler will not terminate any trial before this number of epochs, allowing the model to have some minimum training before making a decision on early stopping. | 10 | -| `gpu_per_trial` | `int, optional` | The number of GPUs to allocate per trial during tuning. This helps manage GPU usage, particularly in multi-GPU environments. If not provided, the tuner will use all available GPUs. | None | -| `iterations` | `int, optional` | The maximum number of trials to run during tuning. This parameter helps control the total number of hyperparameter combinations tested, ensuring the tuning process does not run indefinitely. | 10 | -| `**train_args` | `dict, optional` | Additional arguments to pass to the `train()` method during tuning. These arguments can include settings like the number of training epochs, batch size, and other training-specific configurations. | {} | +| Parameter | Type | Description | Default Value | +| --------------- | ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------- | +| `data` | `str` | The dataset configuration file (in YAML format) to run the tuner on. This file should specify the training and [validation data](https://www.ultralytics.com/glossary/validation-data) paths, as well as other dataset-specific settings. | | +| `space` | `dict, optional` | A dictionary defining the hyperparameter search space for Ray Tune. Each key corresponds to a hyperparameter name, and the value specifies the range of values to explore during tuning. If not provided, YOLOv8 uses a default search space with various hyperparameters. | | +| `grace_period` | `int, optional` | The grace period in [epochs](https://www.ultralytics.com/glossary/epoch) for the [ASHA scheduler](https://docs.ray.io/en/latest/tune/api/schedulers.html) in Ray Tune. The scheduler will not terminate any trial before this number of epochs, allowing the model to have some minimum training before making a decision on early stopping. | 10 | +| `gpu_per_trial` | `int, optional` | The number of GPUs to allocate per trial during tuning. This helps manage GPU usage, particularly in multi-GPU environments. If not provided, the tuner will use all available GPUs. | None | +| `iterations` | `int, optional` | The maximum number of trials to run during tuning. This parameter helps control the total number of hyperparameter combinations tested, ensuring the tuning process does not run indefinitely. | 10 | +| `**train_args` | `dict, optional` | Additional arguments to pass to the `train()` method during tuning. These arguments can include settings like the number of training epochs, [batch size](https://www.ultralytics.com/glossary/batch-size), and other training-specific configurations. | {} | By customizing these parameters, you can fine-tune the hyperparameter optimization process to suit your specific needs and available computational resources. @@ -75,29 +75,29 @@ By customizing these parameters, you can fine-tune the hyperparameter optimizati The following table lists the default search space parameters for hyperparameter tuning in YOLOv8 with Ray Tune. Each parameter has a specific value range defined by `tune.uniform()`. -| Parameter | Value Range | Description | -| ----------------- | -------------------------- | ---------------------------------------- | -| `lr0` | `tune.uniform(1e-5, 1e-1)` | Initial learning rate | -| `lrf` | `tune.uniform(0.01, 1.0)` | Final learning rate factor | -| `momentum` | `tune.uniform(0.6, 0.98)` | Momentum | -| `weight_decay` | `tune.uniform(0.0, 0.001)` | Weight decay | -| `warmup_epochs` | `tune.uniform(0.0, 5.0)` | Warmup epochs | -| `warmup_momentum` | `tune.uniform(0.0, 0.95)` | Warmup momentum | -| `box` | `tune.uniform(0.02, 0.2)` | Box loss weight | -| `cls` | `tune.uniform(0.2, 4.0)` | Class loss weight | -| `hsv_h` | `tune.uniform(0.0, 0.1)` | Hue augmentation range | -| `hsv_s` | `tune.uniform(0.0, 0.9)` | Saturation augmentation range | -| `hsv_v` | `tune.uniform(0.0, 0.9)` | Value (brightness) augmentation range | -| `degrees` | `tune.uniform(0.0, 45.0)` | Rotation augmentation range (degrees) | -| `translate` | `tune.uniform(0.0, 0.9)` | Translation augmentation range | -| `scale` | `tune.uniform(0.0, 0.9)` | Scaling augmentation range | -| `shear` | `tune.uniform(0.0, 10.0)` | Shear augmentation range (degrees) | -| `perspective` | `tune.uniform(0.0, 0.001)` | Perspective augmentation range | -| `flipud` | `tune.uniform(0.0, 1.0)` | Vertical flip augmentation probability | -| `fliplr` | `tune.uniform(0.0, 1.0)` | Horizontal flip augmentation probability | -| `mosaic` | `tune.uniform(0.0, 1.0)` | Mosaic augmentation probability | -| `mixup` | `tune.uniform(0.0, 1.0)` | Mixup augmentation probability | -| `copy_paste` | `tune.uniform(0.0, 1.0)` | Copy-paste augmentation probability | +| Parameter | Value Range | Description | +| ----------------- | -------------------------- | --------------------------------------------------------------------------- | +| `lr0` | `tune.uniform(1e-5, 1e-1)` | Initial [learning rate](https://www.ultralytics.com/glossary/learning-rate) | +| `lrf` | `tune.uniform(0.01, 1.0)` | Final learning rate factor | +| `momentum` | `tune.uniform(0.6, 0.98)` | Momentum | +| `weight_decay` | `tune.uniform(0.0, 0.001)` | Weight decay | +| `warmup_epochs` | `tune.uniform(0.0, 5.0)` | Warmup epochs | +| `warmup_momentum` | `tune.uniform(0.0, 0.95)` | Warmup momentum | +| `box` | `tune.uniform(0.02, 0.2)` | Box loss weight | +| `cls` | `tune.uniform(0.2, 4.0)` | Class loss weight | +| `hsv_h` | `tune.uniform(0.0, 0.1)` | Hue augmentation range | +| `hsv_s` | `tune.uniform(0.0, 0.9)` | Saturation augmentation range | +| `hsv_v` | `tune.uniform(0.0, 0.9)` | Value (brightness) augmentation range | +| `degrees` | `tune.uniform(0.0, 45.0)` | Rotation augmentation range (degrees) | +| `translate` | `tune.uniform(0.0, 0.9)` | Translation augmentation range | +| `scale` | `tune.uniform(0.0, 0.9)` | Scaling augmentation range | +| `shear` | `tune.uniform(0.0, 10.0)` | Shear augmentation range (degrees) | +| `perspective` | `tune.uniform(0.0, 0.001)` | Perspective augmentation range | +| `flipud` | `tune.uniform(0.0, 1.0)` | Vertical flip augmentation probability | +| `fliplr` | `tune.uniform(0.0, 1.0)` | Horizontal flip augmentation probability | +| `mosaic` | `tune.uniform(0.0, 1.0)` | Mosaic augmentation probability | +| `mixup` | `tune.uniform(0.0, 1.0)` | Mixup augmentation probability | +| `copy_paste` | `tune.uniform(0.0, 1.0)` | Copy-paste augmentation probability | ## Custom Search Space Example diff --git a/docs/en/integrations/roboflow.md b/docs/en/integrations/roboflow.md index e851e1bde7..321e560164 100644 --- a/docs/en/integrations/roboflow.md +++ b/docs/en/integrations/roboflow.md @@ -6,7 +6,7 @@ keywords: Roboflow, YOLOv8, data labeling, computer vision, model training, mode # Roboflow -[Roboflow](https://roboflow.com/?ref=ultralytics) has everything you need to build and deploy computer vision models. Connect Roboflow at any step in your pipeline with APIs and SDKs, or use the end-to-end interface to automate the entire process from image to inference. Whether you're in need of [data labeling](https://roboflow.com/annotate?ref=ultralytics), [model training](https://roboflow.com/train?ref=ultralytics), or [model deployment](https://roboflow.com/deploy?ref=ultralytics), Roboflow gives you building blocks to bring custom computer vision solutions to your project. +[Roboflow](https://roboflow.com/?ref=ultralytics) has everything you need to build and deploy [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) models. Connect Roboflow at any step in your pipeline with APIs and SDKs, or use the end-to-end interface to automate the entire process from image to inference. Whether you're in need of [data labeling](https://roboflow.com/annotate?ref=ultralytics), [model training](https://roboflow.com/train?ref=ultralytics), or [model deployment](https://roboflow.com/deploy?ref=ultralytics), Roboflow gives you building blocks to bring custom computer vision solutions to your project. !!! question "Licensing" @@ -53,9 +53,9 @@ If you want to gather images yourself, try [Collect](https://github.com/roboflow ## Upload, Convert and Label Data for YOLOv8 Format -[Roboflow Annotate](https://docs.roboflow.com/annotate/use-roboflow-annotate?ref=ultralytics) is an online annotation tool for use in labeling images for object detection, classification, and segmentation. +[Roboflow Annotate](https://docs.roboflow.com/annotate/use-roboflow-annotate?ref=ultralytics) is an online annotation tool for use in labeling images for [object detection](https://www.ultralytics.com/glossary/object-detection), classification, and segmentation. -To label data for a YOLOv8 object detection, instance segmentation, or classification model, first create a project in Roboflow. +To label data for a YOLOv8 object detection, [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation), or classification model, first create a project in Roboflow.

Create a Roboflow project @@ -69,7 +69,7 @@ Next, upload your images, and any pre-existing annotations you have from other t Select the batch of images you have uploaded on the Annotate page to which you are taken after uploading images. Then, click "Start Annotating" to label images. -To label with bounding boxes, press the `B` key on your keyboard or click the box icon in the sidebar. Click on a point where you want to start your bounding box, then drag to create the box: +To label with bounding boxes, press the `B` key on your keyboard or click the box icon in the sidebar. Click on a point where you want to start your [bounding box](https://www.ultralytics.com/glossary/bounding-box), then drag to create the box:

Annotating an image in Roboflow @@ -194,7 +194,7 @@ You can also use your uploaded model as a [labeling assistant](https://docs.robo Roboflow provides a range of features for use in evaluating models. -Once you have uploaded a model to Roboflow, you can access our model evaluation tool, which provides a confusion matrix showing the performance of your model as well as an interactive vector analysis plot. These features can help you find opportunities to improve your model. +Once you have uploaded a model to Roboflow, you can access our model evaluation tool, which provides a [confusion matrix](https://www.ultralytics.com/glossary/confusion-matrix) showing the performance of your model as well as an interactive vector analysis plot. These features can help you find opportunities to improve your model. To access a confusion matrix, go to your model page on the Roboflow dashboard, then click "View Detailed Evaluation": @@ -248,7 +248,7 @@ Below are a few of the many pieces of feedback we have received for using YOLOv8 Labeling data for YOLOv8 models using Roboflow is straightforward with Roboflow Annotate. First, create a project on Roboflow and upload your images. After uploading, select the batch of images and click "Start Annotating." You can use the `B` key for bounding boxes or the `P` key for polygons. For faster annotation, use the SAM-based label assistant by clicking the cursor icon in the sidebar. Detailed steps can be found [here](#upload-convert-and-label-data-for-yolov8-format). -### What services does Roboflow offer for collecting YOLOv8 training data? +### What services does Roboflow offer for collecting YOLOv8 [training data](https://www.ultralytics.com/glossary/training-data)? Roboflow provides two key services for collecting YOLOv8 training data: [Universe](https://universe.roboflow.com/?ref=ultralytics) and [Collect](https://github.com/roboflow/roboflow-collect?ref=ultralytics). Universe offers access to over 250,000 vision datasets, while Collect helps you gather images using a webcam and automated prompts. diff --git a/docs/en/integrations/tensorboard.md b/docs/en/integrations/tensorboard.md index 59add9258f..d563aca12b 100644 --- a/docs/en/integrations/tensorboard.md +++ b/docs/en/integrations/tensorboard.md @@ -6,7 +6,7 @@ keywords: YOLOv8, TensorBoard, model training, visualization, machine learning, # Gain Visual Insights with YOLOv8's Integration with TensorBoard -Understanding and fine-tuning computer vision models like [Ultralytics' YOLOv8](https://www.ultralytics.com/) becomes more straightforward when you take a closer look at their training processes. Model training visualization helps with getting insights into the model's learning patterns, performance metrics, and overall behavior. YOLOv8's integration with TensorBoard makes this process of visualization and analysis easier and enables more efficient and informed adjustments to the model. +Understanding and fine-tuning [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) models like [Ultralytics' YOLOv8](https://www.ultralytics.com/) becomes more straightforward when you take a closer look at their training processes. Model training visualization helps with getting insights into the model's learning patterns, performance metrics, and overall behavior. YOLOv8's integration with TensorBoard makes this process of visualization and analysis easier and enables more efficient and informed adjustments to the model. This guide covers how to use TensorBoard with YOLOv8. You'll learn about various visualizations, from tracking metrics to analyzing model graphs. These tools will help you understand your YOLOv8 model's performance better. @@ -16,7 +16,7 @@ This guide covers how to use TensorBoard with YOLOv8. You'll learn about various Tensorboard Overview

-[TensorBoard](https://www.tensorflow.org/tensorboard), TensorFlow's visualization toolkit, is essential for machine learning experimentation. TensorBoard features a range of visualization tools, crucial for monitoring machine learning models. These tools include tracking key metrics like loss and accuracy, visualizing model graphs, and viewing histograms of weights and biases over time. It also provides capabilities for projecting embeddings to lower-dimensional spaces and displaying multimedia data. +[TensorBoard](https://www.tensorflow.org/tensorboard), [TensorFlow](https://www.ultralytics.com/glossary/tensorflow)'s visualization toolkit, is essential for [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) experimentation. TensorBoard features a range of visualization tools, crucial for monitoring machine learning models. These tools include tracking key metrics like loss and accuracy, visualizing model graphs, and viewing histograms of weights and biases over time. It also provides capabilities for projecting [embeddings](https://www.ultralytics.com/glossary/embeddings) to lower-dimensional spaces and displaying multimedia data. ## YOLOv8 Training with TensorBoard @@ -94,7 +94,7 @@ The Time Series feature in the TensorBoard offers a dynamic and detailed perspec - **Filter Tags and Pinned Cards**: This functionality allows users to filter specific metrics and pin cards for quick comparison and access. It's particularly useful for focusing on specific aspects of the training process. -- **Detailed Metric Cards**: Time Series divides metrics into different categories like learning rate (lr), training (train), and validation (val) metrics, each represented by individual cards. +- **Detailed Metric Cards**: Time Series divides metrics into different categories like [learning rate](https://www.ultralytics.com/glossary/learning-rate) (lr), training (train), and validation (val) metrics, each represented by individual cards. - **Graphical Display**: Each card in the Time Series section shows a detailed graph of a specific metric over the course of training. This visual representation aids in identifying trends, patterns, or anomalies in the training process. @@ -106,7 +106,7 @@ The Time Series section is essential for a thorough analysis of the YOLOv8 model ### Scalars -Scalars in the TensorBoard are crucial for plotting and analyzing simple metrics like loss and accuracy during the training of YOLOv8 models. They offer a clear and concise view of how these metrics evolve with each training epoch, providing insights into the model's learning effectiveness and stability. Here's an example of what you can expect to see. +Scalars in the TensorBoard are crucial for plotting and analyzing simple metrics like loss and accuracy during the training of YOLOv8 models. They offer a clear and concise view of how these metrics evolve with each training [epoch](https://www.ultralytics.com/glossary/epoch), providing insights into the model's learning effectiveness and stability. Here's an example of what you can expect to see. ![image](https://github.com/ultralytics/docs/releases/download/0/scalars-metrics-tensorboard.avif) @@ -116,11 +116,11 @@ Scalars in the TensorBoard are crucial for plotting and analyzing simple metrics - **Metrics Tags**: Scalars include performance indicators such as: - - `mAP50 (B)`: Mean Average Precision at 50% Intersection over Union (IoU), crucial for assessing object detection accuracy. + - `mAP50 (B)`: Mean Average [Precision](https://www.ultralytics.com/glossary/precision) at 50% [Intersection over Union](https://www.ultralytics.com/glossary/intersection-over-union-iou) (IoU), crucial for assessing object detection accuracy. - - `mAP50-95 (B)`: Mean Average Precision calculated over a range of IoU thresholds, offering a more comprehensive evaluation of accuracy. + - `mAP50-95 (B)`: [Mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) calculated over a range of IoU thresholds, offering a more comprehensive evaluation of accuracy. - - `Precision (B)`: Indicates the ratio of correctly predicted positive observations, key to understanding prediction accuracy. + - `Precision (B)`: Indicates the ratio of correctly predicted positive observations, key to understanding prediction [accuracy](https://www.ultralytics.com/glossary/accuracy). - `Recall (B)`: Important for models where missing a detection is significant, this metric measures the ability to detect all relevant instances. @@ -130,7 +130,7 @@ Scalars in the TensorBoard are crucial for plotting and analyzing simple metrics #### Importance of Monitoring Scalars -Observing scalar metrics is crucial for fine-tuning the YOLOv8 model. Variations in these metrics, such as spikes or irregular patterns in loss graphs, can highlight potential issues such as overfitting, underfitting, or inappropriate learning rate settings. By closely monitoring these scalars, you can make informed decisions to optimize the training process, ensuring that the model learns effectively and achieves the desired performance. +Observing scalar metrics is crucial for fine-tuning the YOLOv8 model. Variations in these metrics, such as spikes or irregular patterns in loss graphs, can highlight potential issues such as [overfitting](https://www.ultralytics.com/glossary/overfitting), [underfitting](https://www.ultralytics.com/glossary/underfitting), or inappropriate learning rate settings. By closely monitoring these scalars, you can make informed decisions to optimize the training process, ensuring that the model learns effectively and achieves the desired performance. ### Difference Between Scalars and Time Series @@ -142,7 +142,7 @@ The Graphs section of the TensorBoard visualizes the computational graph of the ![image](https://github.com/ultralytics/docs/releases/download/0/tensorboard-yolov8-computational-graph.avif) -Graphs are particularly useful for debugging the model, especially in complex architectures typical in deep learning models like YOLOv8. They help in verifying layer connections and the overall design of the model. +Graphs are particularly useful for debugging the model, especially in complex architectures typical in [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models like YOLOv8. They help in verifying layer connections and the overall design of the model. ## Summary @@ -179,9 +179,9 @@ The TensorBoard dashboard, accessible via [http://localhost:6006/](http://localh When training YOLOv8 models, TensorBoard allows you to visualize an array of important metrics including: - **Loss (Training and Validation):** Indicates how well the model is performing during training and validation. -- **Accuracy/Precision/Recall:** Key performance metrics to evaluate detection accuracy. +- **Accuracy/Precision/[Recall](https://www.ultralytics.com/glossary/recall):** Key performance metrics to evaluate detection accuracy. - **Learning Rate:** Track learning rate changes to understand its impact on training dynamics. -- **mAP (mean Average Precision):** For a comprehensive evaluation of object detection accuracy at various IoU thresholds. +- **mAP (mean Average Precision):** For a comprehensive evaluation of [object detection](https://www.ultralytics.com/glossary/object-detection) accuracy at various IoU thresholds. These visualizations are essential for tracking model performance and making necessary optimizations. For more information on these metrics, refer to our [Performance Metrics guide](../guides/yolo-performance-metrics.md). diff --git a/docs/en/integrations/tensorrt.md b/docs/en/integrations/tensorrt.md index c40b9f654c..0e40198113 100644 --- a/docs/en/integrations/tensorrt.md +++ b/docs/en/integrations/tensorrt.md @@ -6,9 +6,9 @@ keywords: YOLOv8, TensorRT, NVIDIA, GPU, deep learning, model optimization, high # TensorRT Export for YOLOv8 Models -Deploying computer vision models in high-performance environments can require a format that maximizes speed and efficiency. This is especially true when you are deploying your model on NVIDIA GPUs. +Deploying [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) models in high-performance environments can require a format that maximizes speed and efficiency. This is especially true when you are deploying your model on NVIDIA GPUs. -By using the TensorRT export format, you can enhance your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for swift and efficient inference on NVIDIA hardware. This guide will give you easy-to-follow steps for the conversion process and help you make the most of NVIDIA's advanced technology in your deep learning projects. +By using the TensorRT export format, you can enhance your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for swift and efficient inference on NVIDIA hardware. This guide will give you easy-to-follow steps for the conversion process and help you make the most of NVIDIA's advanced technology in your [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) projects. ## TensorRT @@ -16,11 +16,11 @@ By using the TensorRT export format, you can enhance your [Ultralytics YOLOv8](h TensorRT Overview

-[TensorRT](https://developer.nvidia.com/tensorrt), developed by NVIDIA, is an advanced software development kit (SDK) designed for high-speed deep learning inference. It's well-suited for real-time applications like object detection. +[TensorRT](https://developer.nvidia.com/tensorrt), developed by NVIDIA, is an advanced software development kit (SDK) designed for high-speed deep learning inference. It's well-suited for real-time applications like [object detection](https://www.ultralytics.com/glossary/object-detection). This toolkit optimizes deep learning models for NVIDIA GPUs and results in faster and more efficient operations. TensorRT models undergo TensorRT optimization, which includes techniques like layer fusion, precision calibration (INT8 and FP16), dynamic tensor memory management, and kernel auto-tuning. Converting deep learning models into the TensorRT format allows developers to realize the potential of NVIDIA GPUs fully. -TensorRT is known for its compatibility with various model formats, including TensorFlow, PyTorch, and ONNX, providing developers with a flexible solution for integrating and optimizing models from different frameworks. This versatility enables efficient model deployment across diverse hardware and software environments. +TensorRT is known for its compatibility with various model formats, including TensorFlow, [PyTorch](https://www.ultralytics.com/glossary/pytorch), and ONNX, providing developers with a flexible solution for integrating and optimizing models from different frameworks. This versatility enables efficient [model deployment](https://www.ultralytics.com/glossary/model-deployment) across diverse hardware and software environments. ## Key Features of TensorRT Models @@ -28,7 +28,7 @@ TensorRT models offer a range of key features that contribute to their efficienc - **Precision Calibration**: TensorRT supports precision calibration, allowing models to be fine-tuned for specific accuracy requirements. This includes support for reduced precision formats like INT8 and FP16, which can further boost inference speed while maintaining acceptable accuracy levels. -- **Layer Fusion**: The TensorRT optimization process includes layer fusion, where multiple layers of a neural network are combined into a single operation. This reduces computational overhead and improves inference speed by minimizing memory access and computation. +- **Layer Fusion**: The TensorRT optimization process includes layer fusion, where multiple layers of a [neural network](https://www.ultralytics.com/glossary/neural-network-nn) are combined into a single operation. This reduces computational overhead and improves inference speed by minimizing memory access and computation.

TensorRT Layer Fusion @@ -44,7 +44,7 @@ Before we look at the code for exporting YOLOv8 models to the TensorRT format, l TensorRT offers several deployment options, and each option balances ease of integration, performance optimization, and flexibility differently: -- **Deploying within TensorFlow**: This method integrates TensorRT into TensorFlow, allowing optimized models to run in a familiar TensorFlow environment. It's useful for models with a mix of supported and unsupported layers, as TF-TRT can handle these efficiently. +- **Deploying within [TensorFlow](https://www.ultralytics.com/glossary/tensorflow)**: This method integrates TensorRT into TensorFlow, allowing optimized models to run in a familiar TensorFlow environment. It's useful for models with a mix of supported and unsupported layers, as TF-TRT can handle these efficiently.

TensorRT Overview @@ -111,7 +111,7 @@ For more details about the export process, visit the [Ultralytics documentation ### Exporting TensorRT with INT8 Quantization -Exporting Ultralytics YOLO models using TensorRT with INT8 precision executes post-training quantization (PTQ). TensorRT uses calibration for PTQ, which measures the distribution of activations within each activation tensor as the YOLO model processes inference on representative input data, and then uses that distribution to estimate scale values for each tensor. Each activation tensor that is a candidate for quantization has an associated scale that is deduced by a calibration process. +Exporting Ultralytics YOLO models using TensorRT with INT8 [precision](https://www.ultralytics.com/glossary/precision) executes post-training quantization (PTQ). TensorRT uses calibration for PTQ, which measures the distribution of activations within each activation tensor as the YOLO model processes inference on representative input data, and then uses that distribution to estimate scale values for each tensor. Each activation tensor that is a candidate for quantization has an associated scale that is deduced by a calibration process. When processing implicitly quantized networks TensorRT uses INT8 opportunistically to optimize layer execution time. If a layer runs faster in INT8 and has assigned quantization scales on its data inputs and outputs, then a kernel with INT8 precision is assigned to that layer, otherwise TensorRT selects a precision of either FP32 or FP16 for the kernel based on whichever results in faster execution time for that layer. @@ -125,7 +125,7 @@ The arguments provided when using [export](../modes/export.md) for an Ultralytic - `workspace` : Controls the size (in GiB) of the device memory allocation while converting the model weights. - - Adjust the `workspace` value according to your calibration needs and resource availability. While a larger `workspace` may increase calibration time, it allows TensorRT to explore a wider range of optimization tactics, potentially enhancing model performance and accuracy. Conversely, a smaller `workspace` can reduce calibration time but may limit the optimization strategies, affecting the quality of the quantized model. + - Adjust the `workspace` value according to your calibration needs and resource availability. While a larger `workspace` may increase calibration time, it allows TensorRT to explore a wider range of optimization tactics, potentially enhancing model performance and [accuracy](https://www.ultralytics.com/glossary/accuracy). Conversely, a smaller `workspace` can reduce calibration time but may limit the optimization strategies, affecting the quality of the quantized model. - Default is `workspace=4` (GiB), this value may need to be increased if calibration crashes (exits without warning). @@ -139,7 +139,7 @@ The arguments provided when using [export](../modes/export.md) for an Ultralytic !!! note - During calibration, twice the `batch` size provided will be used. Using small batches can lead to inaccurate scaling during calibration. This is because the process adjusts based on the data it sees. Small batches might not capture the full range of values, leading to issues with the final calibration, so the `batch` size is doubled automatically. If no batch size is specified `batch=1`, calibration will be run at `batch=1 * 2` to reduce calibration scaling errors. + During calibration, twice the `batch` size provided will be used. Using small batches can lead to inaccurate scaling during calibration. This is because the process adjusts based on the data it sees. Small batches might not capture the full range of values, leading to issues with the final calibration, so the `batch` size is doubled automatically. If no [batch size](https://www.ultralytics.com/glossary/batch-size) is specified `batch=1`, calibration will be run at `batch=1 * 2` to reduce calibration scaling errors. Experimentation by NVIDIA led them to recommend using at least 500 calibration images that are representative of the data for your model, with INT8 quantization calibration. This is a guideline and not a _hard_ requirement, and **you will need to experiment with what is required to perform well for your dataset**. Since the calibration data is required for INT8 calibration with TensorRT, make certain to use the `data` argument when `int8=True` for TensorRT and use `data="my_dataset.yaml"`, which will use the images from [validation](../modes/val.md) to calibrate with. When no value is passed for `data` with export to TensorRT with INT8 quantization, the default will be to use one of the ["small" example datasets based on the model task](../datasets/index.md) instead of throwing an error. diff --git a/docs/en/integrations/tf-graphdef.md b/docs/en/integrations/tf-graphdef.md index 24ae0dd980..15cbd48426 100644 --- a/docs/en/integrations/tf-graphdef.md +++ b/docs/en/integrations/tf-graphdef.md @@ -6,7 +6,7 @@ keywords: YOLOv8, export, TensorFlow, GraphDef, model deployment, TensorFlow Ser # How to Export to TF GraphDef from YOLOv8 for Deployment -When you are deploying cutting-edge computer vision models, like YOLOv8, in different environments, you might run into compatibility issues. Google's TensorFlow GraphDef, or TF GraphDef, offers a solution by providing a serialized, platform-independent representation of your model. Using the TF GraphDef model format, you can deploy your YOLOv8 model in environments where the complete TensorFlow ecosystem may not be available, such as mobile devices or specialized hardware. +When you are deploying cutting-edge [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) models, like YOLOv8, in different environments, you might run into compatibility issues. Google's [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) GraphDef, or TF GraphDef, offers a solution by providing a serialized, platform-independent representation of your model. Using the TF GraphDef model format, you can deploy your YOLOv8 model in environments where the complete TensorFlow ecosystem may not be available, such as mobile devices or specialized hardware. In this guide, we'll walk you step by step through how to export your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models to the TF GraphDef model format. By converting your model, you can streamline deployment and use YOLOv8's computer vision capabilities in a broader range of applications and platforms. @@ -24,7 +24,7 @@ GraphDef models can use hardware accelerators such as GPUs, TPUs, and AI chips, ## Key Features of TF GraphDef Models -TF GraphDef offers distinct features for streamlining model deployment and optimization. +TF GraphDef offers distinct features for streamlining [model deployment](https://www.ultralytics.com/glossary/model-deployment) and optimization. Here's a look at its key characteristics: @@ -111,7 +111,7 @@ Once you've exported your YOLOv8 model to the TF GraphDef format, the next step However, for more information on deploying your TF GraphDef models, take a look at the following resources: -- **[TensorFlow Serving](https://www.tensorflow.org/tfx/guide/serving)**: A guide on TensorFlow Serving that teaches how to deploy and serve machine learning models efficiently in production environments. +- **[TensorFlow Serving](https://www.tensorflow.org/tfx/guide/serving)**: A guide on TensorFlow Serving that teaches how to deploy and serve [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models efficiently in production environments. - **[TensorFlow Lite](https://www.tensorflow.org/api_docs/python/tf/lite/TFLiteConverter)**: This page describes how to convert machine learning models into a format optimized for on-device inference with TensorFlow Lite. @@ -173,11 +173,11 @@ Exporting YOLOv8 models to the TF GraphDef format offers multiple advantages, in Read more about the benefits in the [TF GraphDef section](#why-should-you-export-to-tf-graphdef) of our documentation. -### Why should I use Ultralytics YOLOv8 over other object detection models? +### Why should I use Ultralytics YOLOv8 over other [object detection](https://www.ultralytics.com/glossary/object-detection) models? Ultralytics YOLOv8 offers numerous advantages compared to other models like YOLOv5 and YOLOv7. Some key benefits include: -1. **State-of-the-Art Performance**: YOLOv8 provides exceptional speed and accuracy for real-time object detection, segmentation, and classification. +1. **State-of-the-Art Performance**: YOLOv8 provides exceptional speed and [accuracy](https://www.ultralytics.com/glossary/accuracy) for real-time object detection, segmentation, and classification. 2. **Ease of Use**: Features a user-friendly API for model training, validation, prediction, and export, making it accessible for both beginners and experts. 3. **Broad Compatibility**: Supports multiple export formats including ONNX, TensorRT, CoreML, and TensorFlow, for versatile deployment options. diff --git a/docs/en/integrations/tf-savedmodel.md b/docs/en/integrations/tf-savedmodel.md index 5de706a8e0..9f04dc7893 100644 --- a/docs/en/integrations/tf-savedmodel.md +++ b/docs/en/integrations/tf-savedmodel.md @@ -6,7 +6,7 @@ keywords: YOLOv8, TF SavedModel, Ultralytics, TensorFlow, model export, model de # Understand How to Export to TF SavedModel Format From YOLOv8 -Deploying machine learning models can be challenging. However, using an efficient and flexible model format can make your job easier. TF SavedModel is an open-source machine-learning framework used by TensorFlow to load machine-learning models in a consistent way. It is like a suitcase for TensorFlow models, making them easy to carry and use on different devices and systems. +Deploying [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models can be challenging. However, using an efficient and flexible model format can make your job easier. TF SavedModel is an open-source machine-learning framework used by TensorFlow to load machine-learning models in a consistent way. It is like a suitcase for TensorFlow models, making them easy to carry and use on different devices and systems. Learning how to export to TF SavedModel from [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models can help you deploy models easily across different platforms and environments. In this guide, we'll walk through how to convert your models to the TF SavedModel format, simplifying the process of running inferences with your models on different devices. @@ -28,7 +28,7 @@ Here are the key features that make TF SavedModel a great option for AI develope - **Ease of Deployment**: TF SavedModel bundles the computational graph, trained parameters, and necessary metadata into a single package. They can be easily loaded and used for inference without requiring the original code that built the model. This makes the deployment of TensorFlow models straightforward and efficient in various production environments. -- **Asset Management**: TF SavedModel supports the inclusion of external assets such as vocabularies, embeddings, or lookup tables. These assets are stored alongside the graph definition and variables, ensuring they are available when the model is loaded. This feature simplifies the management and distribution of models that rely on external resources. +- **Asset Management**: TF SavedModel supports the inclusion of external assets such as vocabularies, [embeddings](https://www.ultralytics.com/glossary/embeddings), or lookup tables. These assets are stored alongside the graph definition and variables, ensuring they are available when the model is loaded. This feature simplifies the management and distribution of models that rely on external resources. ## Deployment Options with TF SavedModel @@ -42,7 +42,7 @@ TF SavedModel provides a range of options to deploy your machine learning models - **Mobile and Embedded Devices:** TensorFlow Lite, a lightweight solution for running machine learning models on mobile, embedded, and IoT devices, supports converting TF SavedModels to the TensorFlow Lite format. This allows you to deploy your models on a wide range of devices, from smartphones and tablets to microcontrollers and edge devices. -- **TensorFlow Runtime:** TensorFlow Runtime (`tfrt`) is a high-performance runtime for executing TensorFlow graphs. It provides lower-level APIs for loading and running TF SavedModels in C++ environments. TensorFlow Runtime offers better performance compared to the standard TensorFlow runtime. It is suitable for deployment scenarios that require low-latency inference and tight integration with existing C++ codebases. +- **TensorFlow Runtime:** TensorFlow Runtime (`tfrt`) is a high-performance runtime for executing [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) graphs. It provides lower-level APIs for loading and running TF SavedModels in C++ environments. TensorFlow Runtime offers better performance compared to the standard TensorFlow runtime. It is suitable for deployment scenarios that require low-latency inference and tight integration with existing C++ codebases. ## Exporting YOLOv8 Models to TF SavedModel @@ -157,7 +157,7 @@ Refer to the [Ultralytics Export documentation](../modes/export.md) for more det ### Why should I use the TensorFlow SavedModel format? -The TensorFlow SavedModel format offers several advantages for model deployment: +The TensorFlow SavedModel format offers several advantages for [model deployment](https://www.ultralytics.com/glossary/model-deployment): - **Portability:** It provides a language-neutral format, making it easy to share and deploy models across different environments. - **Compatibility:** Integrates seamlessly with tools like TensorFlow Serving, TensorFlow Lite, and TensorFlow.js, which are essential for deploying models on various platforms, including web and mobile applications. diff --git a/docs/en/integrations/tfjs.md b/docs/en/integrations/tfjs.md index 726bba251e..ea2d613c62 100644 --- a/docs/en/integrations/tfjs.md +++ b/docs/en/integrations/tfjs.md @@ -6,9 +6,9 @@ keywords: YOLOv8, TensorFlow.js, TF.js, model export, machine learning, object d # Export to TF.js Model Format From a YOLOv8 Model Format -Deploying machine learning models directly in the browser or on Node.js can be tricky. You'll need to make sure your model format is optimized for faster performance so that the model can be used to run interactive applications locally on the user's device. The TensorFlow.js, or TF.js, model format is designed to use minimal power while delivering fast performance. +Deploying [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models directly in the browser or on Node.js can be tricky. You'll need to make sure your model format is optimized for faster performance so that the model can be used to run interactive applications locally on the user's device. The TensorFlow.js, or TF.js, model format is designed to use minimal power while delivering fast performance. -The 'export to TF.js model format' feature allows you to optimize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for high-speed and locally-run object detection inference. In this guide, we'll walk you through converting your models to the TF.js format, making it easier for your models to perform well on various local browsers and Node.js applications. +The 'export to TF.js model format' feature allows you to optimize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for high-speed and locally-run [object detection](https://www.ultralytics.com/glossary/object-detection) inference. In this guide, we'll walk you through converting your models to the TF.js format, making it easier for your models to perform well on various local browsers and Node.js applications. ## Why Should You Export to TF.js? @@ -18,7 +18,7 @@ Exporting your machine learning models to TensorFlow.js, developed by the Tensor TF.js Architecture

-Running models locally also reduces latency and provides a more responsive user experience. TensorFlow.js also comes with offline capabilities, allowing users to use your application even without an internet connection. TF.js is designed for efficient execution of complex models on devices with limited resources as it is engineered for scalability, with GPU acceleration support. +Running models locally also reduces latency and provides a more responsive user experience. [TensorFlow](https://www.ultralytics.com/glossary/tensorflow).js also comes with offline capabilities, allowing users to use your application even without an internet connection. TF.js is designed for efficient execution of complex models on devices with limited resources as it is engineered for scalability, with GPU acceleration support. ## Key Features of TF.js diff --git a/docs/en/integrations/tflite.md b/docs/en/integrations/tflite.md index db8b033844..028675eabb 100644 --- a/docs/en/integrations/tflite.md +++ b/docs/en/integrations/tflite.md @@ -10,9 +10,9 @@ keywords: YOLOv8, TFLite, model export, TensorFlow Lite, edge devices, deploymen TFLite Logo

-Deploying computer vision models on edge devices or embedded devices requires a format that can ensure seamless performance. +Deploying [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) models on edge devices or embedded devices requires a format that can ensure seamless performance. -The TensorFlow Lite or TFLite export format allows you to optimize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for tasks like object detection and image classification in edge device-based applications. In this guide, we'll walk through the steps for converting your models to the TFLite format, making it easier for your models to perform well on various edge devices. +The TensorFlow Lite or TFLite export format allows you to optimize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for tasks like [object detection](https://www.ultralytics.com/glossary/object-detection) and [image classification](https://www.ultralytics.com/glossary/image-classification) in edge device-based applications. In this guide, we'll walk through the steps for converting your models to the TFLite format, making it easier for your models to perform well on various edge devices. ## Why should you export to TFLite? @@ -107,7 +107,7 @@ For more details about the export process, visit the [Ultralytics documentation After successfully exporting your Ultralytics YOLOv8 models to TFLite format, you can now deploy them. The primary and recommended first step for running a TFLite model is to utilize the YOLO("model.tflite") method, as outlined in the previous usage code snippet. However, for in-depth instructions on deploying your TFLite models in various other settings, take a look at the following resources: -- **[Android](https://ai.google.dev/edge/litert/android)**: A quick start guide for integrating TensorFlow Lite into Android applications, providing easy-to-follow steps for setting up and running machine learning models. +- **[Android](https://ai.google.dev/edge/litert/android)**: A quick start guide for integrating [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) Lite into Android applications, providing easy-to-follow steps for setting up and running [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models. - **[iOS](https://ai.google.dev/edge/litert/ios/quickstart)**: Check out this detailed guide for developers on integrating and deploying TensorFlow Lite models in iOS applications, offering step-by-step instructions and resources. @@ -115,7 +115,7 @@ After successfully exporting your Ultralytics YOLOv8 models to TFLite format, yo ## Summary -In this guide, we focused on how to export to TFLite format. By converting your Ultralytics YOLOv8 models to TFLite model format, you can improve the efficiency and speed of YOLOv8 models, making them more effective and suitable for edge computing environments. +In this guide, we focused on how to export to TFLite format. By converting your Ultralytics YOLOv8 models to TFLite model format, you can improve the efficiency and speed of YOLOv8 models, making them more effective and suitable for [edge computing](https://www.ultralytics.com/glossary/edge-computing) environments. For further details on usage, visit the [TFLite official documentation](https://ai.google.dev/edge/litert). @@ -151,9 +151,9 @@ yolo export model=yolov8n.pt format=tflite # creates 'yolov8n_float32.tflite' For more details, visit the [Ultralytics export guide](../modes/export.md). -### What are the benefits of using TensorFlow Lite for YOLOv8 model deployment? +### What are the benefits of using TensorFlow Lite for YOLOv8 [model deployment](https://www.ultralytics.com/glossary/model-deployment)? -TensorFlow Lite (TFLite) is an open-source deep learning framework designed for on-device inference, making it ideal for deploying YOLOv8 models on mobile, embedded, and IoT devices. Key benefits include: +TensorFlow Lite (TFLite) is an open-source [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) framework designed for on-device inference, making it ideal for deploying YOLOv8 models on mobile, embedded, and IoT devices. Key benefits include: - **On-device optimization**: Minimize latency and enhance privacy by processing data locally. - **Platform compatibility**: Supports Android, iOS, embedded Linux, and MCU. diff --git a/docs/en/integrations/torchscript.md b/docs/en/integrations/torchscript.md index 138f975e1c..839caff921 100644 --- a/docs/en/integrations/torchscript.md +++ b/docs/en/integrations/torchscript.md @@ -6,7 +6,7 @@ keywords: YOLOv8, TorchScript, model export, Ultralytics, PyTorch, deep learning # YOLOv8 Model Export to TorchScript for Quick Deployment -Deploying computer vision models across different environments, including embedded systems, web browsers, or platforms with limited Python support, requires a flexible and portable solution. TorchScript focuses on portability and the ability to run models in environments where the entire Python framework is unavailable. This makes it ideal for scenarios where you need to deploy your computer vision capabilities across various devices or platforms. +Deploying [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) models across different environments, including embedded systems, web browsers, or platforms with limited Python support, requires a flexible and portable solution. TorchScript focuses on portability and the ability to run models in environments where the entire Python framework is unavailable. This makes it ideal for scenarios where you need to deploy your computer vision capabilities across various devices or platforms. Export to Torchscript to serialize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for cross-platform compatibility and streamlined deployment. In this guide, we'll show you how to export your YOLOv8 models to the TorchScript format, making it easier for you to use them across a wider range of applications. @@ -24,7 +24,7 @@ TorchScript models can also be optimized through techniques such as operator fus ## Key Features of TorchScript Models -TorchScript, a key part of the PyTorch ecosystem, provides powerful features for optimizing and deploying deep learning models. +TorchScript, a key part of the PyTorch ecosystem, provides powerful features for optimizing and deploying [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models. ![TorchScript Features](https://github.com/ultralytics/docs/releases/download/0/torchscript-features.avif) @@ -44,11 +44,11 @@ Here are the key features that make TorchScript a valuable tool for developers: Before we look at the code for exporting YOLOv8 models to the TorchScript format, let's understand where TorchScript models are normally used. -TorchScript offers various deployment options for machine learning models, such as: +TorchScript offers various deployment options for [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models, such as: - **C++ API**: The most common use case for TorchScript is its C++ API, which allows you to load and execute optimized TorchScript models directly within C++ applications. This is ideal for production environments where Python may not be suitable or available. The C++ API offers low-overhead and efficient execution of TorchScript models, maximizing performance potential. -- **Mobile Deployment**: TorchScript offers tools for converting models into formats readily deployable on mobile devices. PyTorch Mobile provides a runtime for executing these models within iOS and Android apps. This enables low-latency, offline inference capabilities, enhancing user experience and data privacy. +- **Mobile Deployment**: TorchScript offers tools for converting models into formats readily deployable on mobile devices. PyTorch Mobile provides a runtime for executing these models within iOS and Android apps. This enables low-latency, offline inference capabilities, enhancing user experience and [data privacy](https://www.ultralytics.com/glossary/data-privacy). - **Cloud Deployment**: TorchScript models can be deployed to cloud-based servers using solutions like TorchServe. It provides features like model versioning, batching, and metrics monitoring for scalable deployment in production environments. Cloud deployment with TorchScript can make your models accessible via APIs or other web services. @@ -111,7 +111,7 @@ For more details about the export process, visit the [Ultralytics documentation After successfully exporting your Ultralytics YOLOv8 models to TorchScript format, you can now deploy them. The primary and recommended first step for running a TorchScript model is to utilize the YOLO("model.torchscript") method, as outlined in the previous usage code snippet. However, for in-depth instructions on deploying your TorchScript models in various other settings, take a look at the following resources: -- **[Explore Mobile Deployment](https://pytorch.org/mobile/home/)**: The PyTorch Mobile Documentation provides comprehensive guidelines for deploying models on mobile devices, ensuring your applications are efficient and responsive. +- **[Explore Mobile Deployment](https://pytorch.org/mobile/home/)**: The [PyTorch](https://www.ultralytics.com/glossary/pytorch) Mobile Documentation provides comprehensive guidelines for deploying models on mobile devices, ensuring your applications are efficient and responsive. - **[Master Server-Side Deployment](https://pytorch.org/serve/getting_started.html)**: Learn how to deploy models server-side with TorchServe, offering a step-by-step tutorial for scalable, efficient model serving. diff --git a/docs/en/integrations/vscode.md b/docs/en/integrations/vscode.md index 71c4dce808..b6785d1529 100644 --- a/docs/en/integrations/vscode.md +++ b/docs/en/integrations/vscode.md @@ -15,7 +15,7 @@ keywords: Visual Studio Code, VS Code, deep learning, convolutional neural netwo ## Features and Benefits -✅ Are you a data scientist or machine learning engineer building computer vision applications with Ultralytics? +✅ Are you a data scientist or [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) engineer building computer vision applications with Ultralytics? ✅ Do you despise writing the same blocks of code repeatedly? @@ -207,7 +207,7 @@ The best way to find out what snippets are available is to download and install ## Conclusion -The Ultralytics-Snippets extension for VS Code is designed to empower data scientists and machine learning engineers to build computer vision applications using Ultralytics YOLO more efficiently. By providing pre-built code snippets and useful examples, we help you focus on what matters most: creating innovative solutions. Please share your feedback by visiting the [extension page on the VS Code marketplace] and leaving a review. ⭐ +The Ultralytics-Snippets extension for VS Code is designed to empower data scientists and machine learning engineers to build [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) applications using Ultralytics YOLO more efficiently. By providing pre-built code snippets and useful examples, we help you focus on what matters most: creating innovative solutions. Please share your feedback by visiting the [extension page on the VS Code marketplace] and leaving a review. ⭐ ## FAQ diff --git a/docs/en/integrations/weights-biases.md b/docs/en/integrations/weights-biases.md index 232860f92f..cb9dc95131 100644 --- a/docs/en/integrations/weights-biases.md +++ b/docs/en/integrations/weights-biases.md @@ -6,7 +6,7 @@ keywords: YOLOv8, Weights & Biases, model training, experiment tracking, Ultraly # Enhancing YOLOv8 Experiment Tracking and Visualization with Weights & Biases -Object detection models like [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) have become integral to many computer vision applications. However, training, evaluating, and deploying these complex models introduces several challenges. Tracking key training metrics, comparing model variants, analyzing model behavior, and detecting issues require substantial instrumentation and experiment management. +[Object detection](https://www.ultralytics.com/glossary/object-detection) models like [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) have become integral to many [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) applications. However, training, evaluating, and deploying these complex models introduces several challenges. Tracking key training metrics, comparing model variants, analyzing model behavior, and detecting issues require substantial instrumentation and experiment management.


@@ -27,7 +27,7 @@ This guide showcases Ultralytics YOLOv8 integration with Weights & Biases' for e Weights & Biases Overview

-[Weights & Biases](https://wandb.ai/site) is a cutting-edge MLOps platform designed for tracking, visualizing, and managing machine learning experiments. It features automatic logging of training metrics for full experiment reproducibility, an interactive UI for streamlined data analysis, and efficient model management tools for deploying across various environments. +[Weights & Biases](https://wandb.ai/site) is a cutting-edge MLOps platform designed for tracking, visualizing, and managing [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) experiments. It features automatic logging of training metrics for full experiment reproducibility, an interactive UI for streamlined data analysis, and efficient model management tools for deploying across various environments. ## YOLOv8 Training with Weights & Biases @@ -112,7 +112,7 @@ Let's understand the steps showcased in the usage code snippet above. - **Step 3: Add Weights & Biases Callback for Ultralytics**: This step is crucial as it enables the automatic logging of training metrics and validation results to Weights & Biases, providing a detailed view of the model's performance. -- **Step 4: Train and Fine-Tune the Model**: Begin training the model with the specified dataset, number of epochs, and image size. The training process includes logging of metrics and predictions at the end of each epoch, offering a comprehensive view of the model's learning progress. +- **Step 4: Train and Fine-Tune the Model**: Begin training the model with the specified dataset, number of epochs, and image size. The training process includes logging of metrics and predictions at the end of each [epoch](https://www.ultralytics.com/glossary/epoch), offering a comprehensive view of the model's learning progress. - **Step 5: Validate the Model**: After training, the model is validated. This step is crucial for assessing the model's performance on unseen data and ensuring its generalizability. @@ -126,8 +126,8 @@ Upon running the usage code snippet above, you can expect the following key outp - The setup of a new run with its unique ID, indicating the start of the training process. - A concise summary of the model's structure, including the number of layers and parameters. -- Regular updates on important metrics such as box loss, cls loss, dfl loss, precision, recall, and mAP scores during each training epoch. -- At the end of training, detailed metrics including the model's inference speed, and overall accuracy metrics are displayed. +- Regular updates on important metrics such as box loss, cls loss, dfl loss, [precision](https://www.ultralytics.com/glossary/precision), [recall](https://www.ultralytics.com/glossary/recall), and mAP scores during each training epoch. +- At the end of training, detailed metrics including the model's inference speed, and overall [accuracy](https://www.ultralytics.com/glossary/accuracy) metrics are displayed. - Links to the Weights & Biases dashboard for in-depth analysis and visualization of the training process, along with information on local log file locations. ### Viewing the Weights & Biases Dashboard @@ -138,7 +138,7 @@ After running the usage code snippet, you can access the Weights & Biases (W&B) - **Real-Time Metrics Tracking**: Observe metrics like loss, accuracy, and validation scores as they evolve during the training, offering immediate insights for model tuning. [See how experiments are tracked using Weights & Biases](https://imgur.com/D6NVnmN). -- **Hyperparameter Optimization**: Weights & Biases aids in fine-tuning critical parameters such as learning rate, batch size, and more, enhancing the performance of YOLOv8. +- **Hyperparameter Optimization**: Weights & Biases aids in fine-tuning critical parameters such as [learning rate](https://www.ultralytics.com/glossary/learning-rate), batch size, and more, enhancing the performance of YOLOv8. - **Comparative Analysis**: The platform allows side-by-side comparisons of different training runs, essential for assessing the impact of various model configurations. @@ -177,7 +177,7 @@ For further guidance on installation steps, refer to our [YOLOv8 Installation gu Integrating Ultralytics YOLOv8 with Weights & Biases offers several benefits including: - **Real-Time Metrics Tracking:** Observe metric changes during training for immediate insights. -- **Hyperparameter Optimization:** Improve model performance by fine-tuning learning rate, batch size, etc. +- **Hyperparameter Optimization:** Improve model performance by fine-tuning learning rate, [batch size](https://www.ultralytics.com/glossary/batch-size), etc. - **Comparative Analysis:** Side-by-side comparison of different training runs. - **Resource Monitoring:** Keep track of CPU, GPU, and memory usage. - **Model Artifacts Management:** Easy access and sharing of model checkpoints. @@ -238,7 +238,7 @@ Ultralytics YOLOv8 integrated with Weights & Biases offers several unique advant - **High Efficiency:** Real-time tracking of training metrics and performance optimization. - **Scalability:** Easily manage large-scale training jobs with robust resource monitoring and utilization tools. -- **Interactivity:** A user-friendly interactive UI for data visualization and model management. +- **Interactivity:** A user-friendly interactive UI for [data visualization](https://www.ultralytics.com/glossary/data-visualization) and model management. - **Community and Support:** Strong integration documentation and community support with flexible customization and enhancement options. For comparisons with other platforms like Comet and ClearML, refer to [Ultralytics integrations](../integrations/index.md). diff --git a/docs/en/macros/export-args.md b/docs/en/macros/export-args.md index e87e4bb1ba..99dd5f4d0a 100644 --- a/docs/en/macros/export-args.md +++ b/docs/en/macros/export-args.md @@ -1,14 +1,14 @@ -| Argument | Type | Default | Description | -| ----------- | ---------------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `format` | `str` | `'torchscript'` | Target format for the exported model, such as `'onnx'`, `'torchscript'`, `'tensorflow'`, or others, defining compatibility with various deployment environments. | -| `imgsz` | `int` or `tuple` | `640` | Desired image size for the model input. Can be an integer for square images or a tuple `(height, width)` for specific dimensions. | -| `keras` | `bool` | `False` | Enables export to Keras format for TensorFlow SavedModel, providing compatibility with TensorFlow serving and APIs. | -| `optimize` | `bool` | `False` | Applies optimization for mobile devices when exporting to TorchScript, potentially reducing model size and improving performance. | -| `half` | `bool` | `False` | Enables FP16 (half-precision) quantization, reducing model size and potentially speeding up inference on supported hardware. | -| `int8` | `bool` | `False` | Activates INT8 quantization, further compressing the model and speeding up inference with minimal accuracy loss, primarily for edge devices. | -| `dynamic` | `bool` | `False` | Allows dynamic input sizes for ONNX, TensorRT and OpenVINO exports, enhancing flexibility in handling varying image dimensions. | -| `simplify` | `bool` | `False` | Simplifies the model graph for ONNX exports with `onnxslim`, potentially improving performance and compatibility. | -| `opset` | `int` | `None` | Specifies the ONNX opset version for compatibility with different ONNX parsers and runtimes. If not set, uses the latest supported version. | -| `workspace` | `float` | `4.0` | Sets the maximum workspace size in GiB for TensorRT optimizations, balancing memory usage and performance. | -| `nms` | `bool` | `False` | Adds Non-Maximum Suppression (NMS) to the CoreML export, essential for accurate and efficient detection post-processing. | -| `batch` | `int` | `1` | Specifies export model batch inference size or the max number of images the exported model will process concurrently in `predict` mode. | +| Argument | Type | Default | Description | +| ----------- | ---------------- | --------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `format` | `str` | `'torchscript'` | Target format for the exported model, such as `'onnx'`, `'torchscript'`, `'tensorflow'`, or others, defining compatibility with various deployment environments. | +| `imgsz` | `int` or `tuple` | `640` | Desired image size for the model input. Can be an integer for square images or a tuple `(height, width)` for specific dimensions. | +| `keras` | `bool` | `False` | Enables export to Keras format for [TensorFlow](https://www.ultralytics.com/glossary/tensorflow) SavedModel, providing compatibility with TensorFlow serving and APIs. | +| `optimize` | `bool` | `False` | Applies optimization for mobile devices when exporting to TorchScript, potentially reducing model size and improving performance. | +| `half` | `bool` | `False` | Enables FP16 (half-precision) quantization, reducing model size and potentially speeding up inference on supported hardware. | +| `int8` | `bool` | `False` | Activates INT8 quantization, further compressing the model and speeding up inference with minimal [accuracy](https://www.ultralytics.com/glossary/accuracy) loss, primarily for edge devices. | +| `dynamic` | `bool` | `False` | Allows dynamic input sizes for ONNX, TensorRT and OpenVINO exports, enhancing flexibility in handling varying image dimensions. | +| `simplify` | `bool` | `True` | Simplifies the model graph for ONNX exports with `onnxslim`, potentially improving performance and compatibility. | +| `opset` | `int` | `None` | Specifies the ONNX opset version for compatibility with different ONNX parsers and runtimes. If not set, uses the latest supported version. | +| `workspace` | `float` | `4.0` | Sets the maximum workspace size in GiB for TensorRT optimizations, balancing memory usage and performance. | +| `nms` | `bool` | `False` | Adds Non-Maximum Suppression (NMS) to the CoreML export, essential for accurate and efficient detection post-processing. | +| `batch` | `int` | `1` | Specifies export model batch inference size or the max number of images the exported model will process concurrently in `predict` mode. | diff --git a/docs/en/macros/predict-args.md b/docs/en/macros/predict-args.md index 0ad0c90163..f977a30a2f 100644 --- a/docs/en/macros/predict-args.md +++ b/docs/en/macros/predict-args.md @@ -1,17 +1,17 @@ -| Argument | Type | Default | Description | -| --------------- | -------------- | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| `source` | `str` | `'ultralytics/assets'` | Specifies the data source for inference. Can be an image path, video file, directory, URL, or device ID for live feeds. Supports a wide range of formats and sources, enabling flexible application across different types of input. | -| `conf` | `float` | `0.25` | Sets the minimum confidence threshold for detections. Objects detected with confidence below this threshold will be disregarded. Adjusting this value can help reduce false positives. | -| `iou` | `float` | `0.7` | Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Lower values result in fewer detections by eliminating overlapping boxes, useful for reducing duplicates. | -| `imgsz` | `int or tuple` | `640` | Defines the image size for inference. Can be a single integer `640` for square resizing or a (height, width) tuple. Proper sizing can improve detection accuracy and processing speed. | -| `half` | `bool` | `False` | Enables half-precision (FP16) inference, which can speed up model inference on supported GPUs with minimal impact on accuracy. | -| `device` | `str` | `None` | Specifies the device for inference (e.g., `cpu`, `cuda:0` or `0`). Allows users to select between CPU, a specific GPU, or other compute devices for model execution. | -| `max_det` | `int` | `300` | Maximum number of detections allowed per image. Limits the total number of objects the model can detect in a single inference, preventing excessive outputs in dense scenes. | -| `vid_stride` | `int` | `1` | Frame stride for video inputs. Allows skipping frames in videos to speed up processing at the cost of temporal resolution. A value of 1 processes every frame, higher values skip frames. | -| `stream_buffer` | `bool` | `False` | Determines if all frames should be buffered when processing video streams (`True`), or if the model should return the most recent frame (`False`). Useful for real-time applications. | -| `visualize` | `bool` | `False` | Activates visualization of model features during inference, providing insights into what the model is "seeing". Useful for debugging and model interpretation. | -| `augment` | `bool` | `False` | Enables test-time augmentation (TTA) for predictions, potentially improving detection robustness at the cost of inference speed. | -| `agnostic_nms` | `bool` | `False` | Enables class-agnostic Non-Maximum Suppression (NMS), which merges overlapping boxes of different classes. Useful in multi-class detection scenarios where class overlap is common. | -| `classes` | `list[int]` | `None` | Filters predictions to a set of class IDs. Only detections belonging to the specified classes will be returned. Useful for focusing on relevant objects in multi-class detection tasks. | -| `retina_masks` | `bool` | `False` | Uses high-resolution segmentation masks if available in the model. This can enhance mask quality for segmentation tasks, providing finer detail. | -| `embed` | `list[int]` | `None` | Specifies the layers from which to extract feature vectors or embeddings. Useful for downstream tasks like clustering or similarity search. | +| Argument | Type | Default | Description | +| --------------- | -------------- | ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `source` | `str` | `'ultralytics/assets'` | Specifies the data source for inference. Can be an image path, video file, directory, URL, or device ID for live feeds. Supports a wide range of formats and sources, enabling flexible application across different types of input. | +| `conf` | `float` | `0.25` | Sets the minimum confidence threshold for detections. Objects detected with confidence below this threshold will be disregarded. Adjusting this value can help reduce false positives. | +| `iou` | `float` | `0.7` | [Intersection Over Union](https://www.ultralytics.com/glossary/intersection-over-union-iou) (IoU) threshold for Non-Maximum Suppression (NMS). Lower values result in fewer detections by eliminating overlapping boxes, useful for reducing duplicates. | +| `imgsz` | `int or tuple` | `640` | Defines the image size for inference. Can be a single integer `640` for square resizing or a (height, width) tuple. Proper sizing can improve detection [accuracy](https://www.ultralytics.com/glossary/accuracy) and processing speed. | +| `half` | `bool` | `False` | Enables half-[precision](https://www.ultralytics.com/glossary/precision) (FP16) inference, which can speed up model inference on supported GPUs with minimal impact on accuracy. | +| `device` | `str` | `None` | Specifies the device for inference (e.g., `cpu`, `cuda:0` or `0`). Allows users to select between CPU, a specific GPU, or other compute devices for model execution. | +| `max_det` | `int` | `300` | Maximum number of detections allowed per image. Limits the total number of objects the model can detect in a single inference, preventing excessive outputs in dense scenes. | +| `vid_stride` | `int` | `1` | Frame stride for video inputs. Allows skipping frames in videos to speed up processing at the cost of temporal resolution. A value of 1 processes every frame, higher values skip frames. | +| `stream_buffer` | `bool` | `False` | Determines if all frames should be buffered when processing video streams (`True`), or if the model should return the most recent frame (`False`). Useful for real-time applications. | +| `visualize` | `bool` | `False` | Activates visualization of model features during inference, providing insights into what the model is "seeing". Useful for debugging and model interpretation. | +| `augment` | `bool` | `False` | Enables test-time augmentation (TTA) for predictions, potentially improving detection robustness at the cost of inference speed. | +| `agnostic_nms` | `bool` | `False` | Enables class-agnostic Non-Maximum Suppression (NMS), which merges overlapping boxes of different classes. Useful in multi-class detection scenarios where class overlap is common. | +| `classes` | `list[int]` | `None` | Filters predictions to a set of class IDs. Only detections belonging to the specified classes will be returned. Useful for focusing on relevant objects in multi-class detection tasks. | +| `retina_masks` | `bool` | `False` | Uses high-resolution segmentation masks if available in the model. This can enhance mask quality for segmentation tasks, providing finer detail. | +| `embed` | `list[int]` | `None` | Specifies the layers from which to extract feature vectors or [embeddings](https://www.ultralytics.com/glossary/embeddings). Useful for downstream tasks like clustering or similarity search. | diff --git a/docs/en/macros/track-args.md b/docs/en/macros/track-args.md index 2d3a7c8aff..a6678b7066 100644 --- a/docs/en/macros/track-args.md +++ b/docs/en/macros/track-args.md @@ -1,9 +1,9 @@ -| Argument | Type | Default | Description | -| --------- | ------- | -------------- | ---------------------------------------------------------------------------------------------------------------------------- | -| `source` | `str` | `None` | Specifies the source directory for images or videos. Supports file paths and URLs. | -| `persist` | `bool` | `False` | Enables persistent tracking of objects between frames, maintaining IDs across video sequences. | -| `tracker` | `str` | `botsort.yaml` | Specifies the tracking algorithm to use, e.g., `bytetrack.yaml` or `botsort.yaml`. | -| `conf` | `float` | `0.3` | Sets the confidence threshold for detections; lower values allow more objects to be tracked but may include false positives. | -| `iou` | `float` | `0.5` | Sets the Intersection over Union (IoU) threshold for filtering overlapping detections. | -| `classes` | `list` | `None` | Filters results by class index. For example, `classes=[0, 2, 3]` only tracks the specified classes. | -| `verbose` | `bool` | `True` | Controls the display of tracking results, providing a visual output of tracked objects. | +| Argument | Type | Default | Description | +| --------- | ------- | -------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `source` | `str` | `None` | Specifies the source directory for images or videos. Supports file paths and URLs. | +| `persist` | `bool` | `False` | Enables persistent tracking of objects between frames, maintaining IDs across video sequences. | +| `tracker` | `str` | `botsort.yaml` | Specifies the tracking algorithm to use, e.g., `bytetrack.yaml` or `botsort.yaml`. | +| `conf` | `float` | `0.3` | Sets the confidence threshold for detections; lower values allow more objects to be tracked but may include false positives. | +| `iou` | `float` | `0.5` | Sets the [Intersection over Union](https://www.ultralytics.com/glossary/intersection-over-union-iou) (IoU) threshold for filtering overlapping detections. | +| `classes` | `list` | `None` | Filters results by class index. For example, `classes=[0, 2, 3]` only tracks the specified classes. | +| `verbose` | `bool` | `True` | Controls the display of tracking results, providing a visual output of tracked objects. | diff --git a/docs/en/macros/train-args.md b/docs/en/macros/train-args.md index d072003f2c..cb72bdeced 100644 --- a/docs/en/macros/train-args.md +++ b/docs/en/macros/train-args.md @@ -1,50 +1,50 @@ -| Argument | Default | Description | -| ----------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `model` | `None` | Specifies the model file for training. Accepts a path to either a `.pt` pretrained model or a `.yaml` configuration file. Essential for defining the model structure or initializing weights. | -| `data` | `None` | Path to the dataset configuration file (e.g., `coco8.yaml`). This file contains dataset-specific parameters, including paths to training and validation data, class names, and number of classes. | -| `epochs` | `100` | Total number of training epochs. Each epoch represents a full pass over the entire dataset. Adjusting this value can affect training duration and model performance. | -| `time` | `None` | Maximum training time in hours. If set, this overrides the `epochs` argument, allowing training to automatically stop after the specified duration. Useful for time-constrained training scenarios. | -| `patience` | `100` | Number of epochs to wait without improvement in validation metrics before early stopping the training. Helps prevent overfitting by stopping training when performance plateaus. | -| `batch` | `16` | Batch size, with three modes: set as an integer (e.g., `batch=16`), auto mode for 60% GPU memory utilization (`batch=-1`), or auto mode with specified utilization fraction (`batch=0.70`). | -| `imgsz` | `640` | Target image size for training. All images are resized to this dimension before being fed into the model. Affects model accuracy and computational complexity. | -| `save` | `True` | Enables saving of training checkpoints and final model weights. Useful for resuming training or model deployment. | -| `save_period` | `-1` | Frequency of saving model checkpoints, specified in epochs. A value of -1 disables this feature. Useful for saving interim models during long training sessions. | -| `cache` | `False` | Enables caching of dataset images in memory (`True`/`ram`), on disk (`disk`), or disables it (`False`). Improves training speed by reducing disk I/O at the cost of increased memory usage. | -| `device` | `None` | Specifies the computational device(s) for training: a single GPU (`device=0`), multiple GPUs (`device=0,1`), CPU (`device=cpu`), or MPS for Apple silicon (`device=mps`). | -| `workers` | `8` | Number of worker threads for data loading (per `RANK` if Multi-GPU training). Influences the speed of data preprocessing and feeding into the model, especially useful in multi-GPU setups. | -| `project` | `None` | Name of the project directory where training outputs are saved. Allows for organized storage of different experiments. | -| `name` | `None` | Name of the training run. Used for creating a subdirectory within the project folder, where training logs and outputs are stored. | -| `exist_ok` | `False` | If True, allows overwriting of an existing project/name directory. Useful for iterative experimentation without needing to manually clear previous outputs. | -| `pretrained` | `True` | Determines whether to start training from a pretrained model. Can be a boolean value or a string path to a specific model from which to load weights. Enhances training efficiency and model performance. | -| `optimizer` | `'auto'` | Choice of optimizer for training. Options include `SGD`, `Adam`, `AdamW`, `NAdam`, `RAdam`, `RMSProp` etc., or `auto` for automatic selection based on model configuration. Affects convergence speed and stability. | -| `verbose` | `False` | Enables verbose output during training, providing detailed logs and progress updates. Useful for debugging and closely monitoring the training process. | -| `seed` | `0` | Sets the random seed for training, ensuring reproducibility of results across runs with the same configurations. | -| `deterministic` | `True` | Forces deterministic algorithm use, ensuring reproducibility but may affect performance and speed due to the restriction on non-deterministic algorithms. | -| `single_cls` | `False` | Treats all classes in multi-class datasets as a single class during training. Useful for binary classification tasks or when focusing on object presence rather than classification. | -| `rect` | `False` | Enables rectangular training, optimizing batch composition for minimal padding. Can improve efficiency and speed but may affect model accuracy. | -| `cos_lr` | `False` | Utilizes a cosine learning rate scheduler, adjusting the learning rate following a cosine curve over epochs. Helps in managing learning rate for better convergence. | -| `close_mosaic` | `10` | Disables mosaic data augmentation in the last N epochs to stabilize training before completion. Setting to 0 disables this feature. | -| `resume` | `False` | Resumes training from the last saved checkpoint. Automatically loads model weights, optimizer state, and epoch count, continuing training seamlessly. | -| `amp` | `True` | Enables Automatic Mixed Precision (AMP) training, reducing memory usage and possibly speeding up training with minimal impact on accuracy. | -| `fraction` | `1.0` | Specifies the fraction of the dataset to use for training. Allows for training on a subset of the full dataset, useful for experiments or when resources are limited. | -| `profile` | `False` | Enables profiling of ONNX and TensorRT speeds during training, useful for optimizing model deployment. | -| `freeze` | `None` | Freezes the first N layers of the model or specified layers by index, reducing the number of trainable parameters. Useful for fine-tuning or transfer learning. | -| `lr0` | `0.01` | Initial learning rate (i.e. `SGD=1E-2`, `Adam=1E-3`) . Adjusting this value is crucial for the optimization process, influencing how rapidly model weights are updated. | -| `lrf` | `0.01` | Final learning rate as a fraction of the initial rate = (`lr0 * lrf`), used in conjunction with schedulers to adjust the learning rate over time. | -| `momentum` | `0.937` | Momentum factor for SGD or beta1 for Adam optimizers, influencing the incorporation of past gradients in the current update. | -| `weight_decay` | `0.0005` | L2 regularization term, penalizing large weights to prevent overfitting. | -| `warmup_epochs` | `3.0` | Number of epochs for learning rate warmup, gradually increasing the learning rate from a low value to the initial learning rate to stabilize training early on. | -| `warmup_momentum` | `0.8` | Initial momentum for warmup phase, gradually adjusting to the set momentum over the warmup period. | -| `warmup_bias_lr` | `0.1` | Learning rate for bias parameters during the warmup phase, helping stabilize model training in the initial epochs. | -| `box` | `7.5` | Weight of the box loss component in the loss function, influencing how much emphasis is placed on accurately predicting bounding box coordinates. | -| `cls` | `0.5` | Weight of the classification loss in the total loss function, affecting the importance of correct class prediction relative to other components. | -| `dfl` | `1.5` | Weight of the distribution focal loss, used in certain YOLO versions for fine-grained classification. | -| `pose` | `12.0` | Weight of the pose loss in models trained for pose estimation, influencing the emphasis on accurately predicting pose keypoints. | -| `kobj` | `2.0` | Weight of the keypoint objectness loss in pose estimation models, balancing detection confidence with pose accuracy. | -| `label_smoothing` | `0.0` | Applies label smoothing, softening hard labels to a mix of the target label and a uniform distribution over labels, can improve generalization. | -| `nbs` | `64` | Nominal batch size for normalization of loss. | -| `overlap_mask` | `True` | Determines whether segmentation masks should overlap during training, applicable in instance segmentation tasks. | -| `mask_ratio` | `4` | Downsample ratio for segmentation masks, affecting the resolution of masks used during training. | -| `dropout` | `0.0` | Dropout rate for regularization in classification tasks, preventing overfitting by randomly omitting units during training. | -| `val` | `True` | Enables validation during training, allowing for periodic evaluation of model performance on a separate dataset. | -| `plots` | `False` | Generates and saves plots of training and validation metrics, as well as prediction examples, providing visual insights into model performance and learning progression. | +| Argument | Default | Description | +| ----------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `model` | `None` | Specifies the model file for training. Accepts a path to either a `.pt` pretrained model or a `.yaml` configuration file. Essential for defining the model structure or initializing weights. | +| `data` | `None` | Path to the dataset configuration file (e.g., `coco8.yaml`). This file contains dataset-specific parameters, including paths to training and [validation data](https://www.ultralytics.com/glossary/validation-data), class names, and number of classes. | +| `epochs` | `100` | Total number of training epochs. Each [epoch](https://www.ultralytics.com/glossary/epoch) represents a full pass over the entire dataset. Adjusting this value can affect training duration and model performance. | +| `time` | `None` | Maximum training time in hours. If set, this overrides the `epochs` argument, allowing training to automatically stop after the specified duration. Useful for time-constrained training scenarios. | +| `patience` | `100` | Number of epochs to wait without improvement in validation metrics before early stopping the training. Helps prevent [overfitting](https://www.ultralytics.com/glossary/overfitting) by stopping training when performance plateaus. | +| `batch` | `16` | [Batch size](https://www.ultralytics.com/glossary/batch-size), with three modes: set as an integer (e.g., `batch=16`), auto mode for 60% GPU memory utilization (`batch=-1`), or auto mode with specified utilization fraction (`batch=0.70`). | +| `imgsz` | `640` | Target image size for training. All images are resized to this dimension before being fed into the model. Affects model [accuracy](https://www.ultralytics.com/glossary/accuracy) and computational complexity. | +| `save` | `True` | Enables saving of training checkpoints and final model weights. Useful for resuming training or [model deployment](https://www.ultralytics.com/glossary/model-deployment). | +| `save_period` | `-1` | Frequency of saving model checkpoints, specified in epochs. A value of -1 disables this feature. Useful for saving interim models during long training sessions. | +| `cache` | `False` | Enables caching of dataset images in memory (`True`/`ram`), on disk (`disk`), or disables it (`False`). Improves training speed by reducing disk I/O at the cost of increased memory usage. | +| `device` | `None` | Specifies the computational device(s) for training: a single GPU (`device=0`), multiple GPUs (`device=0,1`), CPU (`device=cpu`), or MPS for Apple silicon (`device=mps`). | +| `workers` | `8` | Number of worker threads for data loading (per `RANK` if Multi-GPU training). Influences the speed of data preprocessing and feeding into the model, especially useful in multi-GPU setups. | +| `project` | `None` | Name of the project directory where training outputs are saved. Allows for organized storage of different experiments. | +| `name` | `None` | Name of the training run. Used for creating a subdirectory within the project folder, where training logs and outputs are stored. | +| `exist_ok` | `False` | If True, allows overwriting of an existing project/name directory. Useful for iterative experimentation without needing to manually clear previous outputs. | +| `pretrained` | `True` | Determines whether to start training from a pretrained model. Can be a boolean value or a string path to a specific model from which to load weights. Enhances training efficiency and model performance. | +| `optimizer` | `'auto'` | Choice of optimizer for training. Options include `SGD`, `Adam`, `AdamW`, `NAdam`, `RAdam`, `RMSProp` etc., or `auto` for automatic selection based on model configuration. Affects convergence speed and stability. | +| `verbose` | `False` | Enables verbose output during training, providing detailed logs and progress updates. Useful for debugging and closely monitoring the training process. | +| `seed` | `0` | Sets the random seed for training, ensuring reproducibility of results across runs with the same configurations. | +| `deterministic` | `True` | Forces deterministic algorithm use, ensuring reproducibility but may affect performance and speed due to the restriction on non-deterministic algorithms. | +| `single_cls` | `False` | Treats all classes in multi-class datasets as a single class during training. Useful for binary classification tasks or when focusing on object presence rather than classification. | +| `rect` | `False` | Enables rectangular training, optimizing batch composition for minimal padding. Can improve efficiency and speed but may affect model accuracy. | +| `cos_lr` | `False` | Utilizes a cosine [learning rate](https://www.ultralytics.com/glossary/learning-rate) scheduler, adjusting the learning rate following a cosine curve over epochs. Helps in managing learning rate for better convergence. | +| `close_mosaic` | `10` | Disables mosaic [data augmentation](https://www.ultralytics.com/glossary/data-augmentation) in the last N epochs to stabilize training before completion. Setting to 0 disables this feature. | +| `resume` | `False` | Resumes training from the last saved checkpoint. Automatically loads model weights, optimizer state, and epoch count, continuing training seamlessly. | +| `amp` | `True` | Enables Automatic [Mixed Precision](https://www.ultralytics.com/glossary/mixed-precision) (AMP) training, reducing memory usage and possibly speeding up training with minimal impact on accuracy. | +| `fraction` | `1.0` | Specifies the fraction of the dataset to use for training. Allows for training on a subset of the full dataset, useful for experiments or when resources are limited. | +| `profile` | `False` | Enables profiling of ONNX and TensorRT speeds during training, useful for optimizing model deployment. | +| `freeze` | `None` | Freezes the first N layers of the model or specified layers by index, reducing the number of trainable parameters. Useful for fine-tuning or [transfer learning](https://www.ultralytics.com/glossary/transfer-learning). | +| `lr0` | `0.01` | Initial learning rate (i.e. `SGD=1E-2`, `Adam=1E-3`) . Adjusting this value is crucial for the optimization process, influencing how rapidly model weights are updated. | +| `lrf` | `0.01` | Final learning rate as a fraction of the initial rate = (`lr0 * lrf`), used in conjunction with schedulers to adjust the learning rate over time. | +| `momentum` | `0.937` | Momentum factor for SGD or beta1 for [Adam optimizers](https://www.ultralytics.com/glossary/adam-optimizer), influencing the incorporation of past gradients in the current update. | +| `weight_decay` | `0.0005` | L2 [regularization](https://www.ultralytics.com/glossary/regularization) term, penalizing large weights to prevent overfitting. | +| `warmup_epochs` | `3.0` | Number of epochs for learning rate warmup, gradually increasing the learning rate from a low value to the initial learning rate to stabilize training early on. | +| `warmup_momentum` | `0.8` | Initial momentum for warmup phase, gradually adjusting to the set momentum over the warmup period. | +| `warmup_bias_lr` | `0.1` | Learning rate for bias parameters during the warmup phase, helping stabilize model training in the initial epochs. | +| `box` | `7.5` | Weight of the box loss component in the [loss function](https://www.ultralytics.com/glossary/loss-function), influencing how much emphasis is placed on accurately predicting [bounding box](https://www.ultralytics.com/glossary/bounding-box) coordinates. | +| `cls` | `0.5` | Weight of the classification loss in the total loss function, affecting the importance of correct class prediction relative to other components. | +| `dfl` | `1.5` | Weight of the distribution focal loss, used in certain YOLO versions for fine-grained classification. | +| `pose` | `12.0` | Weight of the pose loss in models trained for pose estimation, influencing the emphasis on accurately predicting pose keypoints. | +| `kobj` | `2.0` | Weight of the keypoint objectness loss in pose estimation models, balancing detection confidence with pose accuracy. | +| `label_smoothing` | `0.0` | Applies label smoothing, softening hard labels to a mix of the target label and a uniform distribution over labels, can improve generalization. | +| `nbs` | `64` | Nominal batch size for normalization of loss. | +| `overlap_mask` | `True` | Determines whether segmentation masks should overlap during training, applicable in [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation) tasks. | +| `mask_ratio` | `4` | Downsample ratio for segmentation masks, affecting the resolution of masks used during training. | +| `dropout` | `0.0` | Dropout rate for regularization in classification tasks, preventing overfitting by randomly omitting units during training. | +| `val` | `True` | Enables validation during training, allowing for periodic evaluation of model performance on a separate dataset. | +| `plots` | `False` | Generates and saves plots of training and validation metrics, as well as prediction examples, providing visual insights into model performance and learning progression. | diff --git a/docs/en/macros/validation-args.md b/docs/en/macros/validation-args.md index 92bfa240f4..5c709f7bfc 100644 --- a/docs/en/macros/validation-args.md +++ b/docs/en/macros/validation-args.md @@ -1,16 +1,16 @@ -| Argument | Type | Default | Description | -| ------------- | ------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `data` | `str` | `None` | Specifies the path to the dataset configuration file (e.g., `coco8.yaml`). This file includes paths to validation data, class names, and number of classes. | -| `imgsz` | `int` | `640` | Defines the size of input images. All images are resized to this dimension before processing. | -| `batch` | `int` | `16` | Sets the number of images per batch. Use `-1` for AutoBatch, which automatically adjusts based on GPU memory availability. | -| `save_json` | `bool` | `False` | If `True`, saves the results to a JSON file for further analysis or integration with other tools. | -| `save_hybrid` | `bool` | `False` | If `True`, saves a hybrid version of labels that combines original annotations with additional model predictions. | -| `conf` | `float` | `0.001` | Sets the minimum confidence threshold for detections. Detections with confidence below this threshold are discarded. | -| `iou` | `float` | `0.6` | Sets the Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Helps in reducing duplicate detections. | -| `max_det` | `int` | `300` | Limits the maximum number of detections per image. Useful in dense scenes to prevent excessive detections. | -| `half` | `bool` | `True` | Enables half-precision (FP16) computation, reducing memory usage and potentially increasing speed with minimal impact on accuracy. | -| `device` | `str` | `None` | Specifies the device for validation (`cpu`, `cuda:0`, etc.). Allows flexibility in utilizing CPU or GPU resources. | -| `dnn` | `bool` | `False` | If `True`, uses the OpenCV DNN module for ONNX model inference, offering an alternative to PyTorch inference methods. | -| `plots` | `bool` | `False` | When set to `True`, generates and saves plots of predictions versus ground truth for visual evaluation of the model's performance. | -| `rect` | `bool` | `False` | If `True`, uses rectangular inference for batching, reducing padding and potentially increasing speed and efficiency. | -| `split` | `str` | `val` | Determines the dataset split to use for validation (`val`, `test`, or `train`). Allows flexibility in choosing the data segment for performance evaluation. | +| Argument | Type | Default | Description | +| ------------- | ------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `data` | `str` | `None` | Specifies the path to the dataset configuration file (e.g., `coco8.yaml`). This file includes paths to [validation data](https://www.ultralytics.com/glossary/validation-data), class names, and number of classes. | +| `imgsz` | `int` | `640` | Defines the size of input images. All images are resized to this dimension before processing. | +| `batch` | `int` | `16` | Sets the number of images per batch. Use `-1` for AutoBatch, which automatically adjusts based on GPU memory availability. | +| `save_json` | `bool` | `False` | If `True`, saves the results to a JSON file for further analysis or integration with other tools. | +| `save_hybrid` | `bool` | `False` | If `True`, saves a hybrid version of labels that combines original annotations with additional model predictions. | +| `conf` | `float` | `0.001` | Sets the minimum confidence threshold for detections. Detections with confidence below this threshold are discarded. | +| `iou` | `float` | `0.6` | Sets the [Intersection Over Union](https://www.ultralytics.com/glossary/intersection-over-union-iou) (IoU) threshold for Non-Maximum Suppression (NMS). Helps in reducing duplicate detections. | +| `max_det` | `int` | `300` | Limits the maximum number of detections per image. Useful in dense scenes to prevent excessive detections. | +| `half` | `bool` | `True` | Enables half-[precision](https://www.ultralytics.com/glossary/precision) (FP16) computation, reducing memory usage and potentially increasing speed with minimal impact on [accuracy](https://www.ultralytics.com/glossary/accuracy). | +| `device` | `str` | `None` | Specifies the device for validation (`cpu`, `cuda:0`, etc.). Allows flexibility in utilizing CPU or GPU resources. | +| `dnn` | `bool` | `False` | If `True`, uses the [OpenCV](https://www.ultralytics.com/glossary/opencv) DNN module for ONNX model inference, offering an alternative to [PyTorch](https://www.ultralytics.com/glossary/pytorch) inference methods. | +| `plots` | `bool` | `False` | When set to `True`, generates and saves plots of predictions versus ground truth for visual evaluation of the model's performance. | +| `rect` | `bool` | `False` | If `True`, uses rectangular inference for batching, reducing padding and potentially increasing speed and efficiency. | +| `split` | `str` | `val` | Determines the dataset split to use for validation (`val`, `test`, or `train`). Allows flexibility in choosing the data segment for performance evaluation. | diff --git a/docs/en/models/fast-sam.md b/docs/en/models/fast-sam.md index e3f889c3b5..bbbe603d39 100644 --- a/docs/en/models/fast-sam.md +++ b/docs/en/models/fast-sam.md @@ -25,7 +25,7 @@ The Fast Segment Anything Model (FastSAM) is a novel, real-time CNN-based soluti ## Overview -FastSAM is designed to address the limitations of the [Segment Anything Model (SAM)](sam.md), a heavy Transformer model with substantial computational resource requirements. The FastSAM decouples the segment anything task into two sequential stages: all-instance segmentation and prompt-guided selection. The first stage uses [YOLOv8-seg](../tasks/segment.md) to produce the segmentation masks of all instances in the image. In the second stage, it outputs the region-of-interest corresponding to the prompt. +FastSAM is designed to address the limitations of the [Segment Anything Model (SAM)](sam.md), a heavy [Transformer](https://www.ultralytics.com/glossary/transformer) model with substantial computational resource requirements. The FastSAM decouples the segment anything task into two sequential stages: all-[instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation) and prompt-guided selection. The first stage uses [YOLOv8-seg](../tasks/segment.md) to produce the segmentation masks of all instances in the image. In the second stage, it outputs the region-of-interest corresponding to the prompt. ## Key Features @@ -58,7 +58,7 @@ The FastSAM models are easy to integrate into your Python applications. Ultralyt ### Predict Usage -To perform object detection on an image, use the `predict` method as shown below: +To perform [object detection](https://www.ultralytics.com/glossary/object-detection) on an image, use the `predict` method as shown below: !!! example @@ -224,7 +224,7 @@ FastSAM is also available directly from the [https://github.com/CASIA-IVA-Lab/Fa python Inference.py --model_path ./weights/FastSAM.pt --img_path ./images/dogs.jpg --text_prompt "the yellow dog" ``` - - Segment objects within a bounding box (provide box coordinates in xywh format): + - Segment objects within a [bounding box](https://www.ultralytics.com/glossary/bounding-box) (provide box coordinates in xywh format): ```shell python Inference.py --model_path ./weights/FastSAM.pt --img_path ./images/dogs.jpg --box_prompt "[570,200,230,400]" @@ -262,7 +262,7 @@ The original FastSAM paper can be found on [arXiv](https://arxiv.org/abs/2306.12 ### What is FastSAM and how does it differ from SAM? -FastSAM, short for Fast Segment Anything Model, is a real-time convolutional neural network (CNN)-based solution designed to reduce computational demands while maintaining high performance in object segmentation tasks. Unlike the Segment Anything Model (SAM), which uses a heavier Transformer-based architecture, FastSAM leverages [Ultralytics YOLOv8-seg](../tasks/segment.md) for efficient instance segmentation in two stages: all-instance segmentation followed by prompt-guided selection. +FastSAM, short for Fast Segment Anything Model, is a real-time [convolutional neural network](https://www.ultralytics.com/glossary/convolutional-neural-network-cnn) (CNN)-based solution designed to reduce computational demands while maintaining high performance in object segmentation tasks. Unlike the Segment Anything Model (SAM), which uses a heavier Transformer-based architecture, FastSAM leverages [Ultralytics YOLOv8-seg](../tasks/segment.md) for efficient instance segmentation in two stages: all-instance segmentation followed by prompt-guided selection. ### How does FastSAM achieve real-time segmentation performance? @@ -270,7 +270,7 @@ FastSAM achieves real-time segmentation by decoupling the segmentation task into ### What are the practical applications of FastSAM? -FastSAM is practical for a variety of computer vision tasks that require real-time segmentation performance. Applications include: +FastSAM is practical for a variety of [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks that require real-time segmentation performance. Applications include: - Industrial automation for quality control and assurance - Real-time video analysis for security and surveillance diff --git a/docs/en/models/index.md b/docs/en/models/index.md index 0753023892..c43af1f57f 100644 --- a/docs/en/models/index.md +++ b/docs/en/models/index.md @@ -17,7 +17,7 @@ Here are some of the key models supported: 3. **[YOLOv5](yolov5.md)**: An improved version of the YOLO architecture by Ultralytics, offering better performance and speed trade-offs compared to previous versions. 4. **[YOLOv6](yolov6.md)**: Released by [Meituan](https://about.meituan.com/) in 2022, and in use in many of the company's autonomous delivery robots. 5. **[YOLOv7](yolov7.md)**: Updated YOLO models released in 2022 by the authors of YOLOv4. -6. **[YOLOv8](yolov8.md) NEW 🚀**: The latest version of the YOLO family, featuring enhanced capabilities such as instance segmentation, pose/keypoints estimation, and classification. +6. **[YOLOv8](yolov8.md) NEW 🚀**: The latest version of the YOLO family, featuring enhanced capabilities such as [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation), pose/keypoints estimation, and classification. 7. **[YOLOv9](yolov9.md)**: An experimental model trained on the Ultralytics [YOLOv5](yolov5.md) codebase implementing Programmable Gradient Information (PGI). 8. **[YOLOv10](yolov10.md)**: By Tsinghua University, featuring NMS-free training and efficiency-accuracy driven architecture, delivering state-of-the-art performance and latency. 9. **[Segment Anything Model (SAM)](sam.md)**: Meta's original Segment Anything Model (SAM). @@ -25,7 +25,7 @@ Here are some of the key models supported: 11. **[Mobile Segment Anything Model (MobileSAM)](mobile-sam.md)**: MobileSAM for mobile applications, by Kyung Hee University. 12. **[Fast Segment Anything Model (FastSAM)](fast-sam.md)**: FastSAM by Image & Video Analysis Group, Institute of Automation, Chinese Academy of Sciences. 13. **[YOLO-NAS](yolo-nas.md)**: YOLO Neural Architecture Search (NAS) Models. -14. **[Realtime Detection Transformers (RT-DETR)](rtdetr.md)**: Baidu's PaddlePaddle Realtime Detection Transformer (RT-DETR) models. +14. **[Realtime Detection Transformers (RT-DETR)](rtdetr.md)**: Baidu's PaddlePaddle Realtime Detection [Transformer](https://www.ultralytics.com/glossary/transformer) (RT-DETR) models. 15. **[YOLO-World](yolo-world.md)**: Real-time Open Vocabulary Object Detection models from Tencent AI Lab.

@@ -43,13 +43,13 @@ Here are some of the key models supported: This example provides simple YOLO training and inference examples. For full documentation on these and other [modes](../modes/index.md) see the [Predict](../modes/predict.md), [Train](../modes/train.md), [Val](../modes/val.md) and [Export](../modes/export.md) docs pages. -Note the below example is for YOLOv8 [Detect](../tasks/detect.md) models for object detection. For additional supported tasks see the [Segment](../tasks/segment.md), [Classify](../tasks/classify.md) and [Pose](../tasks/pose.md) docs. +Note the below example is for YOLOv8 [Detect](../tasks/detect.md) models for [object detection](https://www.ultralytics.com/glossary/object-detection). For additional supported tasks see the [Segment](../tasks/segment.md), [Classify](../tasks/classify.md) and [Pose](../tasks/pose.md) docs. !!! example === "Python" - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()`, `SAM()`, `NAS()` and `RTDETR()` classes to create a model instance in Python: + [PyTorch](https://www.ultralytics.com/glossary/pytorch) pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()`, `SAM()`, `NAS()` and `RTDETR()` classes to create a model instance in Python: ```python from ultralytics import YOLO @@ -101,7 +101,7 @@ For detailed steps, consult our [Contributing Guide](../help/contributing.md). ### What are the key advantages of using Ultralytics YOLOv8 for object detection? -Ultralytics YOLOv8 offers enhanced capabilities such as real-time object detection, instance segmentation, pose estimation, and classification. Its optimized architecture ensures high-speed performance without sacrificing accuracy, making it ideal for a variety of applications. YOLOv8 also includes built-in compatibility with popular datasets and models, as detailed on the [YOLOv8 documentation page](../models/yolov8.md). +Ultralytics YOLOv8 offers enhanced capabilities such as real-time object detection, instance segmentation, pose estimation, and classification. Its optimized architecture ensures high-speed performance without sacrificing [accuracy](https://www.ultralytics.com/glossary/accuracy), making it ideal for a variety of applications. YOLOv8 also includes built-in compatibility with popular datasets and models, as detailed on the [YOLOv8 documentation page](../models/yolov8.md). ### How can I train a YOLOv8 model on custom data? @@ -133,7 +133,7 @@ For more detailed instructions, visit the [Train](../modes/train.md) documentati Ultralytics supports a comprehensive range of YOLO (You Only Look Once) versions from YOLOv3 to YOLOv10, along with models like NAS, SAM, and RT-DETR. Each version is optimized for various tasks such as detection, segmentation, and classification. For detailed information on each model, refer to the [Models Supported by Ultralytics](../models/index.md) documentation. -### Why should I use Ultralytics HUB for machine learning projects? +### Why should I use Ultralytics HUB for [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) projects? Ultralytics HUB provides a no-code, end-to-end platform for training, deploying, and managing YOLO models. It simplifies complex workflows, enabling users to focus on model performance and application. The HUB also offers cloud training capabilities, comprehensive dataset management, and user-friendly interfaces. Learn more about it on the [Ultralytics HUB](../hub/index.md) documentation page. diff --git a/docs/en/models/mobile-sam.md b/docs/en/models/mobile-sam.md index ed3ab1c950..26c92f6829 100644 --- a/docs/en/models/mobile-sam.md +++ b/docs/en/models/mobile-sam.md @@ -122,7 +122,7 @@ If you find MobileSAM useful in your research or development work, please consid ### What is MobileSAM and how does it differ from the original SAM model? -MobileSAM is a lightweight, fast image segmentation model designed for mobile applications. It retains the same pipeline as the original SAM but replaces the heavyweight ViT-H encoder (632M parameters) with a smaller Tiny-ViT encoder (5M parameters). This change results in MobileSAM being approximately 5 times smaller and 7 times faster than the original SAM. For instance, MobileSAM operates at about 12ms per image, compared to the original SAM's 456ms. You can learn more about the MobileSAM implementation in various projects [here](https://github.com/ChaoningZhang/MobileSAM). +MobileSAM is a lightweight, fast [image segmentation](https://www.ultralytics.com/glossary/image-segmentation) model designed for mobile applications. It retains the same pipeline as the original SAM but replaces the heavyweight ViT-H encoder (632M parameters) with a smaller Tiny-ViT encoder (5M parameters). This change results in MobileSAM being approximately 5 times smaller and 7 times faster than the original SAM. For instance, MobileSAM operates at about 12ms per image, compared to the original SAM's 456ms. You can learn more about the MobileSAM implementation in various projects [here](https://github.com/ChaoningZhang/MobileSAM). ### How can I test MobileSAM using Ultralytics? @@ -152,7 +152,7 @@ MobileSAM was trained on a single GPU with a 100k dataset, which is 1% of the or MobileSAM is designed for fast and efficient image segmentation in mobile environments. Primary use cases include: -- **Real-time object detection and segmentation** for mobile applications. +- **Real-time [object detection](https://www.ultralytics.com/glossary/object-detection) and segmentation** for mobile applications. - **Low-latency image processing** in devices with limited computational resources. - **Integration in AI-driven mobile apps** for tasks such as augmented reality (AR) and real-time analytics. diff --git a/docs/en/models/rtdetr.md b/docs/en/models/rtdetr.md index 46269e4458..47710e0320 100644 --- a/docs/en/models/rtdetr.md +++ b/docs/en/models/rtdetr.md @@ -4,11 +4,11 @@ description: Explore Baidu's RT-DETR, a Vision Transformer-based real-time objec keywords: RT-DETR, Baidu, Vision Transformer, real-time object detection, PaddlePaddle, Ultralytics, pre-trained models, AI, machine learning, computer vision --- -# Baidu's RT-DETR: A Vision Transformer-Based Real-Time Object Detector +# Baidu's RT-DETR: A Vision [Transformer](https://www.ultralytics.com/glossary/transformer)-Based Real-Time Object Detector ## Overview -Real-Time Detection Transformer (RT-DETR), developed by Baidu, is a cutting-edge end-to-end object detector that provides real-time performance while maintaining high accuracy. It is based on the idea of DETR (the NMS-free framework), meanwhile introducing conv-based backbone and an efficient hybrid encoder to gain real-time speed. RT-DETR efficiently processes multiscale features by decoupling intra-scale interaction and cross-scale fusion. The model is highly adaptable, supporting flexible adjustment of inference speed using different decoder layers without retraining. RT-DETR excels on accelerated backends like CUDA with TensorRT, outperforming many other real-time object detectors. +Real-Time Detection Transformer (RT-DETR), developed by Baidu, is a cutting-edge end-to-end object detector that provides real-time performance while maintaining high [accuracy](https://www.ultralytics.com/glossary/accuracy). It is based on the idea of DETR (the NMS-free framework), meanwhile introducing conv-based backbone and an efficient hybrid encoder to gain real-time speed. RT-DETR efficiently processes multiscale features by decoupling intra-scale interaction and cross-scale fusion. The model is highly adaptable, supporting flexible adjustment of inference speed using different decoder layers without retraining. RT-DETR excels on accelerated backends like CUDA with TensorRT, outperforming many other real-time object detectors.


@@ -25,7 +25,7 @@ Real-Time Detection Transformer (RT-DETR), developed by Baidu, is a cutting-edge ### Key Features -- **Efficient Hybrid Encoder:** Baidu's RT-DETR uses an efficient hybrid encoder that processes multiscale features by decoupling intra-scale interaction and cross-scale fusion. This unique Vision Transformers-based design reduces computational costs and allows for real-time object detection. +- **Efficient Hybrid Encoder:** Baidu's RT-DETR uses an efficient hybrid encoder that processes multiscale features by decoupling intra-scale interaction and cross-scale fusion. This unique Vision Transformers-based design reduces computational costs and allows for real-time [object detection](https://www.ultralytics.com/glossary/object-detection). - **IoU-aware Query Selection:** Baidu's RT-DETR improves object query initialization by utilizing IoU-aware query selection. This allows the model to focus on the most relevant objects in the scene, enhancing the detection accuracy. - **Adaptable Inference Speed:** Baidu's RT-DETR supports flexible adjustments of inference speed by using different decoder layers without the need for retraining. This adaptability facilitates practical application in various real-time object detection scenarios. @@ -98,7 +98,7 @@ If you use Baidu's RT-DETR in your research or development work, please cite the } ``` -We would like to acknowledge Baidu and the [PaddlePaddle](https://github.com/PaddlePaddle/PaddleDetection) team for creating and maintaining this valuable resource for the computer vision community. Their contribution to the field with the development of the Vision Transformers-based real-time object detector, RT-DETR, is greatly appreciated. +We would like to acknowledge Baidu and the [PaddlePaddle](https://github.com/PaddlePaddle/PaddleDetection) team for creating and maintaining this valuable resource for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) community. Their contribution to the field with the development of the Vision Transformers-based real-time object detector, RT-DETR, is greatly appreciated. ## FAQ @@ -146,7 +146,7 @@ Baidu's RT-DETR stands out due to its efficient hybrid encoder and IoU-aware que ### How does RT-DETR support adaptable inference speed for different real-time applications? -Baidu's RT-DETR allows flexible adjustments of inference speed by using different decoder layers without requiring retraining. This adaptability is crucial for scaling performance across various real-time object detection tasks. Whether you need faster processing for lower precision needs or slower, more accurate detections, RT-DETR can be tailored to meet your specific requirements. +Baidu's RT-DETR allows flexible adjustments of inference speed by using different decoder layers without requiring retraining. This adaptability is crucial for scaling performance across various real-time object detection tasks. Whether you need faster processing for lower [precision](https://www.ultralytics.com/glossary/precision) needs or slower, more accurate detections, RT-DETR can be tailored to meet your specific requirements. ### Can I use RT-DETR models with other Ultralytics modes, such as training, validation, and export? diff --git a/docs/en/models/sam-2.md b/docs/en/models/sam-2.md index 336b294e0f..025c18d267 100644 --- a/docs/en/models/sam-2.md +++ b/docs/en/models/sam-2.md @@ -38,18 +38,18 @@ For a deeper understanding of SAM 2's architecture and capabilities, explore the SAM 2 sets a new benchmark in the field, outperforming previous models on various metrics: -| Metric | SAM 2 | Previous SOTA | -| ---------------------------------- | ------------- | ------------- | -| **Interactive Video Segmentation** | **Best** | - | -| **Human Interactions Required** | **3x fewer** | Baseline | -| **Image Segmentation Accuracy** | **Improved** | SAM | -| **Inference Speed** | **6x faster** | SAM | +| Metric | SAM 2 | Previous SOTA | +| ------------------------------------------------------------------------------------------ | ------------- | ------------- | +| **Interactive Video Segmentation** | **Best** | - | +| **Human Interactions Required** | **3x fewer** | Baseline | +| **[Image Segmentation](https://www.ultralytics.com/glossary/image-segmentation) Accuracy** | **Improved** | SAM | +| **Inference Speed** | **6x faster** | SAM | ## Model Architecture ### Core Components -- **Image and Video Encoder**: Utilizes a transformer-based architecture to extract high-level features from both images and video frames. This component is responsible for understanding the visual content at each timestep. +- **Image and Video Encoder**: Utilizes a [transformer](https://www.ultralytics.com/glossary/transformer)-based architecture to extract high-level features from both images and video frames. This component is responsible for understanding the visual content at each timestep. - **Prompt Encoder**: Processes user-provided prompts (points, boxes, masks) to guide the segmentation task. This allows SAM 2 to adapt to user input and target specific objects within a scene. - **Memory Mechanism**: Includes a memory encoder, memory bank, and memory attention module. These components collectively store and utilize information from past frames, enabling the model to maintain consistent object tracking over time. - **Mask Decoder**: Generates the final segmentation masks based on the encoded image features and prompts. In video, it also uses memory context to ensure accurate tracking across frames. @@ -242,7 +242,7 @@ Despite its strengths, SAM 2 has certain limitations: - **Tracking Stability**: SAM 2 may lose track of objects during extended sequences or significant viewpoint changes. - **Object Confusion**: The model can sometimes confuse similar-looking objects, particularly in crowded scenes. - **Efficiency with Multiple Objects**: Segmentation efficiency decreases when processing multiple objects simultaneously due to the lack of inter-object communication. -- **Detail Accuracy**: May miss fine details, especially with fast-moving objects. Additional prompts can partially address this issue, but temporal smoothness is not guaranteed. +- **Detail [Accuracy](https://www.ultralytics.com/glossary/accuracy)**: May miss fine details, especially with fast-moving objects. Additional prompts can partially address this issue, but temporal smoothness is not guaranteed. ## Citations and Acknowledgements @@ -327,7 +327,7 @@ This mechanism ensures continuity even when objects are temporarily obscured or ### How does SAM 2 compare to other segmentation models like YOLOv8? -SAM 2 and Ultralytics YOLOv8 serve different purposes and excel in different areas. While SAM 2 is designed for comprehensive object segmentation with advanced features like zero-shot generalization and real-time performance, YOLOv8 is optimized for speed and efficiency in object detection and segmentation tasks. Here's a comparison: +SAM 2 and Ultralytics YOLOv8 serve different purposes and excel in different areas. While SAM 2 is designed for comprehensive object segmentation with advanced features like zero-shot generalization and real-time performance, YOLOv8 is optimized for speed and efficiency in [object detection](https://www.ultralytics.com/glossary/object-detection) and segmentation tasks. Here's a comparison: | Model | Size
(MB) | Parameters
(M) | Speed (CPU)
(ms/im) | | ---------------------------------------------- | ----------------------- | ---------------------------- | --------------------------------- | diff --git a/docs/en/models/sam.md b/docs/en/models/sam.md index 3768041383..304fc00287 100644 --- a/docs/en/models/sam.md +++ b/docs/en/models/sam.md @@ -6,7 +6,7 @@ keywords: Segment Anything, SAM, image segmentation, promptable segmentation, ze # Segment Anything Model (SAM) -Welcome to the frontier of image segmentation with the Segment Anything Model, or SAM. This revolutionary model has changed the game by introducing promptable image segmentation with real-time performance, setting new standards in the field. +Welcome to the frontier of [image segmentation](https://www.ultralytics.com/glossary/image-segmentation) with the Segment Anything Model, or SAM. This revolutionary model has changed the game by introducing promptable image segmentation with real-time performance, setting new standards in the field. ## Introduction to SAM: The Segment Anything Model @@ -21,7 +21,7 @@ SAM's advanced design allows it to adapt to new image distributions and tasks wi - **Promptable Segmentation Task:** SAM was designed with a promptable segmentation task in mind, allowing it to generate valid segmentation masks from any given prompt, such as spatial or text clues identifying an object. - **Advanced Architecture:** The Segment Anything Model employs a powerful image encoder, a prompt encoder, and a lightweight mask decoder. This unique architecture enables flexible prompting, real-time mask computation, and ambiguity awareness in segmentation tasks. - **The SA-1B Dataset:** Introduced by the Segment Anything project, the SA-1B dataset features over 1 billion masks on 11 million images. As the largest segmentation dataset to date, it provides SAM with a diverse and large-scale training data source. -- **Zero-Shot Performance:** SAM displays outstanding zero-shot performance across various segmentation tasks, making it a ready-to-use tool for diverse applications with minimal need for prompt engineering. +- **Zero-Shot Performance:** SAM displays outstanding zero-shot performance across various segmentation tasks, making it a ready-to-use tool for diverse applications with minimal need for [prompt engineering](https://www.ultralytics.com/glossary/prompt-engineering). For an in-depth look at the Segment Anything Model and the SA-1B dataset, please visit the [Segment Anything website](https://segment-anything.com/) and check out the research paper [Segment Anything](https://arxiv.org/abs/2304.02643). @@ -36,7 +36,7 @@ This table presents the available models with their specific pre-trained weights ## How to Use SAM: Versatility and Power in Image Segmentation -The Segment Anything Model can be employed for a multitude of downstream tasks that go beyond its training data. This includes edge detection, object proposal generation, instance segmentation, and preliminary text-to-mask prediction. With prompt engineering, SAM can swiftly adapt to new tasks and data distributions in a zero-shot manner, establishing it as a versatile and potent tool for all your image segmentation needs. +The Segment Anything Model can be employed for a multitude of downstream tasks that go beyond its training data. This includes edge detection, object proposal generation, [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation), and preliminary text-to-mask prediction. With prompt engineering, SAM can swiftly adapt to new tasks and data distributions in a zero-shot manner, establishing it as a versatile and potent tool for all your image segmentation needs. ### SAM prediction example @@ -222,7 +222,7 @@ If you find SAM useful in your research or development work, please consider cit } ``` -We would like to express our gratitude to Meta AI for creating and maintaining this valuable resource for the computer vision community. +We would like to express our gratitude to Meta AI for creating and maintaining this valuable resource for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) community. ## FAQ @@ -273,4 +273,4 @@ This function takes the path to your images and optional arguments for pre-train ### What datasets are used to train the Segment Anything Model (SAM)? -SAM is trained on the extensive [SA-1B dataset](https://ai.facebook.com/datasets/segment-anything/) which comprises over 1 billion masks across 11 million images. SA-1B is the largest segmentation dataset to date, providing high-quality and diverse training data, ensuring impressive zero-shot performance in varied segmentation tasks. For more details, visit the [Dataset section](#key-features-of-the-segment-anything-model-sam). +SAM is trained on the extensive [SA-1B dataset](https://ai.facebook.com/datasets/segment-anything/) which comprises over 1 billion masks across 11 million images. SA-1B is the largest segmentation dataset to date, providing high-quality and diverse [training data](https://www.ultralytics.com/glossary/training-data), ensuring impressive zero-shot performance in varied segmentation tasks. For more details, visit the [Dataset section](#key-features-of-the-segment-anything-model-sam). diff --git a/docs/en/models/yolo-nas.md b/docs/en/models/yolo-nas.md index f0aff53b1e..5523cb1b32 100644 --- a/docs/en/models/yolo-nas.md +++ b/docs/en/models/yolo-nas.md @@ -8,7 +8,7 @@ keywords: YOLO-NAS, Deci AI, object detection, deep learning, Neural Architectur ## Overview -Developed by Deci AI, YOLO-NAS is a groundbreaking object detection foundational model. It is the product of advanced Neural Architecture Search technology, meticulously designed to address the limitations of previous YOLO models. With significant improvements in quantization support and accuracy-latency trade-offs, YOLO-NAS represents a major leap in object detection. +Developed by Deci AI, YOLO-NAS is a groundbreaking object detection foundational model. It is the product of advanced Neural Architecture Search technology, meticulously designed to address the limitations of previous YOLO models. With significant improvements in quantization support and [accuracy](https://www.ultralytics.com/glossary/accuracy)-latency trade-offs, YOLO-NAS represents a major leap in object detection. ![Model example image](https://github.com/ultralytics/docs/releases/download/0/yolo-nas-coco-map-metrics.avif) **Overview of YOLO-NAS.** YOLO-NAS employs quantization-aware blocks and selective quantization for optimal performance. The model, when converted to its INT8 quantized version, experiences a minimal precision drop, a significant improvement over other models. These advancements culminate in a superior architecture with unprecedented object detection capabilities and outstanding performance. @@ -31,7 +31,7 @@ Experience the power of next-generation object detection with the pre-trained YO | YOLO-NAS M INT-8 | 51.0 | 3.78 | | YOLO-NAS L INT-8 | 52.1 | 4.78 | -Each model variant is designed to offer a balance between Mean Average Precision (mAP) and latency, helping you optimize your object detection tasks for both performance and speed. +Each model variant is designed to offer a balance between [Mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP) and latency, helping you optimize your object detection tasks for both performance and speed. ## Usage Examples @@ -49,7 +49,7 @@ In this example we validate YOLO-NAS-s on the COCO8 dataset. === "Python" - PyTorch pretrained `*.pt` models files can be passed to the `NAS()` class to create a model instance in python: + [PyTorch](https://www.ultralytics.com/glossary/pytorch) pretrained `*.pt` models files can be passed to the `NAS()` class to create a model instance in python: ```python from ultralytics import NAS @@ -84,7 +84,7 @@ In this example we validate YOLO-NAS-s on the COCO8 dataset. We offer three variants of the YOLO-NAS models: Small (s), Medium (m), and Large (l). Each variant is designed to cater to different computational and performance needs: - **YOLO-NAS-s**: Optimized for environments where computational resources are limited but efficiency is key. -- **YOLO-NAS-m**: Offers a balanced approach, suitable for general-purpose object detection with higher accuracy. +- **YOLO-NAS-m**: Offers a balanced approach, suitable for general-purpose [object detection](https://www.ultralytics.com/glossary/object-detection) with higher accuracy. - **YOLO-NAS-l**: Tailored for scenarios requiring the highest accuracy, where computational resources are less of a constraint. Below is a detailed overview of each model, including links to their pre-trained weights, the tasks they support, and their compatibility with different operating modes. @@ -115,7 +115,7 @@ If you employ YOLO-NAS in your research or development work, please cite SuperGr } ``` -We express our gratitude to Deci AI's [SuperGradients](https://github.com/Deci-AI/super-gradients/) team for their efforts in creating and maintaining this valuable resource for the computer vision community. We believe YOLO-NAS, with its innovative architecture and superior object detection capabilities, will become a critical tool for developers and researchers alike. +We express our gratitude to Deci AI's [SuperGradients](https://github.com/Deci-AI/super-gradients/) team for their efforts in creating and maintaining this valuable resource for the [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) community. We believe YOLO-NAS, with its innovative architecture and superior object detection capabilities, will become a critical tool for developers and researchers alike. ## FAQ @@ -146,7 +146,7 @@ For more information, refer to the [Inference and Validation Examples](#inferenc YOLO-NAS introduces several key features that make it a superior choice for object detection tasks: -- **Quantization-Friendly Basic Block:** Enhanced architecture that improves model performance with minimal precision drop post quantization. +- **Quantization-Friendly Basic Block:** Enhanced architecture that improves model performance with minimal [precision](https://www.ultralytics.com/glossary/precision) drop post quantization. - **Sophisticated Training and Quantization:** Employs advanced training schemes and post-training quantization techniques. - **AutoNAC Optimization and Pre-training:** Utilizes AutoNAC optimization and is pre-trained on prominent datasets like COCO, Objects365, and Roboflow 100. These features contribute to its high accuracy, efficient performance, and suitability for deployment in production environments. Learn more in the [Key Features](#key-features) section. diff --git a/docs/en/models/yolo-world.md b/docs/en/models/yolo-world.md index f5dcd0b72d..96a6e0b606 100644 --- a/docs/en/models/yolo-world.md +++ b/docs/en/models/yolo-world.md @@ -23,7 +23,7 @@ The YOLO-World Model introduces an advanced, real-time [Ultralytics](https://www ## Overview -YOLO-World tackles the challenges faced by traditional Open-Vocabulary detection models, which often rely on cumbersome Transformer models requiring extensive computational resources. These models' dependence on pre-defined object categories also restricts their utility in dynamic scenarios. YOLO-World revitalizes the YOLOv8 framework with open-vocabulary detection capabilities, employing vision-language modeling and pre-training on expansive datasets to excel at identifying a broad array of objects in zero-shot scenarios with unmatched efficiency. +YOLO-World tackles the challenges faced by traditional Open-Vocabulary detection models, which often rely on cumbersome [Transformer](https://www.ultralytics.com/glossary/transformer) models requiring extensive computational resources. These models' dependence on pre-defined object categories also restricts their utility in dynamic scenarios. YOLO-World revitalizes the YOLOv8 framework with open-vocabulary detection capabilities, employing vision-[language modeling](https://www.ultralytics.com/glossary/language-modeling) and pre-training on expansive datasets to excel at identifying a broad array of objects in zero-shot scenarios with unmatched efficiency. ## Key Features @@ -81,13 +81,13 @@ The YOLO-World models are easy to integrate into your Python applications. Ultra We strongly recommend to use `yolov8-worldv2` model for custom training, because it supports deterministic training and also easy to export other formats i.e onnx/tensorrt. -Object detection is straightforward with the `train` method, as illustrated below: +[Object detection](https://www.ultralytics.com/glossary/object-detection) is straightforward with the `train` method, as illustrated below: !!! example === "Python" - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLOWorld()` class to create a model instance in python: + [PyTorch](https://www.ultralytics.com/glossary/pytorch) pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLOWorld()` class to create a model instance in python: ```python from ultralytics import YOLOWorld @@ -197,7 +197,7 @@ Object tracking with YOLO-World model on a video/images is streamlined as follow ![YOLO-World prompt class names overview](https://github.com/ultralytics/docs/releases/download/0/yolo-world-prompt-class-names-overview.avif) -The YOLO-World framework allows for the dynamic specification of classes through custom prompts, empowering users to tailor the model to their specific needs **without retraining**. This feature is particularly useful for adapting the model to new domains or specific tasks that were not originally part of the training data. By setting custom prompts, users can essentially guide the model's focus towards objects of interest, enhancing the relevance and accuracy of the detection results. +The YOLO-World framework allows for the dynamic specification of classes through custom prompts, empowering users to tailor the model to their specific needs **without retraining**. This feature is particularly useful for adapting the model to new domains or specific tasks that were not originally part of the [training data](https://www.ultralytics.com/glossary/training-data). By setting custom prompts, users can essentially guide the model's focus towards objects of interest, enhancing the relevance and accuracy of the detection results. For instance, if your application only requires detecting 'person' and 'bus' objects, you can specify these classes directly: @@ -262,7 +262,7 @@ You can also save a model after setting custom classes. By doing this you create - **Efficiency**: Streamlines the detection process by focusing on relevant objects, reducing computational overhead and speeding up inference. - **Flexibility**: Allows for easy adaptation of the model to new or niche detection tasks without the need for extensive retraining or data collection. - **Simplicity**: Simplifies deployment by eliminating the need to repeatedly specify custom classes at runtime, making the model directly usable with its embedded vocabulary. -- **Performance**: Enhances detection accuracy for specified classes by focusing the model's attention and resources on recognizing the defined objects. +- **Performance**: Enhances detection [accuracy](https://www.ultralytics.com/glossary/accuracy) for specified classes by focusing the model's attention and resources on recognizing the defined objects. This approach provides a powerful means of customizing state-of-the-art object detection models for specific tasks, making advanced AI more accessible and applicable to a broader range of practical applications. @@ -345,7 +345,7 @@ The YOLO-World model is an advanced, real-time object detection approach based o ### How does YOLO-World handle inference with custom prompts? -YOLO-World supports a "prompt-then-detect" strategy, which utilizes an offline vocabulary to enhance efficiency. Custom prompts like captions or specific object categories are pre-encoded and stored as offline vocabulary embeddings. This approach streamlines the detection process without the need for retraining. You can dynamically set these prompts within the model to tailor it to specific detection tasks, as shown below: +YOLO-World supports a "prompt-then-detect" strategy, which utilizes an offline vocabulary to enhance efficiency. Custom prompts like captions or specific object categories are pre-encoded and stored as offline vocabulary [embeddings](https://www.ultralytics.com/glossary/embeddings). This approach streamlines the detection process without the need for retraining. You can dynamically set these prompts within the model to tailor it to specific detection tasks, as shown below: ```python from ultralytics import YOLOWorld diff --git a/docs/en/models/yolov10.md b/docs/en/models/yolov10.md index babf972688..4cfd0cf902 100644 --- a/docs/en/models/yolov10.md +++ b/docs/en/models/yolov10.md @@ -4,7 +4,7 @@ description: Discover YOLOv10, the latest in real-time object detection, elimina keywords: YOLOv10, real-time object detection, NMS-free, deep learning, Tsinghua University, Ultralytics, machine learning, neural networks, performance optimization --- -# YOLOv10: Real-Time End-to-End Object Detection +# YOLOv10: Real-Time End-to-End [Object Detection](https://www.ultralytics.com/glossary/object-detection) YOLOv10, built on the [Ultralytics](https://www.ultralytics.com/) [Python package](https://pypi.org/project/ultralytics/) by researchers at [Tsinghua University](https://www.tsinghua.edu.cn/en/), introduces a new approach to real-time object detection, addressing both the post-processing and model architecture deficiencies found in previous YOLO versions. By eliminating non-maximum suppression (NMS) and optimizing various model components, YOLOv10 achieves state-of-the-art performance with significantly reduced computational overhead. Extensive experiments demonstrate its superior accuracy-latency trade-offs across multiple model scales. @@ -29,7 +29,7 @@ Real-time object detection aims to accurately predict object categories and posi The architecture of YOLOv10 builds upon the strengths of previous YOLO models while introducing several key innovations. The model architecture consists of the following components: -1. **Backbone**: Responsible for feature extraction, the backbone in YOLOv10 uses an enhanced version of CSPNet (Cross Stage Partial Network) to improve gradient flow and reduce computational redundancy. +1. **Backbone**: Responsible for [feature extraction](https://www.ultralytics.com/glossary/feature-extraction), the backbone in YOLOv10 uses an enhanced version of CSPNet (Cross Stage Partial Network) to improve gradient flow and reduce computational redundancy. 2. **Neck**: The neck is designed to aggregate features from different scales and passes them to the head. It includes PAN (Path Aggregation Network) layers for effective multiscale feature fusion. 3. **One-to-Many Head**: Generates multiple predictions per object during training to provide rich supervisory signals and improve learning accuracy. 4. **One-to-One Head**: Generates a single best prediction per object during inference to eliminate the need for NMS, thereby reducing latency and improving efficiency. @@ -72,7 +72,7 @@ Latency measured with TensorRT FP16 on T4 GPU. YOLOv10 employs dual label assignments, combining one-to-many and one-to-one strategies during training to ensure rich supervision and efficient end-to-end deployment. The consistent matching metric aligns the supervision between both strategies, enhancing the quality of predictions during inference. -### Holistic Efficiency-Accuracy Driven Model Design +### Holistic Efficiency-[Accuracy](https://www.ultralytics.com/glossary/accuracy) Driven Model Design #### Efficiency Enhancements @@ -202,20 +202,20 @@ The YOLOv10 models series offers a range of models, each optimized for high-perf Due to the new operations introduced with YOLOv10, not all export formats provided by Ultralytics are currently supported. The following table outlines which formats have been successfully converted using Ultralytics for YOLOv10. Feel free to open a pull request if you're able to [provide a contribution change](../help/contributing.md) for adding export support of additional formats for YOLOv10. -| Export Format | Export Support | Exported Model Inference | Notes | -| ------------------------------------------------- | -------------- | ------------------------ | ------------------------------------------- | -| [TorchScript](../integrations/torchscript.md) | ✅ | ✅ | Standard PyTorch model format. | -| [ONNX](../integrations/onnx.md) | ✅ | ✅ | Widely supported for deployment. | -| [OpenVINO](../integrations/openvino.md) | ✅ | ✅ | Optimized for Intel hardware. | -| [TensorRT](../integrations/tensorrt.md) | ✅ | ✅ | Optimized for NVIDIA GPUs. | -| [CoreML](../integrations/coreml.md) | ✅ | ✅ | Limited to Apple devices. | -| [TF SavedModel](../integrations/tf-savedmodel.md) | ✅ | ✅ | TensorFlow's standard model format. | -| [TF GraphDef](../integrations/tf-graphdef.md) | ✅ | ✅ | Legacy TensorFlow format. | -| [TF Lite](../integrations/tflite.md) | ✅ | ✅ | Optimized for mobile and embedded. | -| [TF Edge TPU](../integrations/edge-tpu.md) | ✅ | ✅ | Specific to Google's Edge TPU devices. | -| [TF.js](../integrations/tfjs.md) | ✅ | ✅ | JavaScript environment for browser use. | -| [PaddlePaddle](../integrations/paddlepaddle.md) | ❌ | ❌ | Popular in China; less global support. | -| [NCNN](../integrations/ncnn.md) | ✅ | ❌ | Layer `torch.topk` not exists or registered | +| Export Format | Export Support | Exported Model Inference | Notes | +| ------------------------------------------------- | -------------- | ------------------------ | -------------------------------------------------------------------------------------- | +| [TorchScript](../integrations/torchscript.md) | ✅ | ✅ | Standard [PyTorch](https://www.ultralytics.com/glossary/pytorch) model format. | +| [ONNX](../integrations/onnx.md) | ✅ | ✅ | Widely supported for deployment. | +| [OpenVINO](../integrations/openvino.md) | ✅ | ✅ | Optimized for Intel hardware. | +| [TensorRT](../integrations/tensorrt.md) | ✅ | ✅ | Optimized for NVIDIA GPUs. | +| [CoreML](../integrations/coreml.md) | ✅ | ✅ | Limited to Apple devices. | +| [TF SavedModel](../integrations/tf-savedmodel.md) | ✅ | ✅ | [TensorFlow](https://www.ultralytics.com/glossary/tensorflow)'s standard model format. | +| [TF GraphDef](../integrations/tf-graphdef.md) | ✅ | ✅ | Legacy TensorFlow format. | +| [TF Lite](../integrations/tflite.md) | ✅ | ✅ | Optimized for mobile and embedded. | +| [TF Edge TPU](../integrations/edge-tpu.md) | ✅ | ✅ | Specific to Google's Edge TPU devices. | +| [TF.js](../integrations/tfjs.md) | ✅ | ✅ | JavaScript environment for browser use. | +| [PaddlePaddle](../integrations/paddlepaddle.md) | ❌ | ❌ | Popular in China; less global support. | +| [NCNN](../integrations/ncnn.md) | ✅ | ❌ | Layer `torch.topk` not exists or registered | ## Conclusion diff --git a/docs/en/models/yolov3.md b/docs/en/models/yolov3.md index 182ccbcd21..33e3cd8256 100644 --- a/docs/en/models/yolov3.md +++ b/docs/en/models/yolov3.md @@ -20,7 +20,7 @@ This document presents an overview of three closely related object detection mod ## Key Features -- **YOLOv3:** Introduced the use of three different scales for detection, leveraging three different sizes of detection kernels: 13x13, 26x26, and 52x52. This significantly improved detection accuracy for objects of different sizes. Additionally, YOLOv3 added features such as multi-label predictions for each bounding box and a better feature extractor network. +- **YOLOv3:** Introduced the use of three different scales for detection, leveraging three different sizes of detection kernels: 13x13, 26x26, and 52x52. This significantly improved detection accuracy for objects of different sizes. Additionally, YOLOv3 added features such as multi-label predictions for each [bounding box](https://www.ultralytics.com/glossary/bounding-box) and a better feature extractor network. - **YOLOv3-Ultralytics:** Ultralytics' implementation of YOLOv3 provides the same performance as the original model but comes with added support for more pre-trained models, additional training methods, and easier customization options. This makes it more versatile and user-friendly for practical applications. @@ -30,7 +30,7 @@ This document presents an overview of three closely related object detection mod The YOLOv3 series, including YOLOv3, YOLOv3-Ultralytics, and YOLOv3u, are designed specifically for object detection tasks. These models are renowned for their effectiveness in various real-world scenarios, balancing accuracy and speed. Each variant offers unique features and optimizations, making them suitable for a range of applications. -All three models support a comprehensive set of modes, ensuring versatility in various stages of model deployment and development. These modes include [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md), providing users with a complete toolkit for effective object detection. +All three models support a comprehensive set of modes, ensuring versatility in various stages of [model deployment](https://www.ultralytics.com/glossary/model-deployment) and development. These modes include [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md), providing users with a complete toolkit for effective object detection. | Model Type | Tasks Supported | Inference | Validation | Training | Export | | ------------------ | -------------------------------------- | --------- | ---------- | -------- | ------ | @@ -48,7 +48,7 @@ This example provides simple YOLOv3 training and inference examples. For full do === "Python" - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: + [PyTorch](https://www.ultralytics.com/glossary/pytorch) pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: ```python from ultralytics import YOLO @@ -101,7 +101,7 @@ Thank you to Joseph Redmon and Ali Farhadi for developing the original YOLOv3. ### What are the differences between YOLOv3, YOLOv3-Ultralytics, and YOLOv3u? -YOLOv3 is the third iteration of the YOLO (You Only Look Once) object detection algorithm developed by Joseph Redmon, known for its balance of accuracy and speed, utilizing three different scales (13x13, 26x26, and 52x52) for detections. YOLOv3-Ultralytics is Ultralytics' adaptation of YOLOv3 that adds support for more pre-trained models and facilitates easier model customization. YOLOv3u is an upgraded variant of YOLOv3-Ultralytics, integrating the anchor-free, objectness-free split head from YOLOv8, improving detection robustness and accuracy for various object sizes. For more details on the variants, refer to the [YOLOv3 series](https://github.com/ultralytics/yolov3). +YOLOv3 is the third iteration of the YOLO (You Only Look Once) [object detection](https://www.ultralytics.com/glossary/object-detection) algorithm developed by Joseph Redmon, known for its balance of [accuracy](https://www.ultralytics.com/glossary/accuracy) and speed, utilizing three different scales (13x13, 26x26, and 52x52) for detections. YOLOv3-Ultralytics is Ultralytics' adaptation of YOLOv3 that adds support for more pre-trained models and facilitates easier model customization. YOLOv3u is an upgraded variant of YOLOv3-Ultralytics, integrating the anchor-free, objectness-free split head from YOLOv8, improving detection robustness and accuracy for various object sizes. For more details on the variants, refer to the [YOLOv3 series](https://github.com/ultralytics/yolov3). ### How can I train a YOLOv3 model using Ultralytics? diff --git a/docs/en/models/yolov4.md b/docs/en/models/yolov4.md index c6f7d0da19..959de10f92 100644 --- a/docs/en/models/yolov4.md +++ b/docs/en/models/yolov4.md @@ -12,11 +12,11 @@ Welcome to the Ultralytics documentation page for YOLOv4, a state-of-the-art, re ## Introduction -YOLOv4 stands for You Only Look Once version 4. It is a real-time object detection model developed to address the limitations of previous YOLO versions like [YOLOv3](yolov3.md) and other object detection models. Unlike other convolutional neural network (CNN) based object detectors, YOLOv4 is not only applicable for recommendation systems but also for standalone process management and human input reduction. Its operation on conventional graphics processing units (GPUs) allows for mass usage at an affordable price, and it is designed to work in real-time on a conventional GPU while requiring only one such GPU for training. +YOLOv4 stands for You Only Look Once version 4. It is a real-time object detection model developed to address the limitations of previous YOLO versions like [YOLOv3](yolov3.md) and other object detection models. Unlike other [convolutional neural network](https://www.ultralytics.com/glossary/convolutional-neural-network-cnn) (CNN) based object detectors, YOLOv4 is not only applicable for recommendation systems but also for standalone process management and human input reduction. Its operation on conventional graphics processing units (GPUs) allows for mass usage at an affordable price, and it is designed to work in real-time on a conventional GPU while requiring only one such GPU for training. ## Architecture -YOLOv4 makes use of several innovative features that work together to optimize its performance. These include Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), Cross mini-Batch Normalization (CmBN), Self-adversarial-training (SAT), Mish-activation, Mosaic data augmentation, DropBlock regularization, and CIoU loss. These features are combined to achieve state-of-the-art results. +YOLOv4 makes use of several innovative features that work together to optimize its performance. These include Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), Cross mini-Batch Normalization (CmBN), Self-adversarial-training (SAT), Mish-activation, Mosaic [data augmentation](https://www.ultralytics.com/glossary/data-augmentation), DropBlock [regularization](https://www.ultralytics.com/glossary/regularization), and CIoU loss. These features are combined to achieve state-of-the-art results. A typical object detector is composed of several parts including the input, the backbone, the neck, and the head. The backbone of YOLOv4 is pre-trained on ImageNet and is used to predict classes and bounding boxes of objects. The backbone could be from several models including VGG, ResNet, ResNeXt, or DenseNet. The neck part of the detector is used to collect feature maps from different stages and usually includes several bottom-up paths and several top-down paths. The head part is what is used to make the final object detections and classifications. @@ -71,9 +71,9 @@ The original YOLOv4 paper can be found on [arXiv](https://arxiv.org/abs/2004.109 ## FAQ -### What is YOLOv4 and why should I use it for object detection? +### What is YOLOv4 and why should I use it for [object detection](https://www.ultralytics.com/glossary/object-detection)? -YOLOv4, which stands for "You Only Look Once version 4," is a state-of-the-art real-time object detection model developed by Alexey Bochkovskiy in 2020. It achieves an optimal balance between speed and accuracy, making it highly suitable for real-time applications. YOLOv4's architecture incorporates several innovative features like Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), and Self-adversarial-training (SAT), among others, to achieve state-of-the-art results. If you're looking for a high-performance model that operates efficiently on conventional GPUs, YOLOv4 is an excellent choice. +YOLOv4, which stands for "You Only Look Once version 4," is a state-of-the-art real-time object detection model developed by Alexey Bochkovskiy in 2020. It achieves an optimal balance between speed and [accuracy](https://www.ultralytics.com/glossary/accuracy), making it highly suitable for real-time applications. YOLOv4's architecture incorporates several innovative features like Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), and Self-adversarial-training (SAT), among others, to achieve state-of-the-art results. If you're looking for a high-performance model that operates efficiently on conventional GPUs, YOLOv4 is an excellent choice. ### How does the architecture of YOLOv4 enhance its performance? @@ -85,7 +85,7 @@ The architecture of YOLOv4 includes several key components: the backbone, the ne ### Why is YOLOv4 considered suitable for real-time object detection on conventional GPUs? -YOLOv4 is designed to optimize both speed and accuracy, making it ideal for real-time object detection tasks that require quick and reliable performance. It operates efficiently on conventional GPUs, needing only one for both training and inference. This makes it accessible and practical for various applications ranging from recommendation systems to standalone process management, thereby reducing the need for extensive hardware setups and making it a cost-effective solution for real-time object detection. +YOLOv4 is designed to optimize both speed and accuracy, making it ideal for real-time object detection tasks that require quick and reliable performance. It operates efficiently on conventional GPUs, needing only one for both training and inference. This makes it accessible and practical for various applications ranging from [recommendation systems](https://www.ultralytics.com/glossary/recommendation-system) to standalone process management, thereby reducing the need for extensive hardware setups and making it a cost-effective solution for real-time object detection. ### How can I get started with YOLOv4 if Ultralytics does not currently support it? diff --git a/docs/en/models/yolov5.md b/docs/en/models/yolov5.md index 4baa08e960..8ff1c36ec0 100644 --- a/docs/en/models/yolov5.md +++ b/docs/en/models/yolov5.md @@ -8,7 +8,7 @@ keywords: YOLOv5, YOLOv5u, object detection, Ultralytics, anchor-free, pre-train ## Overview -YOLOv5u represents an advancement in object detection methodologies. Originating from the foundational architecture of the [YOLOv5](https://github.com/ultralytics/yolov5) model developed by Ultralytics, YOLOv5u integrates the anchor-free, objectness-free split head, a feature previously introduced in the [YOLOv8](yolov8.md) models. This adaptation refines the model's architecture, leading to an improved accuracy-speed tradeoff in object detection tasks. Given the empirical results and its derived features, YOLOv5u provides an efficient alternative for those seeking robust solutions in both research and practical applications. +YOLOv5u represents an advancement in [object detection](https://www.ultralytics.com/glossary/object-detection) methodologies. Originating from the foundational architecture of the [YOLOv5](https://github.com/ultralytics/yolov5) model developed by Ultralytics, YOLOv5u integrates the anchor-free, objectness-free split head, a feature previously introduced in the [YOLOv8](yolov8.md) models. This adaptation refines the model's architecture, leading to an improved accuracy-speed tradeoff in object detection tasks. Given the empirical results and its derived features, YOLOv5u provides an efficient alternative for those seeking robust solutions in both research and practical applications. ![Ultralytics YOLOv5](https://github.com/ultralytics/docs/releases/download/0/ultralytics-yolov5-splash.avif) @@ -60,7 +60,7 @@ This example provides simple YOLOv5 training and inference examples. For full do === "Python" - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: + [PyTorch](https://www.ultralytics.com/glossary/pytorch) pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: ```python from ultralytics import YOLO @@ -117,7 +117,7 @@ Please note that YOLOv5 models are provided under [AGPL-3.0](https://github.com/ ### What is Ultralytics YOLOv5u and how does it differ from YOLOv5? -Ultralytics YOLOv5u is an advanced version of YOLOv5, integrating the anchor-free, objectness-free split head that enhances the accuracy-speed tradeoff for real-time object detection tasks. Unlike the traditional YOLOv5, YOLOv5u adopts an anchor-free detection mechanism, making it more flexible and adaptive in diverse scenarios. For more detailed information on its features, you can refer to the [YOLOv5 Overview](#overview). +Ultralytics YOLOv5u is an advanced version of YOLOv5, integrating the anchor-free, objectness-free split head that enhances the [accuracy](https://www.ultralytics.com/glossary/accuracy)-speed tradeoff for real-time object detection tasks. Unlike the traditional YOLOv5, YOLOv5u adopts an anchor-free detection mechanism, making it more flexible and adaptive in diverse scenarios. For more detailed information on its features, you can refer to the [YOLOv5 Overview](#overview). ### How does the anchor-free Ultralytics head improve object detection performance in YOLOv5u? diff --git a/docs/en/models/yolov6.md b/docs/en/models/yolov6.md index 5cf52931f7..b670d58d31 100644 --- a/docs/en/models/yolov6.md +++ b/docs/en/models/yolov6.md @@ -30,7 +30,7 @@ YOLOv6 provides various pre-trained models with different scales: - YOLOv6-L: 52.8% AP at 116 FPS. - YOLOv6-L6: State-of-the-art accuracy in real-time. -YOLOv6 also provides quantized models for different precisions and models optimized for mobile platforms. +YOLOv6 also provides quantized models for different [precisions](https://www.ultralytics.com/glossary/precision) and models optimized for mobile platforms. ## Usage Examples @@ -40,7 +40,7 @@ This example provides simple YOLOv6 training and inference examples. For full do === "Python" - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: + [PyTorch](https://www.ultralytics.com/glossary/pytorch) pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: ```python from ultralytics import YOLO @@ -72,7 +72,7 @@ This example provides simple YOLOv6 training and inference examples. For full do ## Supported Tasks and Modes -The YOLOv6 series offers a range of models, each optimized for high-performance [Object Detection](../tasks/detect.md). These models cater to varying computational needs and accuracy requirements, making them versatile for a wide array of applications. +The YOLOv6 series offers a range of models, each optimized for high-performance [Object Detection](../tasks/detect.md). These models cater to varying computational needs and [accuracy](https://www.ultralytics.com/glossary/accuracy) requirements, making them versatile for a wide array of applications. | Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | | ---------- | ------------------- | -------------------------------------- | --------- | ---------- | -------- | ------ | @@ -82,7 +82,7 @@ The YOLOv6 series offers a range of models, each optimized for high-performance | YOLOv6-L | `yolov6-l.pt` | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | | YOLOv6-L6 | `yolov6-l6.pt` | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | -This table provides a detailed overview of the YOLOv6 model variants, highlighting their capabilities in object detection tasks and their compatibility with various operational modes such as [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md). This comprehensive support ensures that users can fully leverage the capabilities of YOLOv6 models in a broad range of object detection scenarios. +This table provides a detailed overview of the YOLOv6 model variants, highlighting their capabilities in [object detection](https://www.ultralytics.com/glossary/object-detection) tasks and their compatibility with various operational modes such as [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md). This comprehensive support ensures that users can fully leverage the capabilities of YOLOv6 models in a broad range of object detection scenarios. ## Citations and Acknowledgements @@ -155,7 +155,7 @@ These models are evaluated on the COCO dataset using an NVIDIA Tesla T4 GPU. For ### How does the Anchor-Aided Training (AAT) strategy benefit YOLOv6? -Anchor-Aided Training (AAT) in YOLOv6 combines elements of anchor-based and anchor-free approaches, enhancing the model's detection capabilities without compromising inference efficiency. This strategy leverages anchors during training to improve bounding box predictions, making YOLOv6 effective in diverse object detection tasks. +Anchor-Aided Training (AAT) in YOLOv6 combines elements of anchor-based and anchor-free approaches, enhancing the model's detection capabilities without compromising inference efficiency. This strategy leverages anchors during training to improve [bounding box](https://www.ultralytics.com/glossary/bounding-box) predictions, making YOLOv6 effective in diverse object detection tasks. ### Which operational modes are supported by YOLOv6 models in Ultralytics? diff --git a/docs/en/models/yolov7.md b/docs/en/models/yolov7.md index b13467a974..1ba9dc271b 100644 --- a/docs/en/models/yolov7.md +++ b/docs/en/models/yolov7.md @@ -6,7 +6,7 @@ keywords: YOLOv7, real-time object detection, Ultralytics, AI, computer vision, # YOLOv7: Trainable Bag-of-Freebies -YOLOv7 is a state-of-the-art real-time object detector that surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS. It has the highest accuracy (56.8% AP) among all known real-time object detectors with 30 FPS or higher on GPU V100. Moreover, YOLOv7 outperforms other object detectors such as YOLOR, YOLOX, Scaled-YOLOv4, YOLOv5, and many others in speed and accuracy. The model is trained on the MS COCO dataset from scratch without using any other datasets or pre-trained weights. Source code for YOLOv7 is available on GitHub. +YOLOv7 is a state-of-the-art real-time object detector that surpasses all known object detectors in both speed and [accuracy](https://www.ultralytics.com/glossary/accuracy) in the range from 5 FPS to 160 FPS. It has the highest accuracy (56.8% AP) among all known real-time object detectors with 30 FPS or higher on GPU V100. Moreover, YOLOv7 outperforms other object detectors such as YOLOR, YOLOX, Scaled-YOLOv4, YOLOv5, and many others in speed and accuracy. The model is trained on the MS COCO dataset from scratch without using any other datasets or pre-trained weights. Source code for YOLOv7 is available on GitHub. ![YOLOv7 comparison with SOTA object detectors](https://github.com/ultralytics/docs/releases/download/0/yolov7-comparison-sota-object-detectors.avif) @@ -62,7 +62,7 @@ From the results in the YOLO comparison table we know that the proposed method h ## Overview -Real-time object detection is an important component in many computer vision systems, including multi-object tracking, autonomous driving, robotics, and medical image analysis. In recent years, real-time object detection development has focused on designing efficient architectures and improving the inference speed of various CPUs, GPUs, and neural processing units (NPUs). YOLOv7 supports both mobile GPU and GPU devices, from the edge to the cloud. +Real-time object detection is an important component in many [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) systems, including multi-object tracking, autonomous driving, robotics, and medical image analysis. In recent years, real-time object detection development has focused on designing efficient architectures and improving the inference speed of various CPUs, GPUs, and neural processing units (NPUs). YOLOv7 supports both mobile GPU and GPU devices, from the edge to the cloud. Unlike traditional real-time object detectors that focus on architecture optimization, YOLOv7 introduces a focus on the optimization of the training process. This includes modules and optimization methods designed to improve the accuracy of object detection without increasing the inference cost, a concept known as the "trainable bag-of-freebies". @@ -115,7 +115,7 @@ The original YOLOv7 paper can be found on [arXiv](https://arxiv.org/pdf/2207.026 ## FAQ -### What is YOLOv7 and why is it considered a breakthrough in real-time object detection? +### What is YOLOv7 and why is it considered a breakthrough in real-time [object detection](https://www.ultralytics.com/glossary/object-detection)? YOLOv7 is a cutting-edge real-time object detection model that achieves unparalleled speed and accuracy. It surpasses other models, such as YOLOX, YOLOv5, and PPYOLOE, in both parameters usage and inference speed. YOLOv7's distinguishing features include its model re-parameterization and dynamic label assignment, which optimize its performance without increasing inference costs. For more technical details about its architecture and comparison metrics with other state-of-the-art object detectors, refer to the [YOLOv7 paper](https://arxiv.org/pdf/2207.02696.pdf). diff --git a/docs/en/models/yolov8.md b/docs/en/models/yolov8.md index c95902beba..f7a32ef009 100644 --- a/docs/en/models/yolov8.md +++ b/docs/en/models/yolov8.md @@ -8,7 +8,7 @@ keywords: YOLOv8, real-time object detection, YOLO series, Ultralytics, computer ## Overview -YOLOv8 is the latest iteration in the YOLO series of real-time object detectors, offering cutting-edge performance in terms of accuracy and speed. Building upon the advancements of previous YOLO versions, YOLOv8 introduces new features and optimizations that make it an ideal choice for various object detection tasks in a wide range of applications. +YOLOv8 is the latest iteration in the YOLO series of real-time object detectors, offering cutting-edge performance in terms of accuracy and speed. Building upon the advancements of previous YOLO versions, YOLOv8 introduces new features and optimizations that make it an ideal choice for various [object detection](https://www.ultralytics.com/glossary/object-detection) tasks in a wide range of applications. ![Ultralytics YOLOv8](https://github.com/ultralytics/docs/releases/download/0/yolov8-comparison-plots.avif) @@ -25,14 +25,14 @@ YOLOv8 is the latest iteration in the YOLO series of real-time object detectors, ## Key Features -- **Advanced Backbone and Neck Architectures:** YOLOv8 employs state-of-the-art backbone and neck architectures, resulting in improved feature extraction and object detection performance. +- **Advanced Backbone and Neck Architectures:** YOLOv8 employs state-of-the-art backbone and neck architectures, resulting in improved [feature extraction](https://www.ultralytics.com/glossary/feature-extraction) and object detection performance. - **Anchor-free Split Ultralytics Head:** YOLOv8 adopts an anchor-free split Ultralytics head, which contributes to better accuracy and a more efficient detection process compared to anchor-based approaches. - **Optimized Accuracy-Speed Tradeoff:** With a focus on maintaining an optimal balance between accuracy and speed, YOLOv8 is suitable for real-time object detection tasks in diverse application areas. - **Variety of Pre-trained Models:** YOLOv8 offers a range of pre-trained models to cater to various tasks and performance requirements, making it easier to find the right model for your specific use case. ## Supported Tasks and Modes -The YOLOv8 series offers a diverse range of models, each specialized for specific tasks in computer vision. These models are designed to cater to various requirements, from object detection to more complex tasks like instance segmentation, pose/keypoints detection, oriented object detection, and classification. +The YOLOv8 series offers a diverse range of models, each specialized for specific tasks in computer vision. These models are designed to cater to various requirements, from object detection to more complex tasks like [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation), pose/keypoints detection, oriented object detection, and classification. Each variant of the YOLOv8 series is optimized for its respective task, ensuring high performance and accuracy. Additionally, these models are compatible with various operational modes including [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md), facilitating their use in different stages of deployment and development. @@ -44,7 +44,7 @@ Each variant of the YOLOv8 series is optimized for its respective task, ensuring | YOLOv8-obb | `yolov8n-obb.pt` `yolov8s-obb.pt` `yolov8m-obb.pt` `yolov8l-obb.pt` `yolov8x-obb.pt` | [Oriented Detection](../tasks/obb.md) | ✅ | ✅ | ✅ | ✅ | | YOLOv8-cls | `yolov8n-cls.pt` `yolov8s-cls.pt` `yolov8m-cls.pt` `yolov8l-cls.pt` `yolov8x-cls.pt` | [Classification](../tasks/classify.md) | ✅ | ✅ | ✅ | ✅ | -This table provides an overview of the YOLOv8 model variants, highlighting their applicability in specific tasks and their compatibility with various operational modes such as Inference, Validation, Training, and Export. It showcases the versatility and robustness of the YOLOv8 series, making them suitable for a variety of applications in computer vision. +This table provides an overview of the YOLOv8 model variants, highlighting their applicability in specific tasks and their compatibility with various operational modes such as Inference, Validation, Training, and Export. It showcases the versatility and robustness of the YOLOv8 series, making them suitable for a variety of applications in [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv). ## Performance Metrics @@ -133,7 +133,7 @@ Note the below example is for YOLOv8 [Detect](../tasks/detect.md) models for obj === "Python" - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: + [PyTorch](https://www.ultralytics.com/glossary/pytorch) pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: ```python from ultralytics import YOLO @@ -189,7 +189,7 @@ Please note that the DOI is pending and will be added to the citation once it is ### What is YOLOv8 and how does it differ from previous YOLO versions? -YOLOv8 is the latest iteration in the Ultralytics YOLO series, designed to improve real-time object detection performance with advanced features. Unlike earlier versions, YOLOv8 incorporates an **anchor-free split Ultralytics head**, state-of-the-art backbone and neck architectures, and offers optimized accuracy-speed tradeoff, making it ideal for diverse applications. For more details, check the [Overview](#overview) and [Key Features](#key-features) sections. +YOLOv8 is the latest iteration in the Ultralytics YOLO series, designed to improve real-time object detection performance with advanced features. Unlike earlier versions, YOLOv8 incorporates an **anchor-free split Ultralytics head**, state-of-the-art backbone and neck architectures, and offers optimized [accuracy](https://www.ultralytics.com/glossary/accuracy)-speed tradeoff, making it ideal for diverse applications. For more details, check the [Overview](#overview) and [Key Features](#key-features) sections. ### How can I use YOLOv8 for different computer vision tasks? @@ -201,7 +201,7 @@ YOLOv8 models achieve state-of-the-art performance across various benchmarking d ### How do I train a YOLOv8 model? -Training a YOLOv8 model can be done using either Python or CLI. Below are examples for training a model using a COCO-pretrained YOLOv8 model on the COCO8 dataset for 100 epochs: +Training a YOLOv8 model can be done using either Python or CLI. Below are examples for training a model using a COCO-pretrained YOLOv8 model on the COCO8 dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch): !!! example diff --git a/docs/en/models/yolov9.md b/docs/en/models/yolov9.md index a83f85d3ee..a0b2b74834 100644 --- a/docs/en/models/yolov9.md +++ b/docs/en/models/yolov9.md @@ -4,7 +4,7 @@ description: Explore YOLOv9, the latest leap in real-time object detection, feat keywords: YOLOv9, object detection, real-time, PGI, GELAN, deep learning, MS COCO, AI, neural networks, model efficiency, accuracy, Ultralytics --- -# YOLOv9: A Leap Forward in Object Detection Technology +# YOLOv9: A Leap Forward in [Object Detection](https://www.ultralytics.com/glossary/object-detection) Technology YOLOv9 marks a significant advancement in real-time object detection, introducing groundbreaking techniques such as Programmable Gradient Information (PGI) and the Generalized Efficient Layer Aggregation Network (GELAN). This model demonstrates remarkable improvements in efficiency, accuracy, and adaptability, setting new benchmarks on the MS COCO dataset. The YOLOv9 project, while developed by a separate open-source team, builds upon the robust codebase provided by [Ultralytics](https://www.ultralytics.com/) [YOLOv5](yolov5.md), showcasing the collaborative spirit of the AI research community. @@ -23,7 +23,7 @@ YOLOv9 marks a significant advancement in real-time object detection, introducin ## Introduction to YOLOv9 -In the quest for optimal real-time object detection, YOLOv9 stands out with its innovative approach to overcoming information loss challenges inherent in deep neural networks. By integrating PGI and the versatile GELAN architecture, YOLOv9 not only enhances the model's learning capacity but also ensures the retention of crucial information throughout the detection process, thereby achieving exceptional accuracy and performance. +In the quest for optimal real-time object detection, YOLOv9 stands out with its innovative approach to overcoming information loss challenges inherent in deep [neural networks](https://www.ultralytics.com/glossary/neural-network-nn). By integrating PGI and the versatile GELAN architecture, YOLOv9 not only enhances the model's learning capacity but also ensures the retention of crucial information throughout the detection process, thereby achieving exceptional accuracy and performance. ## Core Innovations of YOLOv9 @@ -47,7 +47,7 @@ The concept of Reversible Functions is another cornerstone of YOLOv9's design. A X = v_zeta(r_psi(X)) ``` -with `psi` and `zeta` as parameters for the reversible and its inverse function, respectively. This property is crucial for deep learning architectures, as it allows the network to retain a complete information flow, thereby enabling more accurate updates to the model's parameters. YOLOv9 incorporates reversible functions within its architecture to mitigate the risk of information degradation, especially in deeper layers, ensuring the preservation of critical data for object detection tasks. +with `psi` and `zeta` as parameters for the reversible and its inverse function, respectively. This property is crucial for [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) architectures, as it allows the network to retain a complete information flow, thereby enabling more accurate updates to the model's parameters. YOLOv9 incorporates reversible functions within its architecture to mitigate the risk of information degradation, especially in deeper layers, ensuring the preservation of critical data for object detection tasks. ### Impact on Lightweight Models @@ -86,7 +86,7 @@ By benchmarking, you can ensure that your model not only performs well in contro ## Performance on MS COCO Dataset -The performance of YOLOv9 on the [COCO dataset](../datasets/detect/coco.md) exemplifies its significant advancements in real-time object detection, setting new benchmarks across various model sizes. Table 1 presents a comprehensive comparison of state-of-the-art real-time object detectors, illustrating YOLOv9's superior efficiency and accuracy. +The performance of YOLOv9 on the [COCO dataset](../datasets/detect/coco.md) exemplifies its significant advancements in real-time object detection, setting new benchmarks across various model sizes. Table 1 presents a comprehensive comparison of state-of-the-art real-time object detectors, illustrating YOLOv9's superior efficiency and [accuracy](https://www.ultralytics.com/glossary/accuracy). **Table 1. Comparison of State-of-the-Art Real-Time Object Detectors** @@ -109,7 +109,7 @@ The performance of YOLOv9 on the [COCO dataset](../datasets/detect/coco.md) exem | [YOLOv9c-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov9c-seg.pt) | 640 | 52.4 | 42.2 | 27.9 | 159.4 | | [YOLOv9e-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov9e-seg.pt) | 640 | 55.1 | 44.3 | 60.5 | 248.4 | -YOLOv9's iterations, ranging from the tiny `t` variant to the extensive `e` model, demonstrate improvements not only in accuracy (mAP metrics) but also in efficiency with a reduced number of parameters and computational needs (FLOPs). This table underscores YOLOv9's ability to deliver high precision while maintaining or reducing the computational overhead compared to prior versions and competing models. +YOLOv9's iterations, ranging from the tiny `t` variant to the extensive `e` model, demonstrate improvements not only in accuracy (mAP metrics) but also in efficiency with a reduced number of parameters and computational needs (FLOPs). This table underscores YOLOv9's ability to deliver high [precision](https://www.ultralytics.com/glossary/precision) while maintaining or reducing the computational overhead compared to prior versions and competing models. Comparatively, YOLOv9 exhibits remarkable gains: @@ -118,7 +118,7 @@ Comparatively, YOLOv9 exhibits remarkable gains: The YOLOv9c model, in particular, highlights the effectiveness of the architecture's optimizations. It operates with 42% fewer parameters and 21% less computational demand than YOLOv7 AF, yet it achieves comparable accuracy, demonstrating YOLOv9's significant efficiency improvements. Furthermore, the YOLOv9e model sets a new standard for large models, with 15% fewer parameters and 25% less computational need than [YOLOv8x](yolov8.md), alongside an incremental 1.7% improvement in AP. -These results showcase YOLOv9's strategic advancements in model design, emphasizing its enhanced efficiency without compromising on the precision essential for real-time object detection tasks. The model not only pushes the boundaries of performance metrics but also emphasizes the importance of computational efficiency, making it a pivotal development in the field of computer vision. +These results showcase YOLOv9's strategic advancements in model design, emphasizing its enhanced efficiency without compromising on the precision essential for real-time object detection tasks. The model not only pushes the boundaries of performance metrics but also emphasizes the importance of computational efficiency, making it a pivotal development in the field of [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv). ## Conclusion @@ -132,7 +132,7 @@ This example provides simple YOLOv9 training and inference examples. For full do === "Python" - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: + [PyTorch](https://www.ultralytics.com/glossary/pytorch) pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: ```python from ultralytics import YOLO @@ -235,4 +235,4 @@ YOLOv9 is designed to mitigate information loss, which is particularly important ### What tasks and modes does YOLOv9 support? -YOLOv9 supports various tasks including object detection and instance segmentation. It is compatible with multiple operational modes such as inference, validation, training, and export. This versatility makes YOLOv9 adaptable to diverse real-time computer vision applications. Refer to the [supported tasks and modes](#supported-tasks-and-modes) section for more information. +YOLOv9 supports various tasks including object detection and [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation). It is compatible with multiple operational modes such as inference, validation, training, and export. This versatility makes YOLOv9 adaptable to diverse real-time computer vision applications. Refer to the [supported tasks and modes](#supported-tasks-and-modes) section for more information. diff --git a/docs/en/modes/benchmark.md b/docs/en/modes/benchmark.md index bdce015e5c..209a0e03e0 100644 --- a/docs/en/modes/benchmark.md +++ b/docs/en/modes/benchmark.md @@ -10,7 +10,7 @@ keywords: model benchmarking, YOLOv8, Ultralytics, performance evaluation, expor ## Introduction -Once your model is trained and validated, the next logical step is to evaluate its performance in various real-world scenarios. Benchmark mode in Ultralytics YOLOv8 serves this purpose by providing a robust framework for assessing the speed and accuracy of your model across a range of export formats. +Once your model is trained and validated, the next logical step is to evaluate its performance in various real-world scenarios. Benchmark mode in Ultralytics YOLOv8 serves this purpose by providing a robust framework for assessing the speed and [accuracy](https://www.ultralytics.com/glossary/accuracy) of your model across a range of export formats.


@@ -32,8 +32,8 @@ Once your model is trained and validated, the next logical step is to evaluate i ### Key Metrics in Benchmark Mode -- **mAP50-95:** For object detection, segmentation, and pose estimation. -- **accuracy_top5:** For image classification. +- **mAP50-95:** For [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and pose estimation. +- **accuracy_top5:** For [image classification](https://www.ultralytics.com/glossary/image-classification). - **Inference Time:** Time taken for each image in milliseconds. ### Supported Export Formats @@ -73,15 +73,15 @@ Run YOLOv8n benchmarks on all supported export formats including ONNX, TensorRT Arguments such as `model`, `data`, `imgsz`, `half`, `device`, and `verbose` provide users with the flexibility to fine-tune the benchmarks to their specific needs and compare the performance of different export formats with ease. -| Key | Default Value | Description | -| --------- | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | -| `model` | `None` | Specifies the path to the model file. Accepts both `.pt` and `.yaml` formats, e.g., `"yolov8n.pt"` for pre-trained models or configuration files. | -| `data` | `None` | Path to a YAML file defining the dataset for benchmarking, typically including paths and settings for validation data. Example: `"coco8.yaml"`. | -| `imgsz` | `640` | The input image size for the model. Can be a single integer for square images or a tuple `(width, height)` for non-square, e.g., `(640, 480)`. | -| `half` | `False` | Enables FP16 (half-precision) inference, reducing memory usage and possibly increasing speed on compatible hardware. Use `half=True` to enable. | -| `int8` | `False` | Activates INT8 quantization for further optimized performance on supported devices, especially useful for edge devices. Set `int8=True` to use. | -| `device` | `None` | Defines the computation device(s) for benchmarking, such as `"cpu"`, `"cuda:0"`, or a list of devices like `"cuda:0,1"` for multi-GPU setups. | -| `verbose` | `False` | Controls the level of detail in logging output. A boolean value; set `verbose=True` for detailed logs or a float for thresholding errors. | +| Key | Default Value | Description | +| --------- | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `model` | `None` | Specifies the path to the model file. Accepts both `.pt` and `.yaml` formats, e.g., `"yolov8n.pt"` for pre-trained models or configuration files. | +| `data` | `None` | Path to a YAML file defining the dataset for benchmarking, typically including paths and settings for [validation data](https://www.ultralytics.com/glossary/validation-data). Example: `"coco8.yaml"`. | +| `imgsz` | `640` | The input image size for the model. Can be a single integer for square images or a tuple `(width, height)` for non-square, e.g., `(640, 480)`. | +| `half` | `False` | Enables FP16 (half-precision) inference, reducing memory usage and possibly increasing speed on compatible hardware. Use `half=True` to enable. | +| `int8` | `False` | Activates INT8 quantization for further optimized performance on supported devices, especially useful for edge devices. Set `int8=True` to use. | +| `device` | `None` | Defines the computation device(s) for benchmarking, such as `"cpu"`, `"cuda:0"`, or a list of devices like `"cuda:0,1"` for multi-GPU setups. | +| `verbose` | `False` | Controls the level of detail in logging output. A boolean value; set `verbose=True` for detailed logs or a float for thresholding errors. | ## Export Formats @@ -95,7 +95,7 @@ See full `export` details in the [Export](../modes/export.md) page. ### How do I benchmark my YOLOv8 model's performance using Ultralytics? -Ultralytics YOLOv8 offers a Benchmark mode to assess your model's performance across different export formats. This mode provides insights into key metrics such as mean Average Precision (mAP50-95), accuracy, and inference time in milliseconds. To run benchmarks, you can use either Python or CLI commands. For example, to benchmark on a GPU: +Ultralytics YOLOv8 offers a Benchmark mode to assess your model's performance across different export formats. This mode provides insights into key metrics such as [mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP50-95), accuracy, and inference time in milliseconds. To run benchmarks, you can use either Python or CLI commands. For example, to benchmark on a GPU: !!! example @@ -142,7 +142,7 @@ YOLOv8 supports a variety of export formats, each tailored for specific hardware - **ONNX:** Best for CPU performance. - **TensorRT:** Ideal for GPU efficiency. - **OpenVINO:** Optimized for Intel hardware. -- **CoreML & TensorFlow:** Useful for iOS and general ML applications. +- **CoreML & [TensorFlow](https://www.ultralytics.com/glossary/tensorflow):** Useful for iOS and general ML applications. For a complete list of supported formats and their respective advantages, check out the [Supported Export Formats](#supported-export-formats) section. ### What arguments can I use to fine-tune my YOLOv8 benchmarks? diff --git a/docs/en/modes/export.md b/docs/en/modes/export.md index a29c4c70d9..706dd91cdc 100644 --- a/docs/en/modes/export.md +++ b/docs/en/modes/export.md @@ -76,7 +76,7 @@ This table details the configurations and options available for exporting YOLO m {% include "macros/export-args.md" %} -Adjusting these parameters allows for customization of the export process to fit specific requirements, such as deployment environment, hardware constraints, and performance targets. Selecting the appropriate format and settings is essential for achieving the best balance between model size, speed, and accuracy. +Adjusting these parameters allows for customization of the export process to fit specific requirements, such as deployment environment, hardware constraints, and performance targets. Selecting the appropriate format and settings is essential for achieving the best balance between model size, speed, and [accuracy](https://www.ultralytics.com/glossary/accuracy). ## Export Formats diff --git a/docs/en/modes/index.md b/docs/en/modes/index.md index 6797ac19df..2b56680efc 100644 --- a/docs/en/modes/index.md +++ b/docs/en/modes/index.md @@ -10,7 +10,7 @@ keywords: Ultralytics, YOLOv8, machine learning, model training, validation, pre ## Introduction -Ultralytics YOLOv8 is not just another object detection model; it's a versatile framework designed to cover the entire lifecycle of machine learning models—from data ingestion and model training to validation, deployment, and real-world tracking. Each mode serves a specific purpose and is engineered to offer you the flexibility and efficiency required for different tasks and use-cases. +Ultralytics YOLOv8 is not just another object detection model; it's a versatile framework designed to cover the entire lifecycle of [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) models—from data ingestion and model training to validation, deployment, and real-world tracking. Each mode serves a specific purpose and is engineered to offer you the flexibility and efficiency required for different tasks and use-cases.


@@ -30,7 +30,7 @@ Understanding the different **modes** that Ultralytics YOLOv8 supports is critic - **Train** mode: Fine-tune your model on custom or preloaded datasets. - **Val** mode: A post-training checkpoint to validate model performance. - **Predict** mode: Unleash the predictive power of your model on real-world data. -- **Export** mode: Make your model deployment-ready in various formats. +- **Export** mode: Make your [model deployment](https://www.ultralytics.com/glossary/model-deployment)-ready in various formats. - **Track** mode: Extend your object detection model into real-time tracking applications. - **Benchmark** mode: Analyze the speed and accuracy of your model in diverse deployment environments. @@ -74,7 +74,7 @@ Benchmark mode is used to profile the speed and accuracy of various export forma ## FAQ -### How do I train a custom object detection model with Ultralytics YOLOv8? +### How do I train a custom [object detection](https://www.ultralytics.com/glossary/object-detection) model with Ultralytics YOLOv8? Training a custom object detection model with Ultralytics YOLOv8 involves using the train mode. You need a dataset formatted in YOLO format, containing images and corresponding annotation files. Use the following command to start the training process: @@ -104,7 +104,7 @@ Ultralytics YOLOv8 uses various metrics during the validation process to assess - **mAP (mean Average Precision)**: This evaluates the accuracy of object detection. - **IOU (Intersection over Union)**: Measures the overlap between predicted and ground truth bounding boxes. -- **Precision and Recall**: Precision measures the ratio of true positive detections to the total detected positives, while recall measures the ratio of true positive detections to the total actual positives. +- **[Precision](https://www.ultralytics.com/glossary/precision) and [Recall](https://www.ultralytics.com/glossary/recall)**: Precision measures the ratio of true positive detections to the total detected positives, while recall measures the ratio of true positive detections to the total actual positives. You can run the following command to start the validation: @@ -154,7 +154,7 @@ Detailed steps for each export format can be found in the [Export Guide](../mode ### What is the purpose of the benchmark mode in Ultralytics YOLOv8? -Benchmark mode in Ultralytics YOLOv8 is used to analyze the speed and accuracy of various export formats such as ONNX, TensorRT, and OpenVINO. It provides metrics like model size, `mAP50-95` for object detection, and inference time across different hardware setups, helping you choose the most suitable format for your deployment needs. +Benchmark mode in Ultralytics YOLOv8 is used to analyze the speed and [accuracy](https://www.ultralytics.com/glossary/accuracy) of various export formats such as ONNX, TensorRT, and OpenVINO. It provides metrics like model size, `mAP50-95` for object detection, and inference time across different hardware setups, helping you choose the most suitable format for your deployment needs. !!! example diff --git a/docs/en/modes/predict.md b/docs/en/modes/predict.md index 5ca5dab9d8..196d9e2028 100644 --- a/docs/en/modes/predict.md +++ b/docs/en/modes/predict.md @@ -10,7 +10,7 @@ keywords: Ultralytics, YOLOv8, model prediction, inference, predict mode, real-t ## Introduction -In the world of machine learning and computer vision, the process of making sense out of visual data is called 'inference' or 'prediction'. Ultralytics YOLOv8 offers a powerful feature known as **predict mode** that is tailored for high-performance, real-time inference on a wide range of data sources. +In the world of [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv), the process of making sense out of visual data is called 'inference' or 'prediction'. Ultralytics YOLOv8 offers a powerful feature known as **predict mode** that is tailored for high-performance, real-time inference on a wide range of data sources.


@@ -35,7 +35,7 @@ In the world of machine learning and computer vision, the process of making sens Here's why you should consider YOLOv8's predict mode for your various inference needs: - **Versatility:** Capable of making inferences on images, videos, and even live streams. -- **Performance:** Engineered for real-time, high-speed processing without sacrificing accuracy. +- **Performance:** Engineered for real-time, high-speed processing without sacrificing [accuracy](https://www.ultralytics.com/glossary/accuracy). - **Ease of Use:** Intuitive Python and CLI interfaces for rapid deployment and testing. - **Highly Customizable:** Various settings and parameters to tune the model's inference behavior according to your specific requirements. @@ -104,22 +104,22 @@ YOLOv8 can process different types of input sources for inference, as shown in t Use `stream=True` for processing long videos or large datasets to efficiently manage memory. When `stream=False`, the results for all frames or data points are stored in memory, which can quickly add up and cause out-of-memory errors for large inputs. In contrast, `stream=True` utilizes a generator, which only keeps the results of the current frame or data point in memory, significantly reducing memory consumption and preventing out-of-memory issues. -| Source | Example | Type | Notes | -| --------------- | ------------------------------------------ | --------------- | ------------------------------------------------------------------------------------------- | -| image | `'image.jpg'` | `str` or `Path` | Single image file. | -| URL | `'https://ultralytics.com/images/bus.jpg'` | `str` | URL to an image. | -| screenshot | `'screen'` | `str` | Capture a screenshot. | -| PIL | `Image.open('image.jpg')` | `PIL.Image` | HWC format with RGB channels. | -| OpenCV | `cv2.imread('image.jpg')` | `np.ndarray` | HWC format with BGR channels `uint8 (0-255)`. | -| numpy | `np.zeros((640,1280,3))` | `np.ndarray` | HWC format with BGR channels `uint8 (0-255)`. | -| torch | `torch.zeros(16,3,320,640)` | `torch.Tensor` | BCHW format with RGB channels `float32 (0.0-1.0)`. | -| CSV | `'sources.csv'` | `str` or `Path` | CSV file containing paths to images, videos, or directories. | -| video ✅ | `'video.mp4'` | `str` or `Path` | Video file in formats like MP4, AVI, etc. | -| directory ✅ | `'path/'` | `str` or `Path` | Path to a directory containing images or videos. | -| glob ✅ | `'path/*.jpg'` | `str` | Glob pattern to match multiple files. Use the `*` character as a wildcard. | -| YouTube ✅ | `'https://youtu.be/LNwODJXcvt4'` | `str` | URL to a YouTube video. | -| stream ✅ | `'rtsp://example.com/media.mp4'` | `str` | URL for streaming protocols such as RTSP, RTMP, TCP, or an IP address. | -| multi-stream ✅ | `'list.streams'` | `str` or `Path` | `*.streams` text file with one stream URL per row, i.e. 8 streams will run at batch-size 8. | +| Source | Example | Type | Notes | +| ----------------------------------------------------- | ------------------------------------------ | --------------- | ------------------------------------------------------------------------------------------- | +| image | `'image.jpg'` | `str` or `Path` | Single image file. | +| URL | `'https://ultralytics.com/images/bus.jpg'` | `str` | URL to an image. | +| screenshot | `'screen'` | `str` | Capture a screenshot. | +| PIL | `Image.open('image.jpg')` | `PIL.Image` | HWC format with RGB channels. | +| [OpenCV](https://www.ultralytics.com/glossary/opencv) | `cv2.imread('image.jpg')` | `np.ndarray` | HWC format with BGR channels `uint8 (0-255)`. | +| numpy | `np.zeros((640,1280,3))` | `np.ndarray` | HWC format with BGR channels `uint8 (0-255)`. | +| torch | `torch.zeros(16,3,320,640)` | `torch.Tensor` | BCHW format with RGB channels `float32 (0.0-1.0)`. | +| CSV | `'sources.csv'` | `str` or `Path` | CSV file containing paths to images, videos, or directories. | +| video ✅ | `'video.mp4'` | `str` or `Path` | Video file in formats like MP4, AVI, etc. | +| directory ✅ | `'path/'` | `str` or `Path` | Path to a directory containing images or videos. | +| glob ✅ | `'path/*.jpg'` | `str` | Glob pattern to match multiple files. Use the `*` character as a wildcard. | +| YouTube ✅ | `'https://youtu.be/LNwODJXcvt4'` | `str` | URL to a YouTube video. | +| stream ✅ | `'rtsp://example.com/media.mp4'` | `str` | URL for streaming protocols such as RTSP, RTMP, TCP, or an IP address. | +| multi-stream ✅ | `'list.streams'` | `str` or `Path` | `*.streams` text file with one stream URL per row, i.e. 8 streams will run at batch-size 8. | Below are code examples for using each source type: @@ -229,7 +229,7 @@ Below are code examples for using each source type: === "torch" - Run inference on an image represented as a PyTorch tensor. + Run inference on an image represented as a [PyTorch](https://www.ultralytics.com/glossary/pytorch) tensor. ```python import torch @@ -328,9 +328,10 @@ Below are code examples for using each source type: results = model(source, stream=True) # generator of Results objects ``` - === "Streams" + === "Stream" + + Use the stream mode to run inference on live video streams using RTSP, RTMP, TCP, or IP address protocols. If a single stream is provided, the model runs inference with a [batch size](https://www.ultralytics.com/glossary/batch-size) of 1. For multiple streams, a `.streams` text file can be used to perform batched inference, where the batch size is determined by the number of streams provided (e.g., batch-size 8 for 8 streams). - Run inference on remote streaming sources using RTSP, RTMP, TCP and IP address protocols. If multiple streams are provided in a `*.streams` text file then batched inference will run, i.e. 8 streams will run at batch-size 8, otherwise single streams will run at batch-size 1. ```python from ultralytics import YOLO @@ -338,15 +339,43 @@ Below are code examples for using each source type: model = YOLO("yolov8n.pt") # Single stream with batch-size 1 inference - source = "rtsp://example.com/media.mp4" # RTSP, RTMP, TCP or IP streaming address + source = "rtsp://example.com/media.mp4" # RTSP, RTMP, TCP, or IP streaming address + + # Run inference on the source + results = model(source, stream=True) # generator of Results objects + ``` + + For single stream usage, the batch size is set to 1 by default, allowing efficient real-time processing of the video feed. + + === "Multi-Stream" + + To handle multiple video streams simultaneously, use a `.streams` text file containing the streaming sources. The model will run batched inference where the batch size equals the number of streams. This setup enables efficient processing of multiple feeds concurrently. + + ```python + from ultralytics import YOLO + + # Load a pretrained YOLOv8n model + model = YOLO("yolov8n.pt") - # Multiple streams with batched inference (i.e. batch-size 8 for 8 streams) - source = "path/to/list.streams" # *.streams text file with one streaming address per row + # Multiple streams with batched inference (e.g., batch-size 8 for 8 streams) + source = "path/to/list.streams" # *.streams text file with one streaming address per line # Run inference on the source results = model(source, stream=True) # generator of Results objects ``` + Example `.streams` text file: + + ```txt + rtsp://example.com/media1.mp4 + rtsp://example.com/media2.mp4 + rtmp://example2.com/live + tcp://192.168.1.100:554 + ... + ``` + + Each row in the file represents a streaming source, allowing you to monitor and perform inference on several video streams at once. + ## Inference Arguments `model.predict()` accepts multiple arguments that can be passed at inference time to override defaults: @@ -779,7 +808,7 @@ This script will run predictions on each frame of the video, visualize the resul ### What is Ultralytics YOLOv8 and its predict mode for real-time inference? -Ultralytics YOLOv8 is a state-of-the-art model for real-time object detection, segmentation, and classification. Its **predict mode** allows users to perform high-speed inference on various data sources such as images, videos, and live streams. Designed for performance and versatility, it also offers batch processing and streaming modes. For more details on its features, check out the [Ultralytics YOLOv8 predict mode](#key-features-of-predict-mode). +Ultralytics YOLOv8 is a state-of-the-art model for real-time [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and classification. Its **predict mode** allows users to perform high-speed inference on various data sources such as images, videos, and live streams. Designed for performance and versatility, it also offers batch processing and streaming modes. For more details on its features, check out the [Ultralytics YOLOv8 predict mode](#key-features-of-predict-mode). ### How can I run inference using Ultralytics YOLOv8 on different data sources? diff --git a/docs/en/modes/track.md b/docs/en/modes/track.md index 7ed84189cc..46c43b0b1a 100644 --- a/docs/en/modes/track.md +++ b/docs/en/modes/track.md @@ -12,9 +12,9 @@ Object tracking in the realm of video analytics is a critical task that not only ## Why Choose Ultralytics YOLO for Object Tracking? -The output from Ultralytics trackers is consistent with standard object detection but has the added value of object IDs. This makes it easy to track objects in video streams and perform subsequent analytics. Here's why you should consider using Ultralytics YOLO for your object tracking needs: +The output from Ultralytics trackers is consistent with standard [object detection](https://www.ultralytics.com/glossary/object-detection) but has the added value of object IDs. This makes it easy to track objects in video streams and perform subsequent analytics. Here's why you should consider using Ultralytics YOLO for your object tracking needs: -- **Efficiency:** Process video streams in real-time without compromising accuracy. +- **Efficiency:** Process video streams in real-time without compromising [accuracy](https://www.ultralytics.com/glossary/accuracy). - **Flexibility:** Supports multiple tracking algorithms and configurations. - **Ease of Use:** Simple Python API and CLI options for quick integration and deployment. - **Customizability:** Easy to use with custom trained YOLO models, allowing integration into domain-specific applications. @@ -153,7 +153,7 @@ For a comprehensive list of tracking arguments, refer to the [ultralytics/cfg/tr ### Persisting Tracks Loop -Here is a Python script using OpenCV (`cv2`) and YOLOv8 to run object tracking on video frames. This script still assumes you have already installed the necessary packages (`opencv-python` and `ultralytics`). The `persist=True` argument tells the tracker that the current image or frame is the next in a sequence and to expect tracks from the previous image in the current image. +Here is a Python script using [OpenCV](https://www.ultralytics.com/glossary/opencv) (`cv2`) and YOLOv8 to run object tracking on video frames. This script still assumes you have already installed the necessary packages (`opencv-python` and `ultralytics`). The `persist=True` argument tells the tracker that the current image or frame is the next in a sequence and to expect tracks from the previous image in the current image. !!! example "Streaming for-loop with tracking" diff --git a/docs/en/modes/train.md b/docs/en/modes/train.md index 03e3be223d..f5722b7280 100644 --- a/docs/en/modes/train.md +++ b/docs/en/modes/train.md @@ -10,7 +10,7 @@ keywords: Ultralytics, YOLOv8, model training, deep learning, object detection, ## Introduction -Training a deep learning model involves feeding it data and adjusting its parameters so that it can make accurate predictions. Train mode in Ultralytics YOLOv8 is engineered for effective and efficient training of object detection models, fully utilizing modern hardware capabilities. This guide aims to cover all the details you need to get started with training your own models using YOLOv8's robust set of features. +Training a [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) model involves feeding it data and adjusting its parameters so that it can make accurate predictions. Train mode in Ultralytics YOLOv8 is engineered for effective and efficient training of object detection models, fully utilizing modern hardware capabilities. This guide aims to cover all the details you need to get started with training your own models using YOLOv8's robust set of features.


@@ -47,7 +47,7 @@ The following are some notable features of YOLOv8's Train mode: ## Usage Examples -Train YOLOv8n on the COCO8 dataset for 100 epochs at image size 640. The training device can be specified using the `device` argument. If no argument is passed GPU `device=0` will be used if available, otherwise `device='cpu'` will be used. See Arguments section below for a full list of training arguments. +Train YOLOv8n on the COCO8 dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) at image size 640. The training device can be specified using the `device` argument. If no argument is passed GPU `device=0` will be used if available, otherwise `device='cpu'` will be used. See Arguments section below for a full list of training arguments. !!! example "Single-GPU and CPU Training Example" @@ -140,7 +140,7 @@ While leveraging the computational power of the M1/M2 chips, this enables more e Resuming training from a previously saved state is a crucial feature when working with deep learning models. This can come in handy in various scenarios, like when the training process has been unexpectedly interrupted, or when you wish to continue training a model with new data or for more epochs. -When training is resumed, Ultralytics YOLO loads the weights from the last saved model and also restores the optimizer state, learning rate scheduler, and the epoch number. This allows you to continue the training process seamlessly from where it was left off. +When training is resumed, Ultralytics YOLO loads the weights from the last saved model and also restores the optimizer state, [learning rate](https://www.ultralytics.com/glossary/learning-rate) scheduler, and the epoch number. This allows you to continue the training process seamlessly from where it was left off. You can easily resume training in Ultralytics YOLO by setting the `resume` argument to `True` when calling the `train` method, and specifying the path to the `.pt` file containing the partially trained model weights. @@ -173,7 +173,7 @@ Remember that checkpoints are saved at the end of every epoch by default, or at ## Train Settings -The training settings for YOLO models encompass various hyperparameters and configurations used during the training process. These settings influence the model's performance, speed, and accuracy. Key training settings include batch size, learning rate, momentum, and weight decay. Additionally, the choice of optimizer, loss function, and training dataset composition can impact the training process. Careful tuning and experimentation with these settings are crucial for optimizing performance. +The training settings for YOLO models encompass various hyperparameters and configurations used during the training process. These settings influence the model's performance, speed, and [accuracy](https://www.ultralytics.com/glossary/accuracy). Key training settings include batch size, learning rate, momentum, and weight decay. Additionally, the choice of optimizer, [loss function](https://www.ultralytics.com/glossary/loss-function), and training dataset composition can impact the training process. Careful tuning and experimentation with these settings are crucial for optimizing performance. {% include "macros/train-args.md" %} @@ -181,13 +181,13 @@ The training settings for YOLO models encompass various hyperparameters and conf The `batch` argument can be configured in three ways: - - **Fixed Batch Size**: Set an integer value (e.g., `batch=16`), specifying the number of images per batch directly. + - **Fixed [Batch Size](https://www.ultralytics.com/glossary/batch-size)**: Set an integer value (e.g., `batch=16`), specifying the number of images per batch directly. - **Auto Mode (60% GPU Memory)**: Use `batch=-1` to automatically adjust batch size for approximately 60% CUDA memory utilization. - **Auto Mode with Utilization Fraction**: Set a fraction value (e.g., `batch=0.70`) to adjust batch size based on the specified fraction of GPU memory usage. ## Augmentation Settings and Hyperparameters -Augmentation techniques are essential for improving the robustness and performance of YOLO models by introducing variability into the training data, helping the model generalize better to unseen data. The following table outlines the purpose and effect of each augmentation argument: +Augmentation techniques are essential for improving the robustness and performance of YOLO models by introducing variability into the [training data](https://www.ultralytics.com/glossary/training-data), helping the model generalize better to unseen data. The following table outlines the purpose and effect of each augmentation argument: {% include "macros/augmentation-args.md" %} @@ -243,7 +243,7 @@ After running this script, you will need to sign in to your ClearML account on t ### TensorBoard -[TensorBoard](https://www.tensorflow.org/tensorboard) is a visualization toolkit for TensorFlow. It allows you to visualize your TensorFlow graph, plot quantitative metrics about the execution of your graph, and show additional data like images that pass through it. +[TensorBoard](https://www.tensorflow.org/tensorboard) is a visualization toolkit for [TensorFlow](https://www.ultralytics.com/glossary/tensorflow). It allows you to visualize your TensorFlow graph, plot quantitative metrics about the execution of your graph, and show additional data like images that pass through it. To use TensorBoard in [Google Colab](https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb): @@ -272,7 +272,7 @@ After setting up your logger, you can then proceed with your model training. All ## FAQ -### How do I train an object detection model using Ultralytics YOLOv8? +### How do I train an [object detection](https://www.ultralytics.com/glossary/object-detection) model using Ultralytics YOLOv8? To train an object detection model using Ultralytics YOLOv8, you can either use the Python API or the CLI. Below is an example for both: diff --git a/docs/en/modes/val.md b/docs/en/modes/val.md index 85b15f51e5..91eb4c2a87 100644 --- a/docs/en/modes/val.md +++ b/docs/en/modes/val.md @@ -10,7 +10,7 @@ keywords: Ultralytics, YOLOv8, model validation, machine learning, object detect ## Introduction -Validation is a critical step in the machine learning pipeline, allowing you to assess the quality of your trained models. Val mode in Ultralytics YOLOv8 provides a robust suite of tools and metrics for evaluating the performance of your object detection models. This guide serves as a complete resource for understanding how to effectively use the Val mode to ensure that your models are both accurate and reliable. +Validation is a critical step in the [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) pipeline, allowing you to assess the quality of your trained models. Val mode in Ultralytics YOLOv8 provides a robust suite of tools and metrics for evaluating the performance of your [object detection](https://www.ultralytics.com/glossary/object-detection) models. This guide serves as a complete resource for understanding how to effectively use the Val mode to ensure that your models are both accurate and reliable.


@@ -30,7 +30,7 @@ Here's why using YOLOv8's Val mode is advantageous: - **Precision:** Get accurate metrics like mAP50, mAP75, and mAP50-95 to comprehensively evaluate your model. - **Convenience:** Utilize built-in features that remember training settings, simplifying the validation process. - **Flexibility:** Validate your model with the same or different datasets and image sizes. -- **Hyperparameter Tuning:** Use validation metrics to fine-tune your model for better performance. +- **[Hyperparameter Tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning):** Use validation metrics to fine-tune your model for better performance. ### Key Features of Val Mode @@ -47,7 +47,7 @@ These are the notable functionalities offered by YOLOv8's Val mode: ## Usage Examples -Validate trained YOLOv8n model accuracy on the COCO8 dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. See Arguments section below for a full list of export arguments. +Validate trained YOLOv8n model [accuracy](https://www.ultralytics.com/glossary/accuracy) on the COCO8 dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. See Arguments section below for a full list of export arguments. !!! example @@ -156,7 +156,7 @@ For a complete performance evaluation, it's crucial to review all these metrics. Using Ultralytics YOLO for validation provides several advantages: -- **Precision:** YOLOv8 offers accurate performance metrics including mAP50, mAP75, and mAP50-95. +- **[Precision](https://www.ultralytics.com/glossary/precision):** YOLOv8 offers accurate performance metrics including mAP50, mAP75, and mAP50-95. - **Convenience:** The models remember their training settings, making validation straightforward. - **Flexibility:** You can validate against the same or different datasets and image sizes. - **Hyperparameter Tuning:** Validation metrics help in fine-tuning models for better performance. @@ -165,7 +165,7 @@ These benefits ensure that your models are evaluated thoroughly and can be optim ### Can I validate my YOLOv8 model using a custom dataset? -Yes, you can validate your YOLOv8 model using a [custom dataset](https://docs.ultralytics.com/datasets/). Specify the `data` argument with the path to your dataset configuration file. This file should include paths to the validation data, class names, and other relevant details. +Yes, you can validate your YOLOv8 model using a [custom dataset](https://docs.ultralytics.com/datasets/). Specify the `data` argument with the path to your dataset configuration file. This file should include paths to the [validation data](https://www.ultralytics.com/glossary/validation-data), class names, and other relevant details. Example in Python: diff --git a/docs/en/quickstart.md b/docs/en/quickstart.md index a844dbbe70..7b5a3a27c0 100644 --- a/docs/en/quickstart.md +++ b/docs/en/quickstart.md @@ -143,7 +143,7 @@ See the `ultralytics` [pyproject.toml](https://github.com/ultralytics/ultralytic !!! tip - PyTorch requirements vary by operating system and CUDA requirements, so it's recommended to install PyTorch first following instructions at [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally/). + [PyTorch](https://www.ultralytics.com/glossary/pytorch) requirements vary by operating system and CUDA requirements, so it's recommended to install PyTorch first following instructions at [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally/). PyTorch Installation Instructions @@ -170,7 +170,7 @@ The Ultralytics command line interface (CLI) allows for simple single-line comma === "Train" - Train a detection model for 10 epochs with an initial learning_rate of 0.01 + Train a detection model for 10 [epochs](https://www.ultralytics.com/glossary/epoch) with an initial learning_rate of 0.01 ```bash yolo train data=coco8.yaml model=yolov8n.pt epochs=10 lr0=0.01 ``` @@ -221,7 +221,7 @@ The Ultralytics command line interface (CLI) allows for simple single-line comma ## Use Ultralytics with Python -YOLOv8's Python interface allows for seamless integration into your Python projects, making it easy to load, run, and process the model's output. Designed with simplicity and ease of use in mind, the Python interface enables users to quickly implement object detection, segmentation, and classification in their projects. This makes YOLOv8's Python interface an invaluable tool for anyone looking to incorporate these functionalities into their Python projects. +YOLOv8's Python interface allows for seamless integration into your Python projects, making it easy to load, run, and process the model's output. Designed with simplicity and ease of use in mind, the Python interface enables users to quickly implement [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and classification in their projects. This makes YOLOv8's Python interface an invaluable tool for anyone looking to incorporate these functionalities into their Python projects. For example, users can load a model, train it, evaluate its performance on a validation set, and even export it to ONNX format with just a few lines of code. Check out the [Python Guide](usage/python.md) to learn more about using YOLOv8 within your Python projects. @@ -253,7 +253,7 @@ For example, users can load a model, train it, evaluate its performance on a val ## Ultralytics Settings -The Ultralytics library provides a powerful settings management system to enable fine-grained control over your experiments. By making use of the `SettingsManager` housed within the `ultralytics.utils` module, users can readily access and alter their settings. These are stored in a YAML file and can be viewed or modified either directly within the Python environment or via the Command-Line Interface (CLI). +The Ultralytics library provides a powerful settings management system to enable fine-grained control over your experiments. By making use of the `SettingsManager` housed within the `ultralytics.utils` module, users can readily access and alter their settings. These are stored in a JSON file in the environment user configuration directory, and can be viewed or modified directly within the Python environment or via the Command-Line Interface (CLI). ### Inspecting Settings @@ -321,25 +321,25 @@ Ultralytics allows users to easily modify their settings. Changes can be perform The table below provides an overview of the settings available for adjustment within Ultralytics. Each setting is outlined along with an example value, the data type, and a brief description. -| Name | Example Value | Data Type | Description | -| ------------------ | --------------------- | --------- | -------------------------------------------------------------------------------------------- | -| `settings_version` | `'0.0.4'` | `str` | Ultralytics _settings_ version (different from Ultralytics [pip] version) | -| `datasets_dir` | `'/path/to/datasets'` | `str` | The directory where the datasets are stored | -| `weights_dir` | `'/path/to/weights'` | `str` | The directory where the model weights are stored | -| `runs_dir` | `'/path/to/runs'` | `str` | The directory where the experiment runs are stored | -| `uuid` | `'a1b2c3d4'` | `str` | The unique identifier for the current settings | -| `sync` | `True` | `bool` | Whether to sync analytics and crashes to HUB | -| `api_key` | `''` | `str` | Ultralytics HUB [API Key] | -| `clearml` | `True` | `bool` | Whether to use [ClearML] logging | -| `comet` | `True` | `bool` | Whether to use [Comet ML] for experiment tracking and visualization | -| `dvc` | `True` | `bool` | Whether to use [DVC for experiment tracking] and version control | -| `hub` | `True` | `bool` | Whether to use [Ultralytics HUB] integration | -| `mlflow` | `True` | `bool` | Whether to use [MLFlow] for experiment tracking | -| `neptune` | `True` | `bool` | Whether to use [Neptune] for experiment tracking | -| `raytune` | `True` | `bool` | Whether to use [Ray Tune] for hyperparameter tuning | -| `tensorboard` | `True` | `bool` | Whether to use [TensorBoard] for visualization | -| `wandb` | `True` | `bool` | Whether to use [Weights & Biases] logging | -| `vscode_msg` | `True` | `bool` | When VS Code terminal detected, enables prompt to download [Ultralytics-Snippets] extension. | +| Name | Example Value | Data Type | Description | +| ------------------ | --------------------- | --------- | ----------------------------------------------------------------------------------------------------------------- | +| `settings_version` | `'0.0.4'` | `str` | Ultralytics _settings_ version (different from Ultralytics [pip] version) | +| `datasets_dir` | `'/path/to/datasets'` | `str` | The directory where the datasets are stored | +| `weights_dir` | `'/path/to/weights'` | `str` | The directory where the model weights are stored | +| `runs_dir` | `'/path/to/runs'` | `str` | The directory where the experiment runs are stored | +| `uuid` | `'a1b2c3d4'` | `str` | The unique identifier for the current settings | +| `sync` | `True` | `bool` | Whether to sync analytics and crashes to HUB | +| `api_key` | `''` | `str` | Ultralytics HUB [API Key] | +| `clearml` | `True` | `bool` | Whether to use [ClearML] logging | +| `comet` | `True` | `bool` | Whether to use [Comet ML] for experiment tracking and visualization | +| `dvc` | `True` | `bool` | Whether to use [DVC for experiment tracking] and version control | +| `hub` | `True` | `bool` | Whether to use [Ultralytics HUB] integration | +| `mlflow` | `True` | `bool` | Whether to use [MLFlow] for experiment tracking | +| `neptune` | `True` | `bool` | Whether to use [Neptune] for experiment tracking | +| `raytune` | `True` | `bool` | Whether to use [Ray Tune] for [hyperparameter tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning) | +| `tensorboard` | `True` | `bool` | Whether to use [TensorBoard] for visualization | +| `wandb` | `True` | `bool` | Whether to use [Weights & Biases] logging | +| `vscode_msg` | `True` | `bool` | When VS Code terminal detected, enables prompt to download [Ultralytics-Snippets] extension. | As you navigate through your projects or experiments, be sure to revisit these settings to ensure that they are optimally configured for your needs. diff --git a/docs/en/reference/nn/tasks.md b/docs/en/reference/nn/tasks.md index 8e60888546..ebfe803229 100644 --- a/docs/en/reference/nn/tasks.md +++ b/docs/en/reference/nn/tasks.md @@ -47,6 +47,14 @@ keywords: Ultralytics, YOLO, nn tasks, DetectionModel, PoseModel, RTDETRDetectio


+## ::: ultralytics.nn.tasks.SafeClass + +


+ +## ::: ultralytics.nn.tasks.SafeUnpickler + +


+ ## ::: ultralytics.nn.tasks.temporary_modules


diff --git a/docs/en/reference/utils/__init__.md b/docs/en/reference/utils/__init__.md index b8147dac01..9b7d1b584d 100644 --- a/docs/en/reference/utils/__init__.md +++ b/docs/en/reference/utils/__init__.md @@ -35,6 +35,10 @@ keywords: Ultralytics, utils, TQDM, Python, ML, Machine Learning utilities, YOLO


+## ::: ultralytics.utils.JSONDict + +


+ ## ::: ultralytics.utils.SettingsManager


diff --git a/docs/en/solutions/index.md b/docs/en/solutions/index.md index b627fed03a..52423c14f5 100644 --- a/docs/en/solutions/index.md +++ b/docs/en/solutions/index.md @@ -6,13 +6,13 @@ keywords: Ultralytics, YOLOv8, object counting, object blurring, security system # Ultralytics Solutions: Harness YOLOv8 to Solve Real-World Problems -Ultralytics Solutions provide cutting-edge applications of YOLO models, offering real-world solutions like object counting, blurring, and security systems, enhancing efficiency and accuracy in diverse industries. Discover the power of YOLOv8 for practical, impactful implementations. +Ultralytics Solutions provide cutting-edge applications of YOLO models, offering real-world solutions like object counting, blurring, and security systems, enhancing efficiency and [accuracy](https://www.ultralytics.com/glossary/accuracy) in diverse industries. Discover the power of YOLOv8 for practical, impactful implementations. ![Ultralytics Solutions Thumbnail](https://github.com/ultralytics/docs/releases/download/0/ultralytics-solutions-thumbnail.avif) ## Solutions -Here's our curated list of Ultralytics solutions that can be used to create awesome computer vision projects. +Here's our curated list of Ultralytics solutions that can be used to create awesome [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) projects. - [Object Counting](../guides/object-counting.md) 🚀 NEW: Learn to perform real-time object counting with YOLOv8. Gain the expertise to accurately count objects in live video streams. - [Object Cropping](../guides/object-cropping.md) 🚀 NEW: Master object cropping with YOLOv8 for precise extraction of objects from images and videos. @@ -21,14 +21,14 @@ Here's our curated list of Ultralytics solutions that can be used to create awes - [Objects Counting in Regions](../guides/region-counting.md) 🚀 NEW: Count objects in specific regions using YOLOv8 for accurate detection in varied areas. - [Security Alarm System](../guides/security-alarm-system.md) 🚀 NEW: Create a security alarm system with YOLOv8 that triggers alerts upon detecting new objects. Customize the system to fit your specific needs. - [Heatmaps](../guides/heatmaps.md) 🚀 NEW: Utilize detection heatmaps to visualize data intensity across a matrix, providing clear insights in computer vision tasks. -- [Instance Segmentation with Object Tracking](../guides/instance-segmentation-and-tracking.md) 🚀 NEW: Implement instance segmentation and object tracking with YOLOv8 to achieve precise object boundaries and continuous monitoring. +- [Instance Segmentation with Object Tracking](../guides/instance-segmentation-and-tracking.md) 🚀 NEW: Implement [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation) and object tracking with YOLOv8 to achieve precise object boundaries and continuous monitoring. - [VisionEye View Objects Mapping](../guides/vision-eye.md) 🚀 NEW: Develop systems that mimic human eye focus on specific objects, enhancing the computer's ability to discern and prioritize details. - [Speed Estimation](../guides/speed-estimation.md) 🚀 NEW: Estimate object speed using YOLOv8 and object tracking techniques, crucial for applications like autonomous vehicles and traffic monitoring. -- [Distance Calculation](../guides/distance-calculation.md) 🚀 NEW: Calculate distances between objects using bounding box centroids in YOLOv8, essential for spatial analysis. +- [Distance Calculation](../guides/distance-calculation.md) 🚀 NEW: Calculate distances between objects using [bounding box](https://www.ultralytics.com/glossary/bounding-box) centroids in YOLOv8, essential for spatial analysis. - [Queue Management](../guides/queue-management.md) 🚀 NEW: Implement efficient queue management systems to minimize wait times and improve productivity using YOLOv8. - [Parking Management](../guides/parking-management.md) 🚀 NEW: Organize and direct vehicle flow in parking areas with YOLOv8, optimizing space utilization and user experience. - [Analytics](../guides/analytics.md) 📊 NEW: Conduct comprehensive data analysis to discover patterns and make informed decisions, leveraging YOLOv8 for descriptive, predictive, and prescriptive analytics. -- [Live Inference with Streamlit](../guides/streamlit-live-inference.md) 🚀 NEW: Leverage the power of YOLOv8 for real-time object detection directly through your web browser with a user-friendly Streamlit interface. +- [Live Inference with Streamlit](../guides/streamlit-live-inference.md) 🚀 NEW: Leverage the power of YOLOv8 for real-time [object detection](https://www.ultralytics.com/glossary/object-detection) directly through your web browser with a user-friendly Streamlit interface. ## Contribute to Our Solutions @@ -56,6 +56,6 @@ Ultralytics YOLOv8 can significantly improve queue management systems by accurat Yes, Ultralytics YOLOv8 can be effectively used for monitoring workouts by tracking and analyzing fitness routines in real-time. This allows for precise evaluation of exercise form and performance. Explore our guide on [Workouts Monitoring](../guides/workouts-monitoring.md) to learn how to set up an AI-powered workout monitoring system using YOLOv8. -### How does Ultralytics YOLO help in creating heatmaps for data visualization? +### How does Ultralytics YOLO help in creating heatmaps for [data visualization](https://www.ultralytics.com/glossary/data-visualization)? Ultralytics YOLOv8 can generate heatmaps to visualize data intensity across a given area, highlighting regions of high activity or interest. This feature is particularly useful in understanding patterns and trends in various computer vision tasks. Learn more about creating and using [Heatmaps](../guides/heatmaps.md) with YOLOv8 for comprehensive data analysis and visualization. diff --git a/docs/en/tasks/classify.md b/docs/en/tasks/classify.md index 7df4b2f7c9..62623a403f 100644 --- a/docs/en/tasks/classify.md +++ b/docs/en/tasks/classify.md @@ -9,7 +9,7 @@ model_name: yolov8n-cls Image classification examples -Image classification is the simplest of the three tasks and involves classifying an entire image into one of a set of predefined classes. +[Image classification](https://www.ultralytics.com/glossary/image-classification) is the simplest of the three tasks and involves classifying an entire image into one of a set of predefined classes. The output of an image classifier is a single class label and a confidence score. Image classification is useful when you need to know only what class an image belongs to and don't need to know where objects of that class are located or what their exact shape is. @@ -47,7 +47,7 @@ YOLOv8 pretrained Classify models are shown here. Detect, Segment and Pose model ## Train -Train YOLOv8n-cls on the MNIST160 dataset for 100 epochs at image size 64. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. +Train YOLOv8n-cls on the MNIST160 dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) at image size 64. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. !!! example @@ -84,7 +84,7 @@ YOLO classification dataset format can be found in detail in the [Dataset Guide] ## Val -Validate trained YOLOv8n-cls model accuracy on the MNIST160 dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. +Validate trained YOLOv8n-cls model [accuracy](https://www.ultralytics.com/glossary/accuracy) on the MNIST160 dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. !!! example diff --git a/docs/en/tasks/detect.md b/docs/en/tasks/detect.md index a46956a849..a9c54889bc 100644 --- a/docs/en/tasks/detect.md +++ b/docs/en/tasks/detect.md @@ -8,7 +8,7 @@ keywords: object detection, YOLOv8, pretrained models, training, validation, pre Object detection examples -Object detection is a task that involves identifying the location and class of objects in an image or video stream. +[Object detection](https://www.ultralytics.com/glossary/object-detection) is a task that involves identifying the location and class of objects in an image or video stream. The output of an object detector is a set of bounding boxes that enclose the objects in the image, along with class labels and confidence scores for each box. Object detection is a good choice when you need to identify objects of interest in a scene, but don't need to know exactly where the object is or its exact shape. @@ -46,7 +46,7 @@ YOLOv8 pretrained Detect models are shown here. Detect, Segment and Pose models ## Train -Train YOLOv8n on the COCO8 dataset for 100 epochs at image size 640. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. +Train YOLOv8n on the COCO8 dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) at image size 640. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. !!! example @@ -83,7 +83,7 @@ YOLO detection dataset format can be found in detail in the [Dataset Guide](../d ## Val -Validate trained YOLOv8n model accuracy on the COCO8 dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. +Validate trained YOLOv8n model [accuracy](https://www.ultralytics.com/glossary/accuracy) on the COCO8 dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. !!! example diff --git a/docs/en/tasks/index.md b/docs/en/tasks/index.md index 5b7b75afd6..016a1ca9b9 100644 --- a/docs/en/tasks/index.md +++ b/docs/en/tasks/index.md @@ -9,7 +9,7 @@ keywords: Ultralytics YOLOv8, detection, segmentation, classification, oriented
Ultralytics YOLO supported tasks -YOLOv8 is an AI framework that supports multiple computer vision **tasks**. The framework can be used to perform [detection](detect.md), [segmentation](segment.md), [obb](obb.md), [classification](classify.md), and [pose](pose.md) estimation. Each of these tasks has a different objective and use case. +YOLOv8 is an AI framework that supports multiple [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) **tasks**. The framework can be used to perform [detection](detect.md), [segmentation](segment.md), [obb](obb.md), [classification](classify.md), and [pose](pose.md) estimation. Each of these tasks has a different objective and use case.


@@ -19,18 +19,18 @@ YOLOv8 is an AI framework that supports multiple computer vision **tasks**. The allowfullscreen>
- Watch: Explore Ultralytics YOLO Tasks: Object Detection, Segmentation, OBB, Tracking, and Pose Estimation. + Watch: Explore Ultralytics YOLO Tasks: [Object Detection](https://www.ultralytics.com/glossary/object-detection), Segmentation, OBB, Tracking, and Pose Estimation.

## [Detection](detect.md) -Detection is the primary task supported by YOLOv8. It involves detecting objects in an image or video frame and drawing bounding boxes around them. The detected objects are classified into different categories based on their features. YOLOv8 can detect multiple objects in a single image or video frame with high accuracy and speed. +Detection is the primary task supported by YOLOv8. It involves detecting objects in an image or video frame and drawing bounding boxes around them. The detected objects are classified into different categories based on their features. YOLOv8 can detect multiple objects in a single image or video frame with high [accuracy](https://www.ultralytics.com/glossary/accuracy) and speed. [Detection Examples](detect.md){ .md-button } ## [Segmentation](segment.md) -Segmentation is a task that involves segmenting an image into different regions based on the content of the image. Each region is assigned a label based on its content. This task is useful in applications such as image segmentation and medical imaging. YOLOv8 uses a variant of the U-Net architecture to perform segmentation. +Segmentation is a task that involves segmenting an image into different regions based on the content of the image. Each region is assigned a label based on its content. This task is useful in applications such as [image segmentation](https://www.ultralytics.com/glossary/image-segmentation) and medical imaging. YOLOv8 uses a variant of the U-Net architecture to perform segmentation. [Segmentation Examples](segment.md){ .md-button } @@ -114,7 +114,7 @@ For more details and implementation tips, visit our [pose estimation examples](p ### Why should I choose Ultralytics YOLOv8 for oriented object detection (OBB)? -Oriented Object Detection (OBB) with YOLOv8 provides enhanced precision by detecting objects with an additional angle parameter. This feature is beneficial for applications requiring accurate localization of rotated objects, such as aerial imagery analysis and warehouse automation. +Oriented Object Detection (OBB) with YOLOv8 provides enhanced [precision](https://www.ultralytics.com/glossary/precision) by detecting objects with an additional angle parameter. This feature is beneficial for applications requiring accurate localization of rotated objects, such as aerial imagery analysis and warehouse automation. - **Increased Precision:** The angle component reduces false positives for rotated objects. - **Versatile Applications:** Useful for tasks in geospatial analysis, robotics, etc. diff --git a/docs/en/tasks/obb.md b/docs/en/tasks/obb.md index 2fc2b9da21..9175d82786 100644 --- a/docs/en/tasks/obb.md +++ b/docs/en/tasks/obb.md @@ -5,7 +5,7 @@ keywords: Oriented Bounding Boxes, OBB, Object Detection, YOLOv8, Ultralytics, D model_name: yolov8n-obb --- -# Oriented Bounding Boxes Object Detection +# Oriented Bounding Boxes [Object Detection](https://www.ultralytics.com/glossary/object-detection) @@ -19,28 +19,16 @@ The output of an oriented object detector is a set of rotated bounding boxes tha YOLOv8 OBB models use the `-obb` suffix, i.e. `yolov8n-obb.pt` and are pretrained on [DOTAv1](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/DOTAv1.yaml). -
- - - - -
- -
- Watch: Object Detection using Ultralytics YOLOv8 Oriented Bounding Boxes (YOLOv8-OBB) - 		- -
- Watch: Object Detection with YOLOv8-OBB using Ultralytics HUB -
+

+
+ +
+ Watch: Object Detection using Ultralytics YOLOv8 Oriented Bounding Boxes (YOLOv8-OBB) +

## Visual Samples @@ -67,7 +55,7 @@ YOLOv8 pretrained OBB models are shown here, which are pretrained on the [DOTAv1 ## Train -Train YOLOv8n-obb on the `dota8.yaml` dataset for 100 epochs at image size 640. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. +Train YOLOv8n-obb on the `dota8.yaml` dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) at image size 640. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. !!! example @@ -98,13 +86,24 @@ Train YOLOv8n-obb on the `dota8.yaml` dataset for 100 epochs at image size 640. yolo obb train data=dota8.yaml model=yolov8n-obb.yaml pretrained=yolov8n-obb.pt epochs=100 imgsz=640 ``` +

+
+ +
+ Watch: How to Train Ultralytics YOLOv8-OBB (Oriented Bounding Boxes) Models on DOTA Dataset using Ultralytics HUB +

+ ### Dataset format OBB dataset format can be found in detail in the [Dataset Guide](../datasets/obb/index.md). ## Val -Validate trained YOLOv8n-obb model accuracy on the DOTA8 dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. +Validate trained YOLOv8n-obb model [accuracy](https://www.ultralytics.com/glossary/accuracy) on the DOTA8 dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. !!! example @@ -158,6 +157,17 @@ Use a trained YOLOv8n-obb model to run predictions on images. yolo obb predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' # predict with custom model ``` +

+
+ +
+ Watch: How to Detect and Track Storage Tanks using Ultralytics YOLOv8-OBB | Oriented Bounding Boxes | DOTA +

+ See full `predict` mode details in the [Predict](../modes/predict.md) page. ## Export diff --git a/docs/en/tasks/pose.md b/docs/en/tasks/pose.md index ead809d418..ca0d5feca6 100644 --- a/docs/en/tasks/pose.md +++ b/docs/en/tasks/pose.md @@ -117,7 +117,7 @@ YOLO pose dataset format can be found in detail in the [Dataset Guide](../datase ## Val -Validate trained YOLOv8n-pose model accuracy on the COCO128-pose dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. +Validate trained YOLOv8n-pose model [accuracy](https://www.ultralytics.com/glossary/accuracy) on the COCO128-pose dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. !!! example diff --git a/docs/en/tasks/segment.md b/docs/en/tasks/segment.md index e1c43eea0c..73398d1814 100644 --- a/docs/en/tasks/segment.md +++ b/docs/en/tasks/segment.md @@ -9,7 +9,7 @@ model_name: yolov8n-seg Instance segmentation examples -Instance segmentation goes a step further than object detection and involves identifying individual objects in an image and segmenting them from the rest of the image. +[Instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation) goes a step further than object detection and involves identifying individual objects in an image and segmenting them from the rest of the image. The output of an instance segmentation model is a set of masks or contours that outline each object in the image, along with class labels and confidence scores for each object. Instance segmentation is useful when you need to know not only where objects are in an image, but also what their exact shape is. @@ -47,7 +47,7 @@ YOLOv8 pretrained Segment models are shown here. Detect, Segment and Pose models ## Train -Train YOLOv8n-seg on the COCO128-seg dataset for 100 epochs at image size 640. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. +Train YOLOv8n-seg on the COCO128-seg dataset for 100 [epochs](https://www.ultralytics.com/glossary/epoch) at image size 640. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. !!! example @@ -84,7 +84,7 @@ YOLO segmentation dataset format can be found in detail in the [Dataset Guide](. ## Val -Validate trained YOLOv8n-seg model accuracy on the COCO128-seg dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. +Validate trained YOLOv8n-seg model [accuracy](https://www.ultralytics.com/glossary/accuracy) on the COCO128-seg dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. !!! example @@ -204,7 +204,7 @@ To train a YOLOv8 segmentation model on a custom dataset, you first need to prep Check the [Configuration](../usage/cfg.md) page for more available arguments. -### What is the difference between object detection and instance segmentation in YOLOv8? +### What is the difference between [object detection](https://www.ultralytics.com/glossary/object-detection) and instance segmentation in YOLOv8? Object detection identifies and localizes objects within an image by drawing bounding boxes around them, whereas instance segmentation not only identifies the bounding boxes but also delineates the exact shape of each object. YOLOv8 instance segmentation models provide masks or contours that outline each detected object, which is particularly useful for tasks where knowing the precise shape of objects is important, such as medical imaging or autonomous driving. @@ -238,7 +238,7 @@ Loading and validating a pretrained YOLOv8 segmentation model is straightforward yolo segment val model=yolov8n-seg.pt ``` -These steps will provide you with validation metrics like Mean Average Precision (mAP), crucial for assessing model performance. +These steps will provide you with validation metrics like [Mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP), crucial for assessing model performance. ### How can I export a YOLOv8 segmentation model to ONNX format? diff --git a/docs/en/usage/callbacks.md b/docs/en/usage/callbacks.md index 083b65879f..2886f8f512 100644 --- a/docs/en/usage/callbacks.md +++ b/docs/en/usage/callbacks.md @@ -57,22 +57,22 @@ Here are all supported callbacks. See callbacks [source code](https://github.com ### Trainer Callbacks -| Callback | Description | -| --------------------------- | ------------------------------------------------------- | -| `on_pretrain_routine_start` | Triggered at the beginning of pre-training routine | -| `on_pretrain_routine_end` | Triggered at the end of pre-training routine | -| `on_train_start` | Triggered when the training starts | -| `on_train_epoch_start` | Triggered at the start of each training epoch | -| `on_train_batch_start` | Triggered at the start of each training batch | -| `optimizer_step` | Triggered during the optimizer step | -| `on_before_zero_grad` | Triggered before gradients are zeroed | -| `on_train_batch_end` | Triggered at the end of each training batch | -| `on_train_epoch_end` | Triggered at the end of each training epoch | -| `on_fit_epoch_end` | Triggered at the end of each fit epoch | -| `on_model_save` | Triggered when the model is saved | -| `on_train_end` | Triggered when the training process ends | -| `on_params_update` | Triggered when model parameters are updated | -| `teardown` | Triggered when the training process is being cleaned up | +| Callback | Description | +| --------------------------- | ------------------------------------------------------------------------------------------- | +| `on_pretrain_routine_start` | Triggered at the beginning of pre-training routine | +| `on_pretrain_routine_end` | Triggered at the end of pre-training routine | +| `on_train_start` | Triggered when the training starts | +| `on_train_epoch_start` | Triggered at the start of each training [epoch](https://www.ultralytics.com/glossary/epoch) | +| `on_train_batch_start` | Triggered at the start of each training batch | +| `optimizer_step` | Triggered during the optimizer step | +| `on_before_zero_grad` | Triggered before gradients are zeroed | +| `on_train_batch_end` | Triggered at the end of each training batch | +| `on_train_epoch_end` | Triggered at the end of each training epoch | +| `on_fit_epoch_end` | Triggered at the end of each fit epoch | +| `on_model_save` | Triggered when the model is saved | +| `on_train_end` | Triggered when the training process ends | +| `on_params_update` | Triggered when model parameters are updated | +| `teardown` | Triggered when the training process is being cleaned up | ### Validator Callbacks @@ -199,7 +199,7 @@ For more comprehensive usage, refer to the [Prediction Guide](../modes/predict.m Ultralytics YOLO supports various practical implementations of callbacks to enhance and customize different phases like training, validation, and prediction. Some practical examples include: 1. **Logging Custom Metrics**: Log additional metrics at different stages, such as the end of training or validation epochs. -2. **Data Augmentation**: Implement custom data transformations or augmentations during prediction or training batches. +2. **[Data Augmentation](https://www.ultralytics.com/glossary/data-augmentation)**: Implement custom data transformations or augmentations during prediction or training batches. 3. **Intermediate Results**: Save intermediate results such as predictions or frames for further analysis or visualization. Example: Combining frames with prediction results during prediction using `on_predict_batch_end`: diff --git a/docs/en/usage/cfg.md b/docs/en/usage/cfg.md index 2d0ce1dd94..aecc5fc646 100644 --- a/docs/en/usage/cfg.md +++ b/docs/en/usage/cfg.md @@ -4,7 +4,7 @@ description: Optimize your YOLO model's performance with the right settings and keywords: YOLO, hyperparameters, configuration, training, validation, prediction, model settings, Ultralytics, performance optimization, machine learning --- -YOLO settings and hyperparameters play a critical role in the model's performance, speed, and accuracy. These settings and hyperparameters can affect the model's behavior at various stages of the model development process, including training, validation, and prediction. +YOLO settings and hyperparameters play a critical role in the model's performance, speed, and [accuracy](https://www.ultralytics.com/glossary/accuracy). These settings and hyperparameters can affect the model's behavior at various stages of the model development process, including training, validation, and prediction.


@@ -57,9 +57,9 @@ YOLO models can be used for a variety of tasks, including detection, segmentatio - **Pose**: For identifying objects and estimating their keypoints in an image or video. - **OBB**: Oriented (i.e. rotated) bounding boxes suitable for satellite or medical imagery. -| Argument | Default | Description | -| -------- | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `task` | `'detect'` | Specifies the YOLO task to be executed. Options include `detect` for object detection, `segment` for segmentation, `classify` for classification, `pose` for pose estimation and `OBB` for oriented bounding boxes. Each task is tailored to specific types of output and problems within image and video analysis. | +| Argument | Default | Description | +| -------- | ---------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `task` | `'detect'` | Specifies the YOLO task to be executed. Options include `detect` for [object detection](https://www.ultralytics.com/glossary/object-detection), `segment` for segmentation, `classify` for classification, `pose` for pose estimation and `OBB` for oriented bounding boxes. Each task is tailored to specific types of output and problems within image and video analysis. | [Tasks Guide](../tasks/index.md){ .md-button } @@ -82,7 +82,7 @@ YOLO models can be used in different modes depending on the specific problem you ## Train Settings -The training settings for YOLO models encompass various hyperparameters and configurations used during the training process. These settings influence the model's performance, speed, and accuracy. Key training settings include batch size, learning rate, momentum, and weight decay. Additionally, the choice of optimizer, loss function, and training dataset composition can impact the training process. Careful tuning and experimentation with these settings are crucial for optimizing performance. +The training settings for YOLO models encompass various hyperparameters and configurations used during the training process. These settings influence the model's performance, speed, and accuracy. Key training settings include batch size, [learning rate](https://www.ultralytics.com/glossary/learning-rate), momentum, and weight decay. Additionally, the choice of optimizer, [loss function](https://www.ultralytics.com/glossary/loss-function), and training dataset composition can impact the training process. Careful tuning and experimentation with these settings are crucial for optimizing performance. {% include "macros/train-args.md" %} @@ -90,7 +90,7 @@ The training settings for YOLO models encompass various hyperparameters and conf The `batch` argument can be configured in three ways: - - **Fixed Batch Size**: Set an integer value (e.g., `batch=16`), specifying the number of images per batch directly. + - **Fixed [Batch Size](https://www.ultralytics.com/glossary/batch-size)**: Set an integer value (e.g., `batch=16`), specifying the number of images per batch directly. - **Auto Mode (60% GPU Memory)**: Use `batch=-1` to automatically adjust batch size for approximately 60% CUDA memory utilization. - **Auto Mode with Utilization Fraction**: Set a fraction value (e.g., `batch=0.70`) to adjust batch size based on the specified fraction of GPU memory usage. @@ -116,7 +116,7 @@ The val (validation) settings for YOLO models involve various hyperparameters an {% include "macros/validation-args.md" %} -Careful tuning and experimentation with these settings are crucial to ensure optimal performance on the validation dataset and detect and prevent overfitting. +Careful tuning and experimentation with these settings are crucial to ensure optimal performance on the validation dataset and detect and prevent [overfitting](https://www.ultralytics.com/glossary/overfitting). [Val Guide](../modes/val.md){ .md-button } @@ -132,7 +132,7 @@ It is crucial to thoughtfully configure these settings to ensure the exported mo ## Augmentation Settings -Augmentation techniques are essential for improving the robustness and performance of YOLO models by introducing variability into the training data, helping the model generalize better to unseen data. The following table outlines the purpose and effect of each augmentation argument: +Augmentation techniques are essential for improving the robustness and performance of YOLO models by introducing variability into the [training data](https://www.ultralytics.com/glossary/training-data), helping the model generalize better to unseen data. The following table outlines the purpose and effect of each augmentation argument: {% include "macros/augmentation-args.md" %} @@ -149,19 +149,19 @@ Logging, checkpoints, plotting, and file management are important considerations Effective logging, checkpointing, plotting, and file management can help you keep track of the model's progress and make it easier to debug and optimize the training process. -| Argument | Default | Description | -| ---------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `project` | `'runs'` | Specifies the root directory for saving training runs. Each run will be saved in a separate subdirectory within this directory. | -| `name` | `'exp'` | Defines the name of the experiment. If not specified, YOLO automatically increments this name for each run, e.g., `exp`, `exp2`, etc., to avoid overwriting previous experiments. | -| `exist_ok` | `False` | Determines whether to overwrite an existing experiment directory if one with the same name already exists. Setting this to `True` allows overwriting, while `False` prevents it. | -| `plots` | `False` | Controls the generation and saving of training and validation plots. Set to `True` to create plots such as loss curves, precision-recall curves, and sample predictions. Useful for visually tracking model performance over time. | -| `save` | `False` | Enables the saving of training checkpoints and final model weights. Set to `True` to periodically save model states, allowing training to be resumed from these checkpoints or models to be deployed. | +| Argument | Default | Description | +| ---------- | -------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `project` | `'runs'` | Specifies the root directory for saving training runs. Each run will be saved in a separate subdirectory within this directory. | +| `name` | `'exp'` | Defines the name of the experiment. If not specified, YOLO automatically increments this name for each run, e.g., `exp`, `exp2`, etc., to avoid overwriting previous experiments. | +| `exist_ok` | `False` | Determines whether to overwrite an existing experiment directory if one with the same name already exists. Setting this to `True` allows overwriting, while `False` prevents it. | +| `plots` | `False` | Controls the generation and saving of training and validation plots. Set to `True` to create plots such as loss curves, [precision](https://www.ultralytics.com/glossary/precision)-[recall](https://www.ultralytics.com/glossary/recall) curves, and sample predictions. Useful for visually tracking model performance over time. | +| `save` | `False` | Enables the saving of training checkpoints and final model weights. Set to `True` to periodically save model states, allowing training to be resumed from these checkpoints or models to be deployed. | ## FAQ ### How do I improve the performance of my YOLO model during training? -Improving YOLO model performance involves tuning hyperparameters like batch size, learning rate, momentum, and weight decay. Adjusting augmentation settings, selecting the right optimizer, and employing techniques like early stopping or mixed precision can also help. For detailed guidance on training settings, refer to the [Train Guide](../modes/train.md). +Improving YOLO model performance involves tuning hyperparameters like batch size, learning rate, momentum, and weight decay. Adjusting augmentation settings, selecting the right optimizer, and employing techniques like early stopping or [mixed precision](https://www.ultralytics.com/glossary/mixed-precision) can also help. For detailed guidance on training settings, refer to the [Train Guide](../modes/train.md). ### What are the key hyperparameters to consider for YOLO model accuracy? diff --git a/docs/en/usage/cli.md b/docs/en/usage/cli.md index 3e6c4b37a5..d1d7c8de48 100644 --- a/docs/en/usage/cli.md +++ b/docs/en/usage/cli.md @@ -35,7 +35,7 @@ The YOLO command line interface (CLI) allows for simple single-line commands wit === "Train" - Train a detection model for 10 epochs with an initial learning_rate of 0.01 + Train a detection model for 10 [epochs](https://www.ultralytics.com/glossary/epoch) with an initial learning_rate of 0.01 ```bash yolo train data=coco8.yaml model=yolov8n.pt epochs=10 lr0=0.01 ``` @@ -109,7 +109,7 @@ Train YOLOv8n on the COCO8 dataset for 100 epochs at image size 640. For a full ## Val -Validate trained YOLOv8n model accuracy on the COCO8 dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. +Validate trained YOLOv8n model [accuracy](https://www.ultralytics.com/glossary/accuracy) on the COCO8 dataset. No arguments are needed as the `model` retains its training `data` and arguments as model attributes. !!! example @@ -221,7 +221,7 @@ This will create `default_copy.yaml`, which you can then pass as `cfg=default_co ### How do I use the Ultralytics YOLOv8 command line interface (CLI) for model training? -To train a YOLOv8 model using the CLI, you can execute a simple one-line command in the terminal. For example, to train a detection model for 10 epochs with a learning rate of 0.01, you would run: +To train a YOLOv8 model using the CLI, you can execute a simple one-line command in the terminal. For example, to train a detection model for 10 epochs with a [learning rate](https://www.ultralytics.com/glossary/learning-rate) of 0.01, you would run: ```bash yolo train data=coco8.yaml model=yolov8n.pt epochs=10 lr0=0.01 @@ -241,7 +241,7 @@ Each task can be customized with various arguments. For detailed syntax and exam ### How can I validate the accuracy of a trained YOLOv8 model using the CLI? -To validate a YOLOv8 model's accuracy, use the `val` mode. For example, to validate a pretrained detection model with a batch size of 1 and image size of 640, run: +To validate a YOLOv8 model's accuracy, use the `val` mode. For example, to validate a pretrained detection model with a [batch size](https://www.ultralytics.com/glossary/batch-size) of 1 and image size of 640, run: ```bash yolo val model=yolov8n.pt data=coco8.yaml batch=1 imgsz=640 diff --git a/docs/en/usage/engine.md b/docs/en/usage/engine.md index 7e43e08e26..dc44047ff7 100644 --- a/docs/en/usage/engine.md +++ b/docs/en/usage/engine.md @@ -128,7 +128,7 @@ For more details on the customization and source code, see the [`BaseTrainer` Re ### How can I add a callback to the Ultralytics YOLOv8 DetectionTrainer? -You can add callbacks to monitor and modify the training process in Ultralytics YOLOv8 `DetectionTrainer`. For instance, here's how you can add a callback to log model weights after every training epoch: +You can add callbacks to monitor and modify the training process in Ultralytics YOLOv8 `DetectionTrainer`. For instance, here's how you can add a callback to log model weights after every training [epoch](https://www.ultralytics.com/glossary/epoch): ```python from ultralytics.models.yolo.detect import DetectionTrainer @@ -153,8 +153,8 @@ For further details on callback events and entry points, refer to our [Callbacks Ultralytics YOLOv8 offers a high-level abstraction on powerful engine executors, making it ideal for rapid development and customization. Key benefits include: - **Ease of Use**: Both command-line and Python interfaces simplify complex tasks. -- **Performance**: Optimized for real-time object detection and various vision AI applications. -- **Customization**: Easily extendable for custom models, loss functions, and dataloaders. +- **Performance**: Optimized for real-time [object detection](https://www.ultralytics.com/glossary/object-detection) and various vision AI applications. +- **Customization**: Easily extendable for custom models, [loss functions](https://www.ultralytics.com/glossary/loss-function), and dataloaders. Learn more about YOLOv8's capabilities by visiting [Ultralytics YOLO](https://www.ultralytics.com/yolo). diff --git a/docs/en/usage/python.md b/docs/en/usage/python.md index 66b2e6c61d..5236af0a1d 100644 --- a/docs/en/usage/python.md +++ b/docs/en/usage/python.md @@ -6,7 +6,7 @@ keywords: YOLOv8, Python, object detection, segmentation, classification, machin # Python Usage -Welcome to the YOLOv8 Python Usage documentation! This guide is designed to help you seamlessly integrate YOLOv8 into your Python projects for object detection, segmentation, and classification. Here, you'll learn how to load and use pretrained models, train new models, and perform predictions on images. The easy-to-use Python interface is a valuable resource for anyone looking to incorporate YOLOv8 into their Python projects, allowing you to quickly implement advanced object detection capabilities. Let's get started! +Welcome to the YOLOv8 Python Usage documentation! This guide is designed to help you seamlessly integrate YOLOv8 into your Python projects for [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and classification. Here, you'll learn how to load and use pretrained models, train new models, and perform predictions on images. The easy-to-use Python interface is a valuable resource for anyone looking to incorporate YOLOv8 into their Python projects, allowing you to quickly implement advanced object detection capabilities. Let's get started!


@@ -80,7 +80,7 @@ Train mode is used for training a YOLOv8 model on a custom dataset. In this mode ## [Val](../modes/val.md) -Val mode is used for validating a YOLOv8 model after it has been trained. In this mode, the model is evaluated on a validation set to measure its accuracy and generalization performance. This mode can be used to tune the hyperparameters of the model to improve its performance. +Val mode is used for validating a YOLOv8 model after it has been trained. In this mode, the model is evaluated on a validation set to measure its [accuracy](https://www.ultralytics.com/glossary/accuracy) and generalization performance. This mode can be used to tune the hyperparameters of the model to improve its performance. !!! example "Val" @@ -355,7 +355,7 @@ See more detailed examples in our [Predict Mode](../modes/predict.md) section. ### What are the different modes available in YOLOv8? -Ultralytics YOLOv8 provides various modes to cater to different machine learning workflows. These include: +Ultralytics YOLOv8 provides various modes to cater to different [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) workflows. These include: - **[Train](../modes/train.md)**: Train a model using custom datasets. - **[Val](../modes/val.md)**: Validate model performance on a validation set. diff --git a/docs/en/usage/simple-utilities.md b/docs/en/usage/simple-utilities.md index ed59f8dbed..e40a2478ee 100644 --- a/docs/en/usage/simple-utilities.md +++ b/docs/en/usage/simple-utilities.md @@ -31,7 +31,7 @@ The `ultralytics` package comes with a myriad of utilities that can support, enh ### Auto Labeling / Annotations -Dataset annotation is a very resource intensive and time-consuming process. If you have a YOLO object detection model trained on a reasonable amount of data, you can use it and [SAM](../models/sam.md) to auto-annotate additional data (segmentation format). +Dataset annotation is a very resource intensive and time-consuming process. If you have a YOLO [object detection](https://www.ultralytics.com/glossary/object-detection) model trained on a reasonable amount of data, you can use it and [SAM](../models/sam.md) to auto-annotate additional data (segmentation format). ```{ .py .annotate } from ultralytics.data.annotator import auto_annotate @@ -86,7 +86,7 @@ convert_coco( # (1)! For additional information about the `convert_coco` function, [visit the reference page](../reference/data/converter.md#ultralytics.data.converter.convert_coco) -### Get Bounding Box Dimensions +### Get [Bounding Box](https://www.ultralytics.com/glossary/bounding-box) Dimensions ```{.py .annotate } from ultralytics.utils.plotting import Annotator @@ -460,15 +460,16 @@ for obb in obb_boxes: image_with_obb = ann.result() ``` -#### Bounding Boxes Circle Annotation ([Circle Label](https://docs.ultralytics.com/reference/utils/plotting/#ultralytics.utils.plotting.Annotator.circle_label)) +#### Bounding Boxes Circle Annotation [Circle Label](https://docs.ultralytics.com/reference/utils/plotting/#ultralytics.utils.plotting.Annotator.circle_label) ```python import cv2 from ultralytics import YOLO -from ultralytics.utils.plotting import Annotator, colors +from ultralytics.utils.plotting import Annotator model = YOLO("yolov8s.pt") +names = model.names cap = cv2.VideoCapture("path/to/video/file.mp4") w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) @@ -479,15 +480,13 @@ while True: if not ret: break - annotator = Annotator(im0, line_width=2) - + annotator = Annotator(im0) results = model.predict(im0) boxes = results[0].boxes.xyxy.cpu() clss = results[0].boxes.cls.cpu().tolist() for box, cls in zip(boxes, clss): - x1, y1 = int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2) - annotator.circle_label(box, label=model.names[int(cls)], color=colors(int(cls), True)) + annotator.circle_label(box, label=names[int(cls)]) writer.write(im0) cv2.imshow("Ultralytics circle annotation", im0) @@ -500,15 +499,16 @@ cap.release() cv2.destroyAllWindows() ``` -#### Bounding Boxes Text Annotation ([Text Label](https://docs.ultralytics.com/reference/utils/plotting/#ultralytics.utils.plotting.Annotator.text_label)) +#### Bounding Boxes Text Annotation [Text Label](https://docs.ultralytics.com/reference/utils/plotting/#ultralytics.utils.plotting.Annotator.text_label) ```python import cv2 from ultralytics import YOLO -from ultralytics.utils.plotting import Annotator, colors +from ultralytics.utils.plotting import Annotator model = YOLO("yolov8s.pt") +names = model.names cap = cv2.VideoCapture("path/to/video/file.mp4") w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) @@ -519,15 +519,13 @@ while True: if not ret: break - annotator = Annotator(im0, line_width=2) - + annotator = Annotator(im0) results = model.predict(im0) boxes = results[0].boxes.xyxy.cpu() clss = results[0].boxes.cls.cpu().tolist() for box, cls in zip(boxes, clss): - x1, y1 = int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2) - annotator.text_label(box, label=model.names[int(cls)], color=colors(int(cls), True)) + annotator.text_label(box, label=names[int(cls)]) writer.write(im0) cv2.imshow("Ultralytics text annotation", im0) @@ -587,7 +585,7 @@ make_divisible(7, 2) ## FAQ -### What utilities are included in the Ultralytics package to enhance machine learning workflows? +### What utilities are included in the Ultralytics package to enhance [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) workflows? The Ultralytics package includes a variety of utilities designed to streamline and optimize machine learning workflows. Key utilities include [auto-annotation](../reference/data/annotator.md#ultralytics.data.annotator.auto_annotate) for labeling datasets, converting COCO to YOLO format with [convert_coco](../reference/data/converter.md#ultralytics.data.converter.convert_coco), compressing images, and dataset auto-splitting. These tools aim to reduce manual effort, ensure consistency, and enhance data processing efficiency. diff --git a/docs/en/yolov5/environments/aws_quickstart_tutorial.md b/docs/en/yolov5/environments/aws_quickstart_tutorial.md index ffa6a2c936..0e5daf2fe9 100644 --- a/docs/en/yolov5/environments/aws_quickstart_tutorial.md +++ b/docs/en/yolov5/environments/aws_quickstart_tutorial.md @@ -6,7 +6,7 @@ keywords: YOLOv5, AWS, Deep Learning, Machine Learning, AWS EC2, YOLOv5 setup, D # YOLOv5 🚀 on AWS Deep Learning Instance: Your Complete Guide -Setting up a high-performance deep learning environment can be daunting for newcomers, but fear not! 🛠️ With this guide, we'll walk you through the process of getting YOLOv5 up and running on an AWS Deep Learning instance. By leveraging the power of Amazon Web Services (AWS), even those new to machine learning can get started quickly and cost-effectively. The AWS platform's scalability is perfect for both experimentation and production deployment. +Setting up a high-performance deep learning environment can be daunting for newcomers, but fear not! 🛠️ With this guide, we'll walk you through the process of getting YOLOv5 up and running on an AWS Deep Learning instance. By leveraging the power of Amazon Web Services (AWS), even those new to [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) can get started quickly and cost-effectively. The AWS platform's scalability is perfect for both experimentation and production deployment. Other quickstart options for YOLOv5 include our [Colab Notebook](https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb) Open In Colab Open In Kaggle, [GCP Deep Learning VM](./google_cloud_quickstart_tutorial.md), and our Docker image at [Docker Hub](https://hub.docker.com/r/ultralytics/yolov5) Docker Pulls. @@ -24,7 +24,7 @@ In the EC2 dashboard, you'll find the **Launch Instance** button which is your g ### Selecting the Right Amazon Machine Image (AMI) -Here's where you choose the operating system and software stack for your instance. Type 'Deep Learning' into the search field and select the latest Ubuntu-based Deep Learning AMI, unless your needs dictate otherwise. Amazon's Deep Learning AMIs come pre-installed with popular frameworks and GPU drivers to streamline your setup process. +Here's where you choose the operating system and software stack for your instance. Type '[Deep Learning](https://www.ultralytics.com/glossary/deep-learning-dl)' into the search field and select the latest Ubuntu-based Deep Learning AMI, unless your needs dictate otherwise. Amazon's Deep Learning AMIs come pre-installed with popular frameworks and GPU drivers to streamline your setup process. ![Choose AMI](https://github.com/ultralytics/docs/releases/download/0/choose-ami.avif) @@ -92,4 +92,4 @@ sudo swapon /swapfile # activate swap file free -h # verify swap memory ``` -And that's it! 🎉 You've successfully created an AWS Deep Learning instance and run YOLOv5. Whether you're just starting with object detection or scaling up for production, this setup can help you achieve your machine learning goals. Happy training, validating, and deploying! If you encounter any hiccups along the way, the robust AWS documentation and the active Ultralytics community are here to support you. +And that's it! 🎉 You've successfully created an AWS Deep Learning instance and run YOLOv5. Whether you're just starting with [object detection](https://www.ultralytics.com/glossary/object-detection) or scaling up for production, this setup can help you achieve your machine learning goals. Happy training, validating, and deploying! If you encounter any hiccups along the way, the robust AWS documentation and the active Ultralytics community are here to support you. diff --git a/docs/en/yolov5/environments/azureml_quickstart_tutorial.md b/docs/en/yolov5/environments/azureml_quickstart_tutorial.md index 2fd33a861d..82a083d15e 100644 --- a/docs/en/yolov5/environments/azureml_quickstart_tutorial.md +++ b/docs/en/yolov5/environments/azureml_quickstart_tutorial.md @@ -61,7 +61,7 @@ Train the YOLOv5 model: python train.py ``` -Validate the model for Precision, Recall, and mAP +Validate the model for [Precision](https://www.ultralytics.com/glossary/precision), [Recall](https://www.ultralytics.com/glossary/recall), and mAP ```bash python val.py --weights yolov5s.pt diff --git a/docs/en/yolov5/environments/docker_image_quickstart_tutorial.md b/docs/en/yolov5/environments/docker_image_quickstart_tutorial.md index 93c9f0a16a..55b92316dc 100644 --- a/docs/en/yolov5/environments/docker_image_quickstart_tutorial.md +++ b/docs/en/yolov5/environments/docker_image_quickstart_tutorial.md @@ -36,7 +36,7 @@ sudo docker run --ipc=host -it ultralytics/yolov5:latest ### Container with local file access: -To run a container with access to local files (e.g., COCO training data in `/datasets`), use the `-v` flag: +To run a container with access to local files (e.g., COCO [training data](https://www.ultralytics.com/glossary/training-data) in `/datasets`), use the `-v` flag: ```bash sudo docker run --ipc=host -it -v "$(pwd)"/datasets:/usr/src/datasets ultralytics/yolov5:latest diff --git a/docs/en/yolov5/environments/google_cloud_quickstart_tutorial.md b/docs/en/yolov5/environments/google_cloud_quickstart_tutorial.md index cdd397dc17..65ad9c3d62 100644 --- a/docs/en/yolov5/environments/google_cloud_quickstart_tutorial.md +++ b/docs/en/yolov5/environments/google_cloud_quickstart_tutorial.md @@ -6,13 +6,13 @@ keywords: YOLOv5, Google Cloud Platform, GCP, Deep Learning VM, object detection # Mastering YOLOv5 🚀 Deployment on Google Cloud Platform (GCP) Deep Learning Virtual Machine (VM) ⭐ -Embarking on the journey of artificial intelligence and machine learning can be exhilarating, especially when you leverage the power and flexibility of a cloud platform. Google Cloud Platform (GCP) offers robust tools tailored for machine learning enthusiasts and professionals alike. One such tool is the Deep Learning VM that is preconfigured for data science and ML tasks. In this tutorial, we will navigate through the process of setting up YOLOv5 on a GCP Deep Learning VM. Whether you're taking your first steps in ML or you're a seasoned practitioner, this guide is designed to provide you with a clear pathway to implementing object detection models powered by YOLOv5. +Embarking on the journey of [artificial intelligence](https://www.ultralytics.com/glossary/artificial-intelligence-ai) and machine learning can be exhilarating, especially when you leverage the power and flexibility of a cloud platform. Google Cloud Platform (GCP) offers robust tools tailored for machine learning enthusiasts and professionals alike. One such tool is the Deep Learning VM that is preconfigured for data science and ML tasks. In this tutorial, we will navigate through the process of setting up YOLOv5 on a GCP Deep Learning VM. Whether you're taking your first steps in ML or you're a seasoned practitioner, this guide is designed to provide you with a clear pathway to implementing object detection models powered by YOLOv5. 🆓 Plus, if you're a fresh GCP user, you're in luck with a [$300 free credit offer](https://cloud.google.com/free/docs/free-cloud-features#free-trial) to kickstart your projects. In addition to GCP, explore other accessible quickstart options for YOLOv5, like our [Colab Notebook](https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb) Open In Colab for a browser-based experience, or the scalability of [Amazon AWS](./aws_quickstart_tutorial.md). Furthermore, container aficionados can utilize our official Docker image at [Docker Hub](https://hub.docker.com/r/ultralytics/yolov5) Docker Pulls for an encapsulated environment. -## Step 1: Create and Configure Your Deep Learning VM +## Step 1: Create and Configure Your [Deep Learning](https://www.ultralytics.com/glossary/deep-learning-dl) VM Let's begin by creating a virtual machine that's tuned for deep learning: @@ -42,7 +42,7 @@ cd yolov5 pip install -r requirements.txt ``` -This setup process ensures you're working with a Python environment version 3.8.0 or newer and PyTorch 1.8 or above. Our scripts smoothly download [models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) rending from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases), making it hassle-free to start model training. +This setup process ensures you're working with a Python environment version 3.8.0 or newer and [PyTorch](https://www.ultralytics.com/glossary/pytorch) 1.8 or above. Our scripts smoothly download [models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) rending from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases), making it hassle-free to start model training. ## Step 3: Train and Deploy Your YOLOv5 Models 🌐 @@ -62,7 +62,7 @@ python detect.py --weights yolov5s.pt --source path/to/images python export.py --weights yolov5s.pt --include onnx coreml tflite ``` -With just a few commands, YOLOv5 allows you to train custom object detection models tailored to your specific needs or utilize pre-trained weights for quick results on a variety of tasks. +With just a few commands, YOLOv5 allows you to train custom [object detection](https://www.ultralytics.com/glossary/object-detection) models tailored to your specific needs or utilize pre-trained weights for quick results on a variety of tasks. ![Terminal command image illustrating model training on a GCP Deep Learning VM](https://github.com/ultralytics/docs/releases/download/0/terminal-command-model-training.avif) @@ -80,7 +80,7 @@ free -h # confirm the memory increment ### Concluding Thoughts -Congratulations! You are now empowered to harness the capabilities of YOLOv5 with the computational prowess of Google Cloud Platform. This combination provides scalability, efficiency, and versatility for your object detection tasks. Whether for personal projects, academic research, or industrial applications, you have taken a pivotal step into the world of AI and machine learning on the cloud. +Congratulations! You are now empowered to harness the capabilities of YOLOv5 with the computational prowess of Google Cloud Platform. This combination provides scalability, efficiency, and versatility for your object detection tasks. Whether for personal projects, academic research, or industrial applications, you have taken a pivotal step into the world of AI and [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) on the cloud. Do remember to document your journey, share insights with the Ultralytics community, and leverage the collaborative arenas such as [GitHub discussions](https://github.com/ultralytics/yolov5/discussions) to grow further. Now, go forth and innovate with YOLOv5 and GCP! 🌟 diff --git a/docs/en/yolov5/index.md b/docs/en/yolov5/index.md index ba4e4e3ab8..3605058463 100644 --- a/docs/en/yolov5/index.md +++ b/docs/en/yolov5/index.md @@ -22,11 +22,11 @@ keywords: YOLOv5, Ultralytics, object detection, computer vision, deep learning,

-Welcome to the Ultralytics' YOLOv5🚀 Documentation! YOLOv5, the fifth iteration of the revolutionary "You Only Look Once" object detection model, is designed to deliver high-speed, high-accuracy results in real-time. +Welcome to the Ultralytics' YOLOv5🚀 Documentation! YOLOv5, the fifth iteration of the revolutionary "You Only Look Once" [object detection](https://www.ultralytics.com/glossary/object-detection) model, is designed to deliver high-speed, high-accuracy results in real-time.

-Built on PyTorch, this powerful deep learning framework has garnered immense popularity for its versatility, ease of use, and high performance. Our documentation guides you through the installation process, explains the architectural nuances of the model, showcases various use-cases, and provides a series of detailed tutorials. These resources will help you harness the full potential of YOLOv5 for your computer vision projects. Let's get started! +Built on PyTorch, this powerful [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) framework has garnered immense popularity for its versatility, ease of use, and high performance. Our documentation guides you through the installation process, explains the architectural nuances of the model, showcases various use-cases, and provides a series of detailed tutorials. These resources will help you harness the full potential of YOLOv5 for your [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) projects. Let's get started! @@ -42,10 +42,10 @@ Here's a compilation of comprehensive tutorials that will guide you through diff - [Test-Time Augmentation (TTA)](tutorials/test_time_augmentation.md): Explore how to use TTA to improve your model's prediction accuracy. - [Model Ensembling](tutorials/model_ensembling.md): Learn the strategy of combining multiple models for improved performance. - [Model Pruning/Sparsity](tutorials/model_pruning_and_sparsity.md): Understand pruning and sparsity concepts, and how to create a more efficient model. -- [Hyperparameter Evolution](tutorials/hyperparameter_evolution.md): Discover the process of automated hyperparameter tuning for better model performance. -- [Transfer Learning with Frozen Layers](tutorials/transfer_learning_with_frozen_layers.md): Learn how to implement transfer learning by freezing layers in YOLOv5. +- [Hyperparameter Evolution](tutorials/hyperparameter_evolution.md): Discover the process of automated [hyperparameter tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning) for better model performance. +- [Transfer Learning with Frozen Layers](tutorials/transfer_learning_with_frozen_layers.md): Learn how to implement [transfer learning](https://www.ultralytics.com/glossary/transfer-learning) by freezing layers in YOLOv5. - [Architecture Summary](tutorials/architecture_description.md) 🌟 Delve into the structural details of the YOLOv5 model. -- [Roboflow for Datasets](tutorials/roboflow_datasets_integration.md): Understand how to utilize Roboflow for dataset management, labeling, and active learning. +- [Roboflow for Datasets](tutorials/roboflow_datasets_integration.md): Understand how to utilize Roboflow for dataset management, labeling, and [active learning](https://www.ultralytics.com/glossary/active-learning). - [ClearML Logging](tutorials/clearml_logging_integration.md) 🌟 Learn how to integrate ClearML for efficient logging during your model training. - [YOLOv5 with Neural Magic](tutorials/neural_magic_pruning_quantization.md) Discover how to use Neural Magic's Deepsparse to prune and quantize your YOLOv5 model. - [Comet Logging](tutorials/comet_logging_integration.md) 🌟 NEW: Explore how to utilize Comet for improved model training logging. @@ -95,7 +95,7 @@ We're excited to see the innovative ways you'll use YOLOv5. Dive in, experiment, ### What are the key features of Ultralytics YOLOv5? -Ultralytics YOLOv5 is renowned for its high-speed and high-accuracy object detection capabilities. Built on PyTorch, it is versatile and user-friendly, making it suitable for various computer vision projects. Key features include real-time inference, support for multiple training tricks like Test-Time Augmentation (TTA) and Model Ensembling, and compatibility with export formats such as TFLite, ONNX, CoreML, and TensorRT. To delve deeper into how Ultralytics YOLOv5 can elevate your project, explore our [TFLite, ONNX, CoreML, TensorRT Export guide](tutorials/model_export.md). +Ultralytics YOLOv5 is renowned for its high-speed and high-[accuracy](https://www.ultralytics.com/glossary/accuracy) object detection capabilities. Built on [PyTorch](https://www.ultralytics.com/glossary/pytorch), it is versatile and user-friendly, making it suitable for various computer vision projects. Key features include real-time inference, support for multiple training tricks like Test-Time Augmentation (TTA) and Model Ensembling, and compatibility with export formats such as TFLite, ONNX, CoreML, and TensorRT. To delve deeper into how Ultralytics YOLOv5 can elevate your project, explore our [TFLite, ONNX, CoreML, TensorRT Export guide](tutorials/model_export.md). ### How can I train a custom YOLOv5 model on my dataset? @@ -107,7 +107,7 @@ Ultralytics YOLOv5 is preferred over models like RCNN due to its superior speed ### How can I optimize YOLOv5 model performance during training? -Optimizing YOLOv5 model performance involves tuning various hyperparameters and incorporating techniques like data augmentation and transfer learning. Ultralytics provides comprehensive resources on hyperparameter evolution and pruning/sparsity to improve model efficiency. You can discover practical tips in our [Tips for Best Training Results guide](tutorials/tips_for_best_training_results.md), which offers actionable insights for achieving optimal performance during training. +Optimizing YOLOv5 model performance involves tuning various hyperparameters and incorporating techniques like [data augmentation](https://www.ultralytics.com/glossary/data-augmentation) and transfer learning. Ultralytics provides comprehensive resources on hyperparameter evolution and pruning/sparsity to improve model efficiency. You can discover practical tips in our [Tips for Best Training Results guide](tutorials/tips_for_best_training_results.md), which offers actionable insights for achieving optimal performance during training. ### What environments are supported for running YOLOv5 applications? diff --git a/docs/en/yolov5/quickstart_tutorial.md b/docs/en/yolov5/quickstart_tutorial.md index 582dfcbda8..e6ddb8fd38 100644 --- a/docs/en/yolov5/quickstart_tutorial.md +++ b/docs/en/yolov5/quickstart_tutorial.md @@ -6,7 +6,7 @@ keywords: YOLOv5, Quickstart, real-time object detection, AI, ML, PyTorch, infer # YOLOv5 Quickstart 🚀 -Embark on your journey into the dynamic realm of real-time object detection with YOLOv5! This guide is crafted to serve as a comprehensive starting point for AI enthusiasts and professionals aiming to master YOLOv5. From initial setup to advanced training techniques, we've got you covered. By the end of this guide, you'll have the knowledge to implement YOLOv5 into your projects confidently. Let's ignite the engines and soar into YOLOv5! +Embark on your journey into the dynamic realm of real-time [object detection](https://www.ultralytics.com/glossary/object-detection) with YOLOv5! This guide is crafted to serve as a comprehensive starting point for AI enthusiasts and professionals aiming to master YOLOv5. From initial setup to advanced training techniques, we've got you covered. By the end of this guide, you'll have the knowledge to implement YOLOv5 into your projects confidently. Let's ignite the engines and soar into YOLOv5! ## Install @@ -18,7 +18,7 @@ cd yolov5 pip install -r requirements.txt # install dependencies ``` -## Inference with PyTorch Hub +## Inference with [PyTorch](https://www.ultralytics.com/glossary/pytorch) Hub Experience the simplicity of YOLOv5 [PyTorch Hub](./tutorials/pytorch_hub_model_loading.md) inference, where [models](https://github.com/ultralytics/yolov5/tree/master/models) are seamlessly downloaded from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). @@ -57,7 +57,7 @@ python detect.py --weights yolov5s.pt --source 0 # ## Training -Replicate the YOLOv5 [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) benchmarks with the instructions below. The necessary [models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) are pulled directly from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). Training YOLOv5n/s/m/l/x on a V100 GPU should typically take 1/2/4/6/8 days respectively (note that [Multi-GPU](./tutorials/multi_gpu_training.md) setups work faster). Maximize performance by using the highest possible `--batch-size` or use `--batch-size -1` for the YOLOv5 [AutoBatch](https://github.com/ultralytics/yolov5/pull/5092) feature. The following batch sizes are ideal for V100-16GB GPUs. +Replicate the YOLOv5 [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) benchmarks with the instructions below. The necessary [models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) are pulled directly from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). Training YOLOv5n/s/m/l/x on a V100 GPU should typically take 1/2/4/6/8 days respectively (note that [Multi-GPU](./tutorials/multi_gpu_training.md) setups work faster). Maximize performance by using the highest possible `--batch-size` or use `--batch-size -1` for the YOLOv5 [AutoBatch](https://github.com/ultralytics/yolov5/pull/5092) feature. The following [batch sizes](https://www.ultralytics.com/glossary/batch-size) are ideal for V100-16GB GPUs. ```bash python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml --batch-size 128 @@ -69,4 +69,4 @@ python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml - YOLO training curves -To conclude, YOLOv5 is not only a state-of-the-art tool for object detection but also a testament to the power of machine learning in transforming the way we interact with the world through visual understanding. As you progress through this guide and begin applying YOLOv5 to your projects, remember that you are at the forefront of a technological revolution, capable of achieving remarkable feats. Should you need further insights or support from fellow visionaries, you're invited to our [GitHub repository](https://github.com/ultralytics/yolov5) home to a thriving community of developers and researchers. Keep exploring, keep innovating, and enjoy the marvels of YOLOv5. Happy detecting! 🌠🔍 +To conclude, YOLOv5 is not only a state-of-the-art tool for object detection but also a testament to the power of [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) in transforming the way we interact with the world through visual understanding. As you progress through this guide and begin applying YOLOv5 to your projects, remember that you are at the forefront of a technological revolution, capable of achieving remarkable feats. Should you need further insights or support from fellow visionaries, you're invited to our [GitHub repository](https://github.com/ultralytics/yolov5) home to a thriving community of developers and researchers. Keep exploring, keep innovating, and enjoy the marvels of YOLOv5. Happy detecting! 🌠🔍 diff --git a/docs/en/yolov5/tutorials/architecture_description.md b/docs/en/yolov5/tutorials/architecture_description.md index bb9ade6976..53788270ce 100644 --- a/docs/en/yolov5/tutorials/architecture_description.md +++ b/docs/en/yolov5/tutorials/architecture_description.md @@ -6,7 +6,7 @@ keywords: YOLOv5 architecture, object detection, Ultralytics, YOLO, model struct # Ultralytics YOLOv5 Architecture -YOLOv5 (v6.0/6.1) is a powerful object detection algorithm developed by Ultralytics. This article dives deep into the YOLOv5 architecture, data augmentation strategies, training methodologies, and loss computation techniques. This comprehensive understanding will help improve your practical application of object detection in various fields, including surveillance, autonomous vehicles, and image recognition. +YOLOv5 (v6.0/6.1) is a powerful object detection algorithm developed by Ultralytics. This article dives deep into the YOLOv5 architecture, [data augmentation](https://www.ultralytics.com/glossary/data-augmentation) strategies, training methodologies, and loss computation techniques. This comprehensive understanding will help improve your practical application of object detection in various fields, including surveillance, autonomous vehicles, and [image recognition](https://www.ultralytics.com/glossary/image-recognition). ## 1. Model Structure @@ -104,9 +104,9 @@ SPPF time: 0.20780706405639648 ## 2. Data Augmentation Techniques -YOLOv5 employs various data augmentation techniques to improve the model's ability to generalize and reduce overfitting. These techniques include: +YOLOv5 employs various data augmentation techniques to improve the model's ability to generalize and reduce [overfitting](https://www.ultralytics.com/glossary/overfitting). These techniques include: -- **Mosaic Augmentation**: An image processing technique that combines four training images into one in ways that encourage object detection models to better handle various object scales and translations. +- **Mosaic Augmentation**: An image processing technique that combines four training images into one in ways that encourage [object detection](https://www.ultralytics.com/glossary/object-detection) models to better handle various object scales and translations. ![mosaic](https://github.com/ultralytics/docs/releases/download/0/mosaic-augmentation.avif) @@ -138,9 +138,9 @@ YOLOv5 applies several sophisticated training strategies to enhance the model's - **Multiscale Training**: The input images are randomly rescaled within a range of 0.5 to 1.5 times their original size during the training process. - **AutoAnchor**: This strategy optimizes the prior anchor boxes to match the statistical characteristics of the ground truth boxes in your custom data. -- **Warmup and Cosine LR Scheduler**: A method to adjust the learning rate to enhance model performance. +- **Warmup and Cosine LR Scheduler**: A method to adjust the [learning rate](https://www.ultralytics.com/glossary/learning-rate) to enhance model performance. - **Exponential Moving Average (EMA)**: A strategy that uses the average of parameters over past steps to stabilize the training process and reduce generalization error. -- **Mixed Precision Training**: A method to perform operations in half-precision format, reducing memory usage and enhancing computational speed. +- **[Mixed Precision](https://www.ultralytics.com/glossary/mixed-precision) Training**: A method to perform operations in half-[precision](https://www.ultralytics.com/glossary/precision) format, reducing memory usage and enhancing computational speed. - **Hyperparameter Evolution**: A strategy to automatically tune hyperparameters to achieve optimal performance. ## 4. Additional Features @@ -153,7 +153,7 @@ The loss in YOLOv5 is computed as a combination of three individual loss compone - **Objectness Loss (BCE Loss)**: Another Binary Cross-Entropy loss, calculates the error in detecting whether an object is present in a particular grid cell or not. - **Location Loss (CIoU Loss)**: Complete IoU loss, measures the error in localizing the object within the grid cell. -The overall loss function is depicted by: +The overall [loss function](https://www.ultralytics.com/glossary/loss-function) is depicted by: ![loss](https://latex.codecogs.com/svg.image?Loss=\lambda_1L_{cls}+\lambda_2L_{obj}+\lambda_3L_{loc}) @@ -176,7 +176,7 @@ The YOLOv5 architecture makes some important changes to the box prediction strat However, in YOLOv5, the formula for predicting the box coordinates has been updated to reduce grid sensitivity and prevent the model from predicting unbounded box dimensions. -The revised formulas for calculating the predicted bounding box are as follows: +The revised formulas for calculating the predicted [bounding box](https://www.ultralytics.com/glossary/bounding-box) are as follows: ![bx]() ![by]() @@ -193,7 +193,7 @@ Compare the height and width scaling ratio(relative to anchor) before and after ### 4.4 Build Targets -The build target process in YOLOv5 is critical for training efficiency and model accuracy. It involves assigning ground truth boxes to the appropriate grid cells in the output map and matching them with the appropriate anchor boxes. +The build target process in YOLOv5 is critical for training efficiency and model [accuracy](https://www.ultralytics.com/glossary/accuracy). It involves assigning ground truth boxes to the appropriate grid cells in the output map and matching them with the appropriate anchor boxes. This process follows these steps: diff --git a/docs/en/yolov5/tutorials/clearml_logging_integration.md b/docs/en/yolov5/tutorials/clearml_logging_integration.md index 90012d193c..f8ee5c348e 100644 --- a/docs/en/yolov5/tutorials/clearml_logging_integration.md +++ b/docs/en/yolov5/tutorials/clearml_logging_integration.md @@ -14,7 +14,7 @@ keywords: ClearML, YOLOv5, machine learning, experiment tracking, data versionin 🔨 Track every YOLOv5 training run in the experiment manager -🔧 Version and easily access your custom training data with the integrated ClearML Data Versioning Tool +🔧 Version and easily access your custom [training data](https://www.ultralytics.com/glossary/training-data) with the integrated ClearML Data Versioning Tool 🔦 Remotely train and monitor your YOLOv5 training runs using ClearML Agent @@ -85,8 +85,8 @@ This will capture: - Console output - Scalars (mAP_0.5, mAP_0.5:0.95, precision, recall, losses, learning rates, ...) - General info such as machine details, runtime, creation date etc. -- All produced plots such as label correlogram and confusion matrix -- Images with bounding boxes per epoch +- All produced plots such as label correlogram and [confusion matrix](https://www.ultralytics.com/glossary/confusion-matrix) +- Images with bounding boxes per [epoch](https://www.ultralytics.com/glossary/epoch) - Mosaic per epoch - Validation images per epoch diff --git a/docs/en/yolov5/tutorials/comet_logging_integration.md b/docs/en/yolov5/tutorials/comet_logging_integration.md index 63608fc2cd..c5f20dda93 100644 --- a/docs/en/yolov5/tutorials/comet_logging_integration.md +++ b/docs/en/yolov5/tutorials/comet_logging_integration.md @@ -12,7 +12,7 @@ This guide will cover how to use YOLOv5 with [Comet](https://bit.ly/yolov5-readm ## About Comet -Comet builds tools that help data scientists, engineers, and team leaders accelerate and optimize machine learning and deep learning models. +Comet builds tools that help data scientists, engineers, and team leaders accelerate and optimize [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) and [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) models. Track and visualize model metrics in real time, save your hyperparameters, datasets, and model checkpoints, and visualize your model predictions with [Comet Custom Panels](https://www.comet.com/docs/v2/guides/comet-dashboard/code-panels/about-panels/?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github)! Comet makes sure you never lose track of your work and makes it easy to share results and collaborate across teams of all sizes! @@ -72,7 +72,7 @@ By default, Comet will log the following items ## Metrics -- Box Loss, Object Loss, Classification Loss for the training and validation data +- Box Loss, Object Loss, Classification Loss for the training and [validation data](https://www.ultralytics.com/glossary/validation-data) - mAP_0.5, mAP_0.5:0.95 metrics for the validation data. - Precision and Recall for the validation data @@ -83,7 +83,7 @@ By default, Comet will log the following items ## Visualizations -- Confusion Matrix of the model predictions on the validation data +- [Confusion Matrix](https://www.ultralytics.com/glossary/confusion-matrix) of the model predictions on the validation data - Plots for the PR and F1 curves across all classes - Correlogram of the Class Labels @@ -120,9 +120,9 @@ python train.py \ By default, model predictions (images, ground truth labels and bounding boxes) will be logged to Comet. -You can control the frequency of logged predictions and the associated images by passing the `bbox_interval` command line argument. Predictions can be visualized using Comet's Object Detection Custom Panel. This frequency corresponds to every Nth batch of data per epoch. In the example below, we are logging every 2nd batch of data for each epoch. +You can control the frequency of logged predictions and the associated images by passing the `bbox_interval` command line argument. Predictions can be visualized using Comet's [Object Detection](https://www.ultralytics.com/glossary/object-detection) Custom Panel. This frequency corresponds to every Nth batch of data per [epoch](https://www.ultralytics.com/glossary/epoch). In the example below, we are logging every 2nd batch of data for each epoch. -**Note:** The YOLOv5 validation dataloader will default to a batch size of 32, so you will have to set the logging frequency accordingly. +**Note:** The YOLOv5 validation dataloader will default to a [batch size](https://www.ultralytics.com/glossary/batch-size) of 32, so you will have to set the logging frequency accordingly. Here is an [example project using the Panel](https://www.comet.com/examples/comet-example-yolov5?shareable=YcwMiJaZSXfcEXpGOHDD12vA1&utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github) @@ -152,7 +152,7 @@ env COMET_MAX_IMAGE_UPLOADS=200 python train.py \ ### Logging Class Level Metrics -Use the `COMET_LOG_PER_CLASS_METRICS` environment variable to log mAP, precision, recall, f1 for each class. +Use the `COMET_LOG_PER_CLASS_METRICS` environment variable to log mAP, [precision](https://www.ultralytics.com/glossary/precision), [recall](https://www.ultralytics.com/glossary/recall), f1 for each class. ```shell env COMET_LOG_PER_CLASS_METRICS=true python train.py \ diff --git a/docs/en/yolov5/tutorials/hyperparameter_evolution.md b/docs/en/yolov5/tutorials/hyperparameter_evolution.md index 8b2a132479..3db460b126 100644 --- a/docs/en/yolov5/tutorials/hyperparameter_evolution.md +++ b/docs/en/yolov5/tutorials/hyperparameter_evolution.md @@ -61,7 +61,7 @@ copy_paste: 0.0 # segment copy-paste (probability) ## 2. Define Fitness -Fitness is the value we seek to maximize. In YOLOv5 we define a default fitness function as a weighted combination of metrics: `mAP@0.5` contributes 10% of the weight and `mAP@0.5:0.95` contributes the remaining 90%, with [Precision `P` and Recall `R`](https://en.wikipedia.org/wiki/Precision_and_recall) absent. You may adjust these as you see fit or use the default fitness definition in utils/metrics.py (recommended). +Fitness is the value we seek to maximize. In YOLOv5 we define a default fitness function as a weighted combination of metrics: `mAP@0.5` contributes 10% of the weight and `mAP@0.5:0.95` contributes the remaining 90%, with [Precision `P` and [Recall](https://www.ultralytics.com/glossary/recall) `R`](https://en.wikipedia.org/wiki/Precision_and_recall) absent. You may adjust these as you see fit or use the default fitness definition in utils/metrics.py (recommended). ```python def fitness(x): @@ -72,7 +72,7 @@ def fitness(x): ## 3. Evolve -Evolution is performed about a base scenario which we seek to improve upon. The base scenario in this example is finetuning COCO128 for 10 epochs using pretrained YOLOv5s. The base scenario training command is: +Evolution is performed about a base scenario which we seek to improve upon. The base scenario in this example is [finetuning](https://www.ultralytics.com/glossary/fine-tuning) COCO128 for 10 [epochs](https://www.ultralytics.com/glossary/epoch) using pretrained YOLOv5s. The base scenario training command is: ```bash python train.py --epochs 10 --data coco128.yaml --weights yolov5s.pt --cache diff --git a/docs/en/yolov5/tutorials/model_ensembling.md b/docs/en/yolov5/tutorials/model_ensembling.md index f358106537..814c896921 100644 --- a/docs/en/yolov5/tutorials/model_ensembling.md +++ b/docs/en/yolov5/tutorials/model_ensembling.md @@ -4,11 +4,11 @@ description: Learn how to use YOLOv5 model ensembling during testing and inferen keywords: YOLOv5, model ensembling, testing, inference, mAP, Recall, Ultralytics, object detection, PyTorch --- -📚 This guide explains how to use YOLOv5 🚀 **model ensembling** during testing and inference for improved mAP and Recall. +📚 This guide explains how to use YOLOv5 🚀 **model ensembling** during testing and inference for improved mAP and [Recall](https://www.ultralytics.com/glossary/recall). From [https://en.wikipedia.org/wiki/Ensemble_learning](https://en.wikipedia.org/wiki/Ensemble_learning): -> Ensemble modeling is a process where multiple diverse models are created to predict an outcome, either by using many different modeling algorithms or using different training data sets. The ensemble model then aggregates the prediction of each base model and results in once final prediction for the unseen data. The motivation for using ensemble models is to reduce the generalization error of the prediction. As long as the base models are diverse and independent, the prediction error of the model decreases when the ensemble approach is used. The approach seeks the wisdom of crowds in making a prediction. Even though the ensemble model has multiple base models within the model, it acts and performs as a single model. +> Ensemble modeling is a process where multiple diverse models are created to predict an outcome, either by using many different modeling algorithms or using different [training data](https://www.ultralytics.com/glossary/training-data) sets. The ensemble model then aggregates the prediction of each base model and results in once final prediction for the unseen data. The motivation for using ensemble models is to reduce the generalization error of the prediction. As long as the base models are diverse and independent, the prediction error of the model decreases when the ensemble approach is used. The approach seeks the wisdom of crowds in making a prediction. Even though the ensemble model has multiple base models within the model, it acts and performs as a single model. ## Before You Start diff --git a/docs/en/yolov5/tutorials/model_export.md b/docs/en/yolov5/tutorials/model_export.md index dc68c84c10..e5f0c73007 100644 --- a/docs/en/yolov5/tutorials/model_export.md +++ b/docs/en/yolov5/tutorials/model_export.md @@ -6,7 +6,7 @@ keywords: YOLOv5 export, TFLite, ONNX, CoreML, TensorRT, model conversion, YOLOv # TFLite, ONNX, CoreML, TensorRT Export -📚 This guide explains how to export a trained YOLOv5 🚀 model from PyTorch to ONNX and TorchScript formats. +📚 This guide explains how to export a trained YOLOv5 🚀 model from [PyTorch](https://www.ultralytics.com/glossary/pytorch) to ONNX and TorchScript formats. ## Before You Start @@ -103,7 +103,7 @@ This command exports a pretrained YOLOv5s model to TorchScript and ONNX formats. python export.py --weights yolov5s.pt --include torchscript onnx ``` -💡 ProTip: Add `--half` to export models at FP16 half precision for smaller file sizes +💡 ProTip: Add `--half` to export models at FP16 half [precision](https://www.ultralytics.com/glossary/precision) for smaller file sizes Output: @@ -205,7 +205,7 @@ results.print() # or .show(), .save(), .crop(), .pandas(), etc. ## OpenCV DNN inference -OpenCV inference with ONNX models: +[OpenCV](https://www.ultralytics.com/glossary/opencv) inference with ONNX models: ```bash python export.py --weights yolov5s.pt --include onnx diff --git a/docs/en/yolov5/tutorials/multi_gpu_training.md b/docs/en/yolov5/tutorials/multi_gpu_training.md index 4a56570fdd..53f3a1c1fd 100644 --- a/docs/en/yolov5/tutorials/multi_gpu_training.md +++ b/docs/en/yolov5/tutorials/multi_gpu_training.md @@ -18,7 +18,7 @@ pip install -r requirements.txt # install 💡 ProTip! **Docker Image** is recommended for all Multi-GPU trainings. See [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls -💡 ProTip! `torch.distributed.run` replaces `torch.distributed.launch` in **PyTorch>=1.9**. See [docs](https://pytorch.org/docs/stable/distributed.html) for details. +💡 ProTip! `torch.distributed.run` replaces `torch.distributed.launch` in **[PyTorch](https://www.ultralytics.com/glossary/pytorch)>=1.9**. See [docs](https://pytorch.org/docs/stable/distributed.html) for details. ## Training @@ -69,7 +69,7 @@ python -m torch.distributed.run --nproc_per_node 2 train.py --batch 64 --data co

Use SyncBatchNorm (click to expand) -[SyncBatchNorm](https://pytorch.org/docs/master/generated/torch.nn.SyncBatchNorm.html) could increase accuracy for multiple gpu training, however, it will slow down training by a significant factor. It is **only** available for Multiple GPU DistributedDataParallel training. +[SyncBatchNorm](https://pytorch.org/docs/master/generated/torch.nn.SyncBatchNorm.html) could increase [accuracy](https://www.ultralytics.com/glossary/accuracy) for multiple gpu training, however, it will slow down training by a significant factor. It is **only** available for Multiple GPU DistributedDataParallel training. It is best used when the batch-size on **each** GPU is small (<= 8). @@ -121,7 +121,7 @@ python -m torch.distributed.run --master_port 1234 --nproc_per_node 2 ... ## Results -DDP profiling results on an [AWS EC2 P4d instance](../environments/aws_quickstart_tutorial.md) with 8x A100 SXM4-40GB for YOLOv5l for 1 COCO epoch. +DDP profiling results on an [AWS EC2 P4d instance](../environments/aws_quickstart_tutorial.md) with 8x A100 SXM4-40GB for YOLOv5l for 1 COCO [epoch](https://www.ultralytics.com/glossary/epoch).
Profiling code diff --git a/docs/en/yolov5/tutorials/neural_magic_pruning_quantization.md b/docs/en/yolov5/tutorials/neural_magic_pruning_quantization.md index 663a5d1484..1d2a9bcad4 100644 --- a/docs/en/yolov5/tutorials/neural_magic_pruning_quantization.md +++ b/docs/en/yolov5/tutorials/neural_magic_pruning_quantization.md @@ -30,7 +30,7 @@ DeepSparse is an inference runtime with exceptional performance on CPUs. For ins YOLOv5 speed improvement

-For the first time, your deep learning workloads can meet the performance demands of production without the complexity and costs of hardware accelerators. Put simply, DeepSparse gives you the performance of GPUs and the simplicity of software: +For the first time, your [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) workloads can meet the performance demands of production without the complexity and costs of hardware accelerators. Put simply, DeepSparse gives you the performance of GPUs and the simplicity of software: - **Flexible Deployments**: Run consistently across cloud, data center, and edge with any hardware provider from Intel to AMD to ARM - **Infinite Scalability**: Scale vertically to 100s of cores, out with standard Kubernetes, or fully-abstracted with Serverless @@ -40,7 +40,7 @@ For the first time, your deep learning workloads can meet the performance demand DeepSparse takes advantage of model sparsity to gain its performance speedup. -Sparsification through pruning and quantization is a broadly studied technique, allowing order-of-magnitude reductions in the size and compute needed to execute a network, while maintaining high accuracy. DeepSparse is sparsity-aware, meaning it skips the zeroed out parameters, shrinking amount of compute in a forward pass. Since the sparse computation is now memory bound, DeepSparse executes the network depth-wise, breaking the problem into Tensor Columns, vertical stripes of computation that fit in cache. +Sparsification through pruning and quantization is a broadly studied technique, allowing order-of-magnitude reductions in the size and compute needed to execute a network, while maintaining high [accuracy](https://www.ultralytics.com/glossary/accuracy). DeepSparse is sparsity-aware, meaning it skips the zeroed out parameters, shrinking amount of compute in a forward pass. Since the sparse computation is now memory bound, DeepSparse executes the network depth-wise, breaking the problem into Tensor Columns, vertical stripes of computation that fit in cache.

YOLO model pruning @@ -122,7 +122,7 @@ apt-get install libgl1 #### HTTP Server -DeepSparse Server runs on top of the popular FastAPI web framework and Uvicorn web server. With just a single CLI command, you can easily setup a model service endpoint with DeepSparse. The Server supports any Pipeline from DeepSparse, including object detection with YOLOv5, enabling you to send raw images to the endpoint and receive the bounding boxes. +DeepSparse Server runs on top of the popular FastAPI web framework and Uvicorn web server. With just a single CLI command, you can easily setup a model service endpoint with DeepSparse. The Server supports any Pipeline from DeepSparse, including [object detection](https://www.ultralytics.com/glossary/object-detection) with YOLOv5, enabling you to send raw images to the endpoint and receive the bounding boxes. Spin up the Server with the pruned-quantized YOLOv5s: diff --git a/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md b/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md index b00d94db4c..27e26f144f 100644 --- a/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md +++ b/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md @@ -4,7 +4,7 @@ description: Learn how to load YOLOv5 from PyTorch Hub for seamless model infere keywords: YOLOv5, PyTorch Hub, model loading, Ultralytics, object detection, machine learning, AI, tutorial, inference --- -📚 This guide explains how to load YOLOv5 🚀 from PyTorch Hub at [https://pytorch.org/hub/ultralytics_yolov5](https://pytorch.org/hub/ultralytics_yolov5/). +📚 This guide explains how to load YOLOv5 🚀 from [PyTorch](https://www.ultralytics.com/glossary/pytorch) Hub at [https://pytorch.org/hub/ultralytics_yolov5](https://pytorch.org/hub/ultralytics_yolov5/). ## Before You Start @@ -44,7 +44,7 @@ results.pandas().xyxy[0] ### Detailed Example -This example shows **batched inference** with **PIL** and **OpenCV** image sources. `results` can be **printed** to console, **saved** to `runs/hub`, **showed** to screen on supported environments, and returned as **tensors** or **pandas** dataframes. +This example shows **batched inference** with **PIL** and **[OpenCV](https://www.ultralytics.com/glossary/opencv)** image sources. `results` can be **printed** to console, **saved** to `runs/hub`, **showed** to screen on supported environments, and returned as **tensors** or **pandas** dataframes. ```python import cv2 diff --git a/docs/en/yolov5/tutorials/roboflow_datasets_integration.md b/docs/en/yolov5/tutorials/roboflow_datasets_integration.md index 3047e48c2e..55728f21e7 100644 --- a/docs/en/yolov5/tutorials/roboflow_datasets_integration.md +++ b/docs/en/yolov5/tutorials/roboflow_datasets_integration.md @@ -52,7 +52,7 @@ We have released a custom training tutorial demonstrating all of the above capab ## Active Learning -The real world is messy and your model will invariably encounter situations your dataset didn't anticipate. Using [active learning](https://blog.roboflow.com/what-is-active-learning/?ref=ultralytics) is an important strategy to iteratively improve your dataset and model. With the Roboflow and YOLOv5 integration, you can quickly make improvements on your model deployments by using a battle tested machine learning pipeline. +The real world is messy and your model will invariably encounter situations your dataset didn't anticipate. Using [active learning](https://blog.roboflow.com/what-is-active-learning/?ref=ultralytics) is an important strategy to iteratively improve your dataset and model. With the Roboflow and YOLOv5 integration, you can quickly make improvements on your [model deployments](https://www.ultralytics.com/glossary/model-deployment) by using a battle tested [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) pipeline.

Roboflow active learning

@@ -96,10 +96,10 @@ dataset = project.version("YOUR VERSION").download("yolov5") This code will download your dataset in a format compatible with YOLOv5, allowing you to quickly begin training your model. For more details, refer to the [Exporting Data](#exporting-data) section. -### What is active learning and how does it work with YOLOv5 and Roboflow? +### What is [active learning](https://www.ultralytics.com/glossary/active-learning) and how does it work with YOLOv5 and Roboflow? Active learning is a machine learning strategy that iteratively improves a model by intelligently selecting the most informative data points to label. With the Roboflow and YOLOv5 integration, you can implement active learning to continuously enhance your model's performance. This involves deploying a model, capturing new data, using the model to make predictions, and then manually verifying or correcting those predictions to further train the model. For more insights into active learning see the [Active Learning](#active-learning) section above. ### How can I use Ultralytics environments for training YOLOv5 models on different platforms? -Ultralytics provides ready-to-use environments with pre-installed dependencies like CUDA, CUDNN, Python, and PyTorch, making it easier to kickstart your training projects. These environments are available on various platforms such as Google Cloud, AWS, Azure, and Docker. You can also access free GPU notebooks via [Paperspace](https://bit.ly/yolov5-paperspace-notebook), [Google Colab](https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb), and [Kaggle](https://www.kaggle.com/ultralytics/yolov5). For specific setup instructions, visit the [Supported Environments](#supported-environments) section of the documentation. +Ultralytics provides ready-to-use environments with pre-installed dependencies like CUDA, CUDNN, Python, and [PyTorch](https://www.ultralytics.com/glossary/pytorch), making it easier to kickstart your training projects. These environments are available on various platforms such as Google Cloud, AWS, Azure, and Docker. You can also access free GPU notebooks via [Paperspace](https://bit.ly/yolov5-paperspace-notebook), [Google Colab](https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb), and [Kaggle](https://www.kaggle.com/ultralytics/yolov5). For specific setup instructions, visit the [Supported Environments](#supported-environments) section of the documentation. diff --git a/docs/en/yolov5/tutorials/test_time_augmentation.md b/docs/en/yolov5/tutorials/test_time_augmentation.md index d2b959171c..336ad3f79b 100644 --- a/docs/en/yolov5/tutorials/test_time_augmentation.md +++ b/docs/en/yolov5/tutorials/test_time_augmentation.md @@ -6,7 +6,7 @@ keywords: YOLOv5, Test-Time Augmentation, TTA, machine learning, deep learning, # Test-Time Augmentation (TTA) -📚 This guide explains how to use Test Time Augmentation (TTA) during testing and inference for improved mAP and Recall with YOLOv5 🚀. +📚 This guide explains how to use Test Time Augmentation (TTA) during testing and inference for improved mAP and [Recall](https://www.ultralytics.com/glossary/recall) with YOLOv5 🚀. ## Before You Start diff --git a/docs/en/yolov5/tutorials/tips_for_best_training_results.md b/docs/en/yolov5/tutorials/tips_for_best_training_results.md index c24435d93c..634297203e 100644 --- a/docs/en/yolov5/tutorials/tips_for_best_training_results.md +++ b/docs/en/yolov5/tutorials/tips_for_best_training_results.md @@ -8,7 +8,7 @@ keywords: YOLOv5 training, mAP, dataset best practices, model selection, trainin Most of the time good results can be obtained with no changes to the models or training settings, **provided your dataset is sufficiently large and well labelled**. If at first you don't get good results, there are steps you might be able to take to improve, but we always recommend users **first train with all default settings** before considering any changes. This helps establish a performance baseline and spot areas for improvement. -If you have questions about your training results **we recommend you provide the maximum amount of information possible** if you expect a helpful response, including results plots (train losses, val losses, P, R, mAP), PR curve, confusion matrix, training mosaics, test results and dataset statistics images such as labels.png. All of these are located in your `project/name` directory, typically `yolov5/runs/train/exp`. +If you have questions about your training results **we recommend you provide the maximum amount of information possible** if you expect a helpful response, including results plots (train losses, val losses, P, R, mAP), PR curve, [confusion matrix](https://www.ultralytics.com/glossary/confusion-matrix), training mosaics, test results and dataset statistics images such as labels.png. All of these are located in your `project/name` directory, typically `yolov5/runs/train/exp`. We've put together a full guide for users looking to get the best results on their YOLOv5 trainings below. @@ -18,7 +18,7 @@ We've put together a full guide for users looking to get the best results on the - **Instances per class.** ≥ 10000 instances (labeled objects) per class recommended - **Image variety.** Must be representative of deployed environment. For real-world use cases we recommend images from different times of day, different seasons, different weather, different lighting, different angles, different sources (scraped online, collected locally, different cameras) etc. - **Label consistency.** All instances of all classes in all images must be labelled. Partial labelling will not work. -- **Label accuracy.** Labels must closely enclose each object. No space should exist between an object and it's bounding box. No objects should be missing a label. +- **Label [accuracy](https://www.ultralytics.com/glossary/accuracy).** Labels must closely enclose each object. No space should exist between an object and it's [bounding box](https://www.ultralytics.com/glossary/bounding-box). No objects should be missing a label. - **Label verification.** View `train_batch*.jpg` on train start to verify your labels appear correct, i.e. see [example](./train_custom_data.md#local-logging) mosaic. - **Background images.** Background images are images with no objects that are added to a dataset to reduce False Positives (FP). We recommend about 0-10% background images to help reduce FPs (COCO has 1000 background images for reference, 1% of the total). No labels are required for background images. @@ -53,13 +53,13 @@ python train.py --data custom.yaml --weights '' --cfg yolov5s.yaml Before modifying anything, **first train with default settings to establish a performance baseline**. A full list of train.py settings can be found in the [train.py](https://github.com/ultralytics/yolov5/blob/master/train.py) argparser. -- **Epochs.** Start with 300 epochs. If this overfits early then you can reduce epochs. If overfitting does not occur after 300 epochs, train longer, i.e. 600, 1200 etc. epochs. +- **[Epochs](https://www.ultralytics.com/glossary/epoch).** Start with 300 epochs. If this overfits early then you can reduce epochs. If [overfitting](https://www.ultralytics.com/glossary/overfitting) does not occur after 300 epochs, train longer, i.e. 600, 1200 etc. epochs. - **Image size.** COCO trains at native resolution of `--img 640`, though due to the high amount of small objects in the dataset it can benefit from training at higher resolutions such as `--img 1280`. If there are many small objects then custom datasets will benefit from training at native or higher resolution. Best inference results are obtained at the same `--img` as the training was run at, i.e. if you train at `--img 1280` you should also test and detect at `--img 1280`. -- **Batch size.** Use the largest `--batch-size` that your hardware allows for. Small batch sizes produce poor batchnorm statistics and should be avoided. +- **[Batch size](https://www.ultralytics.com/glossary/batch-size).** Use the largest `--batch-size` that your hardware allows for. Small batch sizes produce poor batchnorm statistics and should be avoided. - **Hyperparameters.** Default hyperparameters are in [hyp.scratch-low.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-low.yaml). We recommend you train with default hyperparameters first before thinking of modifying any. In general, increasing augmentation hyperparameters will reduce and delay overfitting, allowing for longer trainings and higher final mAP. Reduction in loss component gain hyperparameters like `hyp['obj']` will help reduce overfitting in those specific loss components. For an automated method of optimizing these hyperparameters, see our [Hyperparameter Evolution Tutorial](./hyperparameter_evolution.md). ## Further Reading -If you'd like to know more, a good place to start is Karpathy's 'Recipe for Training Neural Networks', which has great ideas for training that apply broadly across all ML domains: [https://karpathy.github.io/2019/04/25/recipe/](https://karpathy.github.io/2019/04/25/recipe/) +If you'd like to know more, a good place to start is Karpathy's 'Recipe for Training [Neural Networks](https://www.ultralytics.com/glossary/neural-network-nn)', which has great ideas for training that apply broadly across all ML domains: [https://karpathy.github.io/2019/04/25/recipe/](https://karpathy.github.io/2019/04/25/recipe/) Good luck 🍀 and let us know if you have any other questions! diff --git a/docs/en/yolov5/tutorials/train_custom_data.md b/docs/en/yolov5/tutorials/train_custom_data.md index 6119bc3a7c..aa093e4b81 100644 --- a/docs/en/yolov5/tutorials/train_custom_data.md +++ b/docs/en/yolov5/tutorials/train_custom_data.md @@ -77,7 +77,7 @@ Export in `YOLOv5 Pytorch` format, then copy the snippet into your training scri ### 2.1 Create `dataset.yaml` -[COCO128](https://www.kaggle.com/ultralytics/coco128) is an example small tutorial dataset composed of the first 128 images in [COCO](https://cocodataset.org/) train2017. These same 128 images are used for both training and validation to verify our training pipeline is capable of overfitting. [data/coco128.yaml](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), shown below, is the dataset config file that defines 1) the dataset root directory `path` and relative paths to `train` / `val` / `test` image directories (or `*.txt` files with image paths) and 2) a class `names` dictionary: +[COCO128](https://www.kaggle.com/ultralytics/coco128) is an example small tutorial dataset composed of the first 128 images in [COCO](https://cocodataset.org/) train2017. These same 128 images are used for both training and validation to verify our training pipeline is capable of [overfitting](https://www.ultralytics.com/glossary/overfitting). [data/coco128.yaml](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), shown below, is the dataset config file that defines 1) the dataset root directory `path` and relative paths to `train` / `val` / `test` image directories (or `*.txt` files with image paths) and 2) a class `names` dictionary: ```yaml # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] @@ -183,11 +183,11 @@ You can use ClearML Data to version your dataset and then pass it to YOLOv5 simp Training results are automatically logged with [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) loggers to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc. -This directory contains train and val statistics, mosaics, labels, predictions and augmented mosaics, as well as metrics and charts including precision-recall (PR) curves and confusion matrices. +This directory contains train and val statistics, mosaics, labels, predictions and augmented mosaics, as well as metrics and charts including [precision](https://www.ultralytics.com/glossary/precision)-[recall](https://www.ultralytics.com/glossary/recall) (PR) curves and confusion matrices. Local logging results -Results file `results.csv` is updated after each epoch, and then plotted as `results.png` (below) after training completes. You can also plot any `results.csv` file manually: +Results file `results.csv` is updated after each [epoch](https://www.ultralytics.com/glossary/epoch), and then plotted as `results.png` (below) after training completes. You can also plot any `results.csv` file manually: ```python from utils.plots import plot_results @@ -202,8 +202,8 @@ plot_results("path/to/results.csv") # plot 'results.csv' as 'results.png' Once your model is trained you can use your best checkpoint `best.pt` to: - Run [CLI](https://github.com/ultralytics/yolov5#quick-start-examples) or [Python](./pytorch_hub_model_loading.md) inference on new images and videos -- [Validate](https://github.com/ultralytics/yolov5/blob/master/val.py) accuracy on train, val and test splits -- [Export](./model_export.md) to TensorFlow, Keras, ONNX, TFlite, TF.js, CoreML and TensorRT formats +- [Validate](https://github.com/ultralytics/yolov5/blob/master/val.py) [accuracy](https://www.ultralytics.com/glossary/accuracy) on train, val and test splits +- [Export](./model_export.md) to [TensorFlow](https://www.ultralytics.com/glossary/tensorflow), Keras, ONNX, TFlite, TF.js, CoreML and TensorRT formats - [Evolve](./hyperparameter_evolution.md) hyperparameters to improve performance - [Improve](https://docs.roboflow.com/adding-data/upload-api?ref=ultralytics) your model by sampling real-world images and adding them to your dataset diff --git a/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md b/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md index be6a087015..9e689ad3eb 100644 --- a/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md +++ b/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md @@ -4,7 +4,7 @@ description: Learn to freeze YOLOv5 layers for efficient transfer learning, redu keywords: YOLOv5, transfer learning, freeze layers, machine learning, deep learning, model training, PyTorch, Ultralytics --- -📚 This guide explains how to **freeze** YOLOv5 🚀 layers when **transfer learning**. Transfer learning is a useful way to quickly retrain a model on new data without having to retrain the entire network. Instead, part of the initial weights are frozen in place, and the rest of the weights are used to compute loss and are updated by the optimizer. This requires less resources than normal training and allows for faster training times, though it may also result in reductions to final trained accuracy. +📚 This guide explains how to **freeze** YOLOv5 🚀 layers when **[transfer learning](https://www.ultralytics.com/glossary/transfer-learning)**. Transfer learning is a useful way to quickly retrain a model on new data without having to retrain the entire network. Instead, part of the initial weights are frozen in place, and the rest of the weights are used to compute loss and are updated by the optimizer. This requires less resources than normal training and allows for faster training times, though it may also result in reductions to final trained accuracy. ## Before You Start @@ -121,7 +121,7 @@ train.py --batch 48 --weights yolov5m.pt --data voc.yaml --epochs 50 --cache --i ### Accuracy Comparison -The results show that freezing speeds up training, but reduces final accuracy slightly. +The results show that freezing speeds up training, but reduces final [accuracy](https://www.ultralytics.com/glossary/accuracy) slightly. ![Freezing training mAP50 results](https://github.com/ultralytics/docs/releases/download/0/freezing-training-map50-results.avif) diff --git a/docs/mkdocs_github_authors.yaml b/docs/mkdocs_github_authors.yaml index bcf9cdb0f4..31526516ed 100644 --- a/docs/mkdocs_github_authors.yaml +++ b/docs/mkdocs_github_authors.yaml @@ -34,6 +34,9 @@ 40165666+berry-ding@users.noreply.github.com: avatar: https://avatars.githubusercontent.com/u/40165666?v=4 username: berry-ding +46103969+inisis@users.noreply.github.com: + avatar: https://avatars.githubusercontent.com/u/46103969?v=4 + username: inisis 47978446+sergiuwaxmann@users.noreply.github.com: avatar: https://avatars.githubusercontent.com/u/47978446?v=4 username: sergiuwaxmann diff --git a/docs/overrides/main.html b/docs/overrides/main.html index 48827689c1..18305746f0 100644 --- a/docs/overrides/main.html +++ b/docs/overrides/main.html @@ -1,30 +1,38 @@ -{% extends "base.html" %} - -{% block announce %} - +{% extends "base.html" %} {% block announce %} + {% endblock %} diff --git a/docs/overrides/stylesheets/style.css b/docs/overrides/stylesheets/style.css index 352ab3d522..a9a89d9013 100644 --- a/docs/overrides/stylesheets/style.css +++ b/docs/overrides/stylesheets/style.css @@ -51,7 +51,7 @@ div.highlight { /* Banner (same as the one on the Ultralytics website) -------------------------------------------------------------- */ .md-banner { - background-image: url(https://assets-global.website-files.com/646dd1f1a3703e451ba81ecc/6627a0cab2de939ad35939ed_banner_82.webp); + background-image: url(https://assets-global.website-files.com/646dd1f1a3703e451ba81ecc/66e9a211bf6831d112fd6ce3_banner_yv24.avif); background-size: cover; background-position: center; } @@ -61,44 +61,109 @@ div.highlight { margin-bottom: 0 !important; } -.banner-wrapper { +.banner-wrapper, +.banner-wrapper > .banner-content-wrapper, +.banner-wrapper > .banner-content-wrapper > .banner-info-wrapper { display: flex; - justify-content: center; align-items: center; +} + +.banner-wrapper, +.banner-wrapper > .banner-content-wrapper { + flex-direction: column; +} + +.banner-wrapper { + justify-content: space-between; + gap: 16px; + + padding: 16px; +} + +.banner-wrapper > .banner-content-wrapper, +.banner-wrapper > .banner-content-wrapper > .banner-info-wrapper { + justify-content: center; +} + +.banner-wrapper > .banner-content-wrapper { + gap: 8px; +} + +.banner-wrapper > .banner-content-wrapper > .banner-info-wrapper { + gap: 4px; +} - height: 64px; +.banner-wrapper > .banner-content-wrapper > p, +.banner-wrapper > .banner-content-wrapper > .banner-info-wrapper > p { + margin: 0; +} + +.banner-wrapper > .banner-content-wrapper > p { + font-size: 20px; + font-weight: 500; +} + +.banner-wrapper > .banner-content-wrapper > .banner-info-wrapper > p, +.banner-wrapper > .banner-button-wrapper > .banner-button-wrapper > button { + font-size: 14px; +} + +.banner-wrapper > .banner-content-wrapper > .banner-info-wrapper > p { + color: #f3f3f3; +} - overflow: hidden; +.banner-wrapper > .banner-button-wrapper, +.banner-wrapper > .banner-button-wrapper > .banner-button-wrapper, +.banner-wrapper > .banner-button-wrapper > .banner-button-wrapper > button { + border-radius: 100px; } -.banner-content { - max-height: 64px; +.banner-wrapper > .banner-button-wrapper, +.banner-wrapper > .banner-button-wrapper > .banner-button-wrapper { + padding: 2px; + + background-color: rgba(222, 255, 56, 0.2); } -.banner-content.desktop { - display: none; +.banner-wrapper > .banner-button-wrapper > .banner-button-wrapper.large { + padding: 4px; } -.banner-arrow { - display: none; - max-height: 80px; - margin-left: -16px; - transition: transform ease-in-out 0.5s; +.banner-wrapper > .banner-button-wrapper > .banner-button-wrapper > button { + cursor: pointer; + + min-width: 132px; + padding: 10px; + + font-weight: 500; + color: #111f68; + + background-color: rgb(222, 255, 56); } -.banner-wrapper:hover > .banner-arrow { - transform: translateX(8px); +.banner-wrapper + > .banner-button-wrapper + > .banner-button-wrapper + > button:hover { + background-color: rgba(222, 255, 56, 0.85); } @media screen and (min-width: 768px) { - .banner-content.mobile { - display: none; + .banner-wrapper, + .banner-wrapper > .banner-content-wrapper { + flex-direction: row; } - .banner-content.desktop { - display: revert; + + .banner-wrapper { + gap: 32px; + + padding: 12px; } - .banner-arrow { - display: revert; + + .banner-wrapper > .banner-content-wrapper { + gap: 24px; + + margin: 0 auto; } } /* Banner (same as the one on the Ultralytics website) -------------------------------------------------------------- */ diff --git a/pyproject.toml b/pyproject.toml index 66ad66cb19..51593636dc 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -32,14 +32,12 @@ requires-python = ">=3.8" license = { "text" = "AGPL-3.0" } keywords = ["machine-learning", "deep-learning", "computer-vision", "ML", "DL", "AI", "YOLO", "YOLOv3", "YOLOv5", "YOLOv8", "YOLOv9", "YOLOv10", "HUB", "Ultralytics"] authors = [ - { name = "Glenn Jocher" }, - { name = "Ayush Chaurasia" }, - { name = "Jing Qiu" } + { name = "Glenn Jocher", email = "glenn.jocher@ultralytics.com"}, + { name = "Jing Qiu", email = "jing.qiu@ultralytics.com"}, + { name = "Ayush Chaurasia" } ] maintainers = [ - { name = "Glenn Jocher" }, - { name = "Ayush Chaurasia" }, - { name = "Jing Qiu" } + { name = "Ultralytics", email = "hello@ultralytics.com" } ] classifiers = [ "Development Status :: 4 - Beta", @@ -127,9 +125,11 @@ extra = [ ] [project.urls] +"Homepage" = "https://ultralytics.com" +"Source" = "https://github.com/ultralytics/ultralytics" +"Documentation" = "https://docs.ultralytics.com" "Bug Reports" = "https://github.com/ultralytics/ultralytics/issues" -"Funding" = "https://ultralytics.com" -"Source" = "https://github.com/ultralytics/ultralytics/" +"Changelog" = "https://github.com/ultralytics/ultralytics/releases" [project.scripts] yolo = "ultralytics.cfg:entrypoint" diff --git a/tests/test_exports.py b/tests/test_exports.py index 7bc14c1c78..98e4049d79 100644 --- a/tests/test_exports.py +++ b/tests/test_exports.py @@ -32,7 +32,6 @@ def test_export_onnx(): YOLO(file)(SOURCE, imgsz=32) # exported model inference -@pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="OpenVINO not supported in Python 3.12") @pytest.mark.skipif(not TORCH_1_13, reason="OpenVINO requires torch>=1.13") def test_export_openvino(): """Test YOLO exports to OpenVINO format for model inference compatibility.""" diff --git a/tests/test_integrations.py b/tests/test_integrations.py index aaa8330b37..3a0d1b48a7 100644 --- a/tests/test_integrations.py +++ b/tests/test_integrations.py @@ -27,6 +27,7 @@ def test_mlflow(): """Test training with MLflow tracking enabled (see https://mlflow.org/ for details).""" SETTINGS["mlflow"] = True YOLO("yolov8n-cls.yaml").train(data="imagenet10", imgsz=32, epochs=3, plots=False, device="cpu") + SETTINGS["mlflow"] = False @pytest.mark.skipif(True, reason="Test failing in scheduled CI https://github.com/ultralytics/ultralytics/pull/8868") @@ -58,6 +59,7 @@ def test_mlflow_keep_run_active(): YOLO("yolov8n-cls.yaml").train(data="imagenet10", imgsz=32, epochs=1, plots=False, device="cpu") status = mlflow.get_run(run_id=run_id).info.status assert status == "FINISHED", "MLflow run should be ended by default when MLFLOW_KEEP_RUN_ACTIVE is not set" + SETTINGS["mlflow"] = False @pytest.mark.skipif(not check_requirements("tritonclient", install=False), reason="tritonclient[all] not installed") diff --git a/tests/test_python.py b/tests/test_python.py index b5dd0c883b..55f087f008 100644 --- a/tests/test_python.py +++ b/tests/test_python.py @@ -269,7 +269,10 @@ def test_results(model): r = r.to(device="cpu", dtype=torch.float32) r.save_txt(txt_file=TMP / "runs/tests/label.txt", save_conf=True) r.save_crop(save_dir=TMP / "runs/tests/crops/") - r.tojson(normalize=True) + r.to_json(normalize=True) + r.to_df(decimals=3) + r.to_csv() + r.to_xml() r.plot(pil=True) r.plot(conf=True, boxes=True) print(r, len(r), r.path) # print after methods diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py index 9f6607772e..85944a543c 100644 --- a/ultralytics/__init__.py +++ b/ultralytics/__init__.py @@ -1,6 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license -__version__ = "8.2.95" +__version__ = "8.2.100" import os diff --git a/ultralytics/cfg/__init__.py b/ultralytics/cfg/__init__.py index 6b8edff251..06356e7589 100644 --- a/ultralytics/cfg/__init__.py +++ b/ultralytics/cfg/__init__.py @@ -19,7 +19,7 @@ from ultralytics.utils import ( ROOT, RUNS_DIR, SETTINGS, - SETTINGS_YAML, + SETTINGS_FILE, TESTS_RUNNING, IterableSimpleNamespace, __version__, @@ -532,7 +532,7 @@ def handle_yolo_settings(args: List[str]) -> None: try: if any(args): if args[0] == "reset": - SETTINGS_YAML.unlink() # delete the settings file + SETTINGS_FILE.unlink() # delete the settings file SETTINGS.reset() # create new settings LOGGER.info("Settings reset successfully") # inform the user that settings have been reset else: # save a new setting @@ -540,8 +540,8 @@ def handle_yolo_settings(args: List[str]) -> None: check_dict_alignment(SETTINGS, new) SETTINGS.update(new) - LOGGER.info(f"💡 Learn about settings at {url}") - yaml_print(SETTINGS_YAML) # print the current settings + print(SETTINGS) # print the current settings + LOGGER.info(f"💡 Learn more about Ultralytics Settings at {url}") except Exception as e: LOGGER.warning(f"WARNING ⚠️ settings error: '{e}'. Please see {url} for help.") @@ -712,6 +712,7 @@ def entrypoint(debug=""): "cfg": lambda: yaml_print(DEFAULT_CFG_PATH), "hub": lambda: handle_yolo_hub(args[1:]), "login": lambda: handle_yolo_hub(args), + "logout": lambda: handle_yolo_hub(args), "copy-cfg": copy_default_cfg, "explorer": lambda: handle_explorer(args[1:]), "streamlit-predict": lambda: handle_streamlit_inference(), diff --git a/ultralytics/cfg/default.yaml b/ultralytics/cfg/default.yaml index 205dd65593..a44f609411 100644 --- a/ultralytics/cfg/default.yaml +++ b/ultralytics/cfg/default.yaml @@ -81,7 +81,7 @@ keras: False # (bool) use Kera=s optimize: False # (bool) TorchScript: optimize for mobile int8: False # (bool) CoreML/TF INT8 quantization dynamic: False # (bool) ONNX/TF/TensorRT: dynamic axes -simplify: False # (bool) ONNX: simplify model using `onnxslim` +simplify: True # (bool) ONNX: simplify model using `onnxslim` opset: # (int, optional) ONNX: opset version workspace: 4 # (int) TensorRT: workspace size (GB) nms: False # (bool) CoreML: add NMS diff --git a/ultralytics/data/utils.py b/ultralytics/data/utils.py index 600f62e574..e82d8bb759 100644 --- a/ultralytics/data/utils.py +++ b/ultralytics/data/utils.py @@ -22,7 +22,7 @@ from ultralytics.utils import ( LOGGER, NUM_THREADS, ROOT, - SETTINGS_YAML, + SETTINGS_FILE, TQDM, clean_url, colorstr, @@ -324,7 +324,7 @@ def check_det_dataset(dataset, autodownload=True): if s and autodownload: LOGGER.warning(m) else: - m += f"\nNote dataset download directory is '{DATASETS_DIR}'. You can update this in '{SETTINGS_YAML}'" + m += f"\nNote dataset download directory is '{DATASETS_DIR}'. You can update this in '{SETTINGS_FILE}'" raise FileNotFoundError(m) t = time.time() r = None # success diff --git a/ultralytics/engine/exporter.py b/ultralytics/engine/exporter.py index df90e838d4..d4987f90be 100644 --- a/ultralytics/engine/exporter.py +++ b/ultralytics/engine/exporter.py @@ -95,9 +95,7 @@ from ultralytics.utils.torch_utils import TORCH_1_13, get_latest_opset, select_d def export_formats(): - """YOLOv8 export formats.""" - import pandas # scope for faster 'import ultralytics' - + """Ultralytics YOLO export formats.""" x = [ ["PyTorch", "-", ".pt", True, True], ["TorchScript", "torchscript", ".torchscript", True, True], @@ -113,7 +111,7 @@ def export_formats(): ["PaddlePaddle", "paddle", "_paddle_model", True, True], ["NCNN", "ncnn", "_ncnn_model", True, True], ] - return pandas.DataFrame(x, columns=["Format", "Argument", "Suffix", "CPU", "GPU"]) + return dict(zip(["Format", "Argument", "Suffix", "CPU", "GPU"], zip(*x))) def gd_outputs(gd): diff --git a/ultralytics/engine/model.py b/ultralytics/engine/model.py index 47a7f07a20..6775188915 100644 --- a/ultralytics/engine/model.py +++ b/ultralytics/engine/model.py @@ -206,33 +206,21 @@ class Model(nn.Module): Check if the provided model is an Ultralytics HUB model. This static method determines whether the given model string represents a valid Ultralytics HUB model - identifier. It checks for three possible formats: a full HUB URL, an API key and model ID combination, - or a standalone model ID. + identifier. Args: - model (str): The model identifier to check. This can be a URL, an API key and model ID - combination, or a standalone model ID. + model (str): The model string to check. Returns: (bool): True if the model is a valid Ultralytics HUB model, False otherwise. Examples: - >>> Model.is_hub_model("https://hub.ultralytics.com/models/example_model") + >>> Model.is_hub_model("https://hub.ultralytics.com/models/MODEL") True - >>> Model.is_hub_model("api_key_example_model_id") - True - >>> Model.is_hub_model("example_model_id") - True - >>> Model.is_hub_model("not_a_hub_model.pt") + >>> Model.is_hub_model("yolov8n.pt") False """ - return any( - ( - model.startswith(f"{HUB_WEB_ROOT}/models/"), # i.e. https://hub.ultralytics.com/models/MODEL_ID - [len(x) for x in model.split("_")] == [42, 20], # APIKEY_MODEL - len(model) == 20 and not Path(model).exists() and all(x not in model for x in "./\\"), # MODEL - ) - ) + return model.startswith(f"{HUB_WEB_ROOT}/models/") def _new(self, cfg: str, task=None, model=None, verbose=False) -> None: """ diff --git a/ultralytics/engine/results.py b/ultralytics/engine/results.py index 89b2d5c8e1..57cc4b04bc 100644 --- a/ultralytics/engine/results.py +++ b/ultralytics/engine/results.py @@ -14,6 +14,7 @@ import torch from ultralytics.data.augment import LetterBox from ultralytics.utils import LOGGER, SimpleClass, ops +from ultralytics.utils.checks import check_requirements from ultralytics.utils.plotting import Annotator, colors, save_one_box from ultralytics.utils.torch_utils import smart_inference_mode @@ -818,7 +819,90 @@ class Results(SimpleClass): return results + def to_df(self, normalize=False, decimals=5): + """ + Converts detection results to a Pandas Dataframe. + + This method converts the detection results into Pandas Dataframe format. It includes information + about detected objects such as bounding boxes, class names, confidence scores, and optionally + segmentation masks and keypoints. + + Args: + normalize (bool): Whether to normalize the bounding box coordinates by the image dimensions. + If True, coordinates will be returned as float values between 0 and 1. Defaults to False. + decimals (int): Number of decimal places to round the output values to. Defaults to 5. + + Returns: + (DataFrame): A Pandas Dataframe containing all the information in results in an organized way. + + Examples: + >>> results = model("path/to/image.jpg") + >>> df_result = results[0].to_df() + >>> print(df_result) + """ + import pandas as pd + + return pd.DataFrame(self.summary(normalize=normalize, decimals=decimals)) + + def to_csv(self, normalize=False, decimals=5, *args, **kwargs): + """ + Converts detection results to a CSV format. + + This method serializes the detection results into a CSV format. It includes information + about detected objects such as bounding boxes, class names, confidence scores, and optionally + segmentation masks and keypoints. + + Args: + normalize (bool): Whether to normalize the bounding box coordinates by the image dimensions. + If True, coordinates will be returned as float values between 0 and 1. Defaults to False. + decimals (int): Number of decimal places to round the output values to. Defaults to 5. + *args (Any): Variable length argument list to be passed to pandas.DataFrame.to_csv(). + **kwargs (Any): Arbitrary keyword arguments to be passed to pandas.DataFrame.to_csv(). + + + Returns: + (str): CSV containing all the information in results in an organized way. + + Examples: + >>> results = model("path/to/image.jpg") + >>> csv_result = results[0].to_csv() + >>> print(csv_result) + """ + return self.to_df(normalize=normalize, decimals=decimals).to_csv(*args, **kwargs) + + def to_xml(self, normalize=False, decimals=5, *args, **kwargs): + """ + Converts detection results to XML format. + + This method serializes the detection results into an XML format. It includes information + about detected objects such as bounding boxes, class names, confidence scores, and optionally + segmentation masks and keypoints. + + Args: + normalize (bool): Whether to normalize the bounding box coordinates by the image dimensions. + If True, coordinates will be returned as float values between 0 and 1. Defaults to False. + decimals (int): Number of decimal places to round the output values to. Defaults to 5. + *args (Any): Variable length argument list to be passed to pandas.DataFrame.to_xml(). + **kwargs (Any): Arbitrary keyword arguments to be passed to pandas.DataFrame.to_xml(). + + Returns: + (str): An XML string containing all the information in results in an organized way. + + Examples: + >>> results = model("path/to/image.jpg") + >>> xml_result = results[0].to_xml() + >>> print(xml_result) + """ + check_requirements("lxml") + df = self.to_df(normalize=normalize, decimals=decimals) + return '\n' if df.empty else df.to_xml(*args, **kwargs) + def tojson(self, normalize=False, decimals=5): + """Deprecated version of to_json().""" + LOGGER.warning("WARNING ⚠️ 'result.tojson()' is deprecated, replace with 'result.to_json()'.") + return self.to_json(normalize, decimals) + + def to_json(self, normalize=False, decimals=5): """ Converts detection results to JSON format. @@ -836,7 +920,7 @@ class Results(SimpleClass): Examples: >>> results = model("path/to/image.jpg") - >>> json_result = results[0].tojson() + >>> json_result = results[0].to_json() >>> print(json_result) Notes: diff --git a/ultralytics/engine/validator.py b/ultralytics/engine/validator.py index 655f2455ca..5e0f0988c5 100644 --- a/ultralytics/engine/validator.py +++ b/ultralytics/engine/validator.py @@ -110,7 +110,8 @@ class BaseValidator: if self.training: self.device = trainer.device self.data = trainer.data - self.args.half = self.device.type != "cpu" # force FP16 val during training + # force FP16 val during training + self.args.half = self.device.type != "cpu" and trainer.amp model = trainer.ema.ema or trainer.model model = model.half() if self.args.half else model.float() # self.model = model diff --git a/ultralytics/hub/__init__.py b/ultralytics/hub/__init__.py index d8d7b4a274..33b0c3748d 100644 --- a/ultralytics/hub/__init__.py +++ b/ultralytics/hub/__init__.py @@ -79,7 +79,6 @@ def logout(): ``` """ SETTINGS["api_key"] = "" - SETTINGS.save() LOGGER.info(f"{PREFIX}logged out ✅. To log in again, use 'yolo hub login'.") diff --git a/ultralytics/hub/session.py b/ultralytics/hub/session.py index b112d29ff1..170bb82b67 100644 --- a/ultralytics/hub/session.py +++ b/ultralytics/hub/session.py @@ -5,6 +5,7 @@ import threading import time from http import HTTPStatus from pathlib import Path +from urllib.parse import parse_qs, urlparse import requests @@ -77,7 +78,6 @@ class HUBTrainingSession: if not session.client.authenticated: if identifier.startswith(f"{HUB_WEB_ROOT}/models/"): LOGGER.warning(f"{PREFIX}WARNING ⚠️ Login to Ultralytics HUB with 'yolo hub login API_KEY'.") - exit() return None if args and not identifier.startswith(f"{HUB_WEB_ROOT}/models/"): # not a HUB model URL session.create_model(args) @@ -96,7 +96,8 @@ class HUBTrainingSession: self.model_url = f"{HUB_WEB_ROOT}/models/{self.model.id}" if self.model.is_trained(): print(emojis(f"Loading trained HUB model {self.model_url} 🚀")) - self.model_file = self.model.get_weights_url("best") + url = self.model.get_weights_url("best") # download URL with auth + self.model_file = checks.check_file(url, download_dir=Path(SETTINGS["weights_dir"]) / "hub" / self.model.id) return # Set training args and start heartbeats for HUB to monitor agent @@ -146,9 +147,8 @@ class HUBTrainingSession: Parses the given identifier to determine the type of identifier and extract relevant components. The method supports different identifier formats: - - A HUB URL, which starts with HUB_WEB_ROOT followed by '/models/' - - An identifier containing an API key and a model ID separated by an underscore - - An identifier that is solely a model ID of a fixed length + - A HUB model URL https://hub.ultralytics.com/models/MODEL + - A HUB model URL with API Key https://hub.ultralytics.com/models/MODEL?api_key=APIKEY - A local filename that ends with '.pt' or '.yaml' Args: @@ -160,32 +160,16 @@ class HUBTrainingSession: Raises: HUBModelError: If the identifier format is not recognized. """ - # Initialize variables api_key, model_id, filename = None, None, None - - # Check if identifier is a HUB URL - if identifier.startswith(f"{HUB_WEB_ROOT}/models/"): - # Extract the model_id after the HUB_WEB_ROOT URL - model_id = identifier.split(f"{HUB_WEB_ROOT}/models/")[-1] + if Path(identifier).suffix in {".pt", ".yaml"}: + filename = identifier + elif identifier.startswith(f"{HUB_WEB_ROOT}/models/"): + parsed_url = urlparse(identifier) + model_id = Path(parsed_url.path).stem # handle possible final backslash robustly + query_params = parse_qs(parsed_url.query) # dictionary, i.e. {"api_key": ["API_KEY_HERE"]} + api_key = query_params.get("api_key", [None])[0] else: - # Split the identifier based on underscores only if it's not a HUB URL - parts = identifier.split("_") - - # Check if identifier is in the format of API key and model ID - if len(parts) == 2 and len(parts[0]) == 42 and len(parts[1]) == 20: - api_key, model_id = parts - # Check if identifier is a single model ID - elif len(parts) == 1 and len(parts[0]) == 20: - model_id = parts[0] - # Check if identifier is a local filename - elif identifier.endswith(".pt") or identifier.endswith(".yaml"): - filename = identifier - else: - raise HUBModelError( - f"model='{identifier}' could not be parsed. Check format is correct. " - f"Supported formats are Ultralytics HUB URL, apiKey_modelId, modelId, local pt or yaml file." - ) - + raise HUBModelError(f"model='{identifier} invalid, correct format is {HUB_WEB_ROOT}/models/MODEL_ID") return api_key, model_id, filename def _set_train_args(self): diff --git a/ultralytics/nn/autobackend.py b/ultralytics/nn/autobackend.py index e5ef51c03e..a0e2e43bbf 100644 --- a/ultralytics/nn/autobackend.py +++ b/ultralytics/nn/autobackend.py @@ -398,8 +398,8 @@ class AutoBackend(nn.Module): from ultralytics.engine.exporter import export_formats raise TypeError( - f"model='{w}' is not a supported model format. " - f"See https://docs.ultralytics.com/modes/predict for help.\n\n{export_formats()}" + f"model='{w}' is not a supported model format. Ultralytics supports: {export_formats()['Format']}\n" + f"See https://docs.ultralytics.com/modes/predict for help." ) # Load external metadata YAML @@ -653,7 +653,7 @@ class AutoBackend(nn.Module): """ from ultralytics.engine.exporter import export_formats - sf = list(export_formats().Suffix) # export suffixes + sf = export_formats()["Suffix"] # export suffixes if not is_url(p) and not isinstance(p, str): check_suffix(p, sf) # checks name = Path(p).name diff --git a/ultralytics/solutions/object_counter.py b/ultralytics/solutions/object_counter.py index ce6c1cb579..398629a8bc 100644 --- a/ultralytics/solutions/object_counter.py +++ b/ultralytics/solutions/object_counter.py @@ -127,10 +127,13 @@ class ObjectCounter: # Draw region or line annotator.draw_region(reg_pts=self.reg_pts, color=(104, 0, 123), thickness=self.tf * 2) - if tracks[0].boxes.id is not None: - boxes = tracks[0].boxes.xyxy.cpu() - clss = tracks[0].boxes.cls.cpu().tolist() - track_ids = tracks[0].boxes.id.int().cpu().tolist() + # Extract tracks for OBB or object detection + track_data = tracks[0].obb or tracks[0].boxes + + if track_data and track_data.id is not None: + boxes = track_data.xyxy.cpu() + clss = track_data.cls.cpu().tolist() + track_ids = track_data.id.int().cpu().tolist() # Extract tracks for box, track_id, cls in zip(boxes, track_ids, clss): diff --git a/ultralytics/solutions/parking_management.py b/ultralytics/solutions/parking_management.py index 19a8ef1689..6128493377 100644 --- a/ultralytics/solutions/parking_management.py +++ b/ultralytics/solutions/parking_management.py @@ -42,10 +42,10 @@ class ParkingPtsSelection: self.image_path = None self.image = None self.canvas_image = None - self.bounding_boxes = [] + self.rg_data = [] # region coordinates self.current_box = [] - self.img_width = 0 - self.img_height = 0 + self.imgw = 0 # image width + self.imgh = 0 # image height # Constants self.canvas_max_width = 1280 @@ -64,17 +64,17 @@ class ParkingPtsSelection: return self.image = Image.open(self.image_path) - self.img_width, self.img_height = self.image.size + self.imgw, self.imgh = self.image.size # Calculate the aspect ratio and resize image - aspect_ratio = self.img_width / self.img_height + aspect_ratio = self.imgw / self.imgh if aspect_ratio > 1: # Landscape orientation - canvas_width = min(self.canvas_max_width, self.img_width) + canvas_width = min(self.canvas_max_width, self.imgw) canvas_height = int(canvas_width / aspect_ratio) else: # Portrait orientation - canvas_height = min(self.canvas_max_height, self.img_height) + canvas_height = min(self.canvas_max_height, self.imgh) canvas_width = int(canvas_height * aspect_ratio) # Check if canvas is already initialized @@ -90,46 +90,34 @@ class ParkingPtsSelection: self.canvas.bind("", self.on_canvas_click) # Reset bounding boxes and current box - self.bounding_boxes = [] + self.rg_data = [] self.current_box = [] def on_canvas_click(self, event): """Handle mouse clicks on canvas to create points for bounding boxes.""" self.current_box.append((event.x, event.y)) - x0, y0 = event.x - 3, event.y - 3 - x1, y1 = event.x + 3, event.y + 3 - self.canvas.create_oval(x0, y0, x1, y1, fill="red") + self.canvas.create_oval(event.x - 3, event.y - 3, event.x + 3, event.y + 3, fill="red") if len(self.current_box) == 4: - self.bounding_boxes.append(self.current_box) - self.draw_bounding_box(self.current_box) + self.rg_data.append(self.current_box) + [ + self.canvas.create_line(self.current_box[i], self.current_box[(i + 1) % 4], fill="blue", width=2) + for i in range(4) + ] self.current_box = [] - def draw_bounding_box(self, box): - """ - Draw bounding box on canvas. - - Args: - box (list): Bounding box data - """ - for i in range(4): - x1, y1 = box[i] - x2, y2 = box[(i + 1) % 4] - self.canvas.create_line(x1, y1, x2, y2, fill="blue", width=2) - def remove_last_bounding_box(self): """Remove the last drawn bounding box from canvas.""" from tkinter import messagebox # scope for multi-environment compatibility - if self.bounding_boxes: - self.bounding_boxes.pop() # Remove the last bounding box + if self.rg_data: + self.rg_data.pop() # Remove the last bounding box self.canvas.delete("all") # Clear the canvas self.canvas.create_image(0, 0, anchor=self.tk.NW, image=self.canvas_image) # Redraw the image # Redraw all bounding boxes - for box in self.bounding_boxes: - self.draw_bounding_box(box) - + for box in self.rg_data: + [self.canvas.create_line(box[i], box[(i + 1) % 4], fill="blue", width=2) for i in range(4)] messagebox.showinfo("Success", "Last bounding box removed.") else: messagebox.showwarning("Warning", "No bounding boxes to remove.") @@ -138,19 +126,19 @@ class ParkingPtsSelection: """Saves rescaled bounding boxes to 'bounding_boxes.json' based on image-to-canvas size ratio.""" from tkinter import messagebox # scope for multi-environment compatibility - canvas_width, canvas_height = self.canvas.winfo_width(), self.canvas.winfo_height() - width_scaling_factor = self.img_width / canvas_width - height_scaling_factor = self.img_height / canvas_height - bounding_boxes_data = [] - for box in self.bounding_boxes: - rescaled_box = [] + rg_data = [] # regions data + for box in self.rg_data: + rs_box = [] # rescaled box list for x, y in box: - rescaled_x = int(x * width_scaling_factor) - rescaled_y = int(y * height_scaling_factor) - rescaled_box.append((rescaled_x, rescaled_y)) - bounding_boxes_data.append({"points": rescaled_box}) + rs_box.append( + ( + int(x * self.imgw / self.canvas.winfo_width()), # width scaling + int(y * self.imgh / self.canvas.winfo_height()), + ) + ) # height scaling + rg_data.append({"points": rs_box}) with open("bounding_boxes.json", "w") as f: - json.dump(bounding_boxes_data, f, indent=4) + json.dump(rg_data, f, indent=4) messagebox.showinfo("Success", "Bounding boxes saved to bounding_boxes.json") @@ -160,102 +148,85 @@ class ParkingManagement: def __init__( self, - model_path, - txt_color=(0, 0, 0), - bg_color=(255, 255, 255), - occupied_region_color=(0, 255, 0), - available_region_color=(0, 0, 255), - margin=10, + model, # Ultralytics YOLO model file path + json_file, # Parking management annotation file created from Parking Annotator + occupied_region_color=(0, 0, 255), # occupied region color + available_region_color=(0, 255, 0), # available region color ): """ Initializes the parking management system with a YOLOv8 model and visualization settings. Args: - model_path (str): Path to the YOLOv8 model. - txt_color (tuple): RGB color tuple for text. - bg_color (tuple): RGB color tuple for background. + model (str): Path to the YOLOv8 model. + json_file (str): file that have all parking slot points data occupied_region_color (tuple): RGB color tuple for occupied regions. available_region_color (tuple): RGB color tuple for available regions. - margin (int): Margin for text display. """ - # Model path and initialization - self.model_path = model_path - self.model = self.load_model() - - # Labels dictionary - self.labels_dict = {"Occupancy": 0, "Available": 0} - - # Visualization details - self.margin = margin - self.bg_color = bg_color - self.txt_color = txt_color - self.occupied_region_color = occupied_region_color - self.available_region_color = available_region_color - - self.window_name = "Ultralytics YOLOv8 Parking Management System" - # Check if environment supports imshow - self.env_check = check_imshow(warn=True) - - def load_model(self): - """Load the Ultralytics YOLO model for inference and analytics.""" + # Model initialization from ultralytics import YOLO - return YOLO(self.model_path) - - @staticmethod - def parking_regions_extraction(json_file): - """ - Extract parking regions from json file. + self.model = YOLO(model) - Args: - json_file (str): file that have all parking slot points - """ + # Load JSON data with open(json_file) as f: - return json.load(f) + self.json_data = json.load(f) - def process_data(self, json_data, im0, boxes, clss): + self.pr_info = {"Occupancy": 0, "Available": 0} # dictionary for parking information + + self.occ = occupied_region_color + self.arc = available_region_color + + self.env_check = check_imshow(warn=True) # check if environment supports imshow + + def process_data(self, im0): """ Process the model data for parking lot management. Args: - json_data (str): json data for parking lot management im0 (ndarray): inference image - boxes (list): bounding boxes data - clss (list): bounding boxes classes list - - Returns: - filled_slots (int): total slots that are filled in parking lot - empty_slots (int): total slots that are available in parking lot """ - annotator = Annotator(im0) - empty_slots, filled_slots = len(json_data), 0 - for region in json_data: - points_array = np.array(region["points"], dtype=np.int32).reshape((-1, 1, 2)) - region_occupied = False + results = self.model.track(im0, persist=True, show=False) # object tracking - for box, cls in zip(boxes, clss): - x_center = int((box[0] + box[2]) / 2) - y_center = int((box[1] + box[3]) / 2) - text = f"{self.model.names[int(cls)]}" + es, fs = len(self.json_data), 0 # empty slots, filled slots + annotator = Annotator(im0) # init annotator + # extract tracks data + if results[0].boxes.id is None: + self.display_frames(im0) + return im0 + + boxes = results[0].boxes.xyxy.cpu().tolist() + clss = results[0].boxes.cls.cpu().tolist() + + for region in self.json_data: + # Convert points to a NumPy array with the correct dtype and reshape properly + pts_array = np.array(region["points"], dtype=np.int32).reshape((-1, 1, 2)) + rg_occupied = False # occupied region initialization + for box, cls in zip(boxes, clss): + xc = int((box[0] + box[2]) / 2) + yc = int((box[1] + box[3]) / 2) annotator.display_objects_labels( - im0, text, self.txt_color, self.bg_color, x_center, y_center, self.margin + im0, self.model.names[int(cls)], (104, 31, 17), (255, 255, 255), xc, yc, 10 ) - dist = cv2.pointPolygonTest(points_array, (x_center, y_center), False) + dist = cv2.pointPolygonTest(pts_array, (xc, yc), False) if dist >= 0: - region_occupied = True + rg_occupied = True break + if rg_occupied: + fs += 1 + es -= 1 + + # Plotting regions + color = self.occ if rg_occupied else self.arc + cv2.polylines(im0, [pts_array], isClosed=True, color=color, thickness=2) - color = self.occupied_region_color if region_occupied else self.available_region_color - cv2.polylines(im0, [points_array], isClosed=True, color=color, thickness=2) - if region_occupied: - filled_slots += 1 - empty_slots -= 1 + self.pr_info["Occupancy"] = fs + self.pr_info["Available"] = es - self.labels_dict["Occupancy"] = filled_slots - self.labels_dict["Available"] = empty_slots + annotator.display_analytics(im0, self.pr_info, (104, 31, 17), (255, 255, 255), 10) - annotator.display_analytics(im0, self.labels_dict, self.txt_color, self.bg_color, self.margin) + self.display_frames(im0) + return im0 def display_frames(self, im0): """ @@ -265,8 +236,7 @@ class ParkingManagement: im0 (ndarray): inference image """ if self.env_check: - cv2.namedWindow(self.window_name) - cv2.imshow(self.window_name, im0) + cv2.imshow("Ultralytics Parking Manager", im0) # Break Window if cv2.waitKey(1) & 0xFF == ord("q"): return diff --git a/ultralytics/utils/__init__.py b/ultralytics/utils/__init__.py index 7328a5fdb2..b4cc312d85 100644 --- a/ultralytics/utils/__init__.py +++ b/ultralytics/utils/__init__.py @@ -3,6 +3,7 @@ import contextlib import importlib.metadata import inspect +import json import logging.config import os import platform @@ -14,6 +15,7 @@ import time import urllib import uuid from pathlib import Path +from threading import Lock from types import SimpleNamespace from typing import Union @@ -800,7 +802,7 @@ IS_RASPBERRYPI = is_raspberrypi() GIT_DIR = get_git_dir() IS_GIT_DIR = is_git_dir() USER_CONFIG_DIR = Path(os.getenv("YOLO_CONFIG_DIR") or get_user_config_dir()) # Ultralytics settings dir -SETTINGS_YAML = USER_CONFIG_DIR / "settings.yaml" +SETTINGS_FILE = USER_CONFIG_DIR / "settings.json" def colorstr(*input): @@ -1038,21 +1040,121 @@ def set_sentry(): sentry_sdk.set_user({"id": SETTINGS["uuid"]}) # SHA-256 anonymized UUID hash -class SettingsManager(dict): +class JSONDict(dict): """ - Manages Ultralytics settings stored in a YAML file. + A dictionary-like class that provides JSON persistence for its contents. - Args: - file (str | Path): Path to the Ultralytics settings YAML file. Default is USER_CONFIG_DIR / 'settings.yaml'. - version (str): Settings version. In case of local version mismatch, new default settings will be saved. + This class extends the built-in dictionary to automatically save its contents to a JSON file whenever they are + modified. It ensures thread-safe operations using a lock. + + Attributes: + file_path (Path): The path to the JSON file used for persistence. + lock (threading.Lock): A lock object to ensure thread-safe operations. + + Methods: + _load: Loads the data from the JSON file into the dictionary. + _save: Saves the current state of the dictionary to the JSON file. + __setitem__: Stores a key-value pair and persists it to disk. + __delitem__: Removes an item and updates the persistent storage. + update: Updates the dictionary and persists changes. + clear: Clears all entries and updates the persistent storage. + + Examples: + >>> json_dict = JSONDict("data.json") + >>> json_dict["key"] = "value" + >>> print(json_dict["key"]) + value + >>> del json_dict["key"] + >>> json_dict.update({"new_key": "new_value"}) + >>> json_dict.clear() + """ + + def __init__(self, file_path: Union[str, Path] = "data.json"): + """Initialize a JSONDict object with a specified file path for JSON persistence.""" + super().__init__() + self.file_path = Path(file_path) + self.lock = Lock() + self._load() + + def _load(self): + """Load the data from the JSON file into the dictionary.""" + try: + if self.file_path.exists(): + with open(self.file_path) as f: + self.update(json.load(f)) + except json.JSONDecodeError: + print(f"Error decoding JSON from {self.file_path}. Starting with an empty dictionary.") + except Exception as e: + print(f"Error reading from {self.file_path}: {e}") + + def _save(self): + """Save the current state of the dictionary to the JSON file.""" + try: + self.file_path.parent.mkdir(parents=True, exist_ok=True) + with open(self.file_path, "w") as f: + json.dump(dict(self), f, indent=2) + except Exception as e: + print(f"Error writing to {self.file_path}: {e}") + + def __setitem__(self, key, value): + """Store a key-value pair and persist to disk.""" + with self.lock: + super().__setitem__(key, value) + self._save() + + def __delitem__(self, key): + """Remove an item and update the persistent storage.""" + with self.lock: + super().__delitem__(key) + self._save() + + def __str__(self): + """Return a pretty-printed JSON string representation of the dictionary.""" + return f'JSONDict("{self.file_path}"):\n{json.dumps(dict(self), indent=2, ensure_ascii=False)}' + + def update(self, *args, **kwargs): + """Update the dictionary and persist changes.""" + with self.lock: + super().update(*args, **kwargs) + self._save() + + def clear(self): + """Clear all entries and update the persistent storage.""" + with self.lock: + super().clear() + self._save() + + +class SettingsManager(JSONDict): + """ + SettingsManager class for managing and persisting Ultralytics settings. + + This class extends JSONDict to provide JSON persistence for settings, ensuring thread-safe operations and default + values. It validates settings on initialization and provides methods to update or reset settings. + + Attributes: + file (Path): The path to the JSON file used for persistence. + version (str): The version of the settings schema. + defaults (Dict): A dictionary containing default settings. + help_msg (str): A help message for users on how to view and update settings. + + Methods: + _validate_settings: Validates the current settings and resets if necessary. + update: Updates settings, validating keys and types. + reset: Resets the settings to default and saves them. + + Examples: + Initialize and update settings: + >>> settings = SettingsManager() + >>> settings.update(runs_dir="/new/runs/dir") + >>> print(settings["runs_dir"]) + /new/runs/dir """ - def __init__(self, file=SETTINGS_YAML, version="0.0.5"): + def __init__(self, file=SETTINGS_FILE, version="0.0.6"): """Initializes the SettingsManager with default settings and loads user settings.""" - import copy import hashlib - from ultralytics.utils.checks import check_version from ultralytics.utils.torch_utils import torch_distributed_zero_first root = GIT_DIR or Path() @@ -1081,45 +1183,42 @@ class SettingsManager(dict): "vscode_msg": True, } self.help_msg = ( - f"\nView settings with 'yolo settings' or at '{self.file}'" - "\nUpdate settings with 'yolo settings key=value', i.e. 'yolo settings runs_dir=path/to/dir'. " + f"\nView Ultralytics Settings with 'yolo settings' or at '{self.file}'" + "\nUpdate Settings with 'yolo settings key=value', i.e. 'yolo settings runs_dir=path/to/dir'. " "For help see https://docs.ultralytics.com/quickstart/#ultralytics-settings." ) - super().__init__(copy.deepcopy(self.defaults)) - with torch_distributed_zero_first(RANK): - if not self.file.exists(): - self.save() - - self.load() - correct_keys = self.keys() == self.defaults.keys() - correct_types = all(type(a) is type(b) for a, b in zip(self.values(), self.defaults.values())) - correct_version = check_version(self["settings_version"], self.version) - if not (correct_keys and correct_types and correct_version): - LOGGER.warning( - "WARNING ⚠️ Ultralytics settings reset to default values. This may be due to a possible problem " - f"with your settings or a recent ultralytics package update. {self.help_msg}" - ) + super().__init__(self.file) + + if not self.file.exists() or not self: # Check if file doesn't exist or is empty + LOGGER.info(f"Creating new Ultralytics Settings v{version} file ✅ {self.help_msg}") self.reset() - if self.get("datasets_dir") == self.get("runs_dir"): - LOGGER.warning( - f"WARNING ⚠️ Ultralytics setting 'datasets_dir: {self.get('datasets_dir')}' " - f"must be different than 'runs_dir: {self.get('runs_dir')}'. " - f"Please change one to avoid possible issues during training. {self.help_msg}" - ) + self._validate_settings() + + def _validate_settings(self): + """Validate the current settings and reset if necessary.""" + correct_keys = set(self.keys()) == set(self.defaults.keys()) + correct_types = all(isinstance(self.get(k), type(v)) for k, v in self.defaults.items()) + correct_version = self.get("settings_version", "") == self.version - def load(self): - """Loads settings from the YAML file.""" - super().update(yaml_load(self.file)) + if not (correct_keys and correct_types and correct_version): + LOGGER.warning( + "WARNING ⚠️ Ultralytics settings reset to default values. This may be due to a possible problem " + f"with your settings or a recent ultralytics package update. {self.help_msg}" + ) + self.reset() - def save(self): - """Saves the current settings to the YAML file.""" - yaml_save(self.file, dict(self)) + if self.get("datasets_dir") == self.get("runs_dir"): + LOGGER.warning( + f"WARNING ⚠️ Ultralytics setting 'datasets_dir: {self.get('datasets_dir')}' " + f"must be different than 'runs_dir: {self.get('runs_dir')}'. " + f"Please change one to avoid possible issues during training. {self.help_msg}" + ) def update(self, *args, **kwargs): - """Updates a setting value in the current settings.""" + """Updates settings, validating keys and types.""" for k, v in kwargs.items(): if k not in self.defaults: raise KeyError(f"No Ultralytics setting '{k}'. {self.help_msg}") @@ -1127,20 +1226,16 @@ class SettingsManager(dict): if not isinstance(v, t): raise TypeError(f"Ultralytics setting '{k}' must be of type '{t}', not '{type(v)}'. {self.help_msg}") super().update(*args, **kwargs) - self.save() def reset(self): """Resets the settings to default and saves them.""" self.clear() self.update(self.defaults) - self.save() def deprecation_warn(arg, new_arg): """Issue a deprecation warning when a deprecated argument is used, suggesting an updated argument.""" - LOGGER.warning( - f"WARNING ⚠️ '{arg}' is deprecated and will be removed in in the future. " f"Please use '{new_arg}' instead." - ) + LOGGER.warning(f"WARNING ⚠️ '{arg}' is deprecated and will be removed in in the future. Use '{new_arg}' instead.") def clean_url(url): @@ -1159,11 +1254,8 @@ def vscode_msg(ext="ultralytics.ultralytics-snippets") -> str: path = (USER_CONFIG_DIR.parents[2] if WINDOWS else USER_CONFIG_DIR.parents[1]) / ".vscode/extensions" obs_file = path / ".obsolete" # file tracks uninstalled extensions, while source directory remains installed = any(path.glob(f"{ext}*")) and ext not in (obs_file.read_text("utf-8") if obs_file.exists() else "") - return ( - "" - if installed - else f"{colorstr('VS Code:')} view Ultralytics VS Code Extension ⚡ at https://docs.ultralytics.com/integrations/vscode" - ) + url = "https://docs.ultralytics.com/integrations/vscode" + return "" if installed else f"{colorstr('VS Code:')} view Ultralytics VS Code Extension ⚡ at {url}" # Run below code on utils init ------------------------------------------------------------------------------------ @@ -1171,6 +1263,7 @@ def vscode_msg(ext="ultralytics.ultralytics-snippets") -> str: # Check first-install steps PREFIX = colorstr("Ultralytics: ") SETTINGS = SettingsManager() # initialize settings +PERSISTENT_CACHE = JSONDict(USER_CONFIG_DIR / "persistent_cache.json") # initialize persistent cache DATASETS_DIR = Path(SETTINGS["datasets_dir"]) # global datasets directory WEIGHTS_DIR = Path(SETTINGS["weights_dir"]) # global weights directory RUNS_DIR = Path(SETTINGS["runs_dir"]) # global runs directory diff --git a/ultralytics/utils/benchmarks.py b/ultralytics/utils/benchmarks.py index 212c2f7bfe..53ad62c5fe 100644 --- a/ultralytics/utils/benchmarks.py +++ b/ultralytics/utils/benchmarks.py @@ -85,7 +85,7 @@ def benchmark( y = [] t0 = time.time() - for i, (name, format, suffix, cpu, gpu) in export_formats().iterrows(): # index, (name, format, suffix, CPU, GPU) + for i, (name, format, suffix, cpu, gpu) in enumerate(zip(*export_formats().values())): emoji, filename = "❌", None # export defaults try: # Checks @@ -97,8 +97,8 @@ def benchmark( assert MACOS or LINUX, "CoreML and TF.js export only supported on macOS and Linux" assert not IS_RASPBERRYPI, "CoreML and TF.js export not supported on Raspberry Pi" assert not IS_JETSON, "CoreML and TF.js export not supported on NVIDIA Jetson" - if i in {3, 5}: # CoreML and OpenVINO - assert not IS_PYTHON_3_12, "CoreML and OpenVINO not supported on Python 3.12" + if i in {5}: # CoreML + assert not IS_PYTHON_3_12, "CoreML not supported on Python 3.12" if i in {6, 7, 8}: # TF SavedModel, TF GraphDef, and TFLite assert not isinstance(model, YOLOWorld), "YOLOWorldv2 TensorFlow exports not supported by onnx2tf yet" if i in {9, 10}: # TF EdgeTPU and TF.js @@ -322,9 +322,12 @@ class ProfileModels: num_warmup_runs (int, optional): Number of warmup runs before the actual profiling starts. Default is 10. min_time (float, optional): Minimum time in seconds for profiling a model. Default is 60. imgsz (int, optional): Size of the image used during profiling. Default is 640. - half (bool, optional): Flag to indicate whether to use half-precision floating point for profiling. + half (bool, optional): Flag to indicate whether to use FP16 half-precision for TensorRT profiling. trt (bool, optional): Flag to indicate whether to profile using TensorRT. Default is True. device (torch.device, optional): Device used for profiling. If None, it is determined automatically. + + Notes: + FP16 'half' argument option removed for ONNX as slower on CPU than FP32 """ self.paths = paths self.num_timed_runs = num_timed_runs @@ -353,10 +356,17 @@ class ProfileModels: model_info = model.info() if self.trt and self.device.type != "cpu" and not engine_file.is_file(): engine_file = model.export( - format="engine", half=self.half, imgsz=self.imgsz, device=self.device, verbose=False + format="engine", + half=self.half, + imgsz=self.imgsz, + device=self.device, + verbose=False, ) onnx_file = model.export( - format="onnx", half=self.half, imgsz=self.imgsz, simplify=True, device=self.device, verbose=False + format="onnx", + imgsz=self.imgsz, + device=self.device, + verbose=False, ) elif file.suffix == ".onnx": model_info = self.get_onnx_model_info(file) diff --git a/ultralytics/utils/checks.py b/ultralytics/utils/checks.py index 6b308bc146..70d3d088b4 100644 --- a/ultralytics/utils/checks.py +++ b/ultralytics/utils/checks.py @@ -656,9 +656,10 @@ def check_amp(model): def amp_allclose(m, im): """All close FP32 vs AMP results.""" - a = m(im, device=device, verbose=False)[0].boxes.data # FP32 inference + batch = [im] * 8 + a = m(batch, imgsz=128, device=device, verbose=False)[0].boxes.data # FP32 inference with autocast(enabled=True): - b = m(im, device=device, verbose=False)[0].boxes.data # AMP inference + b = m(batch, imgsz=128, device=device, verbose=False)[0].boxes.data # AMP inference del m return a.shape == b.shape and torch.allclose(a, b.float(), atol=0.5) # close to 0.5 absolute tolerance diff --git a/ultralytics/utils/plotting.py b/ultralytics/utils/plotting.py index 3626e77839..f3edf78168 100644 --- a/ultralytics/utils/plotting.py +++ b/ultralytics/utils/plotting.py @@ -419,7 +419,7 @@ class Annotator: # Convert im back to PIL and update draw self.fromarray(self.im) - def kpts(self, kpts, shape=(640, 640), radius=5, kpt_line=True, conf_thres=0.25, kpt_color=None): + def kpts(self, kpts, shape=(640, 640), radius=None, kpt_line=True, conf_thres=0.25, kpt_color=None): """ Plot keypoints on the image. @@ -436,6 +436,7 @@ class Annotator: - Modifies self.im in-place. - If self.pil is True, converts image to numpy array and back to PIL. """ + radius = radius if radius is not None else self.lw if self.pil: # Convert to numpy first self.im = np.asarray(self.im).copy() @@ -471,7 +472,7 @@ class Annotator: pos1, pos2, kpt_color or self.limb_color[i].tolist(), - thickness=2, + thickness=int(np.ceil(self.lw / 2)), lineType=cv2.LINE_AA, ) if self.pil: diff --git a/ultralytics/utils/torch_utils.py b/ultralytics/utils/torch_utils.py index 758a4e11fe..a39969299c 100644 --- a/ultralytics/utils/torch_utils.py +++ b/ultralytics/utils/torch_utils.py @@ -110,15 +110,17 @@ def autocast(enabled: bool, device: str = "cuda"): def get_cpu_info(): """Return a string with system CPU information, i.e. 'Apple M2'.""" - with contextlib.suppress(Exception): - import cpuinfo # pip install py-cpuinfo + from ultralytics.utils import PERSISTENT_CACHE # avoid circular import error - k = "brand_raw", "hardware_raw", "arch_string_raw" # keys sorted by preference (not all keys always available) - info = cpuinfo.get_cpu_info() # info dict - string = info.get(k[0] if k[0] in info else k[1] if k[1] in info else k[2], "unknown") - return string.replace("(R)", "").replace("CPU ", "").replace("@ ", "") + if "cpu_info" not in PERSISTENT_CACHE: + with contextlib.suppress(Exception): + import cpuinfo # pip install py-cpuinfo - return "unknown" + k = "brand_raw", "hardware_raw", "arch_string_raw" # keys sorted by preference + info = cpuinfo.get_cpu_info() # info dict + string = info.get(k[0] if k[0] in info else k[1] if k[1] in info else k[2], "unknown") + PERSISTENT_CACHE["cpu_info"] = string.replace("(R)", "").replace("CPU ", "").replace("@ ", "") + return PERSISTENT_CACHE.get("cpu_info", "unknown") def select_device(device="", batch=0, newline=False, verbose=True): @@ -247,7 +249,7 @@ def fuse_conv_and_bn(conv, bn): ) # Prepare filters - w_conv = conv.weight.clone().view(conv.out_channels, -1) + w_conv = conv.weight.view(conv.out_channels, -1) w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var))) fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape)) @@ -278,7 +280,7 @@ def fuse_deconv_and_bn(deconv, bn): ) # Prepare filters - w_deconv = deconv.weight.clone().view(deconv.out_channels, -1) + w_deconv = deconv.weight.view(deconv.out_channels, -1) w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var))) fuseddconv.weight.copy_(torch.mm(w_bn, w_deconv).view(fuseddconv.weight.shape))