Note that benchmarking results might vary based on the exact hardware and software configuration of a system, as well as the current workload of the system at the time the benchmarks are run. For the most reliable results use a dataset with a large number of images, i.e. `data='coco128.yaml' (128 val images), or `data='coco.yaml'` (5000 val images).
Note that benchmarking results might vary based on the exact hardware and software configuration of a system, as well as the current workload of the system at the time the benchmarks are run. For the most reliable results use a dataset with a large number of images, i.e. `data='coco8.yaml' (128 val images), or `data='coco.yaml'` (5000 val images).
description: Learn how Ultralytics leverages Continuous Integration (CI) for maintaining high-quality code. Explore our CI tests and the status of these tests for our repositories.
@ -16,13 +16,13 @@ Here's a brief description of our CI actions:
- **[Docker Deployment](https://github.com/ultralytics/ultralytics/actions/workflows/docker.yaml):** This test checks the deployment of the project using Docker to ensure the Dockerfile and related scripts are working correctly.
- **[Broken Links](https://github.com/ultralytics/ultralytics/actions/workflows/links.yml):** This test scans the codebase for any broken or dead links in our markdown or HTML files.
- **[CodeQL](https://github.com/ultralytics/ultralytics/actions/workflows/codeql.yaml):** CodeQL is a tool from GitHub that performs semantic analysis on our code, helping to find potential security vulnerabilities and maintain high-quality code.
- **[PyPi Publishing](https://github.com/ultralytics/ultralytics/actions/workflows/publish.yml):** This test checks if the project can be packaged and published to PyPi without any errors.
- **[PyPI Publishing](https://github.com/ultralytics/ultralytics/actions/workflows/publish.yml):** This test checks if the project can be packaged and published to PyPi without any errors.
### CI Results
Below is the table showing the status of these CI tests for our main repositories:
| Repository | CI | Docker Deployment | Broken Links | CodeQL | PyPi and Docs Publishing |
| Repository | CI | Docker Deployment | Broken Links | CodeQL | PyPI and Docs Publishing |
@ -80,7 +80,7 @@ Before diving into the usage instructions, be sure to check out the range of [YO
model = YOLO(f'{model_variant}.pt')
# Step 4: Setting Up Training Arguments
args = dict(data="coco128.yaml", epochs=16)
args = dict(data="coco8.yaml", epochs=16)
task.connect(args)
# Step 5: Initiating Model Training
@ -97,7 +97,7 @@ Let’s understand the steps showcased in the usage code snippet above.
**Step 3: Loading the YOLOv8 Model**: The selected YOLOv8 model is loaded using Ultralytics' YOLO class, preparing it for training.
**Step 4: Setting Up Training Arguments**: Key training arguments like the dataset (`coco128.yaml`) and the number of epochs (`16`) are organized in a dictionary and connected to the ClearML task. This allows for tracking and potential modification via the ClearML UI. For a detailed understanding of the model training process and best practices, refer to our [YOLOv8 Model Training guide](../modes/train.md).
**Step 4: Setting Up Training Arguments**: Key training arguments like the dataset (`coco8.yaml`) and the number of epochs (`16`) are organized in a dictionary and connected to the ClearML task. This allows for tracking and potential modification via the ClearML UI. For a detailed understanding of the model training process and best practices, refer to our [YOLOv8 Model Training guide](../modes/train.md).
**Step 5: Initiating Model Training**: The model training is started with the specified arguments. The results of the training process are captured in the `results` variable.
@ -71,8 +71,8 @@ Welcome to the Ultralytics Integrations page! This page provides an overview of
- [TFLite Edge TPU](edge-tpu.md): Developed by [Google](https://www.google.com) for optimizing TensorFlow Lite models on Edge TPUs, this model format ensures high-speed, efficient edge computing.
- [TF.js](tfjs.md): Developed by [Google](https://www.google.com) to facilitate machine learning in browsers and Node.js, TF.js allows JavaScript-based deployment of ML models.
- [TF.js](tfjs.md): Developed by [Google](https://www.google.com) to facilitate machine learning in browsers and Node.js, TF.js allows JavaScript-based deployment of ML models.
- [PaddlePaddle](paddlepaddle.md): An open-source deep learning platform by [Baidu](https://www.baidu.com/), PaddlePaddle enables the efficient deployment of AI models and focuses on the scalability of industrial applications.
- [NCNN](ncnn.md): Developed by [Tencent](http://www.tencent.com/), NCNN is an efficient neural network inference framework tailored for mobile devices. It enables direct deployment of AI models into apps, optimizing performance across various mobile platforms.
@ -261,14 +261,14 @@ To reproduce the Ultralytics benchmarks above on all export [formats](../modes/e
# Load a YOLOv8n PyTorch model
model = YOLO('yolov8n.pt')
# Benchmark YOLOv8n speed and accuracy on the COCO128 dataset for all all export formats
results= model.benchmarks(data='coco128.yaml')
# Benchmark YOLOv8n speed and accuracy on the COCO8 dataset for all all export formats
results= model.benchmarks(data='coco8.yaml')
```
=== "CLI"
```bash
# Benchmark YOLOv8n speed and accuracy on the COCO128 dataset for all all export formats
yolo benchmark model=yolov8n.pt data=coco128.yaml
# Benchmark YOLOv8n speed and accuracy on the COCO8 dataset for all all export formats
yolo benchmark model=yolov8n.pt data=coco8.yaml
```
Note that benchmarking results might vary based on the exact hardware and software configuration of a system, as well as the current workload of the system at the time the benchmarks are run. For the most reliable results use a dataset with a large number of images, i.e. `data='coco128.yaml' (128 val images), or `data='coco.yaml'` (5000 val images).
@ -112,13 +112,13 @@ In this example, we demonstrate how to use a custom search space for hyperparame
model = YOLO("yolov8n.pt")
# Run Ray Tune on the model
result_grid = model.tune(data="coco128.yaml",
result_grid = model.tune(data="coco8.yaml",
space={"lr0": tune.uniform(1e-5, 1e-1)},
epochs=50,
use_ray=True)
```
In the code snippet above, we create a YOLO model with the "yolov8n.pt" pretrained weights. Then, we call the `tune()` method, specifying the dataset configuration with "coco128.yaml". We provide a custom search space for the initial learning rate `lr0` using a dictionary with the key "lr0" and the value `tune.uniform(1e-5, 1e-1)`. Finally, we pass additional training arguments, such as the number of epochs directly to the tune method as `epochs=50`.
In the code snippet above, we create a YOLO model with the "yolov8n.pt" pretrained weights. Then, we call the `tune()` method, specifying the dataset configuration with "coco8.yaml". We provide a custom search space for the initial learning rate `lr0` using a dictionary with the key "lr0" and the value `tune.uniform(1e-5, 1e-1)`. Finally, we pass additional training arguments, such as the number of epochs directly to the tune method as `epochs=50`.
@ -32,7 +32,7 @@ Here are the key features that make TF.js a powerful tool for developers:
## Deployment Options with TensorFlow.js
Before we dive into the process of exporting YOLOv8 models to the TF.js format, let's explore some typical deployment scenarios where this format is used.
Before we dive into the process of exporting YOLOv8 models to the TF.js format, let's explore some typical deployment scenarios where this format is used.
TF.js provides a range of options to deploy your machine learning models:
| `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: `"coco128.yaml"`. |
| `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. |
@ -47,7 +47,7 @@ The following are some notable features of YOLOv8's Train mode:
## Usage Examples
Train YOLOv8n on the COCO128 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 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"
@ -64,20 +64,20 @@ Train YOLOv8n on the COCO128 dataset for 100 epochs at image size 640. The train
model = YOLO('yolov8n.yaml').load('yolov8n.pt') # build from YAML and transfer weights
While leveraging the computational power of the M1/M2 chips, this enables more efficient processing of the training tasks. For more detailed guidance and advanced configuration options, please refer to the [PyTorch MPS documentation](https://pytorch.org/docs/stable/notes/mps.html).
@ -178,7 +178,7 @@ The training settings for YOLO models encompass various hyperparameters and conf
| `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., `coco128.yaml`). This file contains dataset-specific parameters, including paths to training and validation data, class names, and number of classes. |
| `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. |
@ -47,7 +47,7 @@ These are the notable functionalities offered by YOLOv8's Val mode:
## Usage Examples
Validate trained YOLOv8n model accuracy on the COCO128 dataset. No argument need to passed as the `model` retains it's training `data` and arguments as model attributes. See Arguments section below for a full list of export arguments.
Validate trained YOLOv8n model accuracy on the COCO8 dataset. No argument need to passed as the `model` retains it's training `data` and arguments as model attributes. See Arguments section below for a full list of export arguments.
!!! Example
@ -79,22 +79,22 @@ Validate trained YOLOv8n model accuracy on the COCO128 dataset. No argument need
When validating YOLO models, several arguments can be fine-tuned to optimize the evaluation process. These arguments control aspects such as input image size, batch processing, and performance thresholds. Below is a detailed breakdown of each argument to help you customize your validation settings effectively.
| `data` | `str` | `None` | Specifies the path to the dataset configuration file (e.g., `coco128.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. |
| `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. |
Each of these settings plays a vital role in the validation process, allowing for a customizable and efficient evaluation of YOLO models. Adjusting these parameters according to your specific needs and resources can help achieve the best balance between accuracy and performance.
- **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val detect data=coco.yaml device=0`
- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=coco128.yaml batch=1 device=0|cpu`
- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=coco8.yaml batch=1 device=0|cpu`
## Train
Train YOLOv8n on the COCO128 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 at image size 640. For a full list of available arguments see the [Configuration](../usage/cfg.md) page.
!!! Example
@ -61,19 +61,19 @@ Train YOLOv8n on the COCO128 dataset for 100 epochs at image size 640. For a ful
model = YOLO('yolov8n.yaml').load('yolov8n.pt') # build from YAML and transfer weights
@ -82,7 +82,7 @@ YOLO detection dataset format can be found in detail in the [Dataset Guide](../d
## Val
Validate trained YOLOv8n model accuracy on the COCO128 dataset. No argument need to passed as the `model` retains it's training `data` and arguments as model attributes.
Validate trained YOLOv8n model accuracy on the COCO8 dataset. No argument need to passed as the `model` retains it's training `data` and arguments as model attributes.
- **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val segment data=coco.yaml device=0`
- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val segment data=coco128-seg.yaml batch=1 device=0|cpu`
- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val segment data=coco8-seg.yaml batch=1 device=0|cpu`
## Train
@ -61,19 +61,19 @@ Train YOLOv8n-seg on the COCO128-seg dataset for 100 epochs at image size 640. F
model = YOLO('yolov8n-seg.yaml').load('yolov8n.pt') # build from YAML and transfer weights
| `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., `coco128.yaml`). This file contains dataset-specific parameters, including paths to training and validation data, class names, and number of classes. |
| `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. |
@ -182,22 +182,22 @@ Visualization arguments:
The val (validation) settings for YOLO models involve various hyperparameters and configurations used to evaluate the model's performance on a validation dataset. These settings influence the model's performance, speed, and accuracy. Common YOLO validation settings include batch size, validation frequency during training, and performance evaluation metrics. Other factors affecting the validation process include the validation dataset's size and composition, as well as the specific task the model is employed for.
| `data` | `str` | `None` | Specifies the path to the dataset configuration file (e.g., `coco128.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. |
| `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. |
Careful tuning and experimentation with these settings are crucial to ensure optimal performance on the validation dataset and detect and prevent overfitting.
@ -110,7 +110,7 @@ Train YOLOv8n on the COCO128 dataset for 100 epochs at image size 640. For a ful
## Val
Validate trained YOLOv8n model accuracy on the COCO128 dataset. No argument need to passed as the `model` retains it's training `data` and arguments as model attributes.
Validate trained YOLOv8n model accuracy on the COCO8 dataset. No argument need to passed as the `model` retains it's training `data` and arguments as model attributes.
!!! Example "Example"
@ -196,7 +196,7 @@ Default arguments can be overridden by simply passing them as arguments in the C
Train a detection model for `10 epochs` with `learning_rate` of `0.01`
See the [`Bboxes` reference section](../reference/utils/instance.md#ultralytics.utils.instance.Bboxes) for more attributes and methods available.
!!! tip
Many of the following functions (and more) can be accessed using the [`Bboxes` class](#bounding-box-horizontal-instances) but if you prefer to work with the functions directly, see the next subsections on how to import these independently.
@ -67,13 +67,13 @@ This will enable integration with the YOLOv5 training script. Every training run
If you want to change the `project_name` or `task_name`, use the `--project` and `--name` arguments of the `train.py` script, by default the project will be called `YOLOv5` and the task `Training`. PLEASE NOTE: ClearML uses `/` as a delimiter for subprojects, so be careful when using `/` in your project name!
They may also be used directly in a Python environment, and accepts the same [arguments](https://docs.ultralytics.com/usage/cfg/) as in the CLI example above:
@ -22,7 +22,7 @@ from ultralytics import YOLO
model = YOLO("model.yaml") # build a YOLOv8n model from scratch
# YOLO("model.pt") use pre-trained model if available
model.info() # display model information
model.train(data="coco128.yaml", epochs=100) # train the model
model.train(data="coco8.yaml", epochs=100) # train the model
Glenn Jocher
7 months ago
committed by
GitHub