@ -124,8 +124,8 @@ All [Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cf
See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examples with these models trained on [COCO](https://docs.ultralytics.com/datasets/detect/coco/), which include 80 pre-trained classes.
See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examples with these models trained on [COCO](https://docs.ultralytics.com/datasets/detect/coco/), which include 80 pre-trained classes.
@ -141,8 +141,8 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examp
See [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) for usage examples with these models trained on [COCO-Seg](https://docs.ultralytics.com/datasets/segment/coco/), which include 80 pre-trained classes.
See [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) for usage examples with these models trained on [COCO-Seg](https://docs.ultralytics.com/datasets/segment/coco/), which include 80 pre-trained classes.
@ -158,8 +158,8 @@ See [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) for usage e
See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples with these models trained on [COCO-Pose](https://docs.ultralytics.com/datasets/pose/coco/), which include 1 pre-trained class, person.
See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples with these models trained on [COCO-Pose](https://docs.ultralytics.com/datasets/pose/coco/), which include 1 pre-trained class, person.
@ -175,8 +175,8 @@ See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples wit
See [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with these models trained on [DOTAv1](https://docs.ultralytics.com/datasets/obb/dota-v2/#dota-v10/), which include 15 pre-trained classes.
See [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with these models trained on [DOTAv1](https://docs.ultralytics.com/datasets/obb/dota-v2/#dota-v10/), which include 15 pre-trained classes.
@ -192,8 +192,8 @@ See [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with
See [Classification Docs](https://docs.ultralytics.com/tasks/classify/) for usage examples with these models trained on [ImageNet](https://docs.ultralytics.com/datasets/classify/imagenet/), which include 1000 pretrained classes.
See [Classification Docs](https://docs.ultralytics.com/tasks/classify/) for usage examples with these models trained on [ImageNet](https://docs.ultralytics.com/datasets/classify/imagenet/), which include 1000 pretrained classes.
YOLO11 is the latest iteration in the Ultralytics YOLO series of real-time object detectors, redefining what's possible with cutting-edge accuracy, speed, and efficiency. Building upon the impressive advancements of previous YOLO versions, YOLO11 introduces significant improvements in architecture and training methods, making it a versatile choice for a wide range of computer vision tasks.
YOLO11 is the latest iteration in the [Ultralytics](https://www.ultralytics.com) YOLO series of real-time object detectors, redefining what's possible with cutting-edge [accuracy](https://www.ultralytics.com/glossary/accuracy), speed, and efficiency. Building upon the impressive advancements of previous YOLO versions, YOLO11 introduces significant improvements in architecture and training methods, making it a versatile choice for a wide range of [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks.
<strong>Watch:</strong> Ultralytics YOLO11 Announcement at #YV24
<strong>Watch:</strong> Ultralytics YOLO11 Announcement at [YOLO Vision 2024](https://www.ultralytics.com/events/yolovision)
</p>
</p>
## Key Features
## Key Features
- **Enhanced Feature Extraction:** YOLO11 employs an improved backbone and neck architecture, which enhances [feature extraction](https://www.ultralytics.com/glossary/feature-extraction) capabilities for more precise object detection and complex task performance.
- **Enhanced Feature Extraction:** YOLO11 employs an improved backbone and neck architecture, which enhances [feature extraction](https://www.ultralytics.com/glossary/feature-extraction) capabilities for more precise object detection and complex task performance.
- **Optimized for Efficiency and Speed:** YOLO11 introduces refined architectural designs and optimized training pipelines, delivering faster processing speeds and maintaining an optimal balance between accuracy and performance.
- **Optimized for Efficiency and Speed:** YOLO11 introduces refined architectural designs and optimized training pipelines, delivering faster processing speeds and maintaining an optimal balance between accuracy and performance.
- **Greater Accuracy with Fewer Parameters:** With advancements in model design, YOLO11m achieves a higher mean Average Precision (mAP) on the COCO dataset while using 22% fewer parameters than YOLOv8m, making it computationally efficient without compromising accuracy.
- **Greater Accuracy with Fewer Parameters:** With advancements in model design, YOLO11m achieves a higher [mean Average Precision](https://www.ultralytics.com/glossary/mean-average-precision-map) (mAP) on the COCO dataset while using 22% fewer parameters than YOLOv8m, making it computationally efficient without compromising accuracy.
- **Adaptability Across Environments:** YOLO11 can be seamlessly deployed across various environments, including edge devices, cloud platforms, and systems supporting NVIDIA GPUs, ensuring maximum flexibility.
- **Adaptability Across Environments:** YOLO11 can be seamlessly deployed across various environments, including edge devices, cloud platforms, and systems supporting NVIDIA GPUs, ensuring maximum flexibility.
- **Broad Range of Supported Tasks:** Whether it's object detection, instance segmentation, image classification, pose estimation, or oriented object detection (OBB), YOLO11 is designed to cater to a diverse set of computer vision challenges.
- **Broad Range of Supported Tasks:** Whether it's object detection, instance segmentation, image classification, pose estimation, or oriented object detection (OBB), YOLO11 is designed to cater to a diverse set of computer vision challenges.
@ -53,7 +53,7 @@ This table provides an overview of the YOLO11 model variants, showcasing their a
See [Detection Docs](../tasks/detect.md) for usage examples with these models trained on [COCO](../datasets/detect/coco.md), which include 80 pre-trained classes.
See [Detection Docs](../tasks/detect.md) for usage examples with these models trained on [COCO](../datasets/detect/coco.md), which include 80 pre-trained classes.
@ -65,7 +65,7 @@ This table provides an overview of the YOLO11 model variants, showcasing their a
See [Segmentation Docs](../tasks/segment.md) for usage examples with these models trained on [COCO](../datasets/segment/coco.md), which include 80 pre-trained classes.
See [Segmentation Docs](../tasks/segment.md) for usage examples with these models trained on [COCO](../datasets/segment/coco.md), which include 80 pre-trained classes.
@ -77,7 +77,7 @@ This table provides an overview of the YOLO11 model variants, showcasing their a
See [Classification Docs](../tasks/classify.md) for usage examples with these models trained on [ImageNet](../datasets/classify/imagenet.md), which include 1000 pre-trained classes.
See [Classification Docs](../tasks/classify.md) for usage examples with these models trained on [ImageNet](../datasets/classify/imagenet.md), which include 1000 pre-trained classes.
@ -89,7 +89,7 @@ This table provides an overview of the YOLO11 model variants, showcasing their a
See [Pose Estimation Docs](../tasks/pose.md) for usage examples with these models trained on [COCO](../datasets/pose/coco.md), which include 1 pre-trained class, 'person'.
See [Pose Estimation Docs](../tasks/pose.md) for usage examples with these models trained on [COCO](../datasets/pose/coco.md), which include 1 pre-trained class, 'person'.
@ -101,7 +101,7 @@ This table provides an overview of the YOLO11 model variants, showcasing their a
See [Oriented Detection Docs](../tasks/obb.md) for usage examples with these models trained on [DOTAv1](../datasets/obb/dota-v2.md#dota-v10), which include 15 pre-trained classes.
See [Oriented Detection Docs](../tasks/obb.md) for usage examples with these models trained on [DOTAv1](../datasets/obb/dota-v2.md#dota-v10), which include 15 pre-trained classes.
@ -113,7 +113,7 @@ This table provides an overview of the YOLO11 model variants, showcasing their a
This section provides simple YOLO11 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.
This section provides simple YOLO11 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 that the example below is for YOLO11 [Detect](../tasks/detect.md) models for object detection. For additional supported tasks, see the [Segment](../tasks/segment.md), [Classify](../tasks/classify.md), [OBB](../tasks/obb.md), and [Pose](../tasks/pose.md) docs.
Note that the example below is for YOLO11 [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), [OBB](../tasks/obb.md), and [Pose](../tasks/pose.md) docs.
!!! example
!!! example
@ -176,9 +176,9 @@ Ultralytics YOLO11 introduces several significant advancements over its predeces
- **Enhanced Feature Extraction:** YOLO11 employs an improved backbone and neck architecture, enhancing [feature extraction](https://www.ultralytics.com/glossary/feature-extraction) capabilities for more precise object detection.
- **Enhanced Feature Extraction:** YOLO11 employs an improved backbone and neck architecture, enhancing [feature extraction](https://www.ultralytics.com/glossary/feature-extraction) capabilities for more precise object detection.
- **Optimized Efficiency and Speed:** Refined architectural designs and optimized training pipelines deliver faster processing speeds while maintaining a balance between accuracy and performance.
- **Optimized Efficiency and Speed:** Refined architectural designs and optimized training pipelines deliver faster processing speeds while maintaining a balance between accuracy and performance.
- **Greater Accuracy with Fewer Parameters:** YOLO11m achieves higher mean Average Precision (mAP) on the COCO dataset with 22% fewer parameters than YOLOv8m, making it computationally efficient without compromising accuracy.
- **Greater Accuracy with Fewer Parameters:** YOLO11m achieves higher mean Average [Precision](https://www.ultralytics.com/glossary/precision) (mAP) on the COCO dataset with 22% fewer parameters than YOLOv8m, making it computationally efficient without compromising accuracy.
- **Adaptability Across Environments:** YOLO11 can be deployed across various environments, including edge devices, cloud platforms, and systems supporting NVIDIA GPUs.
- **Adaptability Across Environments:** YOLO11 can be deployed across various environments, including edge devices, cloud platforms, and systems supporting NVIDIA GPUs.
- **Broad Range of Supported Tasks:** YOLO11 supports diverse computer vision tasks such as object detection, instance segmentation, image classification, pose estimation, and oriented object detection (OBB).
- **Broad Range of Supported Tasks:** YOLO11 supports diverse computer vision tasks such as object detection, [instance segmentation](https://www.ultralytics.com/glossary/instance-segmentation), image classification, pose estimation, and oriented object detection (OBB).
### How do I train a YOLO11 model for object detection?
### How do I train a YOLO11 model for object detection?
@ -213,7 +213,7 @@ YOLO11 models are versatile and support a wide range of computer vision tasks, i
- **Object Detection:** Identifying and locating objects within an image.
- **Object Detection:** Identifying and locating objects within an image.
- **Instance Segmentation:** Detecting objects and delineating their boundaries.
- **Instance Segmentation:** Detecting objects and delineating their boundaries.
- **Image Classification:** Categorizing images into predefined classes.
- **[Image Classification](https://www.ultralytics.com/glossary/image-classification):** Categorizing images into predefined classes.
- **Pose Estimation:** Detecting and tracking keypoints on human bodies.
- **Pose Estimation:** Detecting and tracking keypoints on human bodies.
- **Oriented Object Detection (OBB):** Detecting objects with rotation for higher precision.
- **Oriented Object Detection (OBB):** Detecting objects with rotation for higher precision.
YOLOv6 provides various pre-trained models with different scales:
YOLOv6 provides various pre-trained models with different scales:
- YOLOv6-N: 37.5% AP on COCO val2017 at 1187 FPS with NVIDIA Tesla T4 GPU.
- YOLOv6-N: 37.5% AP on COCO val2017 at 1187 FPS with NVIDIA T4 GPU.
- YOLOv6-S: 45.0% AP at 484 FPS.
- YOLOv6-S: 45.0% AP at 484 FPS.
- YOLOv6-M: 50.0% AP at 226 FPS.
- YOLOv6-M: 50.0% AP at 226 FPS.
- YOLOv6-L: 52.8% AP at 116 FPS.
- YOLOv6-L: 52.8% AP at 116 FPS.
@ -151,7 +151,7 @@ YOLOv6 offers multiple versions, each optimized for different performance requir
- YOLOv6-L: 52.8% AP at 116 FPS
- YOLOv6-L: 52.8% AP at 116 FPS
- YOLOv6-L6: State-of-the-art accuracy in real-time scenarios
- YOLOv6-L6: State-of-the-art accuracy in real-time scenarios
These models are evaluated on the COCO dataset using an NVIDIA Tesla T4 GPU. For more on performance metrics, see the [Performance Metrics](#performance-metrics) section.
These models are evaluated on the COCO dataset using an NVIDIA T4 GPU. For more on performance metrics, see the [Performance Metrics](#performance-metrics) section.
### How does the Anchor-Aided Training (AAT) strategy benefit YOLOv6?
### How does the Anchor-Aided Training (AAT) strategy benefit YOLOv6?
@ -18,7 +18,7 @@ Let's begin by creating a virtual machine that's tuned for deep learning:
1. Head over to the [GCP marketplace](https://console.cloud.google.com/marketplace/details/click-to-deploy-images/deeplearning) and select the **Deep Learning VM**.
1. Head over to the [GCP marketplace](https://console.cloud.google.com/marketplace/details/click-to-deploy-images/deeplearning) and select the **Deep Learning VM**.
2. Opt for a **n1-standard-8** instance; it offers a balance of 8 vCPUs and 30 GB of memory, ideally suited for our needs.
2. Opt for a **n1-standard-8** instance; it offers a balance of 8 vCPUs and 30 GB of memory, ideally suited for our needs.
3. Next, select a GPU. This depends on your workload; even a basic one like the Tesla T4 will markedly accelerate your model training.
3. Next, select a GPU. This depends on your workload; even a basic one like the T4 will markedly accelerate your model training.
4. Tick the box for 'Install NVIDIA GPU driver automatically on first startup?' for hassle-free setup.
4. Tick the box for 'Install NVIDIA GPU driver automatically on first startup?' for hassle-free setup.
5. Allocate a 300 GB SSD Persistent Disk to ensure you don't bottleneck on I/O operations.
5. Allocate a 300 GB SSD Persistent Disk to ensure you don't bottleneck on I/O operations.
6. Hit 'Deploy' and let GCP do its magic in provisioning your custom Deep Learning VM.
6. Hit 'Deploy' and let GCP do its magic in provisioning your custom Deep Learning VM.
Glenn Jocher
5 months ago
committed by
GitHub