Ankle/yolov5_ZWgra
1
0 Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity

Update YOLOv5 READMEs (#13554)

Browse Source 
* Update YOLOv5 READMEs

* Update YOLOv5 READMEs

* Auto-format by https://ultralytics.com/actions

---------

Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Glenn JocherandUltralyticsAssistant authored and GitHub committed 2025-03-28 21:58:22 +01:00
1 parent e9ab205ef6
commit 1953d47255
5 files changed
+317 -274
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+54 -54
View File
@@ -18,7 +18,7 @@
</div>
<br>
Ultralytics YOLOv5 🚀 is a cutting-edge, state-of-the-art (SOTA) computer vision model developed by [Ultralytics](https://www.ultralytics.com/). Based on the PyTorch framework, YOLOv5 is renowned for its ease of use, speed, and accuracy. It incorporates insights and best practices from extensive research and development, making it a popular choice for a wide range of vision AI tasks, including [object detection](https://docs.ultralytics.com/tasks/detect/), [image segmentation](https://docs.ultralytics.com/tasks/segment/), and [image classification](https://docs.ultralytics.com/tasks/classify/).
Ultralytics YOLOv5 🚀 is a cutting-edge, state-of-the-art (SOTA) computer vision model developed by [Ultralytics](https://www.ultralytics.com/). Based on the [PyTorch](https://pytorch.org/) framework, YOLOv5 is renowned for its ease of use, speed, and accuracy. It incorporates insights and best practices from extensive research and development, making it a popular choice for a wide range of vision AI tasks, including [object detection](https://docs.ultralytics.com/tasks/detect/), [image segmentation](https://docs.ultralytics.com/tasks/segment/), and [image classification](https://docs.ultralytics.com/tasks/classify/).
We hope the resources here help you get the most out of YOLOv5. Please browse the [YOLOv5 Docs](https://docs.ultralytics.com/yolov5/) for detailed information, raise an issue on [GitHub](https://github.com/ultralytics/yolov5/issues/new/choose) for support, and join our [Discord community](https://discord.com/invite/ultralytics) for questions and discussions!
@@ -26,17 +26,17 @@ To request an Enterprise License, please complete the form at [Ultralytics Licen
<div align="center">
<a href="https://github.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-github.png" width="2%" alt="Ultralytics GitHub"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%" alt="space">
<a href="https://www.linkedin.com/company/ultralytics/"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-linkedin.png" width="2%" alt="Ultralytics LinkedIn"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%" alt="space">
<a href="https://twitter.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-twitter.png" width="2%" alt="Ultralytics Twitter"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%" alt="space">
<a href="https://youtube.com/ultralytics?sub_confirmation=1"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="2%" alt="Ultralytics YouTube"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%" alt="space">
<a href="https://www.tiktok.com/@ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-tiktok.png" width="2%" alt="Ultralytics TikTok"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%" alt="space">
<a href="https://ultralytics.com/bilibili"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-bilibili.png" width="2%" alt="Ultralytics BiliBili"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%" alt="space">
<a href="https://discord.com/invite/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-discord.png" width="2%" alt="Ultralytics Discord"></a>
</div>
@@ -68,7 +68,7 @@ See the [YOLOv5 Docs](https://docs.ultralytics.com/yolov5/) for full documentati
<details open>
<summary>Install</summary>
Clone the repository and install dependencies from [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment. Ensure you have [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/) installed.
Clone the repository and install dependencies in a [**Python>=3.8.0**](https://www.python.org/) environment. Ensure you have [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/) installed.
```bash
# Clone the YOLOv5 repository
@@ -150,7 +150,7 @@ python detect.py --weights yolov5s.pt --source 'rtsp://example.com/media.mp4'
<details>
<summary>Training</summary>
The commands below demonstrate how to reproduce YOLOv5 [COCO dataset](https://docs.ultralytics.com/datasets/detect/coco/) results. Both [models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) are downloaded automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). Training times for YOLOv5n/s/m/l/x are approximately 1/2/4/6/8 days on a single V100 GPU. Using [Multi-GPU training](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training/) can significantly reduce training time. Use the largest `--batch-size` your hardware allows, or use `--batch-size -1` for YOLOv5 [AutoBatch](https://github.com/ultralytics/yolov5/pull/5092). The batch sizes shown below are for V100-16GB GPUs.
The commands below demonstrate how to reproduce YOLOv5 [COCO dataset](https://docs.ultralytics.com/datasets/detect/coco/) results. Both [models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) are downloaded automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). Training times for YOLOv5n/s/m/l/x are approximately 1/2/4/6/8 days on a single [NVIDIA V100 GPU](https://www.nvidia.com/en-us/data-center/v100/). Using [Multi-GPU training](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training/) can significantly reduce training time. Use the largest `--batch-size` your hardware allows, or use `--batch-size -1` for YOLOv5 [AutoBatch](https://github.com/ultralytics/yolov5/pull/5092). The batch sizes shown below are for V100-16GB GPUs.
```bash
# Train YOLOv5n on COCO for 300 epochs
@@ -180,24 +180,24 @@ python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5x.yaml --
- **[Tips for Best Training Results](https://docs.ultralytics.com/guides/model-training-tips/)** ☘️: Improve your model's performance with expert tips.
- **[Multi-GPU Training](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training/)**: Speed up training using multiple GPUs.
- **[PyTorch Hub Integration](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading/)** 🌟 **NEW**: Easily load models using PyTorch Hub.
- **[Model Export (TFLite, ONNX, CoreML, TensorRT)](https://docs.ultralytics.com/yolov5/tutorials/model_export/)** 🚀: Convert your models to various deployment formats.
- **[NVIDIA Jetson Deployment](https://docs.ultralytics.com/yolov5/tutorials/running_on_jetson_nano/)** 🌟 **NEW**: Deploy YOLOv5 on NVIDIA Jetson devices.
- **[Model Export (TFLite, ONNX, CoreML, TensorRT)](https://docs.ultralytics.com/yolov5/tutorials/model_export/)** 🚀: Convert your models to various deployment formats like [ONNX](https://onnx.ai/) or [TensorRT](https://developer.nvidia.com/tensorrt).
- **[NVIDIA Jetson Deployment](https://docs.ultralytics.com/yolov5/tutorials/running_on_jetson_nano/)** 🌟 **NEW**: Deploy YOLOv5 on [NVIDIA Jetson](https://developer.nvidia.com/embedded-computing) devices.
- **[Test-Time Augmentation (TTA)](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation/)**: Enhance prediction accuracy with TTA.
- **[Model Ensembling](https://docs.ultralytics.com/yolov5/tutorials/model_ensembling/)**: Combine multiple models for better performance.
- **[Model Pruning/Sparsity](https://docs.ultralytics.com/yolov5/tutorials/model_pruning_and_sparsity/)**: Optimize models for size and speed.
- **[Hyperparameter Evolution](https://docs.ultralytics.com/yolov5/tutorials/hyperparameter_evolution/)**: Automatically find the best training hyperparameters.
- **[Transfer Learning with Frozen Layers](https://docs.ultralytics.com/yolov5/tutorials/transfer_learning_with_frozen_layers/)**: Adapt pretrained models to new tasks efficiently.
- **[Transfer Learning with Frozen Layers](https://docs.ultralytics.com/yolov5/tutorials/transfer_learning_with_frozen_layers/)**: Adapt pretrained models to new tasks efficiently using [transfer learning](https://www.ultralytics.com/glossary/transfer-learning).
- **[Architecture Summary](https://docs.ultralytics.com/yolov5/tutorials/architecture_description/)** 🌟 **NEW**: Understand the YOLOv5 model architecture.
- **[Ultralytics HUB Training](https://www.ultralytics.com/hub)** 🚀 **RECOMMENDED**: Train and deploy YOLO models using Ultralytics HUB.
- **[ClearML Logging](https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration/)**: Integrate with ClearML for experiment tracking.
- **[ClearML Logging](https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration/)**: Integrate with [ClearML](https://clear.ml/) for experiment tracking.
- **[Neural Magic DeepSparse Integration](https://docs.ultralytics.com/yolov5/tutorials/neural_magic_pruning_quantization/)**: Accelerate inference with DeepSparse.
- **[Comet Logging](https://docs.ultralytics.com/yolov5/tutorials/comet_logging_integration/)** 🌟 **NEW**: Log experiments using Comet ML.
- **[Comet Logging](https://docs.ultralytics.com/yolov5/tutorials/comet_logging_integration/)** 🌟 **NEW**: Log experiments using [Comet ML](https://www.comet.com/).
</details>
## 🛠️ Integrations
Explore Ultralytics' key integrations with leading AI platforms. These collaborations enhance capabilities for dataset labeling, training, visualization, and model management. Discover how Ultralytics works with [Weights & Biases (W&B)](https://docs.wandb.ai/guides/integrations/ultralytics/), [Comet ML](https://bit.ly/yolov5-readme-comet), [Roboflow](https://roboflow.com/?ref=ultralytics), and [Intel OpenVINO](https://docs.ultralytics.com/integrations/openvino/) to optimize your AI workflows.
Explore Ultralytics' key integrations with leading AI platforms. These collaborations enhance capabilities for [dataset labeling](https://www.ultralytics.com/glossary/data-labeling), training, visualization, and [model management](https://www.ultralytics.com/blog/streamline-custom-vision-ai-ops). Discover how Ultralytics works with [Weights & Biases (W&B)](https://docs.wandb.ai/guides/integrations/ultralytics/), [Comet ML](https://bit.ly/yolov5-readme-comet), [Roboflow](https://roboflow.com/?ref=ultralytics), and [Intel OpenVINO](https://docs.ultralytics.com/integrations/openvino/) to optimize your AI workflows.
<br>
<a href="https://www.ultralytics.com/hub" target="_blank">
@@ -225,7 +225,7 @@ Explore Ultralytics' key integrations with leading AI platforms. These collabora
## ⭐ Ultralytics HUB
Experience seamless AI development with [Ultralytics HUB](https://www.ultralytics.com/hub) ⭐, the ultimate platform for building, training, and deploying computer vision models. Visualize datasets, train YOLOv5 and YOLOv8 🚀 models, and deploy them to real-world applications without writing any code. Transform images into actionable insights using our cutting-edge tools and user-friendly [Ultralytics App](https://www.ultralytics.com/app-install). Start your journey for **Free** today!
Experience seamless AI development with [Ultralytics HUB](https://www.ultralytics.com/hub) ⭐, the ultimate platform for building, training, and deploying [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) models. Visualize datasets, train [YOLOv5](https://docs.ultralytics.com/models/yolov5/) and [YOLOv8](https://docs.ultralytics.com/models/yolov8/) 🚀 models, and deploy them to real-world applications without writing any code. Transform images into actionable insights using our cutting-edge tools and user-friendly [Ultralytics App](https://www.ultralytics.com/app-install). Start your journey for **Free** today!
<a align="center" href="https://www.ultralytics.com/hub" target="_blank">
<img width="100%" src="https://github.com/ultralytics/assets/raw/main/im/ultralytics-hub.png" alt="Ultralytics HUB Platform Screenshot"></a>
@@ -243,8 +243,8 @@ YOLOv5 is designed for simplicity and ease of use. We prioritize real-world perf
<details>
<summary>Figure Notes</summary>
- **COCO AP val** denotes the mean Average Precision (mAP) at IoU thresholds from 0.5 to 0.95, measured on the 5,000-image [COCO val2017 dataset](http://cocodataset.org) across various inference sizes (256 to 1536 pixels).
- **GPU Speed** measures the average inference time per image on the [COCO val2017 dataset](http://cocodataset.org) using an [AWS p3.2xlarge V100 instance](https://aws.amazon.com/ec2/instance-types/p4/) with a batch size of 32.
- **COCO AP val** denotes the [mean Average Precision (mAP)](https://www.ultralytics.com/glossary/mean-average-precision-map) at [Intersection over Union (IoU)](https://www.ultralytics.com/glossary/intersection-over-union-iou) thresholds from 0.5 to 0.95, measured on the 5,000-image [COCO val2017 dataset](https://docs.ultralytics.com/datasets/detect/coco/) across various inference sizes (256 to 1536 pixels).
- **GPU Speed** measures the average inference time per image on the [COCO val2017 dataset](https://docs.ultralytics.com/datasets/detect/coco/) using an [AWS p3.2xlarge V100 instance](https://aws.amazon.com/ec2/instance-types/p3/) with a batch size of 32.
- **EfficientDet** data is sourced from the [google/automl repository](https://github.com/google/automl) at batch size 8.
- **Reproduce** these results using the command: `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`
@@ -254,33 +254,33 @@ YOLOv5 is designed for simplicity and ease of use. We prioritize real-world perf
This table shows the performance metrics for various YOLOv5 models trained on the COCO dataset.
| Model | Size<br><sup>(pixels) | mAP<sup>val<br>50-95 | mAP<sup>val<br>50 | Speed<br><sup>CPU b1<br>(ms) | Speed<br><sup>V100 b1<br>(ms) | Speed<br><sup>V100 b32<br>(ms) | Params<br><sup>(M) | FLOPs<br><sup>@640 (B) |
| ------------------------------------------------------------------------------------------------------ | --------------------- | -------------------- | ----------------- | ---------------------------- | ----------------------------- | ------------------------------ | ------------------ | ---------------------- |
| [YOLOv5n](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5n.pt) | 640 | 28.0 | 45.7 | **45** | **6.3** | **0.6** | **1.9** | **4.5** |
| [YOLOv5s](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s.pt) | 640 | 37.4 | 56.8 | 98 | 6.4 | 0.9 | 7.2 | 16.5 |
| [YOLOv5m](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5m.pt) | 640 | 45.4 | 64.1 | 224 | 8.2 | 1.7 | 21.2 | 49.0 |
| [YOLOv5l](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5l.pt) | 640 | 49.0 | 67.3 | 430 | 10.1 | 2.7 | 46.5 | 109.1 |
| [YOLOv5x](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5x.pt) | 640 | 50.7 | 68.9 | 766 | 12.1 | 4.8 | 86.7 | 205.7 |
| | | | | | | | | |
| [YOLOv5n6](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5n6.pt) | 1280 | 36.0 | 54.4 | 153 | 8.1 | 2.1 | 3.2 | 4.6 |
| [YOLOv5s6](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s6.pt) | 1280 | 44.8 | 63.7 | 385 | 8.2 | 3.6 | 12.6 | 16.8 |
| [YOLOv5m6](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5m6.pt) | 1280 | 51.3 | 69.3 | 887 | 11.1 | 6.8 | 35.7 | 50.0 |
| [YOLOv5l6](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5l6.pt) | 1280 | 53.7 | 71.3 | 1784 | 15.8 | 10.5 | 76.8 | 111.4 |
| [YOLOv5x6](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5x6.pt)<br>+ [[TTA]][tta] | 1280<br>1536 | 55.0<br>**55.8** | 72.7<br>**72.7** | 3136<br>- | 26.2<br>- | 19.4<br>- | 140.7<br>- | 209.8<br>- |
| Model | Size<br><sup>(pixels) | mAP<sup>val<br>50-95 | mAP<sup>val<br>50 | Speed<br><sup>CPU b1<br>(ms) | Speed<br><sup>V100 b1<br>(ms) | Speed<br><sup>V100 b32<br>(ms) | Params<br><sup>(M) | FLOPs<br><sup>@640 (B) |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------- | -------------------- | ----------------- | ---------------------------- | ----------------------------- | ------------------------------ | ------------------ | ---------------------- |
| [YOLOv5n](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5n.pt) | 640 | 28.0 | 45.7 | **45** | **6.3** | **0.6** | **1.9** | **4.5** |
| [YOLOv5s](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s.pt) | 640 | 37.4 | 56.8 | 98 | 6.4 | 0.9 | 7.2 | 16.5 |
| [YOLOv5m](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5m.pt) | 640 | 45.4 | 64.1 | 224 | 8.2 | 1.7 | 21.2 | 49.0 |
| [YOLOv5l](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5l.pt) | 640 | 49.0 | 67.3 | 430 | 10.1 | 2.7 | 46.5 | 109.1 |
| [YOLOv5x](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5x.pt) | 640 | 50.7 | 68.9 | 766 | 12.1 | 4.8 | 86.7 | 205.7 |
| | | | | | | | | |
| [YOLOv5n6](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5n6.pt) | 1280 | 36.0 | 54.4 | 153 | 8.1 | 2.1 | 3.2 | 4.6 |
| [YOLOv5s6](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s6.pt) | 1280 | 44.8 | 63.7 | 385 | 8.2 | 3.6 | 12.6 | 16.8 |
| [YOLOv5m6](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5m6.pt) | 1280 | 51.3 | 69.3 | 887 | 11.1 | 6.8 | 35.7 | 50.0 |
| [YOLOv5l6](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5l6.pt) | 1280 | 53.7 | 71.3 | 1784 | 15.8 | 10.5 | 76.8 | 111.4 |
| [YOLOv5x6](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5x6.pt)<br>+ [[TTA]](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation/) | 1280<br>1536 | 55.0<br>**55.8** | 72.7<br>**72.7** | 3136<br>- | 26.2<br>- | 19.4<br>- | 140.7<br>- | 209.8<br>- |
<details>
<summary>Table Notes</summary>
- All checkpoints were trained for 300 epochs using default settings. Nano (n) and Small (s) models use [hyp.scratch-low.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-low.yaml) hyperparameters, while Medium (m), Large (l), and Extra-Large (x) models use [hyp.scratch-high.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-high.yaml).
- **mAP<sup>val</sup>** values represent single-model, single-scale performance on the [COCO val2017 dataset](http://cocodataset.org).<br>Reproduce using: `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65`
- **Speed** metrics are averaged over COCO val images using an [AWS p3.2xlarge V100 instance](https://aws.amazon.com/ec2/instance-types/p4/). Non-Maximum Suppression (NMS) time (~1 ms/image) is not included.<br>Reproduce using: `python val.py --data coco.yaml --img 640 --task speed --batch 1`
- **mAP<sup>val</sup>** values represent single-model, single-scale performance on the [COCO val2017 dataset](https://docs.ultralytics.com/datasets/detect/coco/).<br>Reproduce using: `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65`
- **Speed** metrics are averaged over COCO val images using an [AWS p3.2xlarge V100 instance](https://aws.amazon.com/ec2/instance-types/p3/). Non-Maximum Suppression (NMS) time (~1 ms/image) is not included.<br>Reproduce using: `python val.py --data coco.yaml --img 640 --task speed --batch 1`
- **TTA** ([Test Time Augmentation](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation/)) includes reflection and scale augmentations for improved accuracy.<br>Reproduce using: `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`
</details>
## 🖼️ Segmentation
The YOLOv5 [release v7.0](https://github.com/ultralytics/yolov5/releases/v7.0) introduced instance segmentation models that achieve state-of-the-art performance. These models are designed for easy training, validation, and deployment. For full details, see the [Release Notes](https://github.com/ultralytics/yolov5/releases/v7.0) and explore the [YOLOv5 Segmentation Colab Notebook](https://github.com/ultralytics/yolov5/blob/master/segment/tutorial.ipynb) for quickstart examples.
The YOLOv5 [release v7.0](https://github.com/ultralytics/yolov5/releases/v7.0) introduced [instance segmentation](https://docs.ultralytics.com/tasks/segment/) models that achieve state-of-the-art performance. These models are designed for easy training, validation, and deployment. For full details, see the [Release Notes](https://github.com/ultralytics/yolov5/releases/v7.0) and explore the [YOLOv5 Segmentation Colab Notebook](https://github.com/ultralytics/yolov5/blob/master/segment/tutorial.ipynb) for quickstart examples.
<details>
<summary>Segmentation Checkpoints</summary>
@@ -290,7 +290,7 @@ The YOLOv5 [release v7.0](https://github.com/ultralytics/yolov5/releases/v7.0) i
<img width="800" src="https://user-images.githubusercontent.com/61612323/204180385-84f3aca9-a5e9-43d8-a617-dda7ca12e54a.png" alt="YOLOv5 Segmentation Performance Chart"></a>
</div>
YOLOv5 segmentation models were trained on the COCO dataset for 300 epochs at an image size of 640 pixels using A100 GPUs. Models were exported to ONNX FP32 for CPU speed tests and TensorRT FP16 for GPU speed tests. All speed tests were conducted on Google [Colab Pro](https://colab.research.google.com/signup) notebooks for reproducibility.
YOLOv5 segmentation models were trained on the [COCO dataset](https://docs.ultralytics.com/datasets/segment/coco/) for 300 epochs at an image size of 640 pixels using A100 GPUs. Models were exported to [ONNX](https://onnx.ai/) FP32 for CPU speed tests and [TensorRT](https://developer.nvidia.com/tensorrt) FP16 for GPU speed tests. All speed tests were conducted on Google [Colab Pro](https://colab.research.google.com/signup) notebooks for reproducibility.
| Model | Size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Train Time<br><sup>300 epochs<br>A100 (hours) | Speed<br><sup>ONNX CPU<br>(ms) | Speed<br><sup>TRT A100<br>(ms) | Params<br><sup>(M) | FLOPs<br><sup>@640 (B) |
| ------------------------------------------------------------------------------------------ | --------------------- | -------------------- | --------------------- | --------------------------------------------- | ------------------------------ | ------------------------------ | ------------------ | ---------------------- |
@@ -312,7 +312,7 @@ YOLOv5 segmentation models were trained on the COCO dataset for 300 epochs at an
### Train
YOLOv5 segmentation training supports automatic download of the COCO128-seg dataset via the `--data coco128-seg.yaml` argument. For the full COCO-segments dataset, download it manually using `bash data/scripts/get_coco.sh --train --val --segments` and then train with `python train.py --data coco.yaml`.
YOLOv5 segmentation training supports automatic download of the [COCO128-seg dataset](https://docs.ultralytics.com/datasets/segment/coco8-seg/) via the `--data coco128-seg.yaml` argument. For the full [COCO-segments dataset](https://docs.ultralytics.com/datasets/segment/coco/), download it manually using `bash data/scripts/get_coco.sh --train --val --segments` and then train with `python train.py --data coco.yaml`.
```bash
# Train on a single GPU
@@ -324,7 +324,7 @@ python -m torch.distributed.run --nproc_per_node 4 --master_port 1 segment/train
### Val
Validate the mask mean Average Precision (mAP) of YOLOv5s-seg on the COCO dataset:
Validate the mask [mean Average Precision (mAP)](https://www.ultralytics.com/glossary/mean-average-precision-map) of YOLOv5s-seg on the COCO dataset:
```bash
# Download COCO validation segments split (780MB, 5000 images)
@@ -364,14 +364,14 @@ python export.py --weights yolov5s-seg.pt --include onnx engine --img 640 --devi
## 🏷️ Classification
YOLOv5 [release v6.2](https://github.com/ultralytics/yolov5/releases/v6.2) introduced support for image classification model training, validation, and deployment. Check the [Release Notes](https://github.com/ultralytics/yolov5/releases/v6.2) for details and the [YOLOv5 Classification Colab Notebook](https://github.com/ultralytics/yolov5/blob/master/classify/tutorial.ipynb) for quickstart guides.
YOLOv5 [release v6.2](https://github.com/ultralytics/yolov5/releases/v6.2) introduced support for [image classification](https://docs.ultralytics.com/tasks/classify/) model training, validation, and deployment. Check the [Release Notes](https://github.com/ultralytics/yolov5/releases/v6.2) for details and the [YOLOv5 Classification Colab Notebook](https://github.com/ultralytics/yolov5/blob/master/classify/tutorial.ipynb) for quickstart guides.
<details>
<summary>Classification Checkpoints</summary>
<br>
YOLOv5-cls classification models were trained on ImageNet for 90 epochs using a 4xA100 instance. ResNet and EfficientNet models were trained alongside under identical settings for comparison. Models were exported to ONNX FP32 (CPU speed tests) and TensorRT FP16 (GPU speed tests). All speed tests were run on Google [Colab Pro](https://colab.research.google.com/signup) for reproducibility.
YOLOv5-cls classification models were trained on [ImageNet](https://docs.ultralytics.com/datasets/classify/imagenet/) for 90 epochs using a 4xA100 instance. [ResNet](https://arxiv.org/abs/1512.03385) and [EfficientNet](https://arxiv.org/abs/1905.11946) models were trained alongside under identical settings for comparison. Models were exported to [ONNX](https://onnx.ai/) FP32 (CPU speed tests) and [TensorRT](https://developer.nvidia.com/tensorrt) FP16 (GPU speed tests). All speed tests were run on Google [Colab Pro](https://colab.research.google.com/signup) for reproducibility.
| Model | Size<br><sup>(pixels) | Acc<br><sup>top1 | Acc<br><sup>top5 | Training<br><sup>90 epochs<br>4xA100 (hours) | Speed<br><sup>ONNX CPU<br>(ms) | Speed<br><sup>TensorRT V100<br>(ms) | Params<br><sup>(M) | FLOPs<br><sup>@224 (B) |
| -------------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | -------------------------------------------- | ------------------------------ | ----------------------------------- | ------------------ | ---------------------- |
@@ -395,7 +395,7 @@ YOLOv5-cls classification models were trained on ImageNet for 90 epochs using a
<summary>Table Notes (click to expand)</summary>
- All checkpoints were trained for 90 epochs using the SGD optimizer with `lr0=0.001` and `weight_decay=5e-5` at an image size of 224 pixels, using default settings.<br>Training runs are logged at [https://wandb.ai/glenn-jocher/YOLOv5-Classifier-v6-2](https://wandb.ai/glenn-jocher/YOLOv5-Classifier-v6-2).
- **Accuracy** values (top-1 and top-5) represent single-model, single-scale performance on the [ImageNet-1k dataset](https://www.image-net.org/index.php).<br>Reproduce using: `python classify/val.py --data ../datasets/imagenet --img 224`
- **Accuracy** values (top-1 and top-5) represent single-model, single-scale performance on the [ImageNet-1k dataset](https://docs.ultralytics.com/datasets/classify/imagenet/).<br>Reproduce using: `python classify/val.py --data ../datasets/imagenet --img 224`
- **Speed** metrics are averaged over 100 inference images using a Google [Colab Pro V100 High-RAM instance](https://colab.research.google.com/signup).<br>Reproduce using: `python classify/val.py --data ../datasets/imagenet --img 224 --batch 1`
- **Export** to ONNX (FP32) and TensorRT (FP16) was performed using `export.py`.<br>Reproduce using: `python export.py --weights yolov5s-cls.pt --include engine onnx --imgsz 224`
@@ -407,7 +407,7 @@ YOLOv5-cls classification models were trained on ImageNet for 90 epochs using a
### Train
YOLOv5 classification training supports automatic download for datasets like MNIST, Fashion-MNIST, CIFAR10, CIFAR100, Imagenette, Imagewoof, and ImageNet using the `--data` argument. For example, start training on MNIST with `--data mnist`.
YOLOv5 classification training supports automatic download for datasets like [MNIST](https://docs.ultralytics.com/datasets/classify/mnist/), [Fashion-MNIST](https://docs.ultralytics.com/datasets/classify/fashion-mnist/), [CIFAR10](https://docs.ultralytics.com/datasets/classify/cifar10/), [CIFAR100](https://docs.ultralytics.com/datasets/classify/cifar100/), [Imagenette](https://docs.ultralytics.com/datasets/classify/imagenette/), [Imagewoof](https://docs.ultralytics.com/datasets/classify/imagewoof/), and [ImageNet](https://docs.ultralytics.com/datasets/classify/imagenet/) using the `--data` argument. For example, start training on MNIST with `--data mnist`.
```bash
# Train on a single GPU using CIFAR-100 dataset
@@ -497,17 +497,17 @@ For bug reports and feature requests related to YOLOv5, please visit [GitHub Iss
<br>
<div align="center">
<a href="https://github.com/ultralytics" title="GitHub"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-github.png" width="3%" alt="Ultralytics GitHub"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
<a href="https://www.linkedin.com/company/ultralytics/" title="LinkedIn"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-linkedin.png" width="3%" alt="Ultralytics LinkedIn"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
<a href="https://twitter.com/ultralytics" title="Twitter"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-twitter.png" width="3%" alt="Ultralytics Twitter"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
<a href="https://youtube.com/ultralytics?sub_confirmation=1" title="YouTube"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="3%" alt="Ultralytics YouTube"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
<a href="https://www.tiktok.com/@ultralytics" title="TikTok"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-tiktok.png" width="3%" alt="Ultralytics TikTok"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
<a href="https://ultralytics.com/bilibili" title="BiliBili"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-bilibili.png" width="3%" alt="Ultralytics BiliBili"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
<a href="https://discord.com/invite/ultralytics" title="Discord"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-discord.png" width="3%" alt="Ultralytics Discord"></a>
<a href="https://github.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-github.png" width="3%" alt="Ultralytics GitHub"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%" alt="space">
<a href="https://www.linkedin.com/company/ultralytics/"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-linkedin.png" width="3%" alt="Ultralytics LinkedIn"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%" alt="space">
<a href="https://twitter.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-twitter.png" width="3%" alt="Ultralytics Twitter"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%" alt="space">
<a href="https://youtube.com/ultralytics?sub_confirmation=1"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="3%" alt="Ultralytics YouTube"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%" alt="space">
<a href="https://www.tiktok.com/@ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-tiktok.png" width="3%" alt="Ultralytics TikTok"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%" alt="space">
<a href="https://ultralytics.com/bilibili"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-bilibili.png" width="3%" alt="Ultralytics BiliBili"></a>
<img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%" alt="space">
<a href="https://discord.com/invite/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-discord.png" width="3%" alt="Ultralytics Discord"></a>
</div>