We support a wide spectrum of mainstream pose analysis tasks in current research community, including 2d multi-person human pose estimation, 2d hand pose estimation, 2d face landmark detection, 133 keypoint whole-body human pose estimation, 3d human mesh recovery, fashion landmark detection and animal pose estimation.
See [demo.md](demo/README.md) for more information.
-**Higher efficiency and higher accuracy**
使用数据集：coco
MMPose implements multiple state-of-the-art (SOTA) deep learning models, including both top-down & bottom-up approaches. We achieve faster training speed and higher accuracy than other popular codebases, such as [HRNet](https://github.com/leoxiaobin/deep-high-resolution-net.pytorch).
在mmpose目录下创建data文件夹并创建coco数据集软链接
See [benchmark.md](docs/en/benchmark.md) for more information.
```
-**Support for various datasets**
mkdir data
The toolbox directly supports multiple popular and representative datasets, COCO, AIC, MPII, MPII-TRB, OCHuman etc.
cd data
See [data_preparation.md](docs/en/data_preparation.md) for more information.
ln -s /path/COCO2017/ coco
-**Well designed, tested and documented**
```
We decompose MMPose into different components and one can easily construct a customized
pose estimation framework by combining different modules.
We provide detailed documentation and API reference, as well as unittests.
## 准确率数据
</details>
| 卡数 | 精度 |
| :--: | :------------------: |
## What's New
| 4 | AP=0.6504；AR=0.7086 |
- 2022-10-14: MMPose [v0.29.0](https://github.com/open-mmlab/mmpose/releases/tag/v0.29.0) is released. Major updates include:
## 源码仓库及问题反馈
- Support [DEKR](https://arxiv.org/abs/2104.02300)(CVPR'2021). See the [model page](/configs/body/2d_kpt_sview_rgb_img/dekr/coco/hrnet_coco.md)
- Support [CID](https://openaccess.thecvf.com/content/CVPR2022/html/Wang_Contextual_Instance_Decoupling_for_Robust_Multi-Person_Pose_Estimation_CVPR_2022_paper.html)(CVPR'2022). See the [model page](/configs/body/2d_kpt_sview_rgb_img/cid/coco/hrnet_coco.md)
- 2022-09-01: **MMPose v1.0.0** beta has been released \[[Code](https://github.com/open-mmlab/mmpose/tree/1.x) | [Docs](https://mmpose.readthedocs.io/en/1.x/)\]. Welcome to try it and your feedback will be greatly appreciated!
- 2022-02-28: MMPose model deployment is supported by [MMDeploy](https://github.com/open-mmlab/mmdeploy) v0.3.0
## 参考
MMPose Webcam API is a simple yet powerful tool to develop interactive webcam applications with MMPose features.
- 2021-12-29: OpenMMLab Open Platform is online! Try our [pose estimation demo](https://platform.openmmlab.com/web-demo/demo/poseestimation)
We will keep up with the latest progress of the community, and support more popular algorithms and frameworks. If you have any feature requests, please feel free to leave a comment in [MMPose Roadmap](https://github.com/open-mmlab/mmpose/issues/9).
### Benchmark
#### Accuracy and Training Speed
MMPose achieves superior of training speed and accuracy on the standard keypoint detection benchmarks like COCO. See more details at [benchmark.md](docs/en/benchmark.md).
#### Inference Speed
We summarize the model complexity and inference speed of major models in MMPose, including FLOPs, parameter counts and inference speeds on both CPU and GPU devices with different batch sizes. Please refer to [inference_speed_summary.md](docs/en/inference_speed_summary.md) for more details.
## Data Preparation
Please refer to [data_preparation.md](docs/en/data_preparation.md) for a general knowledge of data preparation.
## FAQ
Please refer to [FAQ](docs/en/faq.md) for frequently asked questions.
## Contributing
We appreciate all contributions to improve MMPose. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.
## Acknowledgement
MMPose is an open source project that is contributed by researchers and engineers from various colleges and companies.
We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks.
We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new models.
## Citation
If you find this project useful in your research, please consider cite:
```bibtex
@misc{mmpose2020,
title={OpenMMLab Pose Estimation Toolbox and Benchmark},
We support a wide spectrum of mainstream pose analysis tasks in current research community, including 2d multi-person human pose estimation, 2d hand pose estimation, 2d face landmark detection, 133 keypoint whole-body human pose estimation, 3d human mesh recovery, fashion landmark detection and animal pose estimation.
See [demo.md](demo/README.md) for more information.
-**Higher efficiency and higher accuracy**
MMPose implements multiple state-of-the-art (SOTA) deep learning models, including both top-down & bottom-up approaches. We achieve faster training speed and higher accuracy than other popular codebases, such as [HRNet](https://github.com/leoxiaobin/deep-high-resolution-net.pytorch).
See [benchmark.md](docs/en/benchmark.md) for more information.
-**Support for various datasets**
The toolbox directly supports multiple popular and representative datasets, COCO, AIC, MPII, MPII-TRB, OCHuman etc.
See [data_preparation.md](docs/en/data_preparation.md) for more information.
-**Well designed, tested and documented**
We decompose MMPose into different components and one can easily construct a customized
pose estimation framework by combining different modules.
We provide detailed documentation and API reference, as well as unittests.
</details>
## What's New
- 2022-10-14: MMPose [v0.29.0](https://github.com/open-mmlab/mmpose/releases/tag/v0.29.0) is released. Major updates include:
- Support [DEKR](https://arxiv.org/abs/2104.02300)(CVPR'2021). See the [model page](/configs/body/2d_kpt_sview_rgb_img/dekr/coco/hrnet_coco.md)
- Support [CID](https://openaccess.thecvf.com/content/CVPR2022/html/Wang_Contextual_Instance_Decoupling_for_Robust_Multi-Person_Pose_Estimation_CVPR_2022_paper.html)(CVPR'2022). See the [model page](/configs/body/2d_kpt_sview_rgb_img/cid/coco/hrnet_coco.md)
- 2022-09-01: **MMPose v1.0.0** beta has been released \[[Code](https://github.com/open-mmlab/mmpose/tree/1.x) | [Docs](https://mmpose.readthedocs.io/en/1.x/)\]. Welcome to try it and your feedback will be greatly appreciated!
- 2022-02-28: MMPose model deployment is supported by [MMDeploy](https://github.com/open-mmlab/mmdeploy) v0.3.0
MMPose Webcam API is a simple yet powerful tool to develop interactive webcam applications with MMPose features.
- 2021-12-29: OpenMMLab Open Platform is online! Try our [pose estimation demo](https://platform.openmmlab.com/web-demo/demo/poseestimation)
## Installation
MMPose depends on [PyTorch](https://pytorch.org/) and [MMCV](https://github.com/open-mmlab/mmcv).
Below are quick steps for installation.
Please refer to [install.md](docs/en/install.md) for detailed installation guide.
We will keep up with the latest progress of the community, and support more popular algorithms and frameworks. If you have any feature requests, please feel free to leave a comment in [MMPose Roadmap](https://github.com/open-mmlab/mmpose/issues/9).
### Benchmark
#### Accuracy and Training Speed
MMPose achieves superior of training speed and accuracy on the standard keypoint detection benchmarks like COCO. See more details at [benchmark.md](docs/en/benchmark.md).
#### Inference Speed
We summarize the model complexity and inference speed of major models in MMPose, including FLOPs, parameter counts and inference speeds on both CPU and GPU devices with different batch sizes. Please refer to [inference_speed_summary.md](docs/en/inference_speed_summary.md) for more details.
## Data Preparation
Please refer to [data_preparation.md](docs/en/data_preparation.md) for a general knowledge of data preparation.
## FAQ
Please refer to [FAQ](docs/en/faq.md) for frequently asked questions.
## Contributing
We appreciate all contributions to improve MMPose. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.
## Acknowledgement
MMPose is an open source project that is contributed by researchers and engineers from various colleges and companies.
We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks.
We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new models.
## Citation
If you find this project useful in your research, please consider cite:
```bibtex
@misc{mmpose2020,
title={OpenMMLab Pose Estimation Toolbox and Benchmark},
