MMPose is an open-source toolbox for pose estimation based on PyTorch. It is a part of the OpenMMLab project.

The master branch works with PyTorch 1.3+.


Benchmark and Model Zoo

Benchmark with other open source projects are available on

Results and models are available in the of each method's config directory.
A summary can be found in the model zoo page.


If you use this tool in your research, please cite this project.

  author =       {Wang, Can* and Jin, Sheng* and Duan, Haodong and Li, Xuanyi and Li, Zhizhong and Liu, Wentao and Chen, Kai and Qian, Chen and Lin, Dahua},
  title =        {{mmpose}},
  howpublished = {\url{}},
  year =         {2020}

Can Wang and Sheng Jin are equal contributors.


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.