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+.
COCO 17-keypoint pose estimation
-
Support diverse tasks
We support a wide spectrum of mainstream human pose analysis tasks in current research community, including 2d multi-person human pose estimation, 2d hand pose estimation, 133 keypoint whole-body human pose estimation, and 3d human mesh recovery.
-
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. See 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 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.
Supported backbones for human pose estimation:
Supported methods for human pose estimation:
Supported datasets:
- COCO
- COCO-WholeBody
- MPII
- MPII-TRB
- AI Challenger
- OCHuman
- CrowdPose
- sub-JHMDB
- H36m
- OneHand10K
- FreiHand
- CMU Panoptic HandDB
- InterHand2.6M
Results and models are available in the README.md of each method's config directory. A summary can be found in the model zoo page. 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 Issues.
We demonstrate the superiority of our MMPose framework in terms of speed and accuracy on the standard COCO keypoint detection benchmark.
| Model | Input size | MMPose (s/iter) | HRNet (s/iter) | MMPose (mAP) | HRNet (mAP) |
|---|---|---|---|---|---|
| resnet_50 | 256x192 | 0.28 | 0.64 | 0.718 | 0.704 |
| resnet_50 | 384x288 | 0.81 | 1.24 | 0.731 | 0.722 |
| resnet_101 | 256x192 | 0.36 | 0.84 | 0.726 | 0.714 |
| resnet_101 | 384x288 | 0.79 | 1.53 | 0.748 | 0.736 |
| resnet_152 | 256x192 | 0.49 | 1.00 | 0.735 | 0.720 |
| resnet_152 | 384x288 | 0.96 | 1.65 | 0.750 | 0.743 |
| hrnet_w32 | 256x192 | 0.54 | 1.31 | 0.746 | 0.744 |
| hrnet_w32 | 384x288 | 0.76 | 2.00 | 0.760 | 0.758 |
| hrnet_w48 | 256x192 | 0.66 | 1.55 | 0.756 | 0.751 |
| hrnet_w48 | 384x288 | 1.23 | 2.20 | 0.767 | 0.763 |
More details about the benchmark are available on benchmark.md.
Please refer to install.md for installation.
Please refer to data_preparation.md for a general knowledge of data preparation.
Please see getting_started.md for the basic usage of MMPose. There are also tutorials: finetune model, add new dataset, customize data pipelines, add new modules, export a model to ONNX and customize runtime settings.
This project is released under the Apache 2.0 license.
We appreciate all contributions to improve MMPose. Please refer to CONTRIBUTING.md for the contributing guideline.
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.