README.md 26 KB

Introduction

English | 简体中文

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 1.8+.

https://user-images.githubusercontent.com/15977946/124654387-0fd3c500-ded1-11eb-84f6-24eeddbf4d91.mp4


Major Features
  • Support diverse tasks

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 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. 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 dataset_zoo 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.

What's New

  • We are excited to release YOLOX-Pose, a One-Stage multi-person pose estimation model based on YOLOX. Checkout our project page for more details.

yolox-pose_intro

  • Welcome to projects of MMPose, where you can access to the latest features of MMPose, and share your ideas and codes with the community at once. Contribution to MMPose will be simple and smooth:

    • Provide an easy and agile way to integrate algorithms, features and applications into MMPose
    • Allow flexible code structure and style; only need a short code review process
    • Build individual projects with full power of MMPose but not bound up with heavy frameworks
    • Checkout new projects:
    • RTMPose
    • YOLOX-Pose
    • MMPose4AIGC
    • Become a contributors and make MMPose greater. Start your journey from the example project


  • 2022-04-06: MMPose v1.0.0 is officially released, with the main updates including:

    • Release of YOLOX-Pose, a One-Stage multi-person pose estimation model based on YOLOX
    • Development of MMPose for AIGC based on RTMPose, generating high-quality skeleton images for Pose-guided AIGC projects
    • Support for OpenPose-style skeleton visualization
    • More complete and user-friendly documentation and tutorials

Please refer to the release notes for more updates brought by MMPose v1.0.0!

0.x / 1.x Migration

MMPose v1.0.0 is a major update, including many API and config file changes. Currently, a part of the algorithms have been migrated to v1.0.0, and the remaining algorithms will be completed in subsequent versions. We will show the migration progress in the following list.

Migration Progress
Algorithm Status
MTUT (CVPR 2019)
MSPN (ArXiv 2019) done
InterNet (ECCV 2020)
DEKR (CVPR 2021) done
HigherHRNet (CVPR 2020)
DeepPose (CVPR 2014) done
RLE (ICCV 2021) done
SoftWingloss (TIP 2021)
VideoPose3D (CVPR 2019) in progress
Hourglass (ECCV 2016) done
LiteHRNet (CVPR 2021) done
AdaptiveWingloss (ICCV 2019) done
SimpleBaseline2D (ECCV 2018) done
PoseWarper (NeurIPS 2019)
SimpleBaseline3D (ICCV 2017) in progress
HMR (CVPR 2018)
UDP (CVPR 2020) done
VIPNAS (CVPR 2021) done
Wingloss (CVPR 2018)
DarkPose (CVPR 2020) done
Associative Embedding (NIPS 2017) in progress
VoxelPose (ECCV 2020)
RSN (ECCV 2020) done
CID (CVPR 2022) done
CPM (CVPR 2016) done
HRNet (CVPR 2019) done
HRNetv2 (TPAMI 2019) done
SCNet (CVPR 2020) done

If your algorithm has not been migrated, you can continue to use the 0.x branch and old documentation.

Installation

Please refer to installation.md for more detailed installation and dataset preparation.

Getting Started

We provided a series of tutorials about the basic usage of MMPose for new users:

  1. For the basic usage of MMPose:

  2. For developers who wish to develop based on MMPose:

  3. For researchers and developers who are willing to contribute to MMPose:

  4. For some common issues, we provide a FAQ list:

Model Zoo

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.

Supported algorithms:

Supported techniques:

Supported datasets:

Supported backbones:

Model Request

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.

Contributing

We appreciate all contributions to improve MMPose. Please refer to 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:

@misc{mmpose2020,
    title={OpenMMLab Pose Estimation Toolbox and Benchmark},
    author={MMPose Contributors},
    howpublished = {\url{https://github.com/open-mmlab/mmpose}},
    year={2020}
}

License

This project is released under the Apache 2.0 license.

Projects in OpenMMLab

  • MMEngine: OpenMMLab foundational library for training deep learning models.
  • MMCV: OpenMMLab foundational library for computer vision.
  • MIM: MIM installs OpenMMLab packages.
  • MMClassification: OpenMMLab image classification toolbox and benchmark.
  • MMDetection: OpenMMLab detection toolbox and benchmark.
  • MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
  • MMRotate: OpenMMLab rotated object detection toolbox and benchmark.
  • MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
  • MMOCR: OpenMMLab text detection, recognition, and understanding toolbox.
  • MMPose: OpenMMLab pose estimation toolbox and benchmark.
  • MMHuman3D: OpenMMLab 3D human parametric model toolbox and benchmark.
  • MMSelfSup: OpenMMLab self-supervised learning toolbox and benchmark.
  • MMRazor: OpenMMLab model compression toolbox and benchmark.
  • MMFewShot: OpenMMLab fewshot learning toolbox and benchmark.
  • MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
  • MMTracking: OpenMMLab video perception toolbox and benchmark.
  • MMFlow: OpenMMLab optical flow toolbox and benchmark.
  • MMEditing: OpenMMLab image and video editing toolbox.
  • MMGeneration: OpenMMLab image and video generative models toolbox.
  • MMDeploy: OpenMMLab Model Deployment Framework.