Skip to content

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

License

Notifications You must be signed in to change notification settings

Hunkzer/mmskeleton

This branch is 68 commits behind open-mmlab/mmskeleton:master.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Oct 8, 2019
551e3b4 · Oct 8, 2019
Aug 30, 2019
Oct 7, 2019
Sep 23, 2019
Oct 7, 2019
Oct 8, 2019
Oct 8, 2019
Oct 3, 2019
Oct 7, 2019
Oct 7, 2019
Sep 23, 2019
Aug 28, 2019
Oct 4, 2019
Oct 2, 2019
Oct 7, 2019
Oct 8, 2019

Repository files navigation

MMSkeleton

Introduction

MMSkeleton is an open source toolbox for skeleton-based human understanding. It is a part of the open-mmlab project in the charge of Multimedia Laboratory, CUHK. MMSkeleton is developed on our research project ST-GCN.

Updates

  • [2019-10-02] Support custom dataset.
  • [2019-09-23] Add video-based pose estimation demo.
  • [2019-08-29] MMSkeleton v0.5 is released.

Features

  • High extensibility

    MMSkeleton provides a flexible framework for organizing codes and projects systematically, with the ability to extend to various tasks and scale up to complex deep models.

  • Multiple tasks

    MMSkeleton addresses to multiple tasks in human understanding, including but not limited to:

Getting Started

Please see GETTING_STARTED.md and START_RECOGNITION.md for more details of MMSkeleton.

License

The project is release under the Apache 2.0 license.

Contributing

We appreciate all contributions to improve MMSkeleton. Please refer to CONTRIBUTING.md for the contributing guideline.

Citation

Please cite the following paper if you use this repository in your reseach.

@misc{mmskeleton2019,
  author =       {Sijie Yan, Yuanjun Xiong, Jingbo Wang, Dahua Lin},
  title =        {MMSkeleton},
  howpublished = {\url{https://github.com/open-mmlab/mmskeleton}},
  year =         {2019}
}

Contact

For any question, feel free to contact

Sijie Yan     : [email protected]
Jingbo Wang   : [email protected]
Yuanjun Xiong : [email protected]

About

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Cuda 63.7%
  • Python 36.2%
  • Other 0.1%