Documentation: https://mmaction2.readthedocs.io/.
Introduction
MMAction2 is an open-source toolbox for action understanding based on PyTorch. It is a part of the OpenMMLab project.
The master branch works with PyTorch 1.3+.
Major Features
-
Modular design
We decompose the action understanding framework into different components and one can easily construct a customized action understanding framework by combining different modules.
-
Support for various datasets
The toolbox directly supports multiple datasets, UCF101, Kinetics-400, Something-Something V1&V2, Moments in Time, Multi-Moments in Time, THUMOS14, etc.
-
Support for multiple action understanding frameworks
MMAction2 implements popular frameworks for action understanding:
-
For action recognition, various algorithms are implemented, including TSN, TSM, R(2+1)D, I3D, SlowOnly, SlowFast.
-
For temporal action localization, we implement BSN, BMN.
-
-
Well tested and documented
We provide detailed documentation and API reference, as well as unittests.
License
This project is released under the Apache 2.0 license.
Benchmark and Model Zoo
MMAction2 supports various models and is more efficient in training. We compare with other popular codebases and the results are shown as below.
| Model | MMAction2 (s/iter) | MMAction (s/iter) | Temporal-Shift-Module (s/iter) | PySlowFast (s/iter) |
|---|---|---|---|---|
| TSN | 0.29 | 0.36 | 0.45 | x |
| I3D (setting1) | 0.45 | 0.58 | x | x |
| I3D (setting2) | 0.32 | x | x | 0.56 |
| TSM | 0.30 | x | 0.38 | x |
| Slowonly | 0.30 | x | x | 1.03 |
| Slowfast | 0.80 | x | x | 1.40 |
| R(2+1)D | 0.48 | x | x | x |
Supported methods for action recognition:
Supported methods for action localization:
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.
Installation
Please refer to install.md for installation.
Data Preparation
Please refer to data_preparation.md for a general knowledge of data preparation.
Get Started
Please see getting_started.md for the basic usage of MMAction2. There are also tutorials for finetuning models, adding new dataset, designing data pipeline, and adding new modules.
A Colab tutorial is also provided. You may preview the notebook here or directly run on Colab.
Contributing
We appreciate all contributions to improve MMAction2. Please refer to CONTRIBUTING.md for the contributing guideline.
Acknowledgement
MMAction2 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.
Contact
If you have any question, please file an issue or contact the authors:
@dreamerlin Jintao Lin
@JoannaLXY Xuanyi Li
@SuX97 Su Xu
@kennymckormick Haodong Duan