https://github.com/tonysy/pyaction
A Toolkit for Video Action Recognition(Classification/Detection)
https://github.com/tonysy/pyaction
Last synced: 5 months ago
JSON representation
A Toolkit for Video Action Recognition(Classification/Detection)
- Host: GitHub
- URL: https://github.com/tonysy/pyaction
- Owner: tonysy
- License: apache-2.0
- Created: 2021-05-12T05:48:03.000Z (about 4 years ago)
- Default Branch: main
- Last Pushed: 2022-03-23T09:52:05.000Z (about 3 years ago)
- Last Synced: 2025-01-06T02:59:00.015Z (5 months ago)
- Language: Python
- Size: 9.52 MB
- Stars: 17
- Watchers: 4
- Forks: 1
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Introduction
A Toolkit for Video Action Recognition(Classification/Detection)
PyAction is an open source video action recognition codebase from PLUS Group that provides state-of-the-art video action classification/detection models.
Our codebase is built on the top of [SlowFast](https://github.com/facebookresearch/SlowFast).
# Logs
- Main Code Release, configuration will be updated soon.
- Initialize the Project, Code & Model will come soon.
# Highlights
- **Remove all registry mechanism**
- **User-friendly config without `yacs`**
- **Folder-based Experiments Management**
# Supported Models
- C2D
- I3D
- Non-local Network
- SlowFast
- SlowOnly
# License
PyAction is released under the [Apache 2.0 license](LICENSE).
# Model Zoo and Baselines
We provide a large set of baseline results and trained models available for download in the PySlowFast [Model Zoo](MODEL_ZOO.md).
# Installation
Please find installation instructions for PyTorch and PyAction in [INSTALL.md](INSTALL.md). You may follow the instructions in [DATASET.md](pyaction/datasets/DATASET.md) to prepare the datasets.
# Quick Start
Follow the example in [GETTING_STARTED.md](GETTING_STARTED.md) to start playing video models with PySlowFast.
# Related Works
```latex
@inproceedings{zhang2021itanet,
title={Learning Implicit Temporal Alignment for Few-shot Video Classification.},
author={Zhang, Songyang and Zhou, Jiale and He, Xuming},
booktitle={IJCAI},
year={2021}
}
```