基于FAIR的视频理解代码库,用于复制最先进的视频模型。

Yuan-Ting Hu fcf407ec82 solve buck build errors regarding to ava_evaluation 2 weeks ago
ava_evaluation fcf407ec82 solve buck build errors regarding to ava_evaluation 2 weeks ago
configs 64f8d7e1f8 opensourcing revvit (#587) 5 months ago
demo 244f73adc8 Adding materials for `VISUALIZATION_TOOLS.md` 2 years ago
projects 64f8d7e1f8 opensourcing revvit (#587) 5 months ago
slowfast fcf407ec82 solve buck build errors regarding to ava_evaluation 2 weeks ago
tools be70389787 fix eval for checkpoint load 3 weeks ago
CODE_OF_CONDUCT.md 31d2ea7078 Initial commit 3 years ago
CONTRIBUTING.md 31d2ea7078 Initial commit 3 years ago
GETTING_STARTED.md db8b991a3a Adding VISUALIZATION_TOOLS.md 2 years ago
INSTALL.md c4ecfa1cfb add activation checkpoint to ResNet (#421) 1 year ago
LICENSE 31d2ea7078 Initial commit 3 years ago
MODEL_ZOO.md 64f8d7e1f8 opensourcing revvit (#587) 5 months ago
README.md 64f8d7e1f8 opensourcing revvit (#587) 5 months ago
VISUALIZATION_TOOLS.md 3a8b0bd1f5 update links for class name files 2 years ago
linter.sh 25a0f633b7 Make linter and run_local_fb executable. 2 years ago
setup.cfg f878ebc8cd imagenet 1 year ago
setup.py c4ecfa1cfb add activation checkpoint to ResNet (#421) 1 year ago

README.md

PySlowFast

PySlowFast is an open source video understanding codebase from FAIR that provides state-of-the-art video classification models with efficient training. This repository includes implementations of the following methods:

Introduction

The goal of PySlowFast is to provide a high-performance, light-weight pytorch codebase provides state-of-the-art video backbones for video understanding research on different tasks (classification, detection, and etc). It is designed in order to support rapid implementation and evaluation of novel video research ideas. PySlowFast includes implementations of the following backbone network architectures:

  • SlowFast
  • Slow
  • C2D
  • I3D
  • Non-local Network
  • X3D
  • MViTv1 and MViTv2
  • Rev-ViT and Rev-MViT

Updates

License

PySlowFast is released under the Apache 2.0 license.

Model Zoo and Baselines

We provide a large set of baseline results and trained models available for download in the PySlowFast Model Zoo.

Installation

Please find installation instructions for PyTorch and PySlowFast in INSTALL.md. You may follow the instructions in DATASET.md to prepare the datasets.

Quick Start

Follow the example in GETTING_STARTED.md to start playing video models with PySlowFast.

Visualization Tools

We offer a range of visualization tools for the train/eval/test processes, model analysis, and for running inference with trained model. More information at Visualization Tools.

Contributors

PySlowFast is written and maintained by Haoqi Fan, Yanghao Li, Bo Xiong, Wan-Yen Lo, Christoph Feichtenhofer.

Citing PySlowFast

If you find PySlowFast useful in your research, please use the following BibTeX entry for citation.

@misc{fan2020pyslowfast,
  author =       {Haoqi Fan and Yanghao Li and Bo Xiong and Wan-Yen Lo and
                  Christoph Feichtenhofer},
  title =        {PySlowFast},
  howpublished = {\url{https://github.com/facebookresearch/slowfast}},
  year =         {2020}
}