Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A deep learning library for video understanding research.
| Date | Stars |
|---|---|
| 2026-07-31 | 3563 |
| 2026-08-03 | 3563 |
| 2026-08-06 | 3564 |
Today
+1 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<img width="130%" src="./.github/media/logo_horizontal_color.png" />
</p>
<p align="center">
<a href="https://github.com/facebookresearch/pytorchvideo/blob/main/LICENSE">
<img src="https://img.shields.io/pypi/l/pytorchvideo" alt="CircleCI" />
</a>
<a href="https://pypi.org/project/pytorchvideo/">
<img src="https://img.shields.io/pypi/v/pytorchvideo?color=blue&label=release" alt="CircleCI" />
</a>
<a href="https://circleci.com/gh/facebookresearch/pytorchvideo/tree/main">
<img src="https://img.shields.io/circleci/build/github/facebookresearch/pytorchvideo/main?token=efdf3ff5b6f6acf44f4af39b683dea31d40e5901" alt="Coverage" />
</a>
<a href="https://codecov.io/gh/facebookresearch/pytorchvideo/branch/main">
<img src="https://codecov.io/gh/facebookresearch/pytorchvideo/branch/main/graph/badge.svg?token=OSZSI6JU31"/>
</a>
</a>
<a href="https://pytorchvideo.slack.com/join/shared_invite/zt-wx8xsblj-eAfx6wox9tSuFrAm8KaiPg#/shared-invite/email">
<img src="http://img.shields.io/static/v1?label=Join%20us%20on&message=%23pytorchvideo&labelColor=%234A154B&logo=slack"/>
</a>
<p align="center">
<i> A deep learning library for video understanding research.</i>
</p>
<p align="center">
<i>Check the <a href="https://pytorchvideo.org/">website</a> for more information.</i>
</p>
</p>
|<img src="https://media.giphy.com/media/clMMFBLywc4Sa3KXDb/giphy.gif" width="200"> | <img src=".github/media/ava_slowfast.gif" width="1300">
|:-------------------------------:|:--------------------------------------------------:|
| A PyTorchVideo-accelerated X3D model running on a Samsung Galaxy S10 phone. The model runs ~8x faster than real time, requiring roughly 130 ms to process one second of video.| A PyTorchVideo-based SlowFast model performing video action detection.|
## X3D model Web Demo
Integrated to [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). See demo: [](https://huggingface.co/spaces/pytorch/X3D)
## Introduction
PyTorchVideo is a deeplearning library with a focus on video understanding work. PytorchVideo provides reusable, modular and efficient components needed to accelerate the video understanding research. PyTorchVideo is developed using [PyTorch](https://pytorch.org) and supports different deeplearning video components like video models, video datasets, and video-specific transforms.
Key features include:
- **Based on PyTorch:** Built using PyTorch. Makes it easy to use all of the PyTorch-ecosystem components.
- **Reproducible Model Zoo:** Variety of state of the art pretrained video models and their associated benchmarks that are ready to use.
Complementing the model zoo, PyTorchVideo comes with extensive data loaders supporting different datasets.
- **Efficient Video Components:** Video-focused fast and efficient components that are easy to use. Supports accelerated inference on hardware.
## Updates
- Aug 2021: [Multiscale Vision Transformers](https://arxiv.org/abs/2104.11227) has been released in PyTorchVideo, details can be found from [here](https://github.com/facebookresearch/pytorchvideo/blob/main/pytorchvideo/models/vision_transformers.py#L97).
## Installation
Install PyTorchVideo inside a conda environment(Python >=3.7) with
```shell
pip install pytorchvideo
```
For detailed instructions please refer to [INSTALL.md](INSTALL.md).
## License
PyTorchVideo is released under the [Apache 2.0 License](LICENSE).
## Tutorials
Get started with PyTorchVideo by trying out one of our [tutorials](https://pytorchvideo.org/docs/tutorial_overview) or by running examples in the [tutorials folder](./tutorials).
## Model Zoo and Baselines
We provide a large set of baseline results and trained models available for download in the [PyTorchVideo Model Zoo](https://github.com/facebookresearch/pytorchvideo/blob/maExcerpt of 6,504 characters
Read on GitHub
17
16
Yanghao Li
16
14
12
Chay Ryali
5
5
Nikhila Ravi
5
Miguel Martin · NVIDIA · United States
4
Amethyst Reese · @omnilib · United States
4
Binh Tang
3
3
3
3
2
2
Nicolas Hug · United Kingdom
2
2
Richard Barnes
2
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:75ca54b150b92ff6, llm:Repository description: 'A deep learning library for video understanding research.' Language: Python. (facebookresearch/pytorchvideo)
matched fp:75ca54b150b92ff6, llm:Repository description: 'A deep learning library for video understanding research.' Language: Python. (facebookresearch/pytorchvideo)
matched fp:75ca54b150b92ff6, llm:Repository description: 'A deep learning library for video understanding research.' Language: Python. (facebookresearch/pytorchvideo)