#212212th of 242 in ML frameworks and libraries

pytorchvideo

PyTorch library of video models, datasets and transforms for research

Stars
3.6k
License
Apache-2.0
Last commit
Oct 2026
Last release
Sep 2021
Language
Python
Stars, last 29 weeks+35
25 Apr 2026: 3,534 stars2 May 2026: 3,537 stars9 May 2026: 3,539 stars16 May 2026: 3,545 stars23 May 2026: 3,545 stars30 May 2026: 3,546 stars6 Jun 2026: 3,546 stars13 Jun 2026: 3,548 stars20 Jun 2026: 3,549 stars27 Jun 2026: 3,551 stars4 Jul 2026: 3,554 stars11 Jul 2026: 3,555 stars18 Jul 2026: 3,555 stars25 Jul 2026: 3,555 stars1 Aug 2026: 3,556 stars8 Aug 2026: 3,556 stars15 Aug 2026: 3,557 stars22 Aug 2026: 3,557 stars29 Aug 2026: 3,559 stars5 Sept 2026: 3,559 stars12 Sept 2026: 3,559 stars19 Sept 2026: 3,561 stars26 Sept 2026: 3,561 stars3 Oct 2026: 3,564 stars10 Oct 2026: 3,565 stars17 Oct 2026: 3,566 stars24 Oct 2026: 3,568 stars31 Oct 2026: 3,569 stars7 Nov 2026: 3,569 stars14 Nov 2026: 3,569 stars

3,534 on 25 Apr 20263,569 on 14 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

PyTorchVideo is a PyTorch library for video understanding research. It provides a model zoo of pretrained video models (including X3D, SlowFast and Multiscale Vision Transformers), data loaders for video datasets, and video-specific transforms. It installs with pip and includes tutorials and a Hugging Face Spaces demo of X3D.

Who it is for: Researchers and engineers training or running video models in PyTorch

Strengths

  • Model zoo with pretrained video models and published benchmarks
  • Modular components built on PyTorch, so they fit existing PyTorch code
  • Data loaders for several video datasets plus video-specific transforms
  • Installs with pip install pytorchvideo; tutorials included

Weaknesses

  • Last PyPI release was 2021-09-10, despite later commits
  • Research-oriented; no serving layer or application UI
  • README lists only a 2021 update, so newer model coverage is unclear
  • No Docker image provided

What it needs

  • Needs PyTorch, Python >=3.7
  • Models: X3D, SlowFast, Multiscale Vision Transformers

What changed

From the release notes. No flag means the note does not say so, not that the upgrade is safe.

Also in ML frameworks and libraries

See all 242
Also in ML frameworks and libraries
RankProjectScore
1transformersModel-definition library for pretrained text, vision, audio and multimodal models169.3k starsApache-2.094 out of 100
2ultralyticsPython library and CLI for training and running YOLO vision models63.5k starsAGPL-3.094 out of 100
3pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts37.3k starsApache-2.094 out of 100
#4pytorchPython tensor library with GPU support and tape-based autograd105.8k starscustom license93 out of 100
#5supervisionPython toolkit for loading, annotating and counting computer vision detections Live demo ↗ (opens in a new tab)51.7k starsMIT92 out of 100