#180180th of 242 in ML frameworks and libraries

scenic

JAX/Flax library for training attention-based vision models at scale

Stars
3.8k
License
Apache-2.0
Last commit
Oct 2026
Language
Python
Stars, last 29 weeks+78
25 Apr 2026: 3,770 stars2 May 2026: 3,776 stars9 May 2026: 3,778 stars16 May 2026: 3,782 stars23 May 2026: 3,785 stars30 May 2026: 3,786 stars6 Jun 2026: 3,789 stars13 Jun 2026: 3,792 stars20 Jun 2026: 3,793 stars27 Jun 2026: 3,797 stars4 Jul 2026: 3,802 stars11 Jul 2026: 3,808 stars18 Jul 2026: 3,808 stars25 Jul 2026: 3,809 stars1 Aug 2026: 3,810 stars8 Aug 2026: 3,812 stars15 Aug 2026: 3,815 stars22 Aug 2026: 3,815 stars29 Aug 2026: 3,815 stars5 Sept 2026: 3,817 stars12 Sept 2026: 3,819 stars19 Sept 2026: 3,826 stars26 Sept 2026: 3,833 stars3 Oct 2026: 3,834 stars10 Oct 2026: 3,839 stars17 Oct 2026: 3,841 stars24 Oct 2026: 3,844 stars31 Oct 2026: 3,846 stars7 Nov 2026: 3,846 stars14 Nov 2026: 3,848 stars

3,770 on 25 Apr 20263,848 on 14 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Scenic is a JAX and Flax codebase for research on attention-based computer vision models. It provides shared libraries for multi-host, multi-device training (input pipelines, losses, metrics, bipartite matchers, trainers) plus project directories with full training and evaluation loops. It includes reimplemented baselines such as ViT, DETR, CLIP, U-Net and SAM, and code for research projects like ViViT.

Who it is for: Researchers building large-scale vision models in JAX

Strengths

  • Includes reproduced baselines: ViT, DETR, Deformable DETR, CLIP, MAE, ResNet, U-Net, SAM
  • Input pipelines handle multi-host and multi-device splitting, caching and prefetching
  • Projects can be config-only or fork the trainers, losses and models entirely
  • Hosts code for published research such as ViViT, TokenLearner and OWL-ViT

Weaknesses

  • JAX/Flax only, no PyTorch or TensorFlow support
  • Philosophy favors forking and copy-pasting, so code is duplicated across projects
  • Many projects need extra packages from their own requirements files
  • No tagged releases; install is from a git clone

What it needs

  • Needs JAX, Flax, Python 3.9+
  • Models: ViT, DETR, CLIP, ResNet, U-Net

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