huggingface/pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
2 releases in the last 90 days, the latest 41 days ago, with 196 contributors on GitHub.
Gained 27% fewer stars in the last 90 days than in the 90 days before.
Use Cases & Benefits
- Provides a comprehensive collection of PyTorch image encoder models with training, evaluation, inference scripts, and pretrained weights.
- Offers a wide variety of state-of-the-art architectures and pretrained weights enabling flexible and efficient image model experimentation.
- Use for benchmarking and comparing different image classification backbones on datasets like ImageNet with pretrained weights.
- Use for developing custom vision models by fine-tuning or extending popular architectures such as Vision Transformers and ConvNets.
- Use for deploying optimized image encoders in production pipelines with export scripts and support for mixed precision and distributed training.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
Add a set of new very well trained ResNet & ResNet-V2 18/34 (basic block) weights. See https://huggingface.co/blog/rwightman/resnet-trick-or-treat
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
5.2K+38
Open issues
17-46
Compared with peers in Machine Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| rohitg00/ai-engineering-from-scratch | 78.3K | +1.6K | 75 | 1 day ago |
| OpenBMB/VoxCPM | 42.2K | +1.5K | 75 | 183 days ago |
| zeroclaw-labs/zeroclaw | 33.3K | +197 | 75 | 14 days ago |
| huggingface/pytorch-image-models | 37.3K | — | 63 | 41 days ago |
| GeeeekExplorer/nano-vllm | 16.3K | — | 12 | — |
| omnigent-ai/omnigent | 11.2K | — | 60 | 6 days ago |
| Category median | 33.3K | +1.5K | 75 | — |
Also by huggingface
Other repositories from this maintainer that GStars tracks
- Python168.6K stars
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
- Python34.9K stars
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
- Python28.7K stars
lerobot
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
- Python22.1K stars
datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
- Rust21.3K stars
candle
Minimalist ML framework for Rust
Discover Repositories
Search across tracked repositories by name or description