pytorch-image-models
https://github.com/huggingface/pytorch-image-models
Python
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to pytorch-image-models
Help out
- Issues
- ZeroDivisionError in train.py throughput calculation on fast updates / Windows
- Fix ZeroDivisionError in train.py and legacy_train.py throughput calculation
- Bump trufflesecurity/trufflehog from 3.99.4 to 3.99.7 in the actions group across 1 directory
- Add EMO, RapidNet, and TinyNeXt models
- [Draft] MobileViTv3 v1 (XXS/XS/S) and v2 (0.5/0.75/1.0)
- Task and configuration refactoring w/ support for SSL tasks (working on LeJEPA, NEPA initially)
- [FEATURE] [RFC] Support for interchangable attention backends
- Vibe coding some different ideas on vit param sharing/recursion/latents
- [FEATURE] Unified `embed` Interfaces for Vision Transformer Models for MIM Pretrain Research
- [FEATURE] 3D model support for volumetric / medical imaging in timm
- Docs
- Python not yet supported