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
COMMITS
20
in the last year
CONTRIBUTORS
2
active
STARS
0
total
FORKS
0
total
TOP CONTRIBUTORS
R
Ross Wightman J
Jan Bernloehr RECENT COMMITS
R
R
Update README.md
Ross Wightman
R
Use timm/ hub locations
Ross Wightman
R
Add tipsv2 vision encoders
Ross Wightman
R
Update version to 1.0.28.dev0
Ross Wightman
J
validate.py: add --seed for reproducible validation
Jan Bernloehr
R
Update README.md for release
Ross Wightman
R
Version 1.0.27
Ross Wightman
R
Fix empty command line kwarg passing
Ross Wightman
R
Avoid test triggering weights_only error for old PyTorch
Ross Wightman
R
R
Missed _helpers for task based resume/checkpoint
Ross Wightman
R
R
R
Update README.md
Ross Wightman