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
Support better torch.compile use by using torch.tensor for step count in more timm optimizers, enhancing some shared helpers, tweaking some capturable use cases for optimizers that support it.
R
Ross Wightman committed
29993ffcca12b19a02ba44cd2849e82c0a9f841f
Parent: 0a0b4f4
Committed by Ross Wightman <rwightman@users.noreply.github.com>
on 5/27/2026, 10:21:38 PM