MIC-DKFZ/dynamic-network-architectures

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

Implementation of a U-net complete with efficient attention as well as the latest research findings

PyTorch implementations of recent Computer Vision tricks (ReXNet, RepVGG, Unet3p, YOLOv4, CIoU loss, AdaBelief, PolyLoss, MobileOne). Other additions: AdEMAMix

[IEEE TMI Best Paper Award] Official Implementation for UNet++

A scikit-learn compatible neural network library that wraps PyTorch

In-Place Activated BatchNorm for Memory-Optimized Training of DNNs

PyTorch Tutorial for Deep Learning Researchers

Neural networks toolbox focused on medical image analysis