BGU-CS-VIL/WTConv

Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.

Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

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

Collection of common code that's shared among different research projects in FAIR computer vision team.

[JMLR] Differentiable fast wavelet transforms in PyTorch with GPU support.

ResNeSt: Split-Attention Networks

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 Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images