GhostnetCV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
SwinIRSwinIR: Image Restoration Using Swin Transformer (official repository)
Multi-Modal-TransformerThe repository collects many various multi-modal transformer architectures, including image transformer, video transformer, image-language transformer, video-language transformer and related datasets. Additionally, it also collects many useful tutorials and tools in these related domains.
SpliceOfficial Pytorch Implementation for "Splicing ViT Features for Semantic Appearance Transfer" presenting "Splice" (CVPR 2022)
GFNet[NeurIPS 2021] Global Filter Networks for Image Classification
MPViTMPViT:Multi-Path Vision Transformer for Dense Prediction in CVPR 2022
PASSLPASSL包含 SimCLR,MoCo v1/v2,BYOL,CLIP,PixPro,BEiT,MAE等图像自监督算法以及 Vision Transformer,DEiT,Swin Transformer,CvT,T2T-ViT,MLP-Mixer,XCiT,ConvNeXt,PVTv2 等基础视觉算法
koclipKoCLIP: Korean port of OpenAI CLIP, in Flax
LaTeX-OCRpix2tex: Using a ViT to convert images of equations into LaTeX code.
InterpretDLInterpretDL: Interpretation of Deep Learning Models,基于『飞桨』的模型可解释性算法库。
pytorch-vitAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
towheeTowhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
YOLOSYou Only Look at One Sequence (NeurIPS 2021)
Evo-ViTOfficial implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
SReTOfficial PyTorch implementation of our ECCV 2022 paper "Sliced Recursive Transformer"
ImageNet21KOfficial Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper
mobilevit-pytorchA PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer".
transformer-lsOfficial PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).
libaiLiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training
VT-UNet[MICCAI2022] This is an official PyTorch implementation for A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation