DingXiaoH

RepVGG

RepVGG: Making VGG-style ConvNets Great Again

RepLKNet-pytorch

Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)

ACNet

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

DiverseBranchBlock

Diverse Branch Block: Building a Convolution as an Inception-like Unit

RepMLP

RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality (CVPR 2022)

ResRep

ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting (ICCV 2021)

RepOptimizers

Official repo of RepOptimizers and RepOpt-VGG

Centripetal-SGD

Codes of Centripetal SGD

GSM-SGD

Global Sparse Momentum SGD for pruning very deep neural networks

AOFP

Codes of Approximated Oracle Filter Pruning

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

open_clip

An open source implementation of CLIP.

ViT-pytorch

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

YOLOv6

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

ConvNeXt

Code release for ConvNeXt model

CSWin-Transformer

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped, CVPR 2022

cutlass

CUDA Templates for Linear Algebra Subroutines

dingxiaohan

Home

efficientnetv2.pytorch

PyTorch implementation of EfficientNetV2 family

hompage-academic

MetamonPlayer

Simple program to play Metamon automatically

mmcv

OpenMMLab Computer Vision Foundation

mmsegmentation-1

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

myhomepage

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-optimizer

torch-optimizer -- collection of optimizers for Pytorch

RepGhost

RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization

res-mlp-pytorch

Implementation of ResMLP, an all MLP solution to image classification, in Pytorch

Swin-Transformer-Object-Detection

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

vision

Datasets, Transforms and Models specific to Computer Vision