DingXiaoH

M2PT

[CVPR'24] Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities

UniRepLKNet

[CVPR'24] UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition

VL-GPT

VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation

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

RepLKNet-pytorch

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

RepMLP

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

RepOptimizers

Official repo of RepOptimizers and RepOpt-VGG

RepVGG

RepVGG: Making VGG-style ConvNets Great Again

ResRep

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

DingXiaoH/RepVGG

RepVGG: Making VGG-style ConvNets Great Again

DingXiaoH/RepLKNet-pytorch

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

DingXiaoH/ACNet

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

DingXiaoH/DiverseBranchBlock

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

DingXiaoH/RepMLP

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

DingXiaoH/ResRep

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

DingXiaoH/RepOptimizers

Official repo of RepOptimizers and RepOpt-VGG

DingXiaoH/Centripetal-SGD

Codes of Centripetal SGD

DingXiaoH/GSM-SGD

Global Sparse Momentum SGD for pruning very deep neural networks

DingXiaoH/AOFP

Codes of Approximated Oracle Filter Pruning

DingXiaoH/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

DingXiaoH/open_clip

An open source implementation of CLIP.

DingXiaoH/ViT-pytorch

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

DingXiaoH/YOLOv6

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

DingXiaoH/ConvNeXt

Code release for ConvNeXt model

DingXiaoH/CSWin-Transformer

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

DingXiaoH/cutlass

CUDA Templates for Linear Algebra Subroutines

DingXiaoH/dingxiaohan

Home

DingXiaoH/efficientnetv2.pytorch

PyTorch implementation of EfficientNetV2 family

DingXiaoH/hompage-academic

DingXiaoH/MetamonPlayer

Simple program to play Metamon automatically

DingXiaoH/mmcv

OpenMMLab Computer Vision Foundation

DingXiaoH/mmsegmentation-1

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

DingXiaoH/myhomepage

DingXiaoH/pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

DingXiaoH/pytorch-optimizer

torch-optimizer -- collection of optimizers for Pytorch

DingXiaoH/RepGhost

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

DingXiaoH/res-mlp-pytorch

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

DingXiaoH/Swin-Transformer-Object-Detection

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

DingXiaoH/vision

Datasets, Transforms and Models specific to Computer Vision