This is your work, valued

Shenzhen, China

Xiaohan Ding

Elite
@DingXiaoH

ML, CV, Multimodal LLM, PhD from Tsinghua University

RepVGG. RepVGG: Making VGG-style ConvNets Great Again

3.5k

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

943

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

851

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

352

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

306

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

300

RepOptimizers. Official repo of RepOptimizers and RepOpt-VGG

270

Centripetal-SGD. Codes of Centripetal SGD

64

GSM-SGD. Global Sparse Momentum SGD for pruning very deep neural networks

44

AOFP. Codes of Approximated Oracle Filter Pruning

32

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

4

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

1

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

1

open_clip. An open source implementation of CLIP.

1