yehuitang

pythia

The hub for EleutherAI's work on interpretability and learning dynamics

Disout

Code for AAAI 2020 paper, Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks (Disout).

Efficient-AI-Backbones

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

Efficient-Computing

Efficient computing methods developed by Huawei Noah's Ark Lab

pytorch-image-models

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

Disout

Code for AAAI 2020 paper, Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks (Disout).

Pruning

Code for "Co-Evolutionary Compression for Unpaired Image Translation" (ICCV 2019), "SCOP: Scientific Control for Reliable Neural Network Pruning" (NeurIPS 2020) and “Manifold Regularized Dynamic Network Pruning” (CVPR 2021).

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

yehuitang.github.io

yehuitang/Pruning

Code for "Co-Evolutionary Compression for Unpaired Image Translation" (ICCV 2019), "SCOP: Scientific Control for Reliable Neural Network Pruning" (NeurIPS 2020) and “Manifold Regularized Dynamic Network Pruning” (CVPR 2021).

yehuitang/Disout

Code for AAAI 2020 paper, Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks (Disout).

yehuitang/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

yehuitang/yehuitang.github.io