Dapeng Du's starred repositories
DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
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
Self-Attention-GAN
Pytorch implementation of Self-Attention Generative Adversarial Networks (SAGAN)
contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
PyContrast
PyTorch implementation of Contrastive Learning methods
consistent_depth
We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.
Non-local_pytorch
Implementation of Non-local Block.
iterm2-with-oh-my-zsh
iTerm2 + Oh My Zsh 打造舒适终端体验
attention-cnn
Source code for "On the Relationship between Self-Attention and Convolutional Layers"
Domain-generalization
All about domain generalization
Grad-CAM.pytorch
pytorch实现Grad-CAM和Grad-CAM++,可以可视化任意分类网络的Class Activation Map (CAM)图,包括自定义的网络;同时也实现了目标检测faster r-cnn和retinanet两个网络的CAM图;欢迎试用、关注并反馈问题...
Source-Code-Notebook
关于一些经典论文源码的逐行中文笔记
contiguous_pytorch_params
Accelerate training by storing parameters in one contiguous chunk of memory.
StyleTransfer
Implementation of "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" in PyTorch
pytorch-histogram-loss
PyTorch implementation for Histogram Loss
VIB-pytorch
Pytorch implementation of Deep Variational Information Bottleneck
Multi-View-Information-Bottleneck
Implementation of Multi-View Information Bottleneck
Episodic-DG
This is the repo for the paper "Episodic Training for Domain Generalization" https://arxiv.org/abs/1902.00113