武永发's repositories
Background_Substraction
Contains some popular background substraction methods implemented in Python.
Algorithms
Implement some data structures and algorithms in C++.
pytorch-grad-cam
Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more
pytorch-OpCounter
Count the MACs / FLOPs of your PyTorch model.
annotated_deep_learning_paper_implementations
🧠 Implementations/tutorials of deep learning papers with side-by-side notes; including transformers (original, xl, switch, feedback), optimizers(adam, radam, adabelief), gans(dcgan, cyclegan, stylegan2), reinforcement learning (ppo, dqn), capsnet, sketch-rnn, etc.
ApproximateConvolutionalSparseCoding
An implementation of approximate convolutional sparse coding (CSC) based on paper: https://arxiv.org/abs/1711.00328
bgslibrary
A C++ Background Subtraction Library with wrappers for Python, MATLAB, Java and GUI on QT
davis2017-evaluation
Evaluation Framework for DAVIS 2017 Semi-supervised and Unsupervised used in the DAVIS Challenges
deep-sparse
We introduce a way to extend sparse dictionary learning to deep architectures.
DeepLearning
深度学习入门教程, 优秀文章, Deep Learning Tutorial
deepmind-research
This repository contains implementations and illustrative code to accompany DeepMind publications
dense-ulearn-vos
Dense Unsupervised Learning for Video Segmentation (NeurIPS*2021)
DenseCL
Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.
Enjoy-Hamburger
[ICLR 2021 top 3%] Is Attention Better Than Matrix Decomposition?
mmselfsup
OpenMMLab Self-Supervised Learning Toolbox and Benchmark
VFS
Rethinking Self-Supervised Correspondence Learning: A Video Frame-level Similarity Perspective, in ICCV 2021 (Oral)
videowalk
Repository for "Space-Time Correspondence as a Contrastive Random Walk" (NeurIPS 2020)
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch