Ql C's repositories
easy-rl
强化学习中文教程(蘑菇书),在线阅读地址:https://datawhalechina.github.io/easy-rl/
Reinforcement-learning-with-tensorflow
Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
Enhanced-3DTV
The code of enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing
Deep-Compressed-Sensing
Deep Learning/Deep neural network-based Image/Video (Quantized) Compressed/Compressive Sensing (Coding)
Image-Denoising-Benchmark
Collection of image denosing tools in an unification Matlab code
Improved-Efficiency-on-Adaptive-Arithmetic-Coding-for-Data-Compression-Using-Range--Adjusting-Scheme
Context-based adaptive arithmetic coding (CAAC) has high coding efficiency and is adopted by the majority of advanced compression algorithms. In this paper, five new techniques are proposed to further improve the performance of CAAC. They make the frequency table (the table used to estimate the probability distribution of data according to the past input) of CAAC converge to the true probability distribution rapidly and hence improve the coding efficiency. Instead of varying only one entry of the frequency table, the proposed range-adjusting scheme adjusts the entries near to the current input value together. With the proposed mutual-learning scheme, the frequency tables of the contexts highly correlated to the current context are also adjusted. The proposed increasingly adjusting step scheme applies a greater adjusting step for recent data. The proposed adaptive initialization scheme uses a proper model to initialize the frequency table. Moreover, a local frequency table is generated according to local information. We perform several simulations on edge-directed predictionbased lossless image compression, coefficient encoding in JPEG, bit plane coding in JPEG 2000, and motion vector residue coding in video compression. All simulations confirm that the proposed techniques can reduce the bit rate and are beneficial for data compression.
TIP-CSNet
The training codes, the training data, and some pre-trained models for my TIP paper "Image Compressed Sensing using Convolutional Neural Network".
Perceptual-CS
Code for papers "Perceptual Compressive Sensing" at PRCV 2018 and "Fully Convolutional Measurement Network for Compressive Sensing Image Reconstruction" at Neurocomputing 2019.
pytorch-handbook
pytorch handbook是一本开源的书籍,目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门,其中包含的Pytorch教程全部通过测试保证可以成功运行
kPCA
Kernel PCA and Pre-Image Reconstruction
CSNet
Reimplementation of CSNet (Deep network for compressed image sensing, ICME17)
MS-DCSNet-Release
Multi-Scale Deep Compressive Sensing Network, IEEE Inter. Conf. Visual Comm. Image Process. (VCIP), 2018
cvpr2019
cvpr2019 papers,极市团队整理
Non-local-Neural-Networks-Pytorch
This is a pytorch version for Non-local Neural Networks(onging)
MWCNN
Multi-level Wavelet-CNN for Image Restoration
lihang_book_algorithm
致力于将李航博士《统计学习方法》一书中所有算法实现一遍
Non-Local-NN-Pytorch
Pyorch implementation of Non-Local Neural Networks (https://arxiv.org/pdf/1711.07971.pdf)
code-of-learn-deep-learning-with-pytorch
This is code of book "Learn Deep Learning with PyTorch"
Shift-Net
Shift-Net: Image Inpainting via Deep Feature Rearrangement (ECCV, 2018)
Non-local_pytorch
Implementation of Non-local Block.
CompressiveSensingDictionaryLearning
Compressive Sensing using Sparse Dictionary Learning
compression
Data compression in TensorFlow
NLRN_v0
Code of Non-Local Recurrent Network for Image Restoration (NeurIPS 2018)
RNAN
PyTorch code for our ICLR 2019 paper "Residual Non-local Attention Networks for Image Restoration"
DnCNN
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)
PWLS-CSCGR
Convolutional Sparse Coding for Compressed Sensing CT Reconstruction
CSET
CSET (Compressed Sensing Electron Tomography)-toolbox is a three-dimensional TV-based compressed sensing reconstruction toolbox that consists of algebraic iterative algorithms (SART and SIRT) with total variation (TV) based CS. In addition, it integrates a Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) that is an acceleration method to speed up the algorithm convergence.
Learning-based-Image-Video-Compression
Recent papers and codes related to deep learning-based image/video compression. Mainly focus on top venues of machine learning / neural network community.
Self-Attention
simple implements Non-Local Neural Networks for image classification(Fashion-Mnist)