This is the code of my master thesis.

Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.

MASC: Multi Angle and Scale Convolution

scikit-learn: machine learning in Python

LaTeX Beginner's Guide - Second Edition, published by Packt

book Make Your Own GAN

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Data compression in TensorFlow

Python Implementation of Reinforcement Learning: An Introduction

The babel system for LaTeX

It is the MATLAB implementation of the Unified Pin-SVM QPP which can minimize the Pinball loss function in true sense without bothering about the sign of its parameter t. All experimental results …

Awesome multilingual OCR toolkits based on PaddlePaddle （multilingual recognition: English, Chinese, Korean, Japanese, German, French etc. 3.5M practical ultra lightweight OCR system, support train…

PyTorch implementation of Learning Convolutional Networks for Content-Weighted Image Compression

Extremely simple implement for CRNN by Tensorflow

PDE-Net: Learning PDEs from Data

Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations

CS-Net: Channel and Spatial Attention Network for Curvilinear Structure Segmentation

A multivariable calculus text with interactive 3D graphics

This is the codes for paper "Learning Convolutional Networks for Content-weighted Image Compression"

Handwritten recognition with slice+cnn+lstm/multidimentional lstm/cnn+lstm

This is the experimental code for the following paper: "Support Vector Machine Classifier with Asymmetrical Truncated Pinball Loss" Authors: Xin Shen, Ruizhi Zhou, Lingfeng Niu, and Ran He

Smooth Support Vector Machine Toolbox

This solver is a modified version of LIBSVM 3.2.1, and it is used for experiments in the paper: "Support Vector Machine Classifier with Truncated Pinball Loss"