LiangLun

LiangLun

Geek Repo

Company:Southeast University

Location:Nanjing. China

Github PK Tool:Github PK Tool


Organizations
SEU-CodingTogether

LiangLun's repositories

Language:PythonStargazers:1Issues:0Issues:0

DeepRL

本仓库致力于“四个共享”, 【1】提供最全面的DRL书籍、资料、综述等学习资源。【2】阐述深度强化学习的基本原理、前沿算法、场景应用、竞赛分析、论文分享等专业知识。【3】分享最前沿的业界动态和行业发展趋势。【4】汇聚所有深度强化学习领域的研究者与爱好者。

Stargazers:1Issues:0Issues:0

Effective-Python

Learning Python

Language:Jupyter NotebookStargazers:1Issues:1Issues:0

Reinforcement-Learning

learning RL step by step

Language:PythonStargazers:1Issues:0Issues:0

Reinforcement-learning-with-tensorflow

Simple Reinforcement learning tutorials

Language:PythonLicense:MITStargazers:1Issues:0Issues:0

Algorithms

常见数据结构和算法的多语言实现。

Language:JavaLicense:BSD-2-ClauseStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0

my_orc_keras_verification_code_identification

本项目实现了ocr主流算法gru/lstm+ctc+cnn架构,进行不定长度验证码识别,达到不分割字符而识别验证码内容的效果。验证码内容包含了大小字母以及数字,并增加点、线、颜色、位置、字体等干扰项。本项目对gru +ctc+cnn、lstm+ctc+cnn、cnn三种架构进行了对比,实践说明同等训练下gru/lstm+ctc+cnn架构准确率和速度均明显优于cnn架构,gru +ctc+cnn优于lstm+ctc+cnn,在实验2500个样本数据200轮训练时,gru +ctc+cnn架构在500样本测试准确率达90.2%。本项目技术能够训练长序列的ocr识别,更换数据集和相关调整,即可用于比如身份证号码、车牌、手机号、邮编等识别任务,也可用于汉字识别。

Language:PythonStargazers:0Issues:0Issues:0

reinforce

reinforcement learning

Language:Jupyter NotebookStargazers:0Issues:0Issues:0
Language:C++Stargazers:0Issues:0Issues:0

svm

Support Vector Machines in Python

Language:PythonStargazers:0Issues:0Issues:0

tensorflow

An Open Source Machine Learning Framework for Everyone

Language:C++License:Apache-2.0Stargazers:0Issues:0Issues:0