Coder Social home page Coder Social logo

pytorchocr's Introduction

PytorchOCR

简介

PytorchOCR旨在打造一套训练,推理,部署一体的OCR引擎库

添加微信z572459439或者nsnovio,然后进群讨论。备注ocr进群。

更新日志

  • 2021.02.27 添加移动端识别模型文件、移动端DBNet模型文件
  • 2021.02.25 添加服务器端识别模型文件
  • 2021.02.09 添加DBNet模型,修改DBNet网络结构的fpn,inference时候的缩放及后处理
  • 2020.07.01 添加 添加新算法文档
  • 2020.06.29 添加检测的mb3和resnet50_vd预训练模型
  • 2020.06.25 检测模块的训练和预测ok
  • 2020.06.18 更新README
  • 2020.06.17 识别模块的训练和预测ok

todo list

  • crnn训练与python版预测
  • DB训练与python版预测
  • imagenet预训练模型
  • 服务器端识别模型文件
  • DB通用模型
  • 手机端部署
  • With Triton

环境配置

需要的环境如下

  • pytorch 1.4+
  • torchvision 0.5+
  • gcc 4.9+ (pse,pan会用到)

快速安装环境

pip3 install -r requirements.txt

文档教程

文本检测算法

PytorchOCR开源的文本检测算法列表:

模型简介 骨干网络 推荐场景 大小 下载链接
预训练模型 ResNet50 服务器端 97.3M 3cmz
原始超轻量模型,支持中英文、多语种文本检测 MoblieNet 移动端 2.3M c9ko
通用模型,支持中英文、多语种文本检测,比超轻量模型更大,但效果更好 ResNet18 服务器端 47.2M r26k

文本识别算法

PytorchOCR开源的文本识别算法列表:

模型简介 骨干网络 推荐场景 大小 下载链接
原始超轻量模型,支持中英文、数字识别 MoblieNet 移动端 4.2M 7x9q
通用模型,支持中英文、数字识别 ResNet34 服务器端 106.4M sdnc

预训练模型下载地址

链接: https://pan.baidu.com/s/1uMWys5lQ5ZfhnaOCPBVqZw 密码: i9du

结果展示

检测

检测

贡献代码

我们非常欢迎你为PytorchOCR贡献代码,也十分感谢你的反馈。

相关仓库

pytorchocr's People

Contributors

wenmuzhou avatar novioleo avatar bourne-m avatar jinreejing avatar zenfsheng avatar light201212 avatar wushilian avatar dependabot[bot] avatar ebreak avatar afterimagex avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.