Giter VIP home page Giter VIP logo

caffelstm-ocr's Introduction

CaffeLSTM-OCR

基于caffe的LSTM CTC OCR案例,能够利用该案例完成序列的识别,包括验证码、车牌、身份证号码、地址等长序列动长的内容识别
这是一个resnet+blstm的例子,blstm是双向lstm的意思,resnet也只是采用了其中的126部分,丢掉了一大半

这个最大的贡献,是
能够训练长序列的ocr识别,可以使用这个技术完成比如身份证号码、地址、车牌等识别任务

lstm网络设计注意事项:
1.保证CNN得到的featuremap输入到lstm时的宽度至少大于等于最大字符数的3倍左右,即time_step大于等于最大字符数3倍,否则小了不行
2.如果是配合完整的resnet精度应该能够更好
3.这次训练的精度为100%停止的,测试精度是97%左右,算是对复杂验证码OCR的一个证明,证明能力
4.对于自己衔接网络,只要保证最后的time_step能配的上就不会有错
5.训练过程中,如果出现难以收敛,把dropout层的dropout_ratio调低到0.5或者更低比如0.3甚至0,如果过拟合了,就调高,甚至可以0.7、0.9。当然默认是不要修改他,除非你也在研究
6.lstm的num_output个数也影响精度,还有所谓的多层lstm也是可以有的

5BSRM_9299.png demo.png


里面的C++演示程序是干净的

下载

模型、演示图片、和依赖项,依赖项编译自https://github.com/dlunion/CCDL

CaffeLSTM-OCR.rar
train Dataset

caffelstm-ocr's People

Contributors

dlunion avatar hopef avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

caffelstm-ocr's Issues

运行环境的要求

该项目能否在ubuntu下运行,环境要求是什么?
怎么去编译运行?

有个问题想请教一下

跑rec-py.py代码时,报错:
[libprotobuf ERROR google/protobuf/text_format.cc:274] Error parsing text-format caffe.NetParameter: 13:34: Message type "caffe.LayerParameter" has no field named "continuation_indicator_param".
我用的是warpctc-caffe-master
为什么没有continuation_indicator_param?

请问Ubuntu下面的编译问题

您好,感谢分享!请问Ubuntu下面怎么编译呢?有没有makefile或者cmakelists.txt可以提供?我看你这个不是完整的caffe,所以要把你的模块merge到caffe里面进行使用?请问你用那个版本的caffe,非常感谢!

你好有几个问题想问下

  1. 你这个验证码识别的位数最多是5位还是可变的? 我看你的label-test.txt 有的4位有的5位,
    3位的或者6位的能识别吗?
  2. 这个识别验证码的位数(你这里就5位?。。还是由训练样本决定?)在哪里控制的?train.prototxt里的?
  3. label-test.txt 的第32类别就是空的意思?
  4. label-map.txt的顺序为啥不是0-9,A-Z按顺序排列啊?
  5. 如果用于一级汉字3755类识别可以吗?

非常感谢啊!

CCDL-master代码无法编译

请问是否可以提供楼主使用的CCDL-master版本源码,GitHub链接上下载后的源码无法编译,谢谢。

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.