Giter VIP home page Giter VIP logo

Comments (10)

18813055625 avatar 18813055625 commented on May 16, 2024

@haneSier 训练集是这样的:
0
不定长是因为训练的时候只确定了height=32, width=None,所以可以识别任意长度,不过一般有限制。

from chinese-ocr.

18813055625 avatar 18813055625 commented on May 16, 2024

image

from chinese-ocr.

Sierkinhane avatar Sierkinhane commented on May 16, 2024

不定长识别和你给定的训练集长度有关,比如说你训练集中图片长度为200,然而你feed到神经网络里的是将200resize成100的图片,那么在你训练好之后,识别其他不同长度的图片时就要按同样比例放缩

from chinese-ocr.

Aurora11111 avatar Aurora11111 commented on May 16, 2024

@Sierkinhane 那我的数据集全是一样长度的,是不是就不能识别不同长度的那种数据了

from chinese-ocr.

Sierkinhane avatar Sierkinhane commented on May 16, 2024

并不是

from chinese-ocr.

Sierkinhane avatar Sierkinhane commented on May 16, 2024

只要你的放缩比例合适就ok

from chinese-ocr.

Sierkinhane avatar Sierkinhane commented on May 16, 2024

https://github.com/Sierkinhane/crnn_chinese_characters_rec可以看看我的实现,在test.py中

from chinese-ocr.

qingfenghcy avatar qingfenghcy commented on May 16, 2024

https://github.com/Sierkinhane/crnn_chinese_characters_rec可以看看我的实现,在test.py中
请问chinese ocr这个的ctpn是使用的ctpn吗,怎么感觉是faster rcnn

from chinese-ocr.

xiaofengShi avatar xiaofengShi commented on May 16, 2024

from chinese-ocr.

qingfenghcy avatar qingfenghcy commented on May 16, 2024

你好,ctpn是2016年提出的算法,是一种基于目标检测的文字识别网络,在faster的基础上,去掉了roi以及后面的类别和box回归计算,并且在basenet上,faster使用cnn,而ctpn在cnn之后使用rnn和fc来生成预测的anchorbox和类别。这样修改的原因是,ctpn用来处理文本行的提取,使用rnn是为了链接相邻的box,考虑了语义信息,另外,在文本识别任务中,只包含文本和背景两类,因此去掉了faster中的roi层和后续的损失计算。另外,ctpn目前默认只能检测水平文本,修改anchor可以支持垂直文本检查,当前这个repo是我比较早期的项目,很久没有更新过相关文档了,我会在接下来一个月内完成目前文档的更新,并且加入对ctpn,crnn,ctc解码策略的一些解释。 发自我的 iPhone

在 2019年2月27日,下午9:27,Chunyu Hao @.***> 写道: https://github.com/Sierkinhane/crnn_chinese_characters_rec可以看看我的实现,在test.py中 请问chinese ocr这个的ctpn是使用的ctpn吗,怎么感觉是faster rcnn — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

谢谢,会持续关注的

from chinese-ocr.

Related Issues (20)

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.