diaomin / crnn-mxnet-chinese-text-recognition Goto Github PK
View Code? Open in Web Editor NEWAn implementation of CRNN (CNN+LSTM+warpCTC) on MxNet for chinese text recognition
An implementation of CRNN (CNN+LSTM+warpCTC) on MxNet for chinese text recognition
crnn多语种模型训练时,发现英文和数字错误率比中文等高很多,怎样改善?
请问这两个文件是怎么create?
请问为什么你提供的数据集txt会出现int?是记录索引吗?但是在data_utils.data_iter:88行为什么又会转成int?
我想基于你的预训练模型继续进行训练,但是在模型检测那一步发现两个模型的结构是不同的,请问这个问题存在吗,还是我哪里做错了。
谢谢!
百度云的数据集链接失效了
麻烦还能给提供一下吗?我的邮箱[email protected] 十分感谢
请问一下预测的代码有吗?
您好,我在用CRNN训练自己的模型(其中生成了100W数据,人工标注了3W数据),识别的结果有很多重复的字符是,比如:您好,可能就识别成了 您您您好好。想请问这什么原因造成的呢,在生成图片的时候,需要考虑字符在图片中的位置吗,比如左右两边非常大的留白,中间有几个字,这对训练有什么影像吗
@diaomin
Is that work support handwritten chinese text recognition?
你好请问下面这个错误是什么原因
RuntimeError: simple_bind error. Arguments:
l3_init_h: (2, 100)
l3_init_c: (2, 100)
label: (2, 10)
l2_init_c: (2, 100)
l0_init_c: (2, 100)
l1_init_h: (2, 100)
l0_init_h: (2, 100)
l2_init_h: (2, 100)
data: (2, 1, 32, 280)
l1_init_c: (2, 100)
谢谢!
请问不定长数据训练的时候该怎么处理呢?图片全部resize到一个尺寸吗 @diaomin
I notice that you the samples are constant length text, I want to know weather variable length text is ok?
After reading the code I found you change the max_pooling to max_pooling - avg_pooling, which get a difference. May I ask the reason doing this?
I searched online but didn't get any results.
你好,不用百度的warp-ctc,用mxnet自带的ctc能跑通吗
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.