tommymessi / crnn_ctc-centerloss Goto Github PK
View Code? Open in Web Editor NEWctcloss + centerloss crnn text recognition
ctcloss + centerloss crnn text recognition
Thank you for your work . I has a question. Center loss can work with cross entropy loss.
使用ctc+center loss 的训练速度会不会比 ctc loss的训练速度慢很多
这一行会有Segmentation fault (core dumped)的error,请问作者会有这个错误吗
hi,你好,crnn.py 脚本中去重复字符那块,为什么重复字符取最后一次出现的位置,而不是重复字符第一个位置或者所有重复字符都参与centerloss的计算?一直想不通这一点,希望作者给个回复,谢啦
如题,提供的checkpoint文件名里没有.ckpt,如何加载模型?
只有crnn_50.data...crnn_50.index, crnn_50.meta
raw_pred_to_features里面,tail为什么取第一个字符,感觉是不是应该取最后一个字符?
tail = tf.greater(raw_pred[:, :1], self.num_classes - 1)
你好,想了解一下,你的代码中,各个类别的样本中心为什么采用不更新的策略?
Could you please release the model again?
Thank you so much.
作者能否分享一下数据集吗, 我想自己跑跑看, 感谢.
你好,百度网盘的预训练模型链接失效了,请问可以再提供一下吗?
1)将预训练模型载入模型中,将该模型的输出做为label,给center loss+ctc loss正式训练?还是2)将预训练模型单纯使用,产生给center loss的label,另一个正式模型用center loss+ctc loss从新训练?
tensorflow.python.framework.errors_impl.InvalidArgumentError: Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Assign requires shapes of both tensors to match. lhs shape= [6941,512] rhs shape= [6941,6941]
请问在用参照你的方法是实现的center loss训练的时候,有时候准确率会突然比正常水平下降好多,最多有10个百分点,但是又会慢慢训练回来,请问这是正常现象吗?
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.