Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

请问这个是单纯的DenseNet 还是DenseNet+CTC #3

Open
xikunlun001 opened this issue Jul 24, 2018 · 3 comments
Open

请问这个是单纯的DenseNet 还是DenseNet+CTC #3

xikunlun001 opened this issue Jul 24, 2018 · 3 comments

Comments

@xikunlun001
Copy link

我看您这个的效果很好
不知道这个结果为什么超过和DenseNet +CTC
最后不能识别重复字符是denseNet的原因吗

感谢~
@yinchangchang
Copy link
Owner

这是一个单纯的multi-label分类的densenet，没有用CTC。
可以在一定程度上识别重复字符，对整张图片进行了一次从左到右的扫描，能识别不连续的重复字符。
对于连续的重复字符，在相邻的两个扫描中，都会有预测有相同的一个字，这时模型不知道是一个字太大占据了两次扫描的空间，还是两个相同的字。

@xikunlun001
Copy link
Author

@yinchangchang 理解了 感谢~

@kasyoukin
Copy link

这不就是CTC的 merge repeated ？

@woshi91 woshi91 mentioned this issue Feb 27, 2019
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@kasyoukin @xikunlun001 @yinchangchang