Skip to content
New issue

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

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

Already on GitHub? # to your account

Saw a non-null label (index >= num_classes - 1) following a null label #7

Open
lxj0276 opened this issue Jul 23, 2017 · 5 comments
Open

Comments

@lxj0276
Copy link

lxj0276 commented Jul 23, 2017

现在运行ctc'代码时出现这个问题,我想问下你当初的tensorflow的版本是哪个

@ypwhs
Copy link
Owner

ypwhs commented Jul 24, 2017

忘记了,你可以试试更新到最新版,应该是可以跑的。

@GabrielLin
Copy link

The same error shew at Keras 2.0.5 and Tensorflow 1.3.0.

@Sqrt5
Copy link

Sqrt5 commented Oct 30, 2017

尝试把n_class+1程序可以运行,但是不知道对不对
x = Dense(n_class + 1, kernel_initializer='he_normal', activation='softmax')(x)

@jzeng9
Copy link

jzeng9 commented May 27, 2018

同样有这个问题,在使用了 @Sqrt5 的方法之后得到解决,希望可以求证一下可行性。

samueltin added a commit to samueltin/tf-crnn that referenced this issue Aug 9, 2018
ypwhs/captcha_break#7
嘗試把n_class+1程序可以運行,但是不知道對不對
x = Dense(n_class + 1, kernel_initializer='he_normal', activation='softmax')(x)
@ypwhs
Copy link
Owner

ypwhs commented Jun 16, 2019

现在使用 tensorflow 1.13.1 测试完成,模型训练速度快了,精度也高了,你可以试试最新的代码。

# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants