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.

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

ctcloss的参数labels #17

Closed
iredescentone opened this issue Jan 9, 2020 · 1 comment
Closed

ctcloss的参数labels #17

iredescentone opened this issue Jan 9, 2020 · 1 comment

Comments

@iredescentone
Copy link

loss = tf.reduce_mean(tf.nn.ctc_loss(labels=labels, inputs=inference_ret, sequence_length=\

看到您的tf版本是1.1.12,该版本ctcloss对应的输入label是一个稀疏矩阵,确认下您这行代码输入的labels是经过稀疏变换的吗?

@Wenqiang-Miao
Copy link
Collaborator

您好,在读取tfrecord文件的时候转化为sparse tensor了。

非常感谢您的提问,这个问题我之前没有在意过;不过如果labels不是sparse tensor,调用ctc_loss会报错的。

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

No branches or pull requests

2 participants