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

Blank Character Prediction #34

Open
jordanott opened this issue Nov 1, 2018 · 0 comments
Open

Blank Character Prediction #34

jordanott opened this issue Nov 1, 2018 · 0 comments

Comments

@jordanott
Copy link

I'm training a network with CTC. The loss improves over time but the network only predicts blank characters (greedy decoding). Currently, the input sequence is 4 to 5 times as long as the target sequence.

Do you have any suggestions on how to fix this?

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

1 participant