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

Pseudo Label #6

Closed
hulianyuyy opened this issue Nov 22, 2021 · 2 comments
Closed

Pseudo Label #6

hulianyuyy opened this issue Nov 22, 2021 · 2 comments

Comments

@hulianyuyy
Copy link

I'm wondering how to assign labels for frames with CTC loss. It seems CTC Loss can be viewed as sequential SoftMax losses. But the key point is how to obtain the pseudo labels for frames via back propagation. Thanks in advance!

@ycmin95
Copy link
Collaborator

ycmin95 commented Nov 22, 2021

You can refer to this repo, which calculate the gradients of CTC via PyTorch autograd instead of the forward-backward algorithm.

@hulianyuyy
Copy link
Author

Thanks again for your kind reply.

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