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

What is the difference between "input_tokens" and "src_tokens"? #63

Closed

playma opened this issue Nov 15, 2017 · 1 comment

playma commented Nov 15, 2017

Excuse me.
Anyone know what the difference is between "input_tokens" and "src_tokens"?

Contributor

myleott commented Nov 15, 2017 •

edited

There are three main tensors created by the data loader:

src_tokens: the tokens for the source sentence
target: the tokens for the target sentence
input_tokens: the output token produced by the decoder at $t-1$. During training this is the same as target but shifted by one time step (e.g., if target = 3 4 5 6 then input_tokens = 0 3 4 5. During inference this is the actual token generated in the previous time step.

myleott closed this as completed

myleott pushed a commit that referenced this issue


          Add license headers to all files (#63)

e84d0cb

zhao1iang mentioned this issue

RuntimeError during training #674

Closed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment