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.

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

Add unnormalized score loss for training tasknn #30

Closed
dhruvdcoder opened this issue Aug 3, 2021 · 0 comments · Fixed by #31
Closed

Add unnormalized score loss for training tasknn #30

dhruvdcoder opened this issue Aug 3, 2021 · 0 comments · Fixed by #31
Assignees
@dhruvdcoder
Labels
configs Updates to configs--models and/or sweep. enhancement New feature or request

Comments

@dhruvdcoder
Copy link
Collaborator

Currently there is dvn loss which normalizes the score to lie between [0,1]. However, we NCE is not trained with any normalization hence we need to add an unnormalized score loss that returns the negative of the score as the loss.
@dhruvdcoder dhruvdcoder added configs Updates to configs--models and/or sweep. enhancement New feature or request labels Aug 3, 2021
@dhruvdcoder dhruvdcoder self-assigned this Aug 3, 2021
@dhruvdcoder dhruvdcoder mentioned this issue Aug 3, 2021
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@dhruvdcoder dhruvdcoder

Labels
configs Updates to configs--models and/or sweep. enhancement New feature or request
Projects
None yet
Milestone
No milestone
1 participant
@dhruvdcoder