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

Put a parameters criterion to deep models function #161

Open
tgnassou opened this issue Apr 3, 2024 · 1 comment
Open

Put a parameters criterion to deep models function #161

tgnassou opened this issue Apr 3, 2024 · 1 comment
Labels
deep enhancement New feature or request good first issue Good for newcomers

Comments

@tgnassou
Copy link
Collaborator

tgnassou commented Apr 3, 2024

The function to create deep DA models should have a parameter criterion or base_criterion or source_criterion. For now, it is hardcoded as a cross-entropy loss but if the model has a softmax for example one should be able to put a BCELoss.
@tgnassou tgnassou added enhancement New feature or request good first issue Good for newcomers deep labels Apr 3, 2024
Som-III added a commit to Som-III/skada that referenced this issue Apr 3, 2024
@Som-III
issue scikit-adaptation#161 fixed
732c0ed
@Som-III
Copy link

Som-III commented Apr 3, 2024

Added a 'criterion' parameter with default as 'cross_entropy_loss'

@tgnassou tgnassou mentioned this issue Jul 11, 2024
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
deep enhancement New feature or request good first issue Good for newcomers
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@tgnassou @Som-III