Put a parameters criterion to deep models function

scikit-adaptation / skada

Domain adaptation toolbox compatible with scikit-learn and pytorch

https://scikit-adaptation.github.io/

BSD 3-Clause "New" or "Revised" License

54 stars 16 forks source link

Put a parameters criterion to deep models function #161

Open tgnassou opened 3 months ago

tgnassou commented 3 months ago

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.

Som-III commented 3 months ago

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