This repository was archived by the owner on Feb 7, 2025. It is now read-only.
This repository was archived by the owner on Feb 7, 2025. It is now read-only.
PatchAdversarialLoss: give the choice when using least-squares of not having an activation layer #255
Description
Better results have been observed when training autoencoders with no activation layer in the adversarial loss when least-squares is used as a criterion. A flag should allow users to chose whether an activation is present or not in case of least-squares.
Metadata
Metadata
Assignees
Labels
No labels