pytorch/examples
Why there is no tanh activation at the end of TransformerNet?
Offen
#570 geöffnet am 03.06.2019
good first issue
Repository-Metriken
- Stars
- (21.634 Sterne)
- PR-Merge-Metriken
- (PR-Metriken ausstehend)
Beschreibung
In Fast Style Transfer, it seems like there is no tanh layer at the end of TransformerNet model. There is no gurantee that output values fti in certain range e.g. [0, 1] for PIL image.
Using only deconv is also valid? How does it work?