pytorch/examples
Auf GitHub ansehenWhy there is no tanh activation at the end of TransformerNet?
Open
#570 geöffnet am 3. Juni 2019
good first issue
Repository-Metriken
- Stars
- (21.634 Stars)
- PR-Merge-Metriken
- (Keine gemergten PRs in 30 T)
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?