pytorch/examples

Why there is no tanh activation at the end of TransformerNet?

Open

#570 ouverte le 3 juin 2019

Voir sur GitHub
 (0 commentaires) (0 réactions) (0 assignés)Python (9 429 forks)batch import
good first issue

Métriques du dépôt

Stars
 (21 634 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

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?

Guide contributeur