pytorch/examples
Ver no GitHubWhy there is no tanh activation at the end of TransformerNet?
Open
#570 aberto em 3 de jun. de 2019
good first issue
Métricas do repositório
- Stars
- (21.634 stars)
- Métricas de merge de PR
- (Nenhuma PRs mesclada em 30d)
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?