pytorch/examples
GitHub で見るWhy there is no tanh activation at the end of TransformerNet?
Open
#570 opened on 2019年6月3日
good first issue
Repository metrics
- Stars
- (21,634 stars)
- PR merge metrics
- (30d に merged PR はありません)
説明
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?