pytorch/examples

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

オープン

#570 opened on 2019/06/03

 (0 件のコメント) (0 件のリアクション) (0 人の担当者)Python (9,429 件のフォーク)batch import
good first issue

Repository metrics

Stars
 (21,634 個のスター)
PR merge metrics
 (PR metrics pending)

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?

コントリビューターガイド