pytorch/examples

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

Open

#570 建立於 2019年6月3日

在 GitHub 查看
 (0 留言) (0 反應) (0 負責人)Python (9,429 fork)batch import
good first issue

倉庫指標

Star
 (21,634 star)
PR 合併指標
 (30 天內沒有已合併 PR)

描述

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?

貢獻者指南