pytorch/examples

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

開放

#570 建立於 2019年6月3日

 (0 則留言) (0 個反應) (0 位負責人)Python (9,429 個分叉)batch import
good first issue

倉庫指標

星標
 (21,634 顆星)
PR 合併指標
 (PR 指標待抓取)

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