pytorch/examples

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

开放

#570 创建于 2019年6月3日

 (0 条评论) (0 个反应) (0 位负责人)Python (9,429 个派生)batch import
good first issue

仓库指标

星标
 (21,634 个星标)
PR 合并指标
 (PR 指标待抓取)

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?

贡献者指南