pytorch/examples

Is total variation loss necessary in fast_neural_style?

オープン

#278 opened on 2018/01/03

 (0 件のコメント) (1 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 issuequestion

Repository metrics

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

説明

I notice that there is no total variation loss regularization implemented in the example of fast_neural_style. But the paper declared it and their torch version use it. I'm wondering if total variation loss is necessary or not in style transfer.

コントリビューターガイド