pytorch/examples

Why don't we use MSE as a reconstruction loss for VAE ?

オープン

#399 opened on 2018/08/07

 (7 件のコメント) (22 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

Hi,

I am wondering if there is a theoretical reason for using BCE as a reconstruction loss for variation auto-encoders ? Can't we simply use MSE or norm-based reconstruction loss instead ?

Best Regards

コントリビューターガイド