pytorch/examples

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

Open

#399 opened on 2018年8月7日

GitHub で見る
 (7 comments) (22 reactions) (0 assignees)Python (9,429 forks)batch import
good first issue

Repository metrics

Stars
 (21,634 stars)
PR merge metrics
 (30d に merged PR はありません)

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