pytorch/examples

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

Open

#399 建立於 2018年8月7日

在 GitHub 查看
 (7 留言) (22 反應) (0 負責人)Python (9,429 fork)batch import
good first issue

倉庫指標

Star
 (21,634 star)
PR 合併指標
 (30 天內沒有已合併 PR)

描述

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

貢獻者指南