pytorch/examples

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

Open

#399 创建于 2018年8月7日

在 GitHub 查看
 (7 评论) (22 反应) (0 负责人)Python (9,429 fork)batch import
good first issue

仓库指标

Star
 (21,634 star)
PR 合并指标
 (30 天内没有已合并 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

贡献者指南