pytorch/examples

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

开放

#399 创建于 2018年8月7日

 (7 条评论) (22 个反应) (0 位负责人)Python (9,429 个派生)batch import
good first issue

仓库指标

星标
 (21,634 个星标)
PR 合并指标
 (PR 指标待抓取)

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