pytorch/examples

VAE reconstruction loss (BCE)

Open

#460 创建于 2018年12月1日

在 GitHub 查看
 (2 评论) (3 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

The current implementation uses

F.binary_cross_entropy(recon_x, x.view(-1, 784), reduction='sum')

as the reconstruction loss. The image x has pixel values in [0,1]. This is not the same as Bernoulli log likelihood. The images would have to binarized.

In Ladder Variational Autoencoders by Sonderby et al, they binarize the images as a Bernoulli sample after each epoch.

贡献者指南