pytorch/examples

VAE reconstruction loss (BCE)

Open

#460 ouverte le 1 déc. 2018

Voir sur GitHub
 (2 commentaires) (3 réactions) (0 assignés)Python (9 429 forks)batch import
good first issue

Métriques du dépôt

Stars
 (21 634 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

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.

Guide contributeur