pytorch/examples

VAE reconstruction loss (BCE)

Open

#460 aperta il 1 dic 2018

Vedi su GitHub
 (2 commenti) (3 reazioni) (0 assegnatari)Python (9429 fork)batch import
good first issue

Metriche repository

Star
 (21.634 star)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

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.

Guida contributor