pytorch/examples

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

Open

#399 aperta il 7 ago 2018

Vedi su GitHub
 (7 commenti) (22 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

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

Guida contributor