pytorch/examples

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

Aperta

#399 aperta il 7 ago 2018

 (7 commenti) (22 reazioni) (0 assegnatari)Python (9429 fork)batch import
good first issue

Metriche repository

Star
 (21.634 stelle)
Metriche merge PR
 (Metriche PR in attesa)

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