pytorch/examples

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

Open

#399 geöffnet am 7. Aug. 2018

Auf GitHub ansehen
 (7 Kommentare) (22 Reaktionen) (0 zugewiesene Personen)Python (9.429 Forks)batch import
good first issue

Repository-Metriken

Stars
 (21.634 Stars)
PR-Merge-Metriken
 (Keine gemergten PRs in 30 T)

Beschreibung

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

Contributor Guide