is it ok to have loss bigger than one?

[ooodragon94]

I'm using ssim loss for my autoencoder seems like the result comes out real nice

but I see that the loss is bigger than one whereas in the equation, I don't see how it can be bigger than zero

any help or intuition on this?

[VainF]

Hi @ooodragon94, sorry for the late reply. Maybe your decoded images are not strictly limited in [0, 1] ？