multimodal-vae-public icon indicating copy to clipboard operation
multimodal-vae-public copied to clipboard

Published 20 hours ago • verified publisher icon mhw32

Implementation of prior_expert

Open ankit1089sny opened this issue 1 year ago • 0 comments

I was looking at the implementation of prior_expert and found the following line :

logvar = Variable(torch.log(torch.ones(size)))

If it's going to represent N(0,1), logvar should be 0 since variance is 1. Could you confirm if it's ok to replace this with logvar = Variable(torch.zeros(size)) ?

ankit1089sny avatar Mar 08 '23 08:03 ankit1089sny