Peiyao Sheng

You are right. I tried the original loss and there is no obvious differences. It may due to the convergence of DAE. And the second point you mentioned is really...

Hi, the reason for dividing KL loss with imgSize is that the default setting of BCE Loss is mean. And as for the normalized beta, A.5 interprets the conditionally independent...

Hi, I review my log and find that the reconstruction results using 5000 training samples is not good enough so I tried larger size of training set, the result shown...