You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Shouldn't z be a Gaussian distribution? seems that in code your code you just take out the output of a hidden layer (train_z) and then you minimize the MMD of that with a prior!
#3
Closed
AliLotfi92 opened this issue
Jun 20, 2019
· 3 comments
The text was updated successfully, but these errors were encountered:
AliLotfi92
changed the title
Shouldn't z be a Gaussian distribution? seems that in code your code you just take out the output of a hidden layer (train_z) and then you minimize the distance MMD of that with a prior!
Shouldn't z be a Gaussian distribution? seems that in code your code you just take out the output of a hidden layer (train_z) and then you minimize the MMD of that with a prior!
Jun 26, 2019
Nope, a similar issue is still open here: https://github.com/ShengjiaZhao/InfoVAE/issues/1
I should say I've not been able to reproduce the reported results after fixing this. I have the fixed version, let me know if you need that.
No description provided.
The text was updated successfully, but these errors were encountered: