search

kefirski / pytorch_RVAE

Recurrent Variational Autoencoder that generates sequential data implemented with pytorch
MIT License
357 stars 87 forks source link

Loss Function #11

Open dongqian0206 opened 6 years ago

dongqian0206 commented 6 years ago

Hi,

Would you like to tell me why you added scalar '79' in front of the cross entropy (RVAE, Line 110)? loss = 79 cross_entropy + kld_coef(i) kld

best

nguyenvo09 commented 6 years ago

when I remove 79, kld can go to zero very fast.

dongqian0206 commented 6 years ago

Hi, thanks for your reply. We have to use kl annealing to alleviate kl vanishing issue in this model. I think it is the same.

best