VariationalAutoencoderRunner.py (cost= nan)

[daviddao]

When running the VAE example VariationalAutoencoderRunner.py in models/autoencoder , I get following output:

Epoch: 0001 cost= nan
Epoch: 0002 cost= nan
Epoch: 0003 cost= nan
Epoch: 0004 cost= nan
Epoch: 0005 cost= nan
Epoch: 0006 cost= nan
Epoch: 0007 cost= nan
Epoch: 0008 cost= nan
Epoch: 0009 cost= nan
Epoch: 0010 cost= nan
Epoch: 0011 cost= nan
Epoch: 0012 cost= nan
Epoch: 0013 cost= nan
Epoch: 0014 cost= nan
Epoch: 0015 cost= nan
Epoch: 0016 cost= nan
Epoch: 0017 cost= nan
Epoch: 0018 cost= nan
Epoch: 0019 cost= nan
Epoch: 0020 cost= nan

Machine: AWS EC2 GPU instance with image ami-77e0da1d

[martinwicke]

@snurkabill, and idea?

[snurkabill]

Sure I have idea. I don't double checks. VAE needs data scaled between zero and one. Normally scaled data lead to negative logarithm, which is obviously error. Fixed with next PR

[martinwicke]

Fixed in #24.