is_training not set in one of the layer of vladder_small

[l3robot]

Hi, very interesting paper btw!
I'm replicating the code in PyTorch, but noticed that you've not used the is_training parameter for one of the layer below. I was wandering if that was intended, since some papers are keeping the training behaviour of batch normalization in evaluation mode.

Variational-Ladder-Autoencoder/vladder_small.py

Line 66 in 00d517d

ladder0 = fc_bn_lrelu(ladder0, self.network.cs[3])

Thanks

[DanRuta]

@l3robot Have you had success replicating the code in Pytorch? If so, is there any chance it could be made public?