search

Zardinality / WGAN-tensorflow

a tensorflow implementation of WGAN
579 stars 201 forks source link

Why you don't have batchnorm for first layer of critic? #1

Open menglin0320 opened 7 years ago

menglin0320 commented 7 years ago

Some sepcial reason?

kang205 commented 7 years ago

It follows the same setting in DCGAN and PyTorch version of WGAN.

Zardinality commented 7 years ago

Yes. I just follows the model defined in PyTorch version of WGAN. No special reason for this. But since even MLP can do a decent job as a critic, you might want to try how it works with bn in the first layer.