Updating the generator G and the discriminator D with the same batch data, isn't it?

titu1994 / Super-Resolution-using-Generative-Adversarial-Networks

An implementation of SRGAN model in Keras

283 stars 85 forks source link

Updating the generator G and the discriminator D with the same batch data, isn't it? #9

Closed eeric closed 8 years ago

eeric commented 8 years ago

At present, it was describedthat the G and D were updated in the same Theano update and with the same batch data in enhance.py, so the effect of discriminator D was restricted.

It wasn't done to training G and D in separate updates with different data in enhance.py, was it?

titu1994 commented 8 years ago

@eeric You are confusing this repository with the alexjc repository. This one doesnt have any enhance.py