search

tntrung / gan

Tensorflow code of Dist-GAN, GN-GAN and other GAN methods
GNU General Public License v3.0
66 stars 21 forks source link

f(x, G(z)) computation #3

Open sungwoong opened 6 years ago

sungwoong commented 6 years ago

Hi, Trung,

In gaan.py, self.md_x = tf.reduce_mean(self.f_recon - self.f_fake) According to Eq. (7) in your paper, maybe self.md_x = tf.reduce_mean(self.f_real - self.f_fake)

Is it correct? Thanks, Sungwoong.

tntrung commented 6 years ago

Hi Sungwoong,

Yes, the model should work for both cases but empirically we found that using f_recon is a little bit more stable, especially on image datasets. I will take notes about it in the revised version of paper, and also in the code. Thanks very much.

Best, Trung

sungwoong commented 6 years ago

Thanks for your kind answer! Sungwoong.