I want see the values while training, tf.log(predict_real + EPS) and tf.log(1 - predict_fake + EPS).
so, i'm add the code(#add code) in the main.

           if should(a.progress_freq):
                fetches["discrim_loss"] = model.discrim_loss
                fetches["gen_loss_GAN"] = model.gen_loss_GAN
                fetches["gen_loss_L1"] = model.gen_loss_L1

It seems like you copied and pasted from the is_trail from the line above. It currently says
"True for training, False for testing [False]"
https://github.com/carpedm20/DCGAN-tensorflow/blob/9166ef99bf9fcd1d0bf641ae752428bb06903b00/main.py#L26

In updater of progressive GAN, the "reso", "reso_low" and "reso_high" at lines 41,47,48 must be converted to "int" as it will then be used as kernel and stride in F.average_pooling_2d

Hi

the train function returns two variables losses and samples. These two variables are never declared before. The article and documentation also don't explain these variables enough so I could fix it. Could you tell me how they should be declared and used?