code from line 112, models/bicycle_gan_model.py
self.fake_B_random = self.netG(self.real_A_encoded, self.z_random)
Why do we generate the fake_B_random using real_A_encoded instead of real_A_random?
I know that it does not really matter since there is no L1 loss in this part (cLR-GAN).
Doing it in this way means that half of the A input data is unused in training, or do I have some misconception here.
code from line 112, models/bicycle_gan_model.py
self.fake_B_random = self.netG(self.real_A_encoded, self.z_random)Why do we generate the fake_B_random using real_A_encoded instead of real_A_random?
I know that it does not really matter since there is no L1 loss in this part (cLR-GAN).
Doing it in this way means that half of the A input data is unused in training, or do I have some misconception here.