why "self.real_B_random = self.real_B[half_size:]" but not the first half

[civilman628]

For the line below, as the batch size =2. So the two images in self.real_B are different.

self.real_B_random = self.real_B[half_size:]

BicycleGAN/models/bicycle_gan_model.py

Line 100 in 9cd9081

self.real_B_random = self.real_B[half_size:]

BicycleGAN/models/bicycle_gan_model.py

Line 178 in 9cd9081

self.loss_D2, self.losses_D2 = self.backward_D(self.netD2, self.real_data_random, self.fake_data_random)

it seems that the D tries to distinguish between a fake encoded B and a real image, but from a different image file in the code above.

so why not use self.real_B_random = self.real_B[0:half_size] which is the same image instead.

if the 2 images are very random: the 1st encoded image is from a "sneaker" and the 2nd real random image is a "high heel", then such a way is benefit to improve D?

[junyanz]

This is a minor implementation detail that should not significantly affect the results. We chose to use different images for training cVAE-GAN and training cLR-GAN. That is also the reason for batchSize=2. I also recently added a new model in the dev branch that uses the same real image for both cVAE-GAN and cLR-GAN.

If two images are random, D tries to learn the difference between real vs. fake shoes. In both cases, D only takes the images from domain B as its input. D is not conditional on the input image from domain A.

Please see this post for more discussion.