Regarding some details of updating the generator and discriminator

[yunfan0621]

Hi, thank you for sharing the implementation of your great work! And I have some concerns with the following line of code:

Adv-Makeup/model.py

Lines 346 to 348 in f238d37

	loss_G.backward(retain_graph=True)
	nn.utils.clip_grad_norm_(self.discr.parameters(), 5)
	self.gen_opt.step()

Why do you clip the grad of the discriminator when updating the generator (maybe instead of clipping the grad of generator)? I fail to find the corresponding explanation in your paper.

I also notice that when updating the discriminator, fake images are not detached from the generator network (which is a common practice to stop the grad from being propagated to the generator). Do you intend to do so?

I really appreciate it if you could kindly solve my issues.

Best Regards