but, in the original pytorch version, they are using
if lambda_idt > 0:
# G_A should be identity if real_B is fed.
idt_A = self.netG_A(self.real_B)
loss_idt_A = self.criterionIdt(idt_A, self.real_B) * lambda_B * lambda_idt # loss part?
So I think the weight of identity loss should be opt.idloss*opt.lmbd?
I implemented the code based on the paper. The only hyper-parameter in the Equ.3 is lambda. Feel free to change the code to include more tricks from the official repository.
I found in cyclegan.py, you are using opt.idloss as the loss weight of identity loss
but, in the original pytorch version, they are using
So I think the weight of identity loss should be
opt.idloss*opt.lmbd
?