Closed SamuelBroughton closed 4 years ago
Hi,
I can see from this line:
g_loss = g_loss_fake + self.lambda_rec * g_loss_rec + self.lambda_cls * g_loss_cls_spks
in solver.py that adv. loss, reconstruction loss and domian class loss are being computed however, am I correct in saying that this paper does not implement the id mapping loss introduced in the StarGAN-VC paper?
solver.py
Thank you, Sam
I realise this implementation is just a take on StarGAN-VC and not an actual implementation of the paper. Still works very well though.
Hi,
I can see from this line:
in
solver.py
that adv. loss, reconstruction loss and domian class loss are being computed however, am I correct in saying that this paper does not implement the id mapping loss introduced in the StarGAN-VC paper?Thank you, Sam