Closed louiseviden closed 3 years ago
Has the problem been solved?
Has the problem been solved?
no
The problem is related to class_weight=[cw1, cw2] parameter
The problem is related to class_weight=[cw1, cw2] parameter
How can I solve the same problem?
Did you solve the problem? I am facing the issue with SGAN
d_loss_real = self.discriminator.train_on_batch(imgs, [valid, one_hot_labels], class_weight=[cw1, cw2])
d_loss_fake = self.discriminator.train_on_batch(gen_imgs, [fake, fake_labels], class_weight=[cw1, cw2])