gan
gan copied to clipboard
About WGAN-div loss function
In wgan_div_celeba.py#L129, there is d_train_model.add_loss(d_loss + grad_loss)
and d_loss
is defined by K.mean(x_real_score - x_fake_score)
. Should it be d_train_model.add_loss(d_loss - grad_loss)
?