Is my loss function right? WGAN

Question

I am new to GANs, but I was able to train a DCGAN decently. I decided to try a WGAN (not the improved one). I seem to get outputs, but my loss doesn't seem to converge for the generator.

I am using the loss function

from keras import backend as K
def wasserstein_loss(y_true, y_pred):
    return K.mean(y_true * y_pred)

for both the critic and generator. I am labelling real images as -1 and fake ones as 1.

Here's my loss over time:

Is the generator loss supposed to behave like that? Even though the discriminator loss seems to behave as expected, is a swing that large normal?

Answer 1

If anyone's wondering, yes it is right. The weight-clipping WGAN is very sensitive to changes in the weight-clipping hyperparameter, which is probably causing this. Upgrading to the gradient descent version fixed it. Loss should look like this btw