WGAN loss is negative

[Firyuza]

Hello!
When I use formula for loss of WGAN I get negative value for such loss, how did you you avoid this?

Thanks!

[SeaOfOcean]

same issue

[joyyang1215]

I have the same issue that the d_loss is negative for WGAN-GP when I train on my own datasets.
And the image_size is 256x256.
[Sample] d_loss: -2668.97485352, g_loss: 1374.26965332