Style Loss is the major player for good results and not Adversarial Loss.

[praeclarumjj3]

Hi! Thanks for the excellent codebase!

I ran a few experiments to measure the importance of GAN in the current network. It turns out if we don't use style loss, the results are largely blurry. This makes me wonder about the importance of GAN. Could you help me there?

You can confirm the experiments here: https://github.com/praeclarumjj3/AOT-GAN-Experiments#results-using-the-testing-pconv-mask-dataset-without-style-loss

Also, I fixed the bugs present in the adv_loss as mentioned in #2.

[stteovo]

before I send (img, mask) to the backbone, should I normalize the mentioned "mask" to (0, 1) or (-1, 1). I get differrent results with the two diffrrent way of normalization.