Negative Values after substracitng mean in a about esrgan-pytorch HOT 7 CLOSED

This is a known issue and correct

from esrgan-pytorch.

Thanks for your fast answer!

Is there any known workaround or solution for that?

from esrgan-pytorch.

Thanks for your fast answer!

Is there any known workaround or solution for that?

Hello,

You can check here https://github.com/AlexiaJM/RelativisticGAN, which mentioned if you use BCELoss (which is used in ESRGAN), you need to add sigmoid as the last layer of the Discriminator (which is not included here). However, BCEWithLogitsLoss is recommended as it will do sigmoid implicitly.

from esrgan-pytorch.

Thanks for your fast answer!
Is there any known workaround or solution for that?

Hello,

You can check here https://github.com/AlexiaJM/RelativisticGAN, which mentioned if you use BCELoss (which is used in ESRGAN), you need to add sigmoid as the last layer of the Discriminator (which is not included here). However, BCEWithLogitsLoss is recommended as it will do sigmoid implicitly.

Hello,
"add sigmoid as the last layer of the Discriminator" can't solve the problem, because "hr_output" will still larger than "sr_output" sometime.

from esrgan-pytorch.

This is a known issue and correct

Hello,
Is this problem really corrected? i still get the same problem.

from esrgan-pytorch.

If you use BCEWithLogits, it will be more stable than SIgmoid+BCELoss,

from esrgan-pytorch.

This point is not mentioned in the original paper, but it is actually a key factor in the successful training of GAN

from esrgan-pytorch.