D(SR) = 0 and D(HR) = 1 about srgan-pytorch

[Lornatang]

Currently I am trying to improve the training of SRGAN to make it more stable

[Lornatang]

From the current point of view, the training of GAN still has the problem of "model collapse", and it may be necessary to find the best model from the training node of GAN

[Lornatang]

You need to wait patiently for the training results and choose the best one.

[valentin-fngr]

I think he meant wait till the end of the training process. Surprisingly, your model can perform badly during a lot of iterations and then, suddenly, you will see the D(SR) increase and the D(HR) decrease, which is what you want. You just need to be patient due to the instability of GAN training :(

[Lornatang]

For example these methods
WassersteinGAN
WassersteinGAN_GP

[Lornatang]

This is also the case for me during training, usually a common problem when training original GANs.

[valentin-fngr]

Should I still expect some good results ?
Or do I need to investigate on how to fix it ?

[valentin-fngr]

Thank you very much, I now better understand GANs evaluation.
Beautiful work on this repo

[Lornatang]

Thank you.

[rhtm02]

Are you saying that you are learning several times to find the optimal model or that you are learning to the end and finding the optimal model among them?

[rhtm02]

Ok thx a lot

[valentin-fngr]

Currently I am trying to improve the training of SRGAN to make it more stable

How many iterations do you use to train your model ?
I would be interested in knowing what approaches you are going to use to make the training more stable as I am really interested in the subject

[Lornatang]

I will not update on this library though, as this library is the closest implementation to the original paper