Tamar Rott Shaham

This is a WGAN, so no cross-entropy loss is used. You can find more details regarding the training scheme of WGAN at the paper "Improved Training of Wasserstein GANs" by...

I didn't check it yet, but there's a pool request with update for python 1.6. it might help with this.

Thank you for the update! I'll check this on my side and update the code.

you should change --max_size during training to be 1200 (the default is 250, which gives 1000 for x4 SR)

Thank you for letting me know about this. I don't know the reason for this error, didn't happen on my side. I updated a requirement file, maybe this could help.

This is a possible solution, but pat attention that it changed the optimization process and therefore might change performances. So the results won't necessarily be identical to the original version.

We found it to work better empirically. But other solutions might also work. Just be careful and make sure performances are the same.

Thank you! 1. The code does not support multiple GPUs currently. 2. For this you will need to add a loop to the training function for each of your images....

Thanks!

For SR, SinGAN continues to upsample and generate details using the finest scale generator for several times, and is therefore able to super-resolved images. The key idea is that the...