Martin Krasser

@akkara what did you try and what did not work?

Which demo code and which imports are missing. All demo notebooks should run without any modifications required.

This is still work in progress (supporting only scale=4) and I didn't allocate time yet to complete it. It will be extended while working on #18 which I started recently....

Hi @Cristy94, thanks for using this project and sharing your findings. This is something I found with the TF 2.0 release candidates but disappeared with the TF 2.0 final release...

SRGAN model and training is hard-coded for scale 4.

Can you please be more specific?

The usual way to implement this is a model with multiple outputs i.e. x2, x3 and x4. This model is then trained on multiple scales simultaneously. Probably not a big...

> In there you have answered that to evaluate an image other than one from Div2K validation set, we need to downscale. In #19 the discussion was mainly about how...

Hi @Fmstrat, thanks for #81 and this initiative, looks great! I have limited connectivity this week but will review your pull request next week.

Reviewed ... awesome PR, thanks a lot! Maybe a later addition could use `argparse` in the training and inference scripts to set some of the hyper-parameters but your initial PR...