Francesco
Francesco
Just a quick note, I'll have a deeper look when I have some time: try to checkout the version previous to the last PR merge and train with that. I've...
Unfortunately this does not work. https://colab.research.google.com/drive/1L8Q6_MkTqBDL3NCYi6bAdGq_lq7I_vs-
@ontheway16 sorry, I misunderstood. It's a very valid point - I added it in the todo list. Thanks!
> The seams issue can easily be solved by padding. I worked around this exact problem for Prosr image upscaling here: [fperazzi/proSR#21](https://github.com/fperazzi/proSR/issues/21) > > This approach should be easy to...
Hi, I added a first (fairly inefficient) implementation of an option in the model predict function to process the image by patch. The usage is the following, using for instance...
Could you send the output of ```pip freeze```?
Interesting, the TF version is correct. I don't know why this happens. Under Ubuntu 19.04 if I create a new environment with conda and then install the package, everything works....
Hi, if you change the number of channel in the model, you cannot load the pre-trained model weights, as they have 3 input channels. There are two way you can...
Representing more accurately the low resolution distribution would definitely have __some__ positive effect, the magnitude of which can be determined with some experiment. It is of course crucial that the...
Resizing should never be done. Rather, crops of the images should be taken, but this is done automatically in ISR (the 'patch_size' parameter in config.yml (under ['session']['training']) determines the size...