Tamar Rott Shaham
Tamar Rott Shaham
You need to change --max_size (the default is 250), however your desire image size is challenging and you may encounter run time error. On Sat, Apr 11, 2020, 22:27 sabaina-Haroon...
Nice! On Sun, Apr 12, 2020, 09:38 sabaina-Haroon wrote: > You need to change --max_size (the default is 250), however your desire > image size is challenging and you may...
Only the LR image is needed for training. At inference time we continue to upsample the image using the trained model scale. Please see the paper for detailed explanation (section...
Thanks. We didn't try to use the spectral normalization.
Do you have a cuda machine (any GPU)? Otherwise the code doesn't suppose to run without the not_cuda flag.
We do not directly extract the patches of the image at any point. As you said, the receptive field of both the generator and the discriminator is 11x11 which means...
Hi, The results you are getting seems responsible. However, if you want to get higher changes you can do some "advance experiments" and play with the following parameters: `--min_size` -...
The sifid function compares a single real image with a single fake one
Thank you for noticing this. The format should be `jpg`. Code and readme file were updated.
Please use torch==1.4.0 torchvision==0.5.0.