Benchmark Evaluation on KernelGANFKPx4

[royson]

Hello,

Thanks for uploading the code.

I am trying to evaluate KernelGANFKP on Set5 & Set14 & B100 for scaling factor x4:
FKP/KernelGANFKP$ python main.py --SR --sf 4 --dataset {dataset}

However, I am hitting an error during the forward pass of the discriminator if the input patch has a height or width < 27. Is KernelGANFKPx4 not supported for Set5, Set14, and B100 datasets?

[JingyunLiang]

KernelGAN is not suitable for small images by design. You can adjust the crop size here

FKP/KernelGANFKP/config/configs_FKP.py

Line 27 in 127c121

self.parser.add_argument('--input_crop_size', type=int, default=64, help='Generators crop size')

but it will leads to bad performance.