Kernel estimation size problem about kernelgan HOT 2 CLOSED

Q1: We assume the GT kernel is unknown and also its size. KernelGAN estimates a 13x13, 25x25 kernel for X2, X4 respectively. These are sizes we found give a wide enough and "natural" support (a larger one blurs too much and a smaller is not expressive enough). If you want to compare two different size kernels - you may pad the smaller one with zeros without effecting its blur function.

Q2: As written in the paper, all the regularizations are inserted after the bicubic constraint is satisfied and discarded. The final co-efficients are as written in the paper (and you quoted). The parameters you snapped are at the beginning of the training before the bicubic "satisfaction".

from kernelgan.

Besides, the code seems used different parameter for losses from the paper
paper:

code parameters:

Please correct me if I configed the code wrong.

from kernelgan.