Why using correlate not convolution in the function of 'numeric_kernel'?

assafshocher / ZSSR

"Zero-Shot" Super-Resolution using Deep Internal Learning

Other

402 stars 102 forks source link

Why using correlate not convolution in the function of 'numeric_kernel'? #36

Open daifeng2016 opened 3 years ago

daifeng2016 commented 3 years ago

Hi, I am wondering why 'filters.correlate' instead of 'convolution' is used in the function of 'numeric_kernel' in imresize.py. Is the kernel be filipped somewhere? In 'numeric_kernel', it is not.