Why pad 4 pixels before resizing instead of resizing directly？

[kywish]

Hi~, in the part of ouput anomaly map:

map_combined = torch.nn.functional.pad(map_combined, (4, 4, 4, 4)) map_combined = torch.nn.functional.interpolate(map_combined, (orig_height, orig_width), mode='bilinear')

why pad 4 pixel each side? what's the difference with resize to (orig_height, orig_width) directly? 🤔🤔🤔

[nelson1425]

It is similar to applying 11x11 edge filter to 100x100 image. The result will be 90x90 image with detected edges. Resizing it to 100x100 would distort the detected edges. Instead you have to pad the 90x90 image with 5 pixels on each size.