Date: Feb 7, 2013 11:49 AM
Author: Matt J
Subject: Re: sub-pixel shifting of a matrix
"Bruno Luong" <firstname.lastname@example.org> wrote in message <email@example.com>...
> "Matt J" wrote in message <firstname.lastname@example.org>...
> > Maybe, but only because there are some funny sub-optimal things happening inside conv2 implementation-wise, and because the interpolation kernel here happens to be small. There's no way the 3rd version below should be the slowest.
> Of course. The reason is obvious: 2+2 = 2*2, but 10+10 << 10*10.
That doesn't explain why the 3rd version was the slowest. The 3rd version uses a 10+10 tensorial operation so since 10+10 << 10*10, you would expect the 3rd version to be faster (or comparable to) the others.