convolution master data science 02
#005 CNN Strided Convolution Master Data Science 02.11.2018
A strided convolution is another basic building block of convolution that is used in Convolutional Neural Networks. Let's say we want to convolve this \(7 \times 7 \) image with this \(3 \times 3 \) filter, except, that instead of doing it the usual way, we're going to do it with a stride of \(2 \). This means that we take the element-wise product as usual in this upper left \(3 \times 3 \) region, and then multiply and sum elements. That gives us \(91 \). But then instead of stepping the blue box over by one step, we're going to step it over by two steps.