February 2019
Intermediate to advanced
260 pages
6h 3m
English
Stride just increases the step size of this convolution window, which we saw previously:

Instead of going one step, we can go two steps, as follows:

And we do the same thing each time until we reach the position in the bottom-right corner. Notice how the dimension of the output matrix was shrunk to 3 x 3 x 1, and if we increase the stride again, we may end up even with a smaller matrix. This formula has now changed a bit, so we just divide it by the stride:
This division actually shows that the stride can dramatically decrease the ...
Read now
Unlock full access