Hi all;
Chap 14 states
a very important insight about all deep convolutional neural networks: the vast majority of the computation occurs in the early layers. Therefore, we should keep the early layers as fast and simple as possible.
I would like to check my understanding of how this relates with Chap 13; which says:
we doubled the *number of filters* from 8 to 16, resulting in no overall change in the amount of computation.
As I understand the summary of the final model created in Chap14 the number of features is going up faster than the image size is being reduced; so wouldn’t the number of computations required deeper in the network also be increasing?