Anukool ChaturvediHow 1x1 convolution reduces the floating-point operations in CNNThe main purpose of applying kernels (filters) in a CNN architecture is to extract features from an input image, but a kernel of size 1X1…2 min read·Oct 28, 2020----
Anukool ChaturvediHow CNN depth changes after applying filters?In CNNs, a lot of variation in the dimensions of the matrix is seen due to applications of the various filter channels of varying…2 min read·Oct 26, 2020----