Convolution layer - rugbyprof/5443-Data-Mining GitHub Wiki

Convolution layers extracts the features from the input image. We apply convolution layer in two dimensions that is the width and height of the image. The input image, has a total of three matrices of pixels one matrix each for the red, blue and green color channels. The convolution kernel, a single matrix of floating point numbers. The output of the kernel is the altered image which is called a feature map.