Deep Learning with Keras

ConvNets summary

So far, we have described the basic concepts of ConvNets. CNNs apply convolution and pooling operations in one dimension for audio and text data along the time dimension, in two dimensions for images along the (height x width) dimensions, and in three dimensions for videos along the (height x width x time) dimensions. For images, sliding the filter over input volume produces a map that gives the responses of the filter for each spatial position. In other words, a ConvNet has multiple filters stacked together which learn to recognize specific visual features independently of the location in the image. Those visual features are simple in the initial layers of the network, and then more and more sophisticated deeper in the network. ...