MaxPooling2D

MaxPooling2D is a layer that executes 2-dimensional maxpooling on the input data.

MaxPooling2D(;input_shape::Tuple, pool_size::Tuple{Int64, Int64}, strides::Tuple{Int64,Int64}=(pool_size[1],pool_size[2]))

input_shape: a tuple of input data shape, (s1, s2, channels), can be set automatically, unless it is the first layer in the network

pool_size: the shape of kernel, a tuple of two integers

strides: the moving step size in vertical and horizontal direction, default (pool_size[1],pool_size[2])