Build a CNN classifier. For each layer, calculate the number of weights, number of biases and the size of the associated feature maps.

$\backslash$table$[[$Layer$,$Activation map dimensions,Number of weights,Number of biases$],[$INPUT$,1281283,0,0],[$CONV$-9-32,,,],[$POOL$-2,,,],[$CONV$-5-64,,,],[$POOL$-2,,,],[$CONV$-5-64,,,],[$POOL$-2,,,],[$FC$-3,,,]]$

CONV$-$K$-$N: convolutional layer with $N$ filters, each them of size $KK,$ Padding and stride parameters are always $0$ and $1$ respectively.

$*$ POOL$-$K: a $KK$ pooling layer with stride $K$ and padding $0.$

$*FC-N$ : a fully$-$connected layer with $N$ neurons.