. You have designed a convolutional neural network (CNN). The specifications of each layer are represented in the following table. The notation is as follows: CNN (s, n): denotes a CNN layer with n filters of size s Pooling (s): denotes a pooling layer with size s FC (n): denotes a fully-connected layer with n output neurons Please note that padding=0 and stride=1 wherever applicable. The input image is a color image with shape of 256 x 256 x 3 In the following table, you have to determine the shape for the output of each layer and also the number of weights and biases for each layer Activation map size 256 X 256 X 3 Number of weights 0 Number of biases 0 Layer Input Conv(7, 16) Conv(11,32) Pooling(2) Conv(21,64) Pooling(2) Conv(5,64) Pooling(2) FC(4) . You have designed a convolutional neural network (CNN). The specifications of each layer are represented in the following table. The notation is as follows: CNN (s, n): denotes a CNN layer with n filters of size s Pooling (s): denotes a pooling layer with size s FC (n): denotes a fully-connected layer with n output neurons Please note that padding=0 and stride=1 wherever applicable. The input image is a color image with shape of 256 x 256 x 3 In the following table, you have to determine the shape for the output of each layer and also the number of weights and biases for each layer Activation map size 256 X 256 X 3 Number of weights 0 Number of biases 0 Layer Input Conv(7, 16) Conv(11,32) Pooling(2) Conv(21,64) Pooling(2) Conv(5,64) Pooling(2) FC(4)