Problem $10\mathrm{.}18$ How many weights and biases are there at each convolutional layer and fully connected layer in the VGG architecture $($figure $10\mathrm{.}17)?$ Figure $10\mathrm{.}17$ VGG network $($Simonyan $\backslash$& Zisserman, $2014)$ depicted at the same scale as AlexNet $($see figure $10\mathrm{.}16).$ This network consists of a series of convolutional layers and max pooling operations, in which the spatial scale of the representation gradually decreases, but the number of channels gradually increases. The hidden layer after the last convolutional operation is resized to a $1$D vector and three fully connected layers follow. The network outputs $1000$ activations corresponding to the class labels that are passed through a softmax function to create class probabilities.