Question $5[3$ pts$]$: Figure $4$ shows a ResNet block where the input a$[$l$]$ is a $2$x$2$ matrix. The two layers

inside the ResNet block consist of two CNN layers, each has one $3$x$3$ convolution filter. The input images

and the two CNN filters are given as follows:

Input image: ; CNN$1$ filter: ; CNN$2$ filter:

Use zero padding with stride $1.$ Ignore bias, and use ReLu$()$ as the activation functions for all layers.

$$ Calculate output of the first layer of the ResNet block, i$.$e$.,$ a$[$l$+1]($show calculations$)[1$ pt$]$

$$ Calculate output of the second layer of the ResNet block, i$.$e$.,$ a$[$l$+2]($show calculations$)[2$ pts