Let's consider a CNN based architecture designed to classify an image into one of the three classes $-$ a pedestrian, a tree or a traffic signal. Each input image is of size $(512,512,3)($RGB$).$

The network contains the following $11$ layers in order. Note that we will address the input layer as the first layer, the next conv layer as the second layer and so on $($i$.$e$.$ according to the numbers$).$

$1.$ Input image $(512,512,3)$

$2.$ Convolution: $325$x$5$ filters, stride $\text{'}$s$1\text{'},$ padding $\text{'}$p$1\text{'}$

$3.$ Convolution: $323$x$3$ filters, stride $1,$ padding $1$

$4,$ Max Pooling: $2$x$2$ filter, stride $2$

$5.$ Convolution: $643$x$3$ filters, stride $1,$ padding $1$

$6.$ Convolution: $643$x$3$ filters, stride $1,$ padding $1$

$7.$ Max Pooling: $2$x$2$ filter, stride $2$

$8.$ Layer $\text{'}$l$\text{'}$

$9.$ Fully$-$connected: $4096$ neurons

$10.$ Fully$-$connected: $512$ neurons

$11.$ Fully$-$connected: $\text{'}$F$\text{'}$ neurons

Question $2/5$

Mandatory

Comprehension

The $8$th layer is named layer $\text{'}$l$\text{'}.$ Which of the following types could be the layer $\text{'}$l$\text{'}?$