answer the questions and print the output with the solution and Screen Shot The output and the code I want picture Screen Shot. To do this, you will need a data set to train the model. The data set for this lab can be obtained from GitHub repository. You can download it from here

Search in goog$-$le nickmccullub $/$ cats$-$and$-$dogs git$-$hub

Here's what the repository contains:

A folder called training$\_$data that holds $4000$ images of cats and $4000$ images of dogs

A folder called test$\_$data that contains $1000$ images of cats and $1000$ images of dogs

A folder called predictions that $1$ image of a cat and $1$ image of a dog. We will use the images in this predictions folder to make single predictions using our trained model later in this tutorial.

Every image in this data set is a $.$jpg file.

$$The code$$

import numpy as np

import tensorflow as tf

from tensorflow.keras.preprocessing.image import ImageDataGenerator

training$\_$generator $=$ ImageDataGenerator$($

rescale $=1/255,$

shear$\_$range $=0\mathrm{.}2,$

zoom$\_$range $=0\mathrm{.}2,$

horizontal$\_$flip $=$ True$)$

training$\_$set $=$ training$\_$generator.flow$\_$from$\_$directory$(\text{'}$training$\_$data',

target$\_$size $=(64,64),$

batch$\_$size $=32,$

class$\_$mode $=$ 'binary'$)$

test$\_$generator $=$ ImageDataGenerator$($rescale $=1./255)$

test$\_$set $=$ test$\_$generator.flow$\_$from$\_$directory$(\text{'}$test$\_$data',

target$\_$size $=(64,64),$

batch$\_$size $=32,$

class$\_$mode $=$ 'binary'$)$

cnn $=$ tf$.$keras.models.Sequential$()$

cnn$.$add$($tf$.$keras.layers.Conv$2$D$($filters$=32,$ kernel$\_$size$=3,$ activation$=$'relu', input$\_$shape$=[64,64,3]))$

cnn$.$add$($tf$.$keras.layers.MaxPool$2$D$($pool$\_$size$=2,$ strides$=2))$

cnn$.$add$($tf$.$keras.layers.Conv$2$D$($filters$=32,$ kernel$\_$size$=3,$ activation$=$'relu'$))$

cnn$.$add$($tf$.$keras.layers.MaxPool$2$D$($pool$\_$size$=2,$ strides$=2))$

cnn$.$add$($tf$.$keras.layers.Flatten$())$

cnn$.$add$($tf$.$keras.layers.Dense$($units$=128,$ activation$=$relu$))$

cnn$.$add$($tf$.$keras.layers.Dense$($units$=1,$ activation$=$'sigmoid'$))$

cnn$.$compile$($optimizer $=$ 'adam', loss $=$ 'binary$\_$crossentropy', metrics $=[\text{'}$accuracy$\text{'}])$

cnn$.$fit$($x $=$ training$\_$set, validation$\_$data $=$ test$\_$set, epochs $=10)$

from tensorflow.keras.preprocessing import image

test$\_$image$\_1=$ image.load$\_$img$(\text{'}$predictions$/$cat$\_$or$\_$dog$\_1.$jpg$\text{'},$ target$\_$size $=(64,64))$

test$\_$image$\_2=$ image.load$\_$img$(\text{'}$predictions$/$cat$\_$or$\_$dog$\_2.$jpg$\text{'},$ target$\_$size $=(64,64))$

test$\_$image$\_1=$ image.img$\_$to$\_$array$($test$\_$image$\_1)$

test$\_$image$\_2=$ image.img$\_$to$\_$array$($test$\_$image$\_2)$

test$\_$image$\_1=$ np$.$expand$\_$dims$($test$\_$image$\_1,$ axis $=0)$

test$\_$image$\_2=$ np$.$expand$\_$dims$($test$\_$image$\_2,$ axis $=0)$

print$($cnn$.$predict$($test$\_$image$\_1))$

print$($cnn$.$predict$($test$\_$image$\_2))$

$$questions$$

Please print the output of training$\_$generator.flow$\_$from$\_$directory as an image here $[1$ Mark$]$

Please print the output of test$\_$generator.flow$\_$from$\_$directory as an image here $[1$ Mark$]$

What will be the add command if we wanted to have $64$ feature detectors, with a kernel size of $5$x$5[2$ Marks$]$

What will be the add command if we wanted to have a max pooling layer which reduces the size of the image by a factor of $4?[2$ Marks$]$

$$

Please share the output of the first, fifth and tenth epoch of training as an image here $[2$ marks$]$

$$print$($cnn$.$predict$($test$\_$image$\_1))$ and

print$($cnn$.$predict$($test$\_$image$\_2))$

What is the output