PLEASE HELP IN PYTHON

I need to answere the questions in the code explaining how the sections in the code work. Thank you

# TensorFlow and tf$.$keras

import tensorflow as tf

from tensorflow import keras

import numpy as np

import matplotlib.pyplot as plt

#We want to implement a neural network to solve a particular classification problem using high level libraries $($Tensorflow$,$ keras$).$ Please refer to any tutorial about Keras $($on the web$)$ to explain the chunks of code below, every time you are asked to leave an explanation.

#For this problem let's load the database Fashion $($with $10$ different classes$)$ already incorporated in Keras:

#load the database from keras

fashion$\_$mnist $=$ keras.datasets.fashion$\_$mnist

$($train$\_$images, train$\_$labels$),($test$\_$images, test$\_$labels$)=$ fashion$\_$mnist.load$\_$data$()$

class$\_$names $=[\text{'}$T$-$shirt$/$top$\text{'},$ 'Trouser', 'Pullover', 'Dress', 'Coat','Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'$]$

#Let's check the size of our data:

print$($train$\_$images.shape, train$\_$labels.shape, test$\_$images.shape, test$\_$labels.shape$)$

#We have $60000028$x$28$ images to learn and $100000$ images to test after training. Let's have a look at some of the images:

train$\_$images $=$ train$\_$images $/255\mathrm{.}0$

test$\_$images $=$ test$\_$images $/255\mathrm{.}0$

plt$.$figure$($figsize$=(10,10))$

for i in range$(25)$:

plt$.$subplot$(5,5,$i$+1)$

plt$.$xticks$([])$

plt$.$yticks$([])$

plt$.$grid$($False$)$

plt$.$imshow$($train$\_$images$[$i$],$ cmap$=$plt$.$cm$.$binary$)$

plt$.$xlabel$($class$\_$names$[$train$\_$labels$[$i$]])$

# Please explain this code:

tr$\_$labels$=$np$.$zeros$((60000,10))$

t$\_$labels$=$np$.$zeros$((10000,10))$

for i in range$($tr$\_$labels.shape$[0])$:

tr$\_$labels$[$i$,$train$\_$labels$[$i$]]=1$

for i in range$($t$\_$labels.shape$[0])$:

t$\_$labels$[$i$,$test$\_$labels$[$i$]]=1$

# Your explanation here

#Now let's create a model in keras:

model $=$ keras.Sequential$([$

keras.layers.Flatten$($input$\_$shape$=(28,28)),$

keras.layers.Dense$(128,$ activation$=$tf$.$nn$.$relu$),$

keras.layers.Dense$(10,$ activation$=$tf$.$nn$.$softmax$)$

$])$

#Your explanation of the above code here.

#Let's compile our model:

model.compile$($optimizer$=$tf$.$optimizers.Adam$(),$

loss$=$'mean$\_$squared$\_$error',

metrics$=[\text{'}$accuracy$\text{'}])$

#Your explanation of the above code here.

#Let's train our model:

model.fit$($train$\_$images, tr$\_$labels, epochs$=5)$

#Your explanation of the above code here.

#Let's test our model:

test$\_$loss, test$\_$acc $=$ model.evaluate$($test$\_$images, t$\_$labels$)$

print$(\text{'}$Test accuracy:$\text{'},$ test$\_$acc$)$

#Your explanation of the above code here.

#Let's make predictions with our model:

predictions $=$ model.predict$($test$\_$images$)$

#Ready! This is how to train a Neural Network, using TensorFlow and Keras. Now let's see graphically the results of our predictions. So$,$ the following code has nothing to do with Neural Network just with plotting the results. Do not worry about it$!$

def plot$\_$image$($i$,$ predictions$\_$array, true$\_$label, img$)$:

predictions$\_$array, true$\_$label, img $=$ predictions$\_$array$[$i$],$ true$\_$label$[$i$],$ img$[$i$]$

plt$.$grid$($False$)$

plt$.$xticks$([])$

plt$.$yticks$([])$

plt$.$imshow$($img$,$ cmap$=$plt$.$cm$.$binary$)$

predicted$\_$label $=$ np$.$argmax$($predictions$\_$array$)$

if predicted$\_$label $==$ true$\_$label:

color $=$ 'blue'

else:

color $=$ 'red'

plt$.$xlabel$("\{\}\{$:$2\mathrm{.}0$f$\}\%(\{\})".$format$($class$\_$names$[$predicted$\_$label$],$

$100*$np$.$max$($predictions$\_$array$),$

class$\_$names$[$true$\_$label$]),$

color$=$color$)$

def plot$\_$value$\_$array$($i$,$ predictions$\_$array, true$\_$label$)$:

predictions$\_$array, true$\_$label $=$ predictions$\_$array$[$i$],$ true$\_$label$[$i$]$

plt$.$grid$($False$)$

plt$.$xticks$([])$

plt$.$yticks$([])$

thisplot $=$ plt$.$bar$($range$(10),$ predictions$\_$array, color$="$#$777777")$

plt$.$ylim$([0,1])$

predicted$\_$label $=$ np$.$argmax$($predictions$\_$array$)$

thisplot$[$predicted$\_$label$].$set$\_$color$(\text{'}$red$\text{'})$

thisplot$[$true$\_$label$].$set$\_$color$(\text{'}$blue$\text{'})$

# Plot the first X test images, their predicted label, and the true label

# Color correct predictions in blue, incorrect predictions in red

num$\_$rows $=5$

num$\_$cols $=3$

num$\_$images $=$ num$\_$rows$*$num$\_$cols

plt$.$figure$($figsize$=(2*2*$num$\_$cols, $2*$num$\_$rows$))$

for i in range$($num$\_$images$)$:

plt$.$subplot$($num$\_$rows, $2*$num$\_$cols, $2*$i$+1)$

plot$\_$image$($i$,$ predictions, test$\_$labels, test$\_$images$)$

plt$.$subplot$($num$\_$rows, $2*$num$\_$cols, $2*$i$+2)$

plot$\_$value$\_$array$($i$,$ predictions, test$\_$labels$)$

#Your explanation $($interpretation$)$ of the above results here!