As mentioned previously, in this chapter, we are going to use the Oxford-IIIT-Pet dataset. It will be a good idea to encapsulate the preparation of the dataset in a separate data.py script, which can then be used throughout the chapter. As with any other script, first of all, we have to import all the required modules, as shown in the following code snippet:
import glob
import os
from itertools import count
from collections import defaultdict, namedtuple
import cv2
import numpy as np
import tensorflow as tf
import xml.etree.ElementTree as ET
In order to prepare our dataset for use, we will first download and parse the dataset into memory. Then, out of the parsed data, we will create a TensorFlow dataset, which allows us to work with a dataset in a convenient manner as well as prepare the data in the background so that the preparation of the data does not interrupt...
