Localizing an object in images

Now that we can classify objects in images, the next step is to and classify (detect) objects in images. In the dataset we used in the previous recipe, the (objects) were clearly visible, mostly centered, and they covered almost the complete image. However, often this is not the case and we'd want to detect one or multiple objects in an image. In the following recipe, we will show you how to detect an object in images using deep learning.

We will be using a dataset with annotated trucks. The images are taken by a camera mounted at the front of a car. We will be using TensorFlow to implement the object detector.

How to do it...

1. Let's the first:

import numpy as np
import pandas as pd
import glob
import cv2
import matplotlib.pyplot as plt

from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

from keras.models import Sequential, load_model
from keras.layers import Dense...