Consolidating our code

At this point, it would be useful to consolidate our code. We have written a lot of code so far, including helper functions. Let's consolidate the helper functions into a utils.py file as follows.

First, we import the necessary libraries:

import numpy as npimport randomimport osimport cv2from keras.models import Sequentialfrom keras.layers import Flatten, Dense, Conv2D, MaxPooling2Dfrom keras import backend as Kfrom keras.preprocessing.image import load_img, img_to_array

We include the euclidean_distance, contrastive_loss, and accuracy functions needed to train a Siamese neural network in the utils.py file:

def euclidean_distance(vectors):    vector1, vector2 = vectors sum_square = K.sum(K.square(vector1 - vector2), axis=1, ...

Get Neural Network Projects with Python now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.