Recognizing faces

In the previous recipe, we how to detect facial keypoints with a neural network. In the following recipe, we will show how to recognize faces using a deep neural network. By training a classifier from scratch, we get a lot of flexibility.

How to do it...

1. As usual, let's start with importing the libraries and setting the seed:

import glob
import re
import matplotlib.pyplot as plt
import numpy as np
import cv2
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

from keras.models import Model
from keras.layers import Flatten, Dense, Input, GlobalAveragePooling2D, GlobalMaxPooling2D, Activation
from keras.layers import Convolution2D, MaxPooling2D
from keras import optimizers
from keras import backend as K

seed = 2017

2. In the following step, we will load the data and output some example images to get an idea of the data:

 DATA_DIR = 'Data/lfw/'
images = glob.glob(DATA_DIR + '*/*.jpg')
...