How to do it...

You need to complete the following steps:

1. Import the modules:

import cv2
import numpy as np
import matplotlib.pyplot as plt

2. Load the models:

age_model = cv2.dnn.readNetFromCaffe('../data/age_gender/age_net_deploy.prototxt',
                                     '../data/age_gender/age_net.caffemodel')
gender_model = cv2.dnn.readNetFromCaffe('../data/age_gender/gender_net_deploy.prototxt',
                                        '../data/age_gender/gender_net.caffemodel')

3. Load and crop the source image:

orig_frame = cv2.imread('../data/face.jpeg')
dx = (orig_frame.shape[1]-orig_frame.shape[0]) // 2
orig_frame = orig_frame[:,dx:dx+orig_frame.shape[0]]

4. Visualize the image:

plt.figure(figsize=(6,6))
plt.title('original')
plt.axis('off')
plt.imshow(orig_frame[:,:,[2,1,0]])
plt.show()

5. Load the image with mean pixel values and subtract them from the source image:

mean_blob = np.load('../data/age_gender/mean.npy')
frame = cv2.resize(orig_frame, (256,256)).astype(np.float32)
frame -= np.transpose(mean_blob[0], (1,2,0))

6. Set age and gender lists:

AGE_LIST = ['(0, 2)','(4, 6)','(8, 12)','(15, 20)',
            '(25, 32)','(38, 43)','(48, 53)','(60, 100)']
GENDER_LIST = ['male','female']

7. Classify gender:

blob = cv2.dnn.blobFromImage(frame, 1, (256,256))
gender_model.setInput(blob)
gender_prob = gender_model.forward()
gender_id = np.argmax(gender_prob)
print('Gender: {} with prob: {}'.format(GENDER_LIST[gender_id], gender_prob[0, gender_id]))

8. Classify age group:

age_model.setInput(blob)
age_prob = age_model.forward()
age_id = np.argmax(age_prob)
print('Age group: {} with prob: {}'.format(AGE_LIST[age_id], age_prob[0, age_id]))