利用面部识别算法和卷积神经网络的转移学习，分析朝鲜海报上的人物性别分布

from imutils.face_utilsimport FaceAligner
from dlibimport rectangle
import face_recognition
import imutils
import dlib
import cv2
import os

def resize(img):
    resized= cv2.resize(img, (0,0), fx=2.5, fy=2.5)
    return resized

detector= dlib.get_frontal_face_detector()
predictor= dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")#path to the dlib model shape_predictor_68_face_landmarks.dat
fa= FaceAligner(predictor, desiredFaceWidth=224)

images= os.listdir('Posters')
for i, indexin enumerate(images):
    print(index,':', i,'/',len(images))
    image_path= 'Posters\' + index + '\' + index + '.jpg'
    img= cv2.imread(image_path)
    img= resize(img)
    gray= cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    face_locations= face_recognition.face_locations(img, number_of_times_to_upsample=0)

    for j, face_locationin enumerate(face_locations):

        top, right, bottom, left= face_location
        dlib_rect= rectangle(left, top, right, bottom)#convert to dlib rect object
        faceOrig= imutils.resize(img[top:bottom, left:right], width=224)
        faceAligned= fa.align(img, gray, dlib_rect)       
        cv2.imwrite('faces/' + index+ '_' + str(j)+ '.jpg', faceAligned)

import cv2
import os
import matplotlib.pyplot as plt

images= os.listdir('faces')
def smaller(img):
    resized= cv2.resize(img, (0,0), fx=1/2, fy=1/2)
    return resized

plt.axis('off')

for index, imagein enumerate(images):
    img= cv2.imread('faces/' + image)
    img= smaller(img)
    plt.imshow(cv2.cvtColor((img), cv2.COLOR_BGR2RGB))
    plt.show(block=False)
    category= ''
    while categorynot in ['m','f','o']:
        print(index,'/',len(images))
        print(image)
        category= input('Category ? ')

    if index% 4 == 0:
        path= 'data7/test'
    else:
        path= 'data7/train'

    if category== 'm':
        cv2.imwrite(path+ '/male/' + image, img)
    elif category== 'f':
        cv2.imwrite(path+ '/female/' + image, img)
    elif category== 'o':
        cv2.imwrite('data7/other/' + image, img)

import os
import numpy as np
from keras.modelsimport Sequential
from keras.layersimport Dense, Dropout
from keras_vggface.vggfaceimport VGGFace
from inspectimport getsourcefile
from os.pathimport abspath
from generatorimport Generator

path= os.path.dirname(abspath(getsourcefile(lambda:0)))

categories= os.listdir(os.path.join(path,'data7/test'))
y_train= []
X_train= []
y_test= []
X_test= []
batch_size= 10
print('Getting samples')

for i, categoryin enumerate(categories):
    print(category)
    samples= os.listdir(os.path.join(path,'data7/test', category))
    for samplein samples:
        X_test.append(os.path.join(path,'data7/test', category, sample))
        y_test.append(i)

for i, categoryin enumerate(categories):
    print(category)
    samples= os.listdir(os.path.join(path,'data7/train', category))
    for samplein samples:
        X_train.append(os.path.join(path,'data7/train', category, sample))
        y_train.append(i)


training_generator= Generator(width= 224, height= 224, channels= 3, batch_size= batch_size).generate(X_train, y_train, return_labels= False, shuffle= False)
testing_generator= Generator(width= 224, height= 224, channels= 3, batch_size= batch_size).generate(X_test, y_test, return_labels= False, shuffle= False)

def save_features():
    model= VGGFace(include_top=False, input_shape=(224,224,3), weights='vggface', pooling= 'avg')             
    bottleneck_features_train= model.predict_generator(training_generator,len(X_train)// batch_size)
    np.save(open('bottleneck_features_train.npy','wb'), bottleneck_features_train)

    bottleneck_features_test= model.predict_generator(testing_generator,len(X_test)// batch_size)
    np.save(open('bottleneck_features_testing.npy','wb'), bottleneck_features_test)


def create_model():
    train_data= np.load(open('bottleneck_features_train.npy','rb'))
    train_labels= np.array([0]* 80 + [1]* 140)
    train_labels= train_labels[:len(train_labels)- (len(train_labels)% batch_size)]

    validation_data= np.load(open('bottleneck_features_testing.npy','rb'))
    validation_labels= np.array([0]* 30 + [1]* 40)
    validation_labels= validation_labels[:len(validation_labels)- (len(validation_labels)% batch_size)]

    model= Sequential()
    model.add(Dense(256, activation='relu', input_shape=train_data.shape[1:]))
    model.add(Dropout(0.5))
    model.add(Dense(64, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(1, activation='sigmoid'))

    model.compile(optimizer='rmsprop',
                  loss='binary_crossentropy', metrics=['accuracy'])

    model.fit(train_data, train_labels,
              epochs=100,
              batch_size=batch_size,
              validation_data=(validation_data, validation_labels))

    score= model.evaluate(validation_data, validation_labels)
    print('Test loss:', score[0])
    print('Test accuracy:', score[1])
    print("Baseline Error: %.2f%%" % (100-score[1]*100))
调用save_features()和create_model()后的结果:
Epoch 95/100
220/220 [==============================] – 0s – loss: 0.0091 – acc: 0.9955 – val_loss: 1.7121 – val_acc: 0.8714
Epoch 96/100
220/220 [==============================] – 0s – loss: 0.0328 – acc: 0.9909 – val_loss: 0.7962 – val_acc: 0.9143
Epoch 97/100
220/220 [==============================] – 0s – loss: 0.1059 – acc: 0.9727 – val_loss: 0.8883 – val_acc: 0.9000
Epoch 98/100
220/220 [==============================] – 0s – loss: 0.0445 – acc: 0.9864 – val_loss: 0.7507 – val_acc: 0.9143
Epoch 99/100
220/220 [==============================] – 0s – loss: 0.0226 – acc: 0.9864 – val_loss: 0.8338 – val_acc: 0.9143
Epoch 100/100
220/220 [==============================] – 0s – loss: 0.0279 – acc: 0.9909 – val_loss: 0.8331 – val_acc: 0.9429
32/70 [============>……………..] – ETA: 0sTest loss: 0.833102767808
Test accuracy: 0.942857142857
Baseline Error: 5.71%

def extract_info(desc, gender, gender_dict):
    doc= nlp(desc)
    indices= [ifor i, xin enumerate(doc)if x.lemma_== gender]
    for indexin indices:
        s= ''
        i= index+ 1
        gender_dict['total']+= 1
        while ((i <len(doc))and
               (doc[i].pos_in filters)):
            s+= doc[i].lemma_+ ' '
            print('s', s)
            i+= 1

        if s != '': 
            gender_dict[s.strip()]+= 1