【Python深度学习】Tensorflow+CNN进行人脸识别实战（附源码和数据集）

from os import listdir
import numpy as np
from PIL import Image
import cv2
from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras.layers import Dense, Activation, Convolution2D, MaxPooling2D, Flatten
from sklearn.model_selection import train_test_split
from tensorflow.python.keras.utils import np_utils
# 读取人脸图片数据
def img2vector(fileNamestr):
    # 创建向量
    returnVect = np.zeros((57,47))    
    image = Image.open(fileNamestr).convert('L')    
    img = np.asarray(image).reshape(57,47)    
    return img
# 制作人脸数据集
def GetDataset(imgDataDir):   
    print('| Step1 |: Get dataset...')
    imgDataDir='faces_4/'
    FileDir = listdir(imgDataDir)
    m = len(FileDir)
    imgarray=[]
    hwLabels=[]
    hwdata=[]
    # 逐个读取图片文件
    for i in range(m):
        # 提取子目录
        className=i
        subdirName='faces_4/'+str(FileDir[i])+'/'
        fileNames = listdir(subdirName)                
        lenFiles=len(fileNames)
        # 提取文件名
        for j in range(lenFiles): 
            fileNamestr = subdirName+fileNames[j]
            hwLabels.append(className)    
            imgarray=img2vector(fileNamestr)
            hwdata.append(imgarray)
    hwdata = np.array(hwdata)
    return hwdata,hwLabels,6
# CNN模型类
class MyCNN(object):
    FILE_PATH = "face_recognition.h5"  # 模型存储/读取目录
    picHeight = 57  # 模型的人脸图片长47，宽57
    picWidth = 47  
    def __init__(self):
        self.model = None
    # 获取训练数据集
    def read_trainData(self, dataset):        
        self.dataset = dataset
    # 建立Sequential模型，并赋予参数
    def build_model(self):
        print('| Step2 |: Init CNN model...')
        self.model = Sequential()
        print('self.dataset.X_train.shape[1:]',self.dataset.X_train.shape[1:])
        self.model.add( Convolution2D( filters=32,
                                      kernel_size=(5, 5),
                                      padding='same',
                                      #dim_ordering='th',
                                      input_shape=self.dataset.X_train.shape[1:]))
        self.model.add(Activation('relu'))
        self.model.add( MaxPooling2D(pool_size=(2, 2),
                                     strides=(2, 2),
                                     padding='same' ) )
        self.model.add(Convolution2D(filters=64, 
                                     kernel_size=(5, 5), 
                                     padding='same') )
        self.model.add(Activation('relu'))
        self.model.add(MaxPooling2D(pool_size=(2, 2), 
                                    strides=(2, 2), 
                                    padding='same') )
        self.model.add(Flatten())
        self.model.add(Dense(512))
        self.model.add(Activation('relu'))
        self.model.add(Dense(self.dataset.num_classes))
        self.model.add(Activation('softmax'))
        self.model.summary()
    # 模型训练
    def train_model(self):
        print('| Step3 |: Train CNN model...')
        self.model.compile( optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
        # epochs：训练代次、batch_size：每次训练样本数
        self.model.fit(self.dataset.X_train, self.dataset.Y_train, epochs=10, batch_size=20)
    def evaluate_model(self):
        loss, accuracy = self.model.evaluate(self.dataset.X_test, self.dataset.Y_test)
        print('| Step4 |: Evaluate performance...')
        print('===================================')        
        print('Loss   Value   is :', loss)
        print('Accuracy Value is :', accuracy)
    def save(self, file_path=FILE_PATH):        
        print('| Step5 |: Save model...')
        self.model.save(file_path)
        print('Model ',file_path,'is succeesfuly saved.')
# 建立一个用于存储和格式化读取训练数据的类
class DataSet(object):
    def __init__(self, path):
        self.num_classes = None
        self.X_train = None
        self.X_test = None
        self.Y_train = None
        self.Y_test = None
        self.picWidth = 47
        self.picHeight = 57        
        self.makeDataSet(path)  # 在这个类初始化的过程中读取path下的训练数据
    def makeDataSet(self, path):
        # 根据指定路径读取出图片、标签和类别数
        imgs, labels, clasNum = GetDataset(path)
        # 将数据集打乱随机分组
        X_train, X_test, y_train, y_test = train_test_split(imgs, labels, test_size=0.2,random_state=1)
        # 重新格式化和标准化
        X_train = X_train.reshape(X_train.shape[0], 1, self.picHeight, self.picWidth) / 255.0
        X_test = X_test.reshape(X_test.shape[0], 1, self.picHeight, self.picWidth) / 255.0
        X_train = X_train.astype('float32')
        X_test = X_test.astype('float32')
        # 将labels转成 binary class matrices
        Y_train = np_utils.to_categorical(y_train, num_classes=clasNum)
        Y_test = np_utils.to_categorical(y_test, num_classes=clasNum)
        # 将格式化后的数据赋值给类的属性上
        self.X_train = X_train
        self.X_test = X_test
        self.Y_train = Y_train
        self.Y_test = Y_test
        self.num_classes = clasNum
# 人脸图片目录
dataset = DataSet('faces_4/')
model = MyCNN()
model.read_trainData(dataset)
model.build_model()
model.train_model()
model.evaluate_model()
model.save()