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

- 日理万妓 2023-09-30 18:26 50阅读 0赞

> **需要源码和数据集请点赞关注收藏后评论区留言私信~~~**

下面利用tensorflow平台进行人脸识别实战，使用的是Olivetti Faces人脸图像 部分数据集展示如下

![34de97b1459747a781ae0fdb2343a9e5.png][]

程序训练过程如下

![e547200fc08e44289db6427fb32f1b7e.png][]

接下来训练CNN模型 可以看到训练进度和损失值变化

![fb86dd67c938420da1b681106a185154.png][]

接下来展示人脸识别结果

![07ab1e314366475faf82c809567d4ff2.png][]

程序会根据一张图片自动去图片集中寻找相似的人脸 如上图所示

部分代码如下 **需要全部源码和数据集请点赞关注收藏后评论区留言私信~~~**

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()

**创作不易 觉得有帮助请点赞关注收藏~~~**

[34de97b1459747a781ae0fdb2343a9e5.png]: https://img-blog.csdnimg.cn/34de97b1459747a781ae0fdb2343a9e5.png
[e547200fc08e44289db6427fb32f1b7e.png]: https://img-blog.csdnimg.cn/e547200fc08e44289db6427fb32f1b7e.png
[fb86dd67c938420da1b681106a185154.png]: https://img-blog.csdnimg.cn/fb86dd67c938420da1b681106a185154.png
[07ab1e314366475faf82c809567d4ff2.png]: https://img-blog.csdnimg.cn/07ab1e314366475faf82c809567d4ff2.png