# 加载haar人脸识别分类器classfier = cv2.CascadeClassifier("./haarcascade_frontalface_alt2.xml")# 视频来源，这里选择使用摄像头cap = cv2.VideoCapture(camera_idx)#循环读取到每一帧while cap.isOpened():    ok, frame = cap.read()    if not ok:        break 

# 将当前桢图像转换成灰度图像，便于分类器识别grey = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)#通过detectMultiScale函数对人脸进行识别 faceRects = classfier.detectMultiScale(grey, scaleFactor=1.2, minNeighbors=3, minSize=(32, 32))# 将当前帧保存为图片img_name = '%s/%d.jpg' % (path_name, num)cv2.imwrite(img_name, image)

#这是后续demo2版本指定路径的方法，不再自己去定义每个人的名称了，统一划分一个userX类名def create_new_dataset(path_name):    i = 1    while True:        new_path = os.path.join(path_name, f'user{i}')        if not os.path.exists(new_path):            os.makedirs(new_path)            break        i += 1    return new_path

def read_path(path_name):    for dir_item in os.listdir(path_name):        # 从初始路径开始叠加，合并成可识别的操作路径        full_path = os.path.abspath(os.path.join(path_name, dir_item))
        if os.path.isdir(full_path):  # 如果是文件夹，继续递归调用            read_path(full_path)        else:  # 文件            if dir_item.endswith('.jpg'):                image = cv2.imread(full_path)                image = resize_image(image, IMAGE_SIZE, IMAGE_SIZE)
                images.append(image)                labels.append(path_name)
    return images, labels

# 将图片大小设置为64*64IMAGE_SIZE = 64
# 按照指定图像大小调整尺寸def resize_image(image, height=IMAGE_SIZE, width=IMAGE_SIZE):    top, bottom, left, right = (0, 0, 0, 0)
    # 获取图像尺寸    h, w, _ = image.shape
    # 对于长宽不相等的图片，找到最长的一边    longest_edge = max(h, w)
    # 计算短边需要增加多少像素宽度使其与长边等长    if h < longest_edge:        dh = longest_edge - h        top = dh // 2        bottom = dh - top    elif w < longest_edge:        dw = longest_edge - w        left = dw // 2        right = dw - left    else:        pass

class CNN(tf.keras.Model):    # 模型初始化    def __init__(self):        super().__init__()        self.conv1 = tf.keras.layers.Conv2D(            filters=32,  # 卷积层神经元（卷积核）数目            kernel_size=[3, 3],  # 感受野大小            padding='same',  # padding策略（vaild 或 same）            activation=tf.nn.relu,  # 激活函数        )        self.conv2 = tf.keras.layers.Conv2D(filters=32, kernel_size=[3, 3], activation=tf.nn.relu)        self.pool1 = tf.keras.layers.MaxPool2D(pool_size=[2, 2])        self.dropout1 = tf.keras.layers.Dropout(rate=0.5)
        self.conv3 = tf.keras.layers.Conv2D(filters=64, kernel_size=[3, 3], activation=tf.nn.relu, padding='same')        self.conv4 = tf.keras.layers.Conv2D(filters=64, kernel_size=[3, 3], activation=tf.nn.relu)        self.pool2 = tf.keras.layers.MaxPool2D(pool_size=[2, 2])        self.dropout2 = tf.keras.layers.Dropout(rate=0.5)
        self.flaten = tf.keras.layers.Flatten()        self.dense1 = tf.keras.layers.Dense(units=512, activation=tf.nn.relu)        self.dropout3 = tf.keras.layers.Dropout(rate=0.25)        self.dense2 = tf.keras.layers.Dense(units=10)


    # 模型输出    def call(self, inputs):        x = self.conv1(inputs)        x = self.conv2(x)        x = self.pool1(x)        # x = self.dropout1(x)
        x = self.conv3(x)        x = self.conv4(x)        x = self.pool2(x)        # x = self.dropout2(x)
        x = self.flaten(x)        x = self.dense1(x)        # x = self.dropout3(x)        x = self.dense2(x)        output = tf.nn.softmax(x)    return output

adam = tf.keras.optimizers.Adam(learning_rate=learning_rate)  # 选择优化器
sgd = SGD(learning_rate=learning_rate, decay=1e-6,          momentum=0.9, nesterov=True)  # 采用SGD+momentum的优化器进行训练，首先生成一个优化器对象
train_ds=tf.data.Dataset.from_tensor_slices((dataset.train_images,dataset.train_labels)).shuffle(300).batch(    batch)test_ds = tf.data.Dataset.from_tensor_slices((dataset.test_images,dataset.test_labels)).shuffle(300).batch(    batch)
model.compile(optimizer=adam, loss='sparse_categorical_crossentropy', metrics=['acc'])

frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)  pilimg = Image.fromarray(frame)draw = ImageDraw.Draw(pilimg)  font = ImageFont.truetype(20, encoding="utf-8")  face_probe = model.face_predict(image)  # 获得预测值max_prob = max(face_probe)              # 获取最大的预测率max_label_index = np.argmax(face_probe)  # 获取最大预测率对应的标签labels = ['user1', 'user2','user3']# 判断最大预测率是否超过阈值if max_prob >= 0.75:    # 显示最大预测率对应的标签    label = labels[max_label_index] # 获取最大预测率对应的标签    draw.text((x + 25, y - 45), '{}:{:.2%}'.format(label, max_prob), (255, 0, 0), font=font)    frame = cv2.cvtColor(np.array(pilimg), cv2.COLOR_RGB2BGR)else:    # 显示未识别    draw.text((x + 25, y - 45), '未识别', (255, 0, 0), font=font)    frame = cv2.cvtColor(np.array(pilimg), cv2.COLOR_RGB2BGR)

root.after(1, video_loop)# 这句的意思是一秒以后执行video_loop函数# 因为这一句是写在video_loop函数中的所以每过一秒函数执行一次。