TensorFlow实现人脸识别(4)--------对人脸样本进行训练，保存人脸识别模型

经过前面几章的介绍，我们以及可以得到处理好的训练样本图像，在本节中将对这些图像进行训练。主要利用到的是keras。

一、构建Dataset类

1.1 init 完成初始化工作

def __init__(self,path_name):
        self.train_img    = None
        self.train_labels = None
        self.valid_img    = None
        self.valid_labels = None
        self.test_img     = None
        self.test_labels  = None
        self.path_name    = path_name
        self.input_shape  = None

1.2 loadAllData(self,path_name):
加载正样本以及负样本数据 并且将数据images和labels拼接在一起

def loadAllData(self,path_name):
	positive_data_images,positive_data_labels=load_dataset(path_name,'traindata')
	negative_data_images,negative_data_labels=load_dataset(path_name,'testdata')
	#数组拼接
	images =np.concatenate((positive_data_images, negative_data_images),axis=0) 
	labels=np.concatenate((positive_data_labels, negative_data_labels),axis=0)
	return images,labels

1.3 加载数据集

def load(self,img_rows=IMAGE_SIZE,img_cols=IMAGE_SIZE,
		img_channels=3,nb_classes=2):
        images,labels = self.loadAllData(self.path_name) 
        #images为四维数组，尺寸为(图片数量总(包括test+train)*IMAGE_SIZE*IMAGE_SIZE*3)
        #随机划分训练集和验证集
        train_images,valid_images,train_labels,valid_labels = train_test_split(images,  labels,random_state = random.randint(0,100))
        _,            test_images,_,            test_labels = train_test_split(images, labels,test_size = 0.3,random_state = random.randint(0,100))
        
        # 当前的维度顺序如果为'th'，则输入图片数据时的顺序为：channels,rows,cols，
        # 否则:rows,cols,channels
        # 这部分代码就是根据keras库要求的维度顺序重组训练数据集
        if K.image_dim_ordering() == 'th':  #theano的格式
            train_images     = train_images.reshape(train_images.shape[0], 
					            img_channels, img_rows, img_cols)
            valid_images     = valid_images.reshape(valid_images.shape[0], 
					            img_channels, img_rows, img_cols)
            test_images      = test_images.reshape( test_images.shape[0], 
					             img_channels, img_rows, img_cols)
            self.input_shape = (img_channels, img_rows, img_cols)
        else:  # tensorflow格式
            train_images     = train_images.reshape(train_images.shape[0], 
					            img_rows, img_cols, img_channels)
            valid