基于python的人脸识别

# -*- coding: utf-8 -*- """ Created on Tue Apr 10 11:09:54 2018 @author: sunzhijun """ import random import numpy as np from sklearn.cross_validation import train_test_split from keras.preprocessing.image import ImageDataGenerator from keras.models import Sequential from keras.layers import Dense, Dropout, Activation, Flatten from keras.layers import Convolution2D, MaxPooling2D from keras.optimizers import SGD from keras.utils import np_utils from keras.models import load_model from keras import backend as K from loadData import load_dataset, resize_image, IMAGE_SIZE class Dataset: def __init__(self, path_name): # 训练集 self.train_images = None self.train_labels = None # 验证集 self.valid_images = None self.valid_labels = None # 测试集 self.test_images = None self.test_labels = None # 数据集加载路径 self.path_name = path_name # 当前库采用的维度顺序 self.input_shape = None 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') 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 # 加载数据集并按照交叉验证的原则划分数据集并进行相关预处理工作 def load(self, img_rows=IMAGE_SIZE, img_cols=IMAGE_SIZE, img_channels=3, nb_classes=2): # 加载数据集到内存 images, labels = self.loadAllData(self.path_name) print ('images,labels') print (images,labels) train_images, valid_images, train_labels, valid_labels = train_test_split(images, labels, test_size=0.3, random_state=random.randint(0, 100)) _, test_images, _, test_labels = train_test_split(images, labels, test_size=0.5, 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': 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: train_images = train_images.reshape(train_images.shape[0], img_rows, img_cols, img_channels) valid_images = valid_images.reshape(valid_images.shape[0], img_rows, img_cols, img_channels) test_images = test_images.reshape(test_images.shape[0], img_rows, img_cols, img_channels) self.input_shape = (img_rows, img_cols, img_channels) # 输出训练集、验证集、测试集的数量 print(train_images.shape[0], 'train samples') print(valid_images.shape[0], 'valid samples') print(test_images.shape[0], 'test samples') # 我们的模型使用categorical_crossentropy作为损失函数，因此需要根据类别数量nb_classes将 # 类别标签进行one-hot编码使其向量化，在这里我们的类别只有两种，经过转化后标签数据变为二维 train_labels = np_utils.to_categorical(train_labels, nb_classes) valid_labels = np_utils.to_categorical(valid_labels, nb_classes) test_labels = np_utils.to_categorical(test_labels, nb_classes) # 像素数据浮点化以便归一化 train_images = train_images.astype('float32') valid_images = valid_images.astype('float32') test_images = test_images.astype('float32') # 将其归一化,图像的各像素值归一化到0~1区间 train_images /= 255 valid_images /= 255 test_images /= 255 self.train_images = train_images self.valid_images = valid_images self.test_images = test_images self.train_labels = train_labels self.valid_labels = valid_labels self.test_labels = test_labels # CNN网络模型类 class Model: def __init__(self): self.model = None def evaluate(self, dataset): score = self.model.evaluate(dataset.test_images, dataset.test_labels, verbose=1) print("%s: %.2f%%" % (self.model.metrics_names[1], score[1] * 100)) MODEL_PATH = './face.model.h5' def save_model(self, file_path=MODEL_PATH): self.model.save(file_path) def load_model(self, file_path=MODEL_PATH): self.model = load_model(file_path) # 建立模型 def build_model(self, dataset, nb_classes=2): # 构建一个空的网络模型，它是一个线性堆叠模型，各神经网络层会被顺序添加，专业名称为序贯模型或线性堆叠模型 self.model = Sequential() # 以下代码将顺序添加CNN网络需要的各层，一个add就是一个网络层 self.model.add(Convolution2D(32, 3, 3, border_mode='same', input_shape=dataset.input_shape)) # 1 2维卷积层 self.model.add(Activation('relu')) # 2 激活函数层 self.model.add(Convolution2D(32, 3, 3)) # 3 2维卷积层 self.model.add(Activation('relu')) # 4 激活函数层 self.model.add(MaxPooling2D(pool_size=(2, 2))) # 5 池化层 self.model.add(Dropout(0.25)) # 6 Dropout层 self.model.add(Convolution2D(64, 3, 3, border_mode='same')) # 7 2维卷积层 self.model.add(Activation('relu')) # 8 激活函数层 self.model.add(Convolution2D(64, 3, 3)) # 9 2维卷积层 self.model.add(Activation('relu')) # 10 激活函数层 self.model.add(MaxPooling2D(pool_size=(2, 2))) # 11 池化层 self.model.add(Dropout(0.25)) # 12 Dropout层 self.model.add(Flatten()) # 13 Flatten层 self.model.add(Dense(512)) # 14 Dense层,又被称作全连接层 self.model.add(Activation('relu')) # 15 激活函数层 self.model.add(Dropout(0.5)) # 16 Dropout层 self.model.add(Dense(nb_classes)) # 17 Dense层 self.model.add(Activation('softmax')) # 18 分类层，输出最终结果 # 输出模型概况 self.model.summary() # 训练模型 def train(self, dataset, batch_size=20, nb_epoch=8, data_augmentation=True): sgd = SGD(lr=0.01, 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 self.model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy']) # 完成实际的模型配置工作 # 不使用数据提升，所谓的提升就是从我们提供的训练数据中利用旋转、翻转、加噪声等方法创造新的 # 训练数据，有意识的提升训练数据规模，增加模型训练量 if not data_augmentation: self.model.fit(dataset.train_images, dataset.train_labels, batch_size=batch_size, nb_epoch=nb_epoch, validation_data=(dataset.valid_images, dataset.