VGG16_KERAS

参照keras官方文档，将数据集通过url下载的方式改为本地

from __future__ import print_function
import keras
import os
import sys
import matplotlib.pyplot as plt
# from keras.datasets import cifar10  #改成自己输入数据
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D, BatchNormalization
from keras import optimizers
import numpy as np
from keras.layers.core import Lambda
from keras import backend as K
from keras import regularizers
# from keras.utils import data_utils

from six.moves import cPickle

def load_data():
    """Loads CIFAR10 dataset.

    # Returns
        Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
    """
    # dirname = 'cifar-10-batches-py'
    # origin = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
    # path = data_utils.get_file(dirname, origin=origin, untar=True)
    path = 'D:\\Pycharm_proj\\cifar-vgg-master\\cifar-10-batches-py'
    #从上述URL中下载cifar数据集，将其解压放入工程文件
    num_train_samples = 50000
    #将数据集划分为训练集和测试集
    x_train = np.empty((num_train_samples, 3, 32, 32), dtype='uint8')
    y_train = np.empty((num_train_samples,), dtype='uint8')

    for i in range(1, 6):
        fpath = os.path.join(path, 'data_batch_' + str(i))
        (x_train[(i - 1) * 10000: i * 10000, :, :, :],
         y_train[(i - 1) * 10000: i * 10000]) = load_batch(fpath)

    fpath = os.path.join(path, 'test_batch')
    x_test, y_test = load_batch(fpath)

    y_train = np.reshape(y_train, (len(y_train), 1))
    y_test = np.reshape(y_test, (len(y_test), 1))

    if K.image_data_format() == 'channels_last':
        x_train = x_train.transpose(0, 2, 3, 1)
        x_test = x_test.transpose(0, 2, 3, 1)
    #展示数据
    plt.figure()
    for i in range(1,37):
        pic = x_test[10*i].reshape(32, 32, 3)
        label = y_test[10*i]
        plt.subplot(6, 6, i)
        plt.imshow(pic)
        plt.title(label)
    plt.show()
    return (x_train, y_train), (x_test, y_test)

#从数据集文件中读取数据文件
def load_batch(fpath, label_key='labels'):
    """Internal utility for parsing CIFAR data.

    # Arguments
        fpath: path the file to parse.
        label_key: key for label data in the retrieve
            dictionary.

    # Returns
        A tuple `(data, labels)`.
    """
    with open(fpath, 'rb') as f:
        if sys.version_info < (3,):
            d = cPickle.load(f)
        else:
            d = cPickle.load(f, encoding='bytes')
            # decode utf8
            d_decoded = {}
            for k, v in d.items():
                d_decoded[k.decode('utf8')] = v
            d = d_decoded
    data = d['data']
    labels = d[label_key]

    data = data.reshape(data.shape[0], 3, 32, 32)
    return data, labels

#定义用于训练VGG16的模型
class cifar10vgg:
    def __init__(self,train=True):
        self.num_classes = 10
        self.weight_decay = 0.0005
        self.x_shape = [32,32,3]

        self.model = self.build_model()
        if train:
            self.model = self.train(self.model)
        else:
            self.model.load_weights('cifar10vgg.h5')


    def build_model(self):
        # Build the network of vgg for 10 classes with massive dropout and weight decay as described in the paper.

        model = Sequential()
        weight_decay = self.weight_decay
        #参照论文中的网络结构搭建
        model.add(Conv2D(64, (3, 3), padding='same',
                         input_shape=self.x_shape,kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())
        model.add(Dropout(0.3))

        model.add(Conv2D(64, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())

        model.add(MaxPooling2D(pool_size=(2, 2)))

        model.add(Conv2D(128, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())
        model.add(Dropout(0.4))

        model.add(Conv2D(128, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())

        model.add(MaxPooling2D(pool_size=(2, 2)))

        model.add(Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())
        model.add(Dropout(0.4))

        model.add(Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())
        model.add(Dropout(0.4))

        model.add(Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())

        model.add(MaxPooling2D(pool_size=(2, 2)))


        model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())
        model.add(Dropout(0.4))

        model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())
        model.add(Dropout(0.4))

        model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())

        model.add(MaxPooling2D(pool_size=(2, 2)))


        model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())
        model.add(Dropout(0.4))

        model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())
        model.add(Dropout(0.4))

        model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())

        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Dropout(0.5))

        model.add(Flatten())
        model.add(Dense(512,kernel_regularizer=regularizers.l2(weight_decay)))
        model.add(Activation('relu'))
        model.add(BatchNormalization())

        model.add(Dropout(0.5))
        model.add(Dense(self.num_classes))
        model.add(Activation('softmax'))
        return model

    #将数据归一化
    def normalize(self,X_train,X_test):
        #this function normalize inputs for zero mean and unit variance
        # it is used when training a model.
        # Input: training set and test set
        # Output: normalized training set and test set according to the trianing set statistics.
        mean = np.mean(X_train,axis=(0,1,2,3))
        std = np.std(X_train, axis=(0, 1, 2, 3))
        X_train = (X_train-mean)/(std+1e-7)
        X_test = (X_test-mean)/(std+1e-7)
        return X_train, X_test

    def normalize_production(self,x):
        #this function is used to normalize instances in production according to saved training set statistics
        # Input: X - a training set
        # Output X - a normalized training set according to normalization constants.

        #these values produced during first training and are general for the standard cifar10 training set normalization
        mean = 120.707
        std = 64.15
        return (x-mean)/(std+1e-7)

    def predict(self,x,normalize=True,batch_size=50):
        if normalize:
            x = self.normalize_production(x)
        return self.model.predict(x,batch_size)

    def train(self,model):

        #训练参数
        batch_size = 128
        maxepoches = 250
        learning_rate = 0.1
        lr_decay = 1e-6
        lr_drop = 20
        # The data, shuffled and split between train and test sets:
        (x_train, y_train), (x_test, y_test) = load_data()
        x_train = x_train.astype('float32')
        x_test = x_test.astype('float32')
        x_train, x_test = self.normalize(x_train, x_test)

        y_train = keras.utils.to_categorical(y_train, self.num_classes)
        y_test = keras.utils.to_categorical(y_test, self.num_classes)

        def lr_scheduler(epoch):
            return learning_rate * (0.5 ** (epoch // lr_drop))
        reduce_lr = keras.callbacks.LearningRateScheduler(lr_scheduler)

        #data augmentation
        datagen = ImageDataGenerator(
            featurewise_center=False,  # set input mean to 0 over the dataset
            samplewise_center=False,  # set each sample mean to 0
            featurewise_std_normalization=False,  # divide inputs by std of the dataset
            samplewise_std_normalization=False,  # divide each input by its std
            zca_whitening=False,  # apply ZCA whitening
            rotation_range=15,  # randomly rotate images in the range (degrees, 0 to 180)
            width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
            height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
            horizontal_flip=True,  # randomly flip images
            vertical_flip=False)  # randomly flip images
        # (std, mean, and principal components if ZCA whitening is applied).
        datagen.fit(x_train)



        #optimization details
        sgd = optimizers.SGD(lr=learning_rate, decay=lr_decay, momentum=0.9, nesterov=True)
        model.compile(loss='categorical_crossentropy', optimizer=sgd,metrics=['accuracy'])


        # training process in a for loop with learning rate drop every 25 epoches.

        historytemp = model.fit_generator(datagen.flow(x_train, y_train,
                                         batch_size=batch_size),
                            steps_per_epoch=x_train.shape[0] // batch_size,
                            epochs=maxepoches,
                            validation_data=(x_test, y_test), callbacks=[reduce_lr], verbose=2)
        model.save_weights('cifar10vgg.h5') #保存模型
        return model

if __name__ == '__main__':


    (x_train,  y_train),(x_test, y_test) = load_data()
    x_train = x_train.astype('float32')
    x_test = x_test.astype('float32')
    y_train = keras.utils.to_categorical(y_train, 10)
    y_test = keras.utils.to_categorical(y_test, 10)

    model = cifar10vgg()

    predicted_x = model.predict(x_test)
    residuals = np.argmax(predicted_x, 1) != np.argmax(y_test, 1)

    loss = sum(residuals)/len(residuals)
    print("the validation 0/1 loss is: ", loss)