卷积神经网络数据增强——mnist

from __future__ import print_function
import numpy as np
np.random.seed(1337)  # for reproducibility


from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from keras import backend as K

batch_size = 128 
nb_classes = 10
nb_epoch = 3

# 输入数据的维度
img_rows, img_cols = 28, 28
# 使用的卷积滤波器的数量
nb_filters = 32
# 用于 max pooling 的池化面积
pool_size = (2, 2)
# 卷积核的尺寸
kernel_size = (3, 3)

# the data, shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()

if K.image_dim_ordering() == 'th':
    X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
    X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
    X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

model = Sequential()

model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
                        border_mode='valid',
                        input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

model.summary()

# let's train the model using SGD + momentum (how original).
from keras.optimizers import SGD
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
              optimizer=sgd,
              metrics=['accuracy'])

from keras.preprocessing.image import ImageDataGenerator
data_augmentation = True
if not data_augmentation:
    print('Not using data augmentation.')
    model.fit(X_train, Y_train,
              batch_size=batch_size,
              nb_epoch=nb_epoch,
              validation_data=(X_test, Y_test),
              shuffle=True)
else:
    print('Using real-time data augmentation.')

    # 这将做预处理和实时数据增加
    datagen = ImageDataGenerator(
        featurewise_center=False,  # 在数据集上将输入平均值设置为0
        samplewise_center=False,  # 将每个样本均值设置为0
        featurewise_std_normalization=False,  # 将输入除以数据集的std
        samplewise_std_normalization=False,  # 将每个输入除以其std
        zca_whitening=False,  # 应用ZCA白化
        rotation_range=0,  # 在一个范围下随机旋转图像(degrees, 0 to 180)
        width_shift_range=0.1,  # 水平随机移位图像（总宽度的分数）
        height_shift_range=0.1,  # 随机地垂直移动图像（总高度的分数）
        horizontal_flip=True,  # 随机翻转图像
        vertical_flip=False)  # 随机翻转图像

    # 计算特征方向归一化所需的数量
    # (std, mean, and principal components if ZCA whitening is applied)
    datagen.fit(X_train)

    # fit the model on the batches generated by datagen.flow()
    model.fit_generator(datagen.flow(X_train, Y_train,
                        batch_size=batch_size),
                        samples_per_epoch=X_train.shape[0],
                        nb_epoch=nb_epoch,
                        validation_data=(X_test, Y_test))

https://blog.youkuaiyun.com/jacke121/article/details/79245732Keras ImageDataGenerator参数