keras 中提供图片生成器 ImageDataGenerator, 通过设定不同的参数，来生成更多的数据从而达到小样本训练优质模型的能力。

from keras.preprocessing.image import ImageDataGenerator

datagen = ImageDataGenerator(
        rotation_range=40,                                #  旋转范围
        width_shift_range=0.2,                          #  宽度调整范围
        height_shift_range=0.2,                         #  高度调整范围
        rescale=1./255,                                      #  尺度调整范围
        shear_range=0.2,                                  #  弯曲调整范围
        zoom_range=0.2,                                  #  缩放调整范围
        horizontal_flip=True,                              #  水平调整范围
        brightness_range=0.3,                           #  亮度调整范围
        featurewise_center=True,                     #  是否特征居中
        featurewise_std_normalization=True,   #  特征是否归一化
        zca_whitening=True,                             #  是否使用 ZCA白化
        fill_mode='nearest')                               #  填充模式(图片大小不够时)

使用方法

1. 数据对象

对象列表直接传入到 fit 函数中进行 ZCA 等预处理，然后调用 flow 函数来生成样本

(x_train, y_train), (x_test, y_test) = cifar10.load_data()
y_train = np_utils.to_categorical(y_train, num_classes)
y_test = np_utils.to_categorical(y_test, num_classes)

datagen = ImageDataGenerator(
    featurewise_center=True,
    featurewise_std_normalization=True,
    rotation_range=20,
    width_shift_range=0.2,
    height_shift_range=0.2,
    horizontal_flip=True)

# compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied)
datagen.fit(x_train)

# fits the model on batches with real-time data augmentation:
model.fit_generator(datagen.flow(x_train, y_train, batch_size=32),
                    steps_per_epoch=len(x_train) / 32, epochs=epochs)

# here's a more "manual" example
for e in range(epochs):
    print('Epoch', e)
    batches = 0
    for x_batch, y_batch in datagen.flow(x_train, y_train, batch_size=32):
        model.fit(x_batch, y_batch)
        batches += 1
        if batches >= len(x_train) / 32:
            # we need to break the loop by hand because
            # the generator loops indefinitely
            break

2. 文件夹

同对象操作类似，这里只是将 flow 函数转化为 flow_from_directory 函数来完成相应的样本生成。

train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        'data/train',
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        'data/validation',
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

model.fit_generator(
        train_generator,
        steps_per_epoch=2000,
        epochs=50,
        validation_data=validation_generator,
        validation_steps=800)

参考

Building powerful image classification models using very little data
Image Preprocessing