【Tool】Keras 基础学习 III ImageDataGe

2018-09-11 本文已影响6588人 ItchyHiker

图片读取ImageDataGenerator()

ImageDataGenerator()是keras.preprocessing.image模块中的图片生成器，同时也可以在batch中对数据进行增强，扩充数据集大小，增强模型的泛化能力。比如进行旋转，变形，归一化等等。

keras.preprocessing.image.ImageDataGenerator(featurewise_center=False, samplewise_center=False, featurewise_std_normalization=False, samplewise_std_normalization=False, zca_whitening=False, zca_epsilon=1e-06, rotation_range=0.0, width_shift_range=0.0, height_shift_range=0.0, brightness_range=None, shear_range=0.0, zoom_range=0.0, channel_shift_range=0.0, fill_mode='nearest', cval=0.0, horizontal_flip=False, vertical_flip=False, rescale=None, preprocessing_function=None, data_format=None, validation_split=0.0)

参数:

featurewise_center: Boolean. 对输入的图片每个通道减去每个通道对应均值。
samplewise_center: Boolan. 每张图片减去样本均值, 使得每个样本均值为0。
featurewise_std_normalization(): Boolean()
samplewise_std_normalization(): Boolean()
zca_epsilon(): Default 12-6
zca_whitening: Boolean. 去除样本之间的相关性
rotation_range(): 旋转范围
width_shift_range(): 水平平移范围
height_shift_range(): 垂直平移范围
shear_range(): float, 透视变换的范围
zoom_range(): 缩放范围
fill_mode: 填充模式, constant, nearest, reflect
cval: fill_mode == 'constant'的时候填充值
horizontal_flip(): 水平反转
vertical_flip(): 垂直翻转
preprocessing_function(): user提供的处理函数
data_format(): channels_first或者channels_last
validation_split(): 多少数据用于验证集

方法:

apply_transform(x, transform_parameters):根据参数对x进行变换
fit(x, augment=False, rounds=1, seed=None): 将生成器用于数据x,从数据x中获得样本的统计参数, 只有featurewise_center, featurewise_std_normalization或者zca_whitening为True才需要
flow(x, y=None, batch_size=32, shuffle=True, sample_weight=None, seed=None, save_to_dir=None, save_prefix='', save_format='png', subset=None) ):按batch_size大小从x,y生成增强数据
flow_from_directory()从路径生成增强数据,和flow方法相比最大的优点在于不用一次将所有的数据读入内存当中,这样减小内存压力，这样不会发生OOM，血的教训。
get_random_transform(img_shape, seed=None): 返回包含随机图像变换参数的字典
random_transform(x, seed=None): 进行随机图像变换, 通过设置seed可以达到同步变换。
standardize(x): 对x进行归一化

实例：
mnist分类数据增强

 from keras.preprocessing.image import ImageDataGenerator
 from keras.datasets import mnist
 from keras.datasets import cifar10
 from keras.utils import np_utils
 import numpy as np
 import matplotlib.pyplot as plt
 num_classes = 10
 (x_train, y_train), (x_test, y_test) = mnist.load_data()
 x_train = np.expand_dims(x_train, axis = 3)
 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)
 
 data_iter = datagen.flow(x_train, y_train, batch_size=8)
 
while True:
     x_batch, y_batch = data_iter.next()
     for i in range(8):
         print(i//4)
         plt.subplot(2,4,i+1)
         plt.imshow(x_batch[i].reshape(28,28), cmap='gray')
     plt.show()

5FGhke.png

portrait分割数据增强,需要对image和mask同步处理:
featurewise结果：

from keras.preprocessing.image import ImageDataGenerator
from keras.datasets import mnist
from keras.datasets import cifar10
from keras.utils import np_utils
import numpy as np
import matplotlib.pyplot as plt
num_classes = 10
seed = 1
# featurewise需要数据集的统计信息，因此需要先读入一个x_train，用于对增强图像的均值和方差处理。
x_train = np.load('images-224.npy')
imagegen = ImageDataGenerator(
    featurewise_center=True,
    featurewise_std_normalization=True,
    rotation_range=20,
    width_shift_range=0.2,
    height_shift_range=0.2,
    horizontal_flip=True)

maskgen = ImageDataGenerator(
     rescale = 1./255,
     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)
imagegen.fit(x_train)
image_iter = imagegen.flow_from_directory('../data/images',target_size=(224,224), class_mode=None, batch_size=8, seed=seed)
mask_iter = maskgen.flow_from_directory('../data/masks', color_mode='rgb', target_size=(224,224), class_mode=None, batch_size=8, seed=seed)
data_iter = zip(image_iter, mask_iter)
while True:
    for x_batch, y_batch in data_iter:
        for i in range(8):
            print(i//4)
            plt.subplot(2,8,i+1)
            plt.imshow(x_batch[i].reshape(224,224,3))
            plt.subplot(2,8,8+i+1)
            plt.imshow(y_batch[i].reshape(224,224, 3), cmap='gray')
        plt.show()

5FGPpR.png

samplewise结果:

from keras.preprocessing.image import ImageDataGenerator
from keras.datasets import mnist
from keras.datasets import cifar10
from keras.utils import np_utils
import numpy as np
import matplotlib.pyplot as plt
num_classes = 10
seed = 1
imagegen = ImageDataGenerator(
    samplewise_center=True,
    samplewise_std_normalization=True,
    rotation_range=20,
    width_shift_range=0.2,
    height_shift_range=0.2,
    horizontal_flip=True)
maskgen = ImageDataGenerator(
     rescale = 1./255,
     rotation_range=20,
     width_shift_range=0.2,
     height_shift_range=0.2,
     horizontal_flip=True)
image_iter = imagegen.flow_from_directory('../data/images',target_size=(224,224), class_mode=None, batch_size=8, seed=seed)
mask_iter = maskgen.flow_from_directory('../data/masks', color_mode='rgb', target_size=(224,224), class_mode=None, batch_size=8, seed=seed)
data_iter = zip(image_iter, mask_iter)
while True:
    for x_batch, y_batch in data_iter:
        for i in range(8):
            print(i//4)
            plt.subplot(2,8,i+1)
            plt.imshow(x_batch[i].reshape(224,224,3))
            plt.subplot(2,8,8+i+1)
            plt.imshow(y_batch[i].reshape(224,224, 3), cmap='gray')
        plt.show()

5FGa1r.png
注意:flow_from_directory需要提供的路径下面需要有子目录,因此我的目录形式如下:

data/
...images/
........./images
...masks/
........./masks

只有这样提供才能保证正确读取图片，没有子目录会检测不到图片。
此外正如github上的issue:https://github.com/keras-team/keras/pull/3052/commits/81fb0fa7c332b1b9d2669d68797fda041de17088

for subdir in sorted(os.listdir(directory)):
                if os.path.isdir(os.path.join(directory, subdir)):
                    classes.append(subdir)

flow_from_directory()会从路径推测label, 在进行映射之前，会先对路径进行排序，具体顺序是alphanumerically，也是os.listdir()对子目录排序的结果。这样你才知道具体来说哪个路径的类对应哪个label。
原图:

5FGcqY.png

【Tool】Keras 基础学习 III ImageDataGe

图片读取ImageDataGenerator()

猜你喜欢

热点阅读