Python 在预测过程中，数据规范化在 keras 中是如何工作的？

How does data normalization work in keras during prediction?

提问by Alex Taylor

I see that the imageDataGenerator allows me to specify different styles of data normalization, e.g. featurewise_center, samplewise_center, etc.

我看到 imageDataGenerator 允许我指定不同风格的数据规范化，例如 featurewise_center、samplewise_center 等。

I see from the examples that if I specify one of these options, then I need to call the fit method on the generator in order to allow the generator to compute statistics like the mean image on the generator.

我从示例中看到，如果我指定这些选项之一，那么我需要调用生成器上的 fit 方法，以便允许生成器计算统计数据，例如生成器上的平均图像。

(X_train, y_train), (X_test, y_test) = cifar10.load_data()
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_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),
                samples_per_epoch=len(X_train), nb_epoch=nb_epoch)

My question is, how does prediction work if I have specified data normalization during training? I can't see how in the framework I would even pass knowledge of the training set mean/std deviation along to predict to allow me to normalize my test data myself, but I also don't see in the training code where this information is stored.

我的问题是，如果我在训练期间指定了数据标准化，预测如何工作？我看不出在框架中我什至会传递训练集均值/标准偏差的知识来预测以允许我自己规范化我的测试数据，但我也没有在训练代码中看到这些信息的位置存储。

Are the image statistics needed for normalization stored in the model so that they can be used during prediction?

归一化所需的图像统计信息是否存储在模型中，以便在预测过程中使用它们？

回答by Marcin Mo?ejko

Yes - this is a really huge downside of Keras.ImageDataGeneratorthat you couldn't provide the standarization statistics on your own. But - there is an easy method on how to overcome this issue.

是的 - 这是一个非常大的缺点，Keras.ImageDataGenerator因为您无法自己提供标准化统计数据。但是 - 有一个简单的方法可以解决这个问题。

Assuming that you have a function normalize(x)which is normalizing an image batch(remember that generator is not providing a simple image but an array of images - a batchwith shape (nr_of_examples_in_batch, image_dims ..)you could make your own generator with normalization by using:

假设您有一个normalize(x)对图像批次进行标准化的函数（请记住，生成器不提供简单的图像，而是提供一组图像 -具有形状的批次，(nr_of_examples_in_batch, image_dims ..)您可以使用以下方法制作自己的标准化生成器：

def gen_with_norm(gen, normalize):
    for x, y in gen:
        yield normalize(x), y

Then you might simply use gen_with_norm(datagen.flow, normalize)instead of datagen.flow.

那么你可以简单地使用gen_with_norm(datagen.flow, normalize)而不是datagen.flow.

Moreover - you might recover the meanand stdcomputed by a fitmethod by getting it from appropriate fields in datagen (e.g. datagen.meanand datagen.std).

此外 - 您可以通过从 datagen 中的适当字段（例如和）获取它来恢复mean和std计算的fit方法。datagen.meandatagen.std

回答by Martin Thoma

Use the standardizemethod of the generator for each element. Here is a complete example for CIFAR 10:

standardize对每个元素使用生成器的方法。这是 CIFAR 10 的完整示例：

#!/usr/bin/env python

import keras
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D

# input image dimensions
img_rows, img_cols, img_channels = 32, 32, 3
num_classes = 10

batch_size = 32
epochs = 1

# The data, shuffled and split between train and test sets:
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# Convert class vectors to binary class matrices.
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()

model.add(Conv2D(32, (3, 3), padding='same', activation='relu',
                 input_shape=x_train.shape[1:]))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss='categorical_crossentropy', optimizer='rmsprop',
              metrics=['accuracy'])

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

datagen = ImageDataGenerator(zca_whitening=True)

# Compute principal components required for ZCA
datagen.fit(x_train)

# Apply normalization (ZCA and others)
print(x_test.shape)
for i in range(len(x_test)):
    # this is what you are looking for
    x_test[i] = datagen.standardize(x_test[i])
print(x_test.shape)

# Fit the model on the batches generated by datagen.flow().
model.fit_generator(datagen.flow(x_train, y_train,
                                 batch_size=batch_size),
                    steps_per_epoch=x_train.shape[0] // batch_size,
                    epochs=epochs,
                    validation_data=(x_test, y_test))

回答by Hari

I am using the datagen.fitfunction itself.

我正在使用该datagen.fit功能本身。

from keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(
    featurewise_center=True,
    featurewise_std_normalization=True)
train_datagen.fit(train_data)

test_datagen = ImageDataGenerator(  
    featurewise_center=True, 
    featurewise_std_normalization=True)
test_datagen.fit(train_data)

Ideally with this, test_datagenfitted on training dataset will learn the training datasets statistics. Then it will use these statistics to normalize testing data.

理想情况下， test_datagen安装在训练数据集上将学习训练数据集的统计信息。然后它将使用这些统计数据来规范化测试数据。

回答by Alexander Pacha

I also had the same issue and I solved it using the same functionality, that the ImageDataGeneratorused:

我也遇到了同样的问题，我使用相同的功能解决了它，使用的功能是ImageDataGenerator：

# Load Cifar-10 dataset
(trainX, trainY), (testX, testY) = cifar10.load_data()
generator = ImageDataGenerator(featurewise_center=True, 
                               featurewise_std_normalization=True)

# Calculate statistics on train dataset
generator.fit(trainX)
# Apply featurewise_center to test-data with statistics from train data
testX -= generator.mean
# Apply featurewise_std_normalization to test-data with statistics from train data
testX /= (generator.std + K.epsilon())

# Do your regular fitting
model.fit_generator(..., validation_data=(testX, testY), ...)

Note that this is only possible if you have a reasonable small dataset, like CIFAR-10. Otherwise the solution proposed by Marcinsounds good more reasonable.

请注意，这只有在您有一个合理的小数据集（如 CIFAR-10）时才有可能。否则，Marcin 提出的解决方案听起来更合理。