Keras学习---数据预处理篇

1. 数据预处理是必要的，这里以最简单的MNIST dataset的输入数据预处理为例。 

    A. 设置随机种子 
    np.random.seed(1337)  # for reproducibility

    B. 输入数据维度规格化，这里每个样本只是size为784的一维数组。
    X_train = X_train.reshape(60000, 784)

   将类别标签转换为one-hot encoding， 这一步对多分类是必须的
   one_hot_labels  = keras.utils.np_utils.to_categorical(labels, num_classes=10)

   train sets 和test sets可能需要shuffle处理？

   C. 输入数据类型转换，数值归一化

   X_train = X_train.astype('float32')
   X_train /= 255

   MNIST dataset的MLP完整代码如下：

'''Trains a simple deep NN on the MNIST dataset.



Gets to 98.40% test accuracy after 20 epochs

(there is *a lot* of margin for parameter tuning).

2 seconds per epoch on a K520 GPU.

'''



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.core import Dense, Dropout, Activation

from keras.optimizers import SGD, Adam, RMSprop

from keras.utils import np_utils





batch_size = 128

nb_classes = 10

nb_epoch = 20



# the data, shuffled and split between train and test sets

(X_train, y_train), (X_test, y_test) = mnist.load_data()



X_train = X_train.reshape(60000, 784)

X_test = X_test.reshape(10000, 784)

X_train = X_train.astype('float32')

X_test = X_test.astype('float32')

X_train /= 255

X_test /= 255

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(Dense(512, input_shape=(784,)))

model.add(Activation('relu'))

model.add(Dropout(0.2))

model.add(Dense(512))

model.add(Activation('relu'))

model.add(Dropout(0.2))

model.add(Dense(10))

model.add(Activation('softmax'))



model.summary()



#model.compile(loss='categorical_crossentropy',

#              optimizer=RMSprop(),

#              metrics=['accuracy'])

model.compile(loss='categorical_crossentropy',

              optimizer=SGD(lr=0.02),

              metrics=['accuracy'])


history = model.fit(X_train, Y_train,

                    batch_size=batch_size, nb_epoch=nb_epoch,

                    verbose=1, validation_data=(X_test, Y_test))

score = model.evaluate(X_test, Y_test, verbose=0)

print('Test score:', score[0])

print('Test accuracy:', score[1])

2. 如果输入数据是图像，并且使用的是CNN模型，输入数据的维度处理会稍微复杂些。

先了解下Keras 1.x中的image_dim_ordering参数。

“channels_last”对应原本的“tf”，“channels_first”对应原本的“th”。

以128x128的RGB图像为例，“channels_first”应将数据组织为（3,128,128），而“channels_last”应将数据组织为（128,128,3）。

MNIST dataset的CNN模型完整代码如下，特别需要注意input_shape和X_train/X_test。

'''Trains a simple convnet on the MNIST dataset.



Gets to 99.25% test accuracy after 12 epochs

(there is still a lot of margin for parameter tuning).

16 seconds per epoch on a GRID K520 GPU.

'''



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 = 12



# input image dimensions

img_rows, img_cols = 28, 28

# number of convolutional filters to use

nb_filters = 32

# size of pooling area for max pooling

pool_size = (2, 2)

# convolution kernel size

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()
#import gzip
#from six.moves import cPickle
#path=r'C:\Users\ll\.keras\datasets\mnist.pkl.gz'
#f = gzip.open(path, 'rb')
#(X_train, y_train), (x_valid,y_valid),(X_test, y_test)  = cPickle.load(f, encoding='bytes')
#f.close()


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.compile(loss='categorical_crossentropy',

             optimizer='adadelta',

              metrics=['accuracy'])



model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,

          verbose=1, validation_data=(X_test, Y_test))

score = model.evaluate(X_test, Y_test, verbose=0)

print('Test score:', score[0])

print('Test accuracy:', score[1])