【keras】cifar10数据集实现

#!/usr/bin/python3
# -*- coding: utf-8 -*-
# @Time: 2018/8/15
# @Author: xfLi
#file: keras_CIFAR10_V1.py
#cifar10数据集的实现由3个文件组成：
# cifar10_architecture.json， keras_CIFAR10_V1.py， keras_EvaluateCIFAR10.py

from keras.datasets import cifar10
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.optimizers import SGD, Adam, RMSprop
from keras.preprocessing.image import ImageDataGenerator


IMG_CHANNEL = 3
IMG_WIDTH = 32
IMG_HEIGHT = 32
BATCH_SIZE = 128
NB_EPOCH = 20
NB_CLASSES = 10
VERBOSE = 1
VALIDATTION_SPLIT = 0.2
OPTIM = RMSprop()

(x_train, y_train), (x_test, y_test) = cifar10.load_data()
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

#convert to categorical
y_train = np_utils.to_categorical(y_train, NB_CLASSES)
y_test = np_utils.to_categorical(y_test, NB_CLASSES)

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

#net
model = Sequential()
model.add(Conv2D(32, kernel_size=3, padding='same',
                 input_shape=(IMG_WIDTH, IMG_HEIGHT, IMG_CHANNEL)))
model.add(Activation('relu'))
model.add(Conv2D(32, kernel_size=3, padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, kernel_size=3, padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(NB_CLASSES))
model.add(Activation('softmax'))

model.summary()

#编译
model.compile(loss='categorical_crossentropy',
              optimizer=OPTIM,
              metrics=['accuracy'])

datagen = ImageDataGenerator(
        featurewise_center=False,  # set input mean to 0 over the dataset
        samplewise_center=False,  # set each sample mean to 0
        featurewise_std_normalization=False,  # divide inputs by std of the dataset
        samplewise_std_normalization=False,  # divide each input by its std
        zca_whitening=False,  # apply ZCA whitening
        rotation_range=0,  # randomly rotate images in the range (degrees, 0 to 180)
        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
        horizontal_flip=True,  # randomly flip images
        vertical_flip=False)  # randomly flip images
datagen.fit(x_train)

#train
history = model.fit(x_train, y_train, batch_size=BATCH_SIZE,
                    epochs=NB_EPOCH, verbose=VERBOSE,
                    validation_split=VALIDATTION_SPLIT)

print('testing...')

score = model.evaluate(x_test, y_test, batch_size=BATCH_SIZE,
                       verbose=VERBOSE)
print("\nTest score:", score[0])
print('Test accuracy:', score[1])

#save model
model_json = model.to_json()
open('cifar10_architecture.json', 'w').write(model_json)
model.save_weights('cifar10_weights.h5', overwrite=True)