Keras CNN圖像實戰

Cifar-10

Cifar-10是由Hinton的兩個大弟子Alex Krizhevsky、Ilya Sutskever收集的一個用於普適物體識別的數據集。Cifar-10由60000張32*32的RGB彩色圖片構成，共10個分類。50000張訓練，10000張測試（交叉驗證）。這個數據集最大的特點在於將識別遷移到了普適物體，而且應用於多分類（姐妹數據集Cifar-100達到100類，ILSVRC比賽則是1000類）。

實戰一般流程：
1、準備數據集。
2、創建神經網絡模型，一般是Sequenal模型。
3、編譯模型，調用model.compile方法。
4、訓練模型，調用model.fit方法。
5、評估模型，調用model.evaluate方法。

#編譯模型
#model.compile(loss='categorical_crossentropy',optimizer='adadelta',metrics=['accuracy'])

#訓練模型
#model.fit(X_train, Y_train, batch_size=batch_size, epochs=epochs,verbose=1, validation_data=(X_test, Y_test))

#評估模型
#score = model.evaluate(X_test, Y_test, verbose=0)
#print('Test score:', score[0])
#print('Test accuracy:', score[1])

 

實踐代碼：

keras版本

>>> import keras
Using TensorFlow backend.
>>> print(keras.__version__)
1.2.2

#!/usr/bin/env python
# -*- coding: utf-8 -*-

from __future__ import print_function
import keras
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
import math

batch_size = 64
num_classes = 10
epochs = 50
data_augmentation = True

# 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:', 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, num_classes)
y_test = np_utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, 3, 3, input_shape=x_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, 3, 3))
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(num_classes))
model.add(Activation('softmax'))

# initiate RMSprop optimizer
opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)

# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',optimizer=opt,metrics=['accuracy'])
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

if not data_augmentation:
    print('Not using data augmentation.')
    model.fit(x_train, y_train,batch_size=batch_size,epochs=epochs,validation_data=(x_test, y_test),shuffle=True)
else:
    print('Using real-time data augmentation.')

# This will do preprocessing and realtime data augmentation:
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 
height_shift_range=0.1, # randomly shift images vertically (fraction of total 
horizontal_flip=True, # randomly flip images
vertical_flip=False) # randomly flip images

# Compute quantities required for feature-wise normalization
# (std, mean, and principal components if ZCA whitening is applied).
datagen.fit(x_train)

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