keras mnist cnn example

# encoding:utf-8
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
# batch_size 太小会导致训练慢,过拟合等问题,太大会导致欠拟合。所以要适当选择
batch_size = 128
# 0-9手写数字一个有10个类别
num_classes = 10
# 12次完整迭代,差不多够了
epochs = 2

# input image dimensions# 输入的图片是28*28像素的灰度图
img_rows, img_cols = 28, 28

# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# keras输入数据有两种格式,一种是通道数放在前面,一种是通道数放在后面
# 在如何表示一组彩色图片的问题上,Theano和TensorFlow发生了分歧,'th'模式,也即Theano模式会把100张RGB三通道的16×32(高为16宽为32)彩色图表示为下面这种形式(100,3,16,32),Caffe采取的也是这种方式。
# 第0个维度是样本维,代表样本的数目,第1个维度是通道维,代表颜色通道数。后面两个就是高和宽了。这种theano风格的数据组织方法,称为“channels_first”,即通道维靠前。
# 而TensorFlow,的表达形式是(100,16,32,3),即把通道维放在了最后,这种数据组织方式称为“channels_last”。
# Keras默认的数据组织形式在~/.keras/keras.json中规定,可查看该文件的image_data_format一项查看,也可在代码中通过K.image_data_format()函数返回,请在网络的训练和测试中保持维度顺序一致。
if K.image_data_format() == 'channels_first':
    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 # 把类别0-9变成2进制,方便训练
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
# 牛逼的Sequential类可以让我们灵活地插入不同的神经网络层
model = Sequential()
# 加上一个2D卷积层, 32个输出(也就是卷积通道),激活函数选用relu,
# 卷积核的窗口选用3*3像素窗口
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=input_shape))
# 64个通道的卷积层
model.add(Conv2D(64, (3, 3), activation='relu'))
# 池化层是2*2像素的
model.add(MaxPooling2D(pool_size=(2, 2)))
# 对于池化层的输出,采用0.25概率的Dropout
model.add(Dropout(0.25))
# 展平所有像素,比如[28*28] -> [784]
model.add(Flatten())
# 对所有像素使用全连接层,输出为128,激活函数选用relu
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
# 对刚才Dropout的输出采用softmax激活函数,得到最后结果0-9
model.add(Dense(num_classes, activation='softmax'))
# 模型我们使用交叉熵损失函数,最优化方法选用Adadelta
model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

你可能感兴趣的:(深度学习)