mnist_cnn.py 在mnist数据集训练一个简单的神经网络
'''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 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 = 128
num_classes = 10
epochs = 12
# input image dimensions
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()
#数据格式的区别 channels_first对应th,通道维在前;channels_last对应tf,通道维在后(默认为channels_last)
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
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
model = Sequential()
#Conv2D keras.layers.convolutional.conv2D(2D指对2维图片进行操作) 卷积层
#filters 卷积核数目,即输出维度
#kernel_size 卷积核的宽度和长度,单个整数或两个整数构成的list/tuple
#strides 卷积步长,单个整数或两个整数构成的list/tuple,默认为1
#padding "补0策略" valid(默认) 只进行有效卷积,不处理边界;same 保留边界处理结果,输出shape与输入shape相同
#activation 不指定时则不使用激活函数
#使用该层作为第一层时,需指定input_shape
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
#MaxPooling2D 池化层 对input采样,降低维度,减少参数
#用2×2的filter过滤原输出,得到该区域中最大值,构成新的输出
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
#Flatten 把多维数据一维化,常用于卷积层到全连接层的过渡
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
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])