【Keras】卷积神经网络识别手写数据集（mnist_CNN）

网络结构为：

  2 个卷积层 - 1 个池化层 - 2 个全连接层

下面代码拉到自己电脑里可以直接运行：

'''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 # 分类数
epochs = 12 # 训练轮数

# input image dimensions
img_rows, img_cols = 28, 28

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    # 使用 Theano 的顺序：(conv_dim1, channels, conv_dim2, conv_dim3)
    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:
    # 使用 TensorFlow 的顺序：(conv_dim1, conv_dim2, conv_dim3, channels)
    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
'''
    x_train shape: (60000, 28, 28, 1)
    60000 train samples
    10000 test samples
    Train on 60000 samples, validate on 10000 samples
'''
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(将类向量转换为二进制类矩阵)
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

# 下面来构建模型，这里用 2 个卷积层、1 个池化层和 2 个全连接层来构建，如下：
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

# 随后，用 model.compile()函数编译模型，采用多分类的损失函数，用 Adadelta 算法做优化方法，如下：
model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])
# 然后，开始用 model.fit()函数训练模型，输入训练集和测试数据，以及 batch_size 和 nb_epoch参数，如下：
model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_test, y_test))

# 最后，用 model.evaluate()函数来评估模型，输出测试集的损失值和准确率，如下：
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])