搭建一个神经网络需要经过加载数据、模型构建、模型编译、模型训练、模型评估等几个步骤。利用Keras实现一个双层的卷积神经网络，需要先导入类、设置超参数并加载数据。
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

输入照片维度

img_rows, img_cols = 28, 28

加载MNIST数据集进行训练和数据测试

(x_train, y_train), (x_test, y_test) = mnist.load_data()
接下来判断使用Theano还是使用TensorFlow，它们的参数输入顺序不同。
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')

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)
然后需要构建模型，这里构建一个两层卷积的神经网络，例程中有两个卷积层、一个池化层、两个全连接层。
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'))
随后编译模型，采用交叉熵作为损失函数，优化器为keras.optimizers.Adadelta()。
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
接下来进行模型训练，输入训练数据集和测试数据集的数据，还需要输入批次（batch_size）和训练轮数（epochs），这两个参数在之前已经由全局变量设定完成。
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
最后进行模型评估，评估模型的损失以及准确率，并打印出来。
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
除了直接预测外，Keras还可以保存模型。与TensorFlow不同的是，Keras保存模型和权重的文件是HDF5。