from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense
batch_size=128
nb_classes=10
nb_epoch=10
img_size=28*28
(x_train,y_train),(x_test,y_test)=mnist.load_data("E:\Code\PycharmProjects\KerasStudying\data\mnist.npz")
#也可以预先下载好数据：https://s3.amazonaws.com/img-datasets/mnist.npz
x_train=x_train.reshape(-1,img_size).astype('float32')/255
x_test=x_test.reshape(-1,img_size).astype('float32')/255
print(x_train.shape)
print(x_test.shape)
y_train=np_utils.to_categorical(y_train,nb_classes)
print(y_test[:5])
y_test=np_utils.to_categorical(y_test,nb_classes)
print(y_test[:5])
model=Sequential([
Dense(10,input_shape={img_size,},activation="softmax") #单层全连接层，激励函数softmax
])
model.compile(optimizer='rmsprop',loss='categorical_crossentropy',metrics=['accuracy'])
model.fit(x_train,y_train,batch_size=batch_size,epochs=10,verbose=1,validation_data=(x_test,y_test))#训练10轮并打印日志
score=model.evaluate(x_test,y_test,verbose=0)
print('accuracy:'+str(score[1]))
