手写多层神经网络(class)

1.下载数据

2.数据标准化

3.建立模型

4,添加神经层

5.激活模型

6.训练

7测试

from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense,Activation
#1.下载数据
(x_train,y_train),(x_test,y_test) = mnist.load_data()
print(x_train.shape)
print(x_test.shape)
#数据标准化
x_train = x_train.reshape(x_train.shape[0], -1) /255
x_test = x_test.reshape(x_test.shape[0], -1) /255
y_train = np_utils.to_categorical(y_train,num_classes=10)
y_test = np_utils.to_categorical(y_test,num_classes=10)

print(x_train.shape)

#建立模型,添加神经网络

model = Sequential([
    Dense(32, input_dim=784),
    Activation('relu'),
    Dense(10),
    Activation('softmax'),
])

#激活模型
model.compile(optimizer='rmsprop',loss='categorical_crossentropy',
              metrics=['accuracy'])
#训练
model.fit(x_train,y_train,batch_size=32,epochs=2)

#测试
loss, accuracy = model.evaluate(x_test,y_test)
print('loss:',loss,'\naccuracy:',accuracy)

RESULT:
 8512/10000 [========================>.....] - ETA: 0s
 9440/10000 [===========================>..] - ETA: 0sloss: 0.17119394473880528 
accuracy: 0.9499

Process finished with exit code 0