keras 识别手写数字mnist

#加载库
import keras
from keras import layers
import matplotlib.pyplot as plt
import keras.datasets.mnist as mnist

(train_image,train_label),(test_image,test_label)=mnist.load_data()

#建立模型
model = keras.Sequential()
model.add(layers.Flatten()) #展平 （60000，28，28）---》（60000，28*28）
model.add(layers.Dense(64,activation='relu'))
model.add(layers.Dense(10,activation='softmax'))
#编译
model.compile(optimizer = "adam",
              loss="sparse_categorical_crossentropy",
              metrics=['acc']
)
#训练模型
model.fit(train_image,train_label,epochs=50,batch_size=512)
#评估结果
model.evaluate(test_image,test_label)
# [0.34606385231018066, 0.9524000287055969]
model.evaluate(train_image,train_label)
#[0.05486735701560974, 0.9823333621025085]

模型优化
增加隐藏层

model = keras.Sequential()
model.add(layers.Flatten()) #展平 （60000，28，28）---》（60000，28*28）
model.add(layers.Dense(64,activation='relu'))# 隐藏层
model.add(layers.Dense(64,activation='relu'))# 隐藏层
model.add(layers.Dense(64,activation='relu'))# 隐藏层
model.add(layers.Dense(10,activation='softmax'))

model.compile(optimizer = "adam",
              loss="sparse_categorical_crossentropy",
              metrics=['acc']
)

history = model.fit(train_image,train_label,epochs=50,batch_size=512,validation_data=(test_image,test_label))
#画图
epochs=range(len(history.history['acc']))
plt.figure()
plt.plot(epochs,history.history['acc'],'b',label='Training acc')
plt.plot(epochs,history.history['val_acc'],'r',label='Validation acc')
plt.title('Traing and Validation accuracy')
plt.legend()


plt.figure()
plt.plot(epochs,history.history['loss'],'b',label='Training loss')
plt.plot(epochs,history.history['val_loss'],'r',label='Validation val_loss')
plt.title('Traing and Validation loss')
plt.legend()
plt.show()