keras从入门到放弃(十）手写数字识别训练

导入手写数字识别

import keras
from keras import layers
import matplotlib.pyplot as plt
%matplotlib inline
import keras.datasets.mnist as mnist
(train_image, train_label), (test_image, test_label) = mnist.load_data()
train_image.shape
OUT：
(60000, 28, 28)

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
 

即有60000张图片 28*28像素

用切片的方法去取出图片

plt.imshow(train_image[0])
train_label[0]
OUT：
0

  

 

  
1
  
2
  
3
  
4
 

模型训练

model = keras.Sequential()
model.add(layers.Flatten()) # (60000, 28, 28) --->  (60000, 28*28)
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['acc']
)
model.fit(train_image, train_label, epochs=50, batch_size=512)

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
 

文章来源: maoli.blog.csdn.net，作者：刘润森！，版权归原作者所有，如需转载，请联系作者。

原文链接：maoli.blog.csdn.net/article/details/88872695