DL7-tensorflow中模型的保存和加载

简单示例

import tensorflow as tf

a = tf.Variable(tf.random_normal([1, 2]), name='a')
b = tf.Variable(tf.random_normal([2, 3]), name='b')

init = tf.global_variables_initializer()
saver = tf.train.Saver()

with tf.Session() as sess:
    sess.run(init)
    print('a: ', sess.run(a))
    print('b: ', sess.run(b))
    saver_path = saver.save(sess, 'save/test.ckpt')
    print ('Model saved in file: ', saver_path)
WARNING:tensorflow:From C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
a:  [[0.0161621  0.30304506]]
b:  [[-0.76005447  0.32688513 -0.2714278 ]
 [-0.24321812 -0.9551174   0.5906535 ]]
Model saved in file:  save/test.ckpt
import tensorflow as tf

a = tf.Variable(tf.random_normal([1, 2]), name='a')
b = tf.Variable(tf.random_normal([2, 3]), name='b')
saver = tf.train.Saver()

with tf.Session() as sess:
    saver.restore(sess, 'save/test.ckpt')
    print('a: ', sess.run(a))
    print('b: ', sess.run(b))
    print ('Model restored')
WARNING:tensorflow:From C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
INFO:tensorflow:Restoring parameters from save/test.ckpt
a:  [[0.0161621  0.30304506]]
b:  [[-0.76005447  0.32688513 -0.2714278 ]
 [-0.24321812 -0.9551174   0.5906535 ]]
Model restored
  • 0
    点赞
  • 3
    收藏
    觉得还不错? 一键收藏
  • 2
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值