参数保存

最新推荐文章于 2024-06-24 14:58:50 发布

caoxionggang

最新推荐文章于 2024-06-24 14:58:50 发布

阅读量338

点赞数

文章标签：神经网络

本文链接：https://blog.csdn.net/qq_40947321/article/details/87915874

版权

import tensorflow as tf
import numpy as np

## Save to file
# remember to define the same dtype and shape when restore
W = tf.Variable([[1,2,3],[3,4,5]], dtype=tf.float32, name='weights')
b = tf.Variable([[1,2,3]], dtype=tf.float32, name='biases')

# init= tf.initialize_all_variables() # tf 马上就要废弃这种写法
# 替换成下面的写法:
init = tf.global_variables_initializer()

saver = tf.train.Saver()

with tf.Session() as sess:
    sess.run(init)
    save_path = saver.save(sess, "my_net/save_net.ckpt")
    print("Save to path: ", save_path)