tensorflow 保存读取

tensorflow 保存读取

tensorflow 保存读取

import tensorflow as tfimport numpy as np# 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.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_path)W = tf.Variable(np.arange(6).reshape((2,3)), dtype=tf.float32, name="weights")b = tf.Variable(np.arange(3).reshape((1,3)), dtype=tf.float32, name="biases")saver = tf.train.Saver()with tf.Session() as sess: saver.restore(sess, "my_net/save_net.ckpt") print("weights:", sess.run(W)) print("biases:", sess.run(b))

​​https://morvanzhou.github.io/tutorials/machine-learning/tensorflow/5-06-save/​​

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。