TF:利用TF的train.Saver载入曾经训练好的variables(W、b)以供预测新的数据—Jason niu

import tensorflow as tf
import numpy as np

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, "niu/save_net.ckpt") 
    print("weights:", sess.run(W))
    print("biases:", sess.run(b))

  

 

posted @ 2018-01-25 21:58  一个处女座的程序猿  阅读(164)  评论(0编辑  收藏  举报