tf.train.Saver函数的用法之保存全部变量和模型

 

用于保存模型，以后再用就可以直接导入模型进行计算，方便。

例如：

 import tensorflow as tf;
 import numpy as np;
 import matplotlib.pyplot as plt;

 v1 = tf.Variable(tf.constant(1, shape=[1]), name='v1')
 v2 = tf.Variable(tf.constant(2, shape=[1]), name='v2')

 result = v1 + v2

 init = tf.initialize_all_variables()

 saver = tf.train.Saver()

 with tf.Session() as sess:
     sess.run(init)
     saver.save(sess, "/home/penglu/Desktop/lp/model.ckpt")
     # saver.restore(sess, "/home/penglu/Desktop/lp/model.ckpt")
     # print sess.run(result)

结果：

下次需要使用模型就可以用下面的代码：

 import tensorflow as tf;
 import numpy as np;
 import matplotlib.pyplot as plt;

 v1 = tf.Variable(tf.constant(1, shape=[1]), name='v1')
 v2 = tf.Variable(tf.constant(2, shape=[1]), name='v2')

 result = v1 + v2

 init = tf.initialize_all_variables()

 saver = tf.train.Saver()

 with tf.Session() as sess:
     saver.restore(sess, "/home/penglu/Desktop/lp/model.ckpt")
     print sess.run(result)

 或者这个代码：

 import tensorflow as tf;
 import numpy as np;
 import matplotlib.pyplot as plt;

 saver = tf.train.import_meta_graph('/home/penglu/Desktop/lp/model.ckpt.meta')
 with tf.Session() as sess:
 "white-space:pre">  saver.restore(sess, "/home/penglu/Desktop/lp/model.ckpt")
 "white-space:pre">  print sess.run(tf.get_default_graph().get_tensor_by_name('add:0'))