tf.train.NewCheckpointReader實現儲存變數的提取

tf.train.NewCheckpointReader('path')：path是儲存的路徑，這個函數可以得到儲存的所有變數

例如：

先儲存一個模型，參數為v,v1.

import tensorflow as tf;  import numpy as np;  import matplotlib.pyplot as plt;  v = tf.Variable(0, dtype=tf.float32, name='v')v1 = tf.Variable(0, dtype=tf.float32, name='v1')result = v + v1x = tf.placeholder(tf.float32, shape=[1], name='x')test = result + xinit = 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") 

利用tf.train.NewCheckpointReader匯出所有變數

import tensorflow as tf;  import numpy as np;  import matplotlib.pyplot as plt;  reader = tf.train.NewCheckpointReader("/home/penglu/Desktop/lp/model.ckpt")variables = reader.get_variable_to_shape_map()for ele in variables:print ele

輸出：

v1
v