tf.name_scope和tf.variable_scope的区别

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

# 重置已存在的图
tf.reset_default_graph()

with tf.variable_scope('V1'):  
    a1 = tf.get_variable(name='a1', shape=[1], initializer=tf.constant_initializer(1))  
    a2 = tf.Variable(tf.random_normal(shape=[2,3], mean=0, stddev=1), name='a2')  
with tf.name_scope('V2'):  
    a3 = tf.get_variable(name='a1', shape=[1], initializer=tf.constant_initializer(1))  
    a4 = tf.Variable(tf.random_normal(shape=[2,3], mean=0, stddev=1), name='a2')  

with tf.Session() as sess:  
    sess.run(tf.initialize_all_variables())  
    print (a1.name)
    print (a2.name)
    print (a3.name)
    print (a4.name)

结果

V1/a1:0
V1/a2:0
a1:0
V2/a2:0

如果两个都改成name_scope()，那么下面的就会因为命名变量存在而报错