tf.variable_scope和tf.name_scope的区别

最新推荐文章于 2020-05-08 15:21:52 发布

原创最新推荐文章于 2020-05-08 15:21:52 发布 · 393 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#tf.name #tf.scope

TensorFlow 专栏收录该内容

4 篇文章

订阅专栏

本文探讨了TensorFlow中tf.variable_scope与tf.name_scope的区别，通过实例演示了如何使用这两种作用域来管理变量命名，强调了tf.variable_scope可以统一管理tf.get_variable与tf.Variable两种变量的命名，而tf.name_scope仅能作用于tf.Variable。

部署运行你感兴趣的模型镜像

tf.variable_scope可以让变量有相同的命名，包括tf.get_variable得到的变量，还有tf.Variable的变量

tf.name_scope可以让变量有相同的命名，只是限于tf.Variable的变量

例子1：

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

输出：
V1/a1:0
V1/a2:0
V2/a1:0
V2/a2:0

例子2：

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

报错：Variable a1 already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:

例子2修改后：

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

输出：
V1/a2:0
V2/a2:0

您可能感兴趣的与本文相关的镜像