tf.variable_scope() and tf.name

https://blog.csdn.net/UESTC_C2_403/article/details/72328815

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

例如：

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:

换成下面的代码就可以执行：

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

tf.variable_scope() and tf.name_scope()相关推荐

tf.Variable、tf.get_variable、tf.variable_scope、tf.name_scope、random、initializer
转自:tensorflow学习笔记(二十三):variable与get_variable TF.VARIABLE.TF.GET_VARIABLE.TF.VARIABLE_SCOPE以及TF.NAME_ ...
tf.variable_scope和tf.name_scope的用法
tf.variable_scope可以让不同命名空间中的变量取相同的名字,无论tf.get_variable或者tf.Variable生成的变量 tf.name_scope具有类似的功能,但只限于tf ...
tf.Variable、tf.get_variable、tf.variable_scope以及tf.name_scope
tf.Variable与tf.get_variable tensorflow提供了通过变量名称来创建或者获取一个变量的机制.通过这个机制,在不同的函数中可以直接通过变量的名字来使用变量,而不需要将变量 ...
tf.variable_scope与tf.tf.get_variable
实验一. 不设置随机种子,使用不同的初始化方法 import tensorflow as tf; import numpy as np; import matplotlib.pyplot as plt ...
通俗理解tf.name_scope()、tf.variable_scope()
前言:最近做一个实验,遇到TensorFlow变量作用域问题,对tf.name_scope().tf.variable_scope()等进行了较为深刻的比较,记录相关笔记: tf.name_scope ...
tf.name_scope() 和 tf.variable_scope() 的用法和玄机
2019独角兽企业重金招聘Python工程师标准>>> 一. name_scope 和 variable_scope的用途用途1: 共享变量 TensorFlow (TF) 中,n ...
tf.name_scope()与tf.variable_scope()
TensorFlow的tf.name_scope().tf.variable_scope()是两个作用域函数,一般与两个创建/调用变量的函数tf.variable() 和tf.get_variable ...
tf.name_scope tf.variable_scope学习
1. 首先看看比较简单的 tf.name_scope('scope_name'). tf.name_scope 主要结合 tf.Variable() 来使用,方便参数命名管理. ''' Signatu ...
TensorFlow基础笔记(13) tf.name_scope tf.variable_scope学习
转载http://blog.csdn.net/jerr__y/article/details/60877873 1. 首先看看比较简单的 tf.name_scope('scope_name'). tf ...

tf.variable_scope() and tf.name_scope()

tf.variable_scope() and tf.name_scope()相关推荐

最新文章

热门文章