Let's begin by a short introduction to variable sharing. It is a mechanism in TensorFlow that allows for sharing variables accessed in different parts of the code without passing references to the variable around. The method tf.get_variable can be used with the name of the variable as argument to either create a new variable with such name or retrieve the one that was created before. This is different from using the tf.Variable constructor which will create a new variable every time it is called (and potentially add a suffix to the variable name if a variable with such name already exists). It is for the purpose of the variable sharing mechanism that a separate type of scope (variable scope) was introduced.

As a result, we end up having two different types of scopes:

Both scopes have the same effect on all operations as well as variables created using tf.Variable, i.e. the scope will be added as a prefix to the operation or variable name.

However, name scope is ignored by tf.get_variable. We can see that in the following example:

with tf.name_scope("my_scope"):
v1 = tf.get_variable("var1", [1], dtype=tf.float32)
v2 = tf.Variable(1, name="var2", dtype=tf.float32)
a = tf.add(v1, v2) print(v1.name) # var1:0
print(v2.name) # my_scope/var2:0
print(a.name) # my_scope/Add:0

The only way to place a variable accessed using tf.get_variable in a scope is to use variable scope, as in the following example:

with tf.variable_scope("my_scope"):
v1 = tf.get_variable("var1", [1], dtype=tf.float32)
v2 = tf.Variable(1, name="var2", dtype=tf.float32)
a = tf.add(v1, v2) print(v1.name) # my_scope/var1:0
print(v2.name) # my_scope/var2:0
print(a.name) # my_scope/Add:0

Finally, let's look at the difference between the different methods for creating scopes. We can group them in two categories:

  • tf.name_scope(name) (for name scope) and tf.variable_scope(name_or_scope, ...)(for variable scope) create a scope with the name specified as argument
  • tf.op_scope(values, name, default_name=None) (for name scope) and tf.variable_op_scope(values, name_or_scope, default_name=None, ...) (for variable scope) create a scope, just like the functions above, but besides the scope name, they accept an argument default_name which is used instead of name when it is set to None. Moreover, they accept a list of tensors (values) in order to check if all the tensors are from the same, default graph. This is useful when creating new operations, for example, see the implementation of tf.histogram_summary.

大意是说 name_scope及variable_scope的作用都是为了不传引用而访问跨代码区域变量的一种方式,其内部功能是在其代码块内显式创建的变量都会带上scope前缀(如上面例子中的a),这一点它们几乎一样。而它们的差别是,在其作用域中获取变量,它们对 tf.get_variable() 函数的作用是一个会自动添加前缀,一个不会添加前缀。

tensorflow 中 name_scope 及 variable_scope 的异同的更多相关文章

  1. tensorflow 中 name_scope和variable_scope

    import tensorflow as tf with tf.name_scope("hello") as name_scope: arr1 = tf.get_variable( ...

  2. tensorflow中使用tf.variable_scope和tf.get_variable的ValueError

    ValueError: Variable conv1/weights1 already exists, disallowed. Did you mean to set reuse=True in Va ...

  3. tensorflow中命名空间、变量命名的问题

    1.简介 对比分析tf.Variable / tf.get_variable | tf.name_scope / tf.variable_scope的异同 2.说明 tf.Variable创建变量:t ...

  4. Tensorflow中的name_scope和variable_scope

    Tensorflow是一个编程模型,几乎成为了一种编程语言(里面有变量.有操作......). Tensorflow编程分为两个阶段:构图阶段+运行时. Tensorflow构图阶段其实就是在对图进行 ...

  5. TensorFlow学习笔记(1):variable与get_variable, name_scope()和variable_scope()

    Variable tensorflow中有两个关于variable的op,tf.Variable()与tf.get_variable()下面介绍这两个的区别 使用tf.Variable时,如果检测到命 ...

  6. TensorFlow中的L2正则化函数:tf.nn.l2_loss()与tf.contrib.layers.l2_regularizerd()的用法与异同

    tf.nn.l2_loss()与tf.contrib.layers.l2_regularizerd()都是TensorFlow中的L2正则化函数,tf.contrib.layers.l2_regula ...

  7. [翻译] Tensorflow中name scope和variable scope的区别是什么

    翻译自:https://stackoverflow.com/questions/35919020/whats-the-difference-of-name-scope-and-a-variable-s ...

  8. TensorFlow中的变量命名以及命名空间.

    What: 在Tensorflow中, 为了区别不同的变量(例如TensorBoard显示中), 会需要命名空间对不同的变量进行命名. 其中常用的两个函数为: tf.variable_scope, t ...

  9. tensorflow中slim模块api介绍

    tensorflow中slim模块api介绍 翻译 2017年08月29日 20:13:35   http://blog.csdn.net/guvcolie/article/details/77686 ...

随机推荐

  1. vim添加一键编译

    引用来自: http://blog.chinaunix.net/uid-21202106-id-2406761.html; 事先声明,我使用的VIM完全是基于终端的,而不是gvim或vim-x11.因 ...

  2. c# 字符串排序 (面试题)

    将一些字符串,如: "bc", "ad", "ac", "hello", "xman", " ...

  3. Python Excel 导入导出【转】

    一.安装xlrd模块 到python官网下载http://pypi.python.org/pypi/xlrd模块安装,前提是已经安装了python 环境. 二.使用介绍 1.导入模块 import x ...

  4. git设置忽略文件和目录

    1.登录gitbash命令端进入本地git库目录 Administrator@PC201601200946 MINGW32 /d/gitrespository/crmweb (master) 2.创建 ...

  5. swt生成、jar可执行包生成.exe可执行文件(giter)

    http://tomfish88.iteye.com/blog/1074786 —————————————————————————————————————————————————————————— 最 ...

  6. spring mvc 3.0 实现文件上传功能

    http://club.jledu.gov.cn/?uid-5282-action-viewspace-itemid-188672 —————————————————————————————————— ...

  7. easyUI的column的field的颜色属性

     {field:'hasPrintStr',title:'状态',width:10,halign:'center',align:'right',styler: function(value,row,i ...

  8. 第一百六十三节,jQuery,基础核心

    jQuery,基础核心 一.代码风格 在jQuery程序中,不管是页面元素的选择.内置的功能函数,都是美元符号“$”来起 始的.而这个“$”就是jQuery当中最重要且独有的对象:jQuery对象,所 ...

  9. J2EE是什么?

    解答:从整体上讲,J2EE是使用Java技术开发企业级应用的工业标准,它是Java技术不断适应和促进企业级应用过程中的产物.适用于企业级应用的J2EE,提供一个平台独立的.可移植的.多用户的.安全的和 ...

  10. weblogic配置oracle数据源

    在weblogic配置oracle数据源还是挺简单的,网上也有很多关于这方面的文章,写给自己也写给能够得到帮助的人吧.weblogic新建域那些的就不说了哈.点击startWebLogic文件,会弹出 ...