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. c# 常用操作保留

    RanDom如何提高生成随机数的随机性 一个在线考试系统的项目,需要从题库中随机抽取试题,但是如果直接 Random ran=new Randon(),ran.Next(nummin,nummax); ...

  2. H4CK1T CTF 2016 Mexico-Remote pentest writeup

    进去网站之后发现连接都是包含类型的,就能想到文件包含漏洞(话说刚总结过就能遇到这题,也算是复习啦) 这里用php://filter/read=convert.base64-encode/resourc ...

  3. dubbo配置约束

    此处主要记录dubbo配置的一些约束规则. 采用官网提供的原文,描述如下: 一.XML配置(官网原文) 以 timeout 为例: 方法级优先,接口级次之,全局配置再次之. 如果级别一样,则消费方优先 ...

  4. Easyui Datagrid的Rownumber行号显示问题

    Datagrid中当你的行数据超过9999时,第一列的行号rownumber将会因为表格内容过长而导致无法显示全部数字, 这一点Easyui无法做到自适应 所以需要进行修改,这里扩展一个方法就行了. ...

  5. Cross compile perl

    Alex Suykov had do some work for this purpose, and my compile script is based on her patch. Steps St ...

  6. django组件整合

    session Django中默认支持Session,其内部提供了5种类型的Session供开发者使用: 数据库(默认) 缓存 文件 缓存+数据库 加密cookie Django默认支持Session ...

  7. ModelShowDialog缓存上次浏览的URL

    1. 一种解决方法设置每次清楚浏览的页面. In IE7, go to Tools  |  Internet Options.  Click the Browsing History "Se ...

  8. IIS部署ASP.NET MVC (4.0)网站出现的错误

    (1)无法读取配置节“system.web.extensions”,因为它缺少节声明 在IIS中,在基本设置中,将程序池选择为ASP.NET 4.0即OK! (2)由于 Web 服务器上的“ISAPI ...

  9. CentOS firewalld 防火墙操作

    Centos 7 开启端口CentOS 7 默认没有使用iptables,所以通过编辑iptables的配置文件来开启80端口是不可以的 CentOS 7 采用了 firewalld 防火墙 如要查询 ...

  10. [hihoCoder] Trie树

    This is a application of the Trie data structure, with minor extension. The critical part in this pr ...