如何在不默认创建新范围的情况下在 tensorflow 中重用变量范围? [英] How can you re-use a variable scope in tensorflow without a new scope being created by default?

问题描述

我在图表的一个部分创建了一个可变范围，稍后在图表的另一部分我想将 OP 添加到现有范围.这相当于这个蒸馏的例子:

I have created a variable scope in one part of my graph, and later in another part of the graph I want to add OPs to an existing scope. That equates to this distilled example:

import tensorflow as tf

with tf.variable_scope('myscope'):
  tf.Variable(1.0, name='var1')

with tf.variable_scope('myscope', reuse=True):
  tf.Variable(2.0, name='var2')

print([n.name for n in tf.get_default_graph().as_graph_def().node])

产生的结果:

['myscope/var1/initial_value', 
 'myscope/var1', 
 'myscope/var1/Assign', 
 'myscope/var1/read', 
 'myscope_1/var2/initial_value', 
 'myscope_1/var2', 
 'myscope_1/var2/Assign', 
 'myscope_1/var2/read']

我想要的结果是:

['myscope/var1/initial_value', 
 'myscope/var1', 
 'myscope/var1/Assign', 
 'myscope/var1/read', 
 'myscope/var2/initial_value', 
 'myscope/var2', 
 'myscope/var2/Assign', 
 'myscope/var2/read']

我看到这个问题似乎没有直接解决问题的答案:TensorFlow，如何重用变量作用域名称

I saw this question which didn't seem to have an answer that addressed the question directly: TensorFlow, how to reuse a variable scope name

推荐答案

这是在上下文管理器中使用 as 和 somename 来完成此操作的一种直接方法.使用此 somename.original_name_scope 属性，您可以检索该范围，然后向其中添加更多变量.下图为:

Here is one straightforward way to do this using as with somename in a context manager. Using this somename.original_name_scope property, you can retrieve that scope and then add more variables to it. Below is an illustration:

In [6]: with tf.variable_scope('myscope') as ms1:
   ...:   tf.Variable(1.0, name='var1')
   ...: 
   ...: with tf.variable_scope(ms1.original_name_scope) as ms2:
   ...:   tf.Variable(2.0, name='var2')
   ...: 
   ...: print([n.name for n in tf.get_default_graph().as_graph_def().node])
   ...: 
['myscope/var1/initial_value', 
 'myscope/var1', 
 'myscope/var1/Assign', 
 'myscope/var1/read', 
 'myscope/var2/initial_value', 
 'myscope/var2', 
 'myscope/var2/Assign', 
 'myscope/var2/read']

备注
另请注意，设置 reuse=True 是可选的；也就是说，即使您通过了 reuse=True，您仍然会得到相同的结果.

Remark
Please also note that setting reuse=True is optional; That is, even if you pass reuse=True, you'd still get the same result.

另一种方法(感谢 OP 本人！)是在重用变量范围的末尾添加 / ，如下例所示:

Another way (thanks to OP himself!) is to just add / at the end of the variable scope when reusing it as in the following example:

In [13]: with tf.variable_scope('myscope'):
    ...:   tf.Variable(1.0, name='var1')
    ...: 
    ...: # reuse variable scope by appending `/` to the target variable scope
    ...: with tf.variable_scope('myscope/', reuse=True):
    ...:   tf.Variable(2.0, name='var2')
    ...: 
    ...: print([n.name for n in tf.get_default_graph().as_graph_def().node])
    ...: 
['myscope/var1/initial_value', 
 'myscope/var1', 
 'myscope/var1/Assign', 
 'myscope/var1/read', 
 'myscope/var2/initial_value', 
 'myscope/var2', 
 'myscope/var2/Assign', 
 'myscope/var2/read']

备注:
请注意，设置 reuse=True 也是可选的；也就是说，即使您通过了 reuse=True，您仍然会得到相同的结果.

Remark:
Please note that setting reuse=True is again optional; That is, even if you pass reuse=True, you'd still get the same result.

这篇关于如何在不默认创建新范围的情况下在 tensorflow 中重用变量范围?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！