在默认情况下不创建新范围的情况下,如何在 tensorflow 中重用变量范围?

How can you re-use a variable scope in tensorflow without a new scope being created by default?

我在图表的一部分创建了一个变量范围,后来在图表的另一部分我想将 OP 添加到现有范围。这相当于这个提炼的例子:

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:

['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, how to reuse a variable scope name

这是在上下文管理器中使用 assomename 的一种直接方法。使用此 somename.original_name_scope 属性,您可以检索该范围,然后向其添加更多变量。下面是一个例子:

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 reuse=True,您仍然会得到相同的结果。


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:

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 reuse=True,您仍然会得到相同的结果。

kmario23 提到的答案是正确的,但是 tf.get_variable:

创建的变量有一个棘手的情况
with tf.variable_scope('myscope'):
    print(tf.get_variable('var1', shape=[3]))

with tf.variable_scope('myscope/'):
    print(tf.get_variable('var2', shape=[3]))

此代码段将输出:

<tf.Variable 'myscope/var1:0' shape=(3,) dtype=float32_ref>
<tf.Variable 'myscope//var2:0' shape=(3,) dtype=float32_ref>

看来tensorflow还没有提供正式的方法来处理这种情况。我找到的唯一可能的方法是手动分配正确的名称(警告:不能保证正确性):

with tf.variable_scope('myscope'):
    print(tf.get_variable('var1', shape=[3]))

with tf.variable_scope('myscope/') as scope:
    scope._name = 'myscope'
    print(tf.get_variable('var2', shape=[3]))

然后我们可以得到正确的名字:

<tf.Variable 'myscope/var1:0' shape=(3,) dtype=float32_ref>
<tf.Variable 'myscope/var2:0' shape=(3,) dtype=float32_ref>