这两个函数都提供了命名空间管理的功能,它们在大部分情况下是等价的,唯一的区别是在使用tf.get_variable函数时。以下代码简单地说明了这两个函数的区别:
import tensorflow as tf with tf.variable_scope("foo"): # 在命名空间foo下获取变量"bar", 于是得到的变量名称为“foo/bar” a = tf.get_variable("bar", [1]) print(a.name) # 输出: foo/bar:0 with tf.variable_scope("bar"): # 在命名空间bar下获取变量“bar”,于是得到变量名称为“bar/bar”。 # 此时,变量“bar/bar”和变量“foo/bar”并不冲突,于是可以正常运行 b = tf.get_variable("bar", [1]) print(b.name) # 输出: bar/bar:0 with tf.name_scope("a"): # 使用tf.Variable函数生成变量会受tf.name_scope影响,于是这个变量的名称为“a/Variable" a = tf.Variable([1]) print(a.name) # 输出: a/Variable:0 # tf.get_variable函数不受tf.name_scope函数影响,于是变量并不在a这个命名空间中。 a = tf.get_variable("b", [1]) print(a.name) # 输出: b:0 with tf.name_scope("b"): # 因为tf.get_variable不受tf.name_scope影响,所以这时将试图获取名称为“b”的变量。 # 然而这个变量已经被声明了,于是这里会报重复声明的错误: tf.get_variable("b", [1])
输出:
C:\ProgramData\Anaconda3\python.exe "C:\Program Files\JetBrains\PyCharm Community Edition 2017.2.3\helpers\pydev\pydevd.py" --multiproc --qt-support=auto --client 127.0.0.1 --port 56737 --file D:/doc.pycharm/TFbook/p231_variable_scope_and_name_scope.py
pydev debugger: process 295916 is connecting
Connected to pydev debugger (build 172.3968.37)
foo/bar:0
bar/bar:0
a/Variable:0
b:0
Traceback (most recent call last):
File "C:\Program Files\JetBrains\PyCharm Community Edition 2017.2.3\helpers\pydev\pydevd.py", line 1599, in <module>
globals = debugger.run(setup['file'], None, None, is_module)
File "C:\Program Files\JetBrains\PyCharm Community Edition 2017.2.3\helpers\pydev\pydevd.py", line 1026, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "C:\Program Files\JetBrains\PyCharm Community Edition 2017.2.3\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "D:/doc.pycharm/TFbook/p231_variable_scope_and_name_scope.py", line 34, in <module>
tf.get_variable("b", [1])
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1065, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 962, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 367, in get_variable
validate_shape=validate_shape, use_resource=use_resource)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 352, in _true_getter
use_resource=use_resource)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 664, in _get_single_variable
name, "".join(traceback.format_list(tb))))
ValueError: Variable b already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1269, in __init__
self._traceback = _extract_stack()
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op
op_def=op_def)
Process finished with exit code 1