variable_scope和name_scope差别

先看代码：

1.  
   #命名空间函数tf.variable_scope()和tf.name_scope()函数区别于使用
2.  
    
3.  
   import tensorflow as tf
4.  
    
5.  
   with tf.variable_scope("foo"):
6.  
   a = tf.get_variable("bar", [1])
7.  
   print(a.name) #foo/bar:0
8.  
   b = tf.Variable("b", [1])
9.  
   print(b.name) #foo/Variable:0
10.  
     
11.  
    with tf.variable_scope("bar"):
12.  
    a = tf.get_variable("bar", [1])
13.  
    print(a.name) #bar/bar:0
14.  
    b = tf.Variable("b", [1])
15.  
    print(b.name) #bar/Variable:0
16.  
     
17.  
    with tf.name_scope("a"):
18.  
    a = tf.Variable([1])
19.  
    print(a.name) #a/Variable:0
20.  
     
21.  
    with tf.name_scope("b"):
22.  
    b = tf.get_variable("b", [1])
23.  
    print(b.name) #b_1:0
24.  
     
25.  
    with tf.name_scope("b"):
26.  
    c = tf.get_variable("b", [1])
27.  
    print(c.name) #出错，b已存在

可以看出，对于tf.Variable()函数，两者的使用情况都一样；而tf.get_variable()函数，它不受name_scope约束，已经声明过的变量就不能再声明了。

 

 

1. tf.name_scope('scope_name')或tf.name_scope(named_scope)

主要与tf.Variable搭配使用；

当传入字符串时，用以给变量名添加前缀，类似于目录，如case1所示；

当传入已存在的name_scope对象时，则其范围内变量的前缀只与当前传入的对象有关，与更上层的name_scope无关，如case2所示。

import tensorflow as tf

# case 1:
with tf.name_scope('l1'):
    with tf.name_scope('l2'):
        wgt1 = tf.Variable([1,2,3], name='wgts')
        bias1 = tf.Variable([0.1], name='biases')

print wgt1.name, bias1.name
# >>> l1/l2/wgts:0 l1/l2/biases:0

# case 2:
with tf.name_scope('l1') as l1_scp:
    with tf.name_scope('l2'):
        wgt0 = tf.Variable([1,2,3], name='wgts')
        bias0 = tf.Variable([0.1], name='biases')
        with tf.name_scope(l1_scp):
            wgt1 = tf.Variable([1,2,3], name='wgts')
            bias1 = tf.Variable([0.1], name='biases')

print wgt0.name, bias0.name, wgt1.name, bias1.name
# >>> l1_1/l2/wgts:0 l1_1/l2/biases:0 l1_1/wgts:0 l1_1/biases:0

2. tf.variable_scope('scope_name', reuse=None)或

    tf.variable_scope(named_scope)

 

与name_scope一样：当传入字符串时，用以给变量名添加前缀，类似于目录；

当传入已存在的variable_scope对象时，则其范围内变量的前缀只与当前传入的对象有关，与更上层的variable_scope无关。

常于get_variable搭配使用，多用于变量共享；其中 reuse 参数可设为 None、tf.AUTO_REUSE、True、False；

当 reuse=None（默认情况）时，与上层variable_scope的reuse参数一样。

# case 1
with tf.variable_scope('lv1'):
    with tf.variable_scope('lv2'):
        init = tf.constant_initializer(0.1)
        wgt1 = tf.get_variable('wgts', [2,2])
        bias1 = tf.get_variable('biases', [2,2])

print wgt1.name, bias1.name
# >>> lv1/lv2/wgts:0 lv1/lv2/biases:0

当 reuse=tf.AUTO_REUSE 时，自动复用，如果变量存在则复用，不存在则创建。这是最安全的用法。

with tf.variable_scope('lv1'):
    with tf.variable_scope('lv2'):
        init = tf.constant_initializer(0.1)
        wgt1 = tf.get_variable('wgts', [2,2])
        bias1 = tf.get_variable('biases', [2,2])
print wgt1.name, bias1.name
# >>> lv1/lv2/wgts:0 lv1/lv2/biases:0

with tf.variable_scope('lv1', reuse=tf.AUTO_REUSE):
    with tf.variable_scope('lv2'):
        init = tf.constant_initializer(0.1)
        wgt2 = tf.get_variable('wgts', [2,2])
        bias2 = tf.get_variable('biases', [2,2])
print wgt2.name, bias2.name
# >>> lv1/lv2/wgts:0 lv1/lv2/biases:0

with tf.variable_scope('lv1', reuse=tf.AUTO_REUSE):
    with tf.variable_scope('lv2'):
        init = tf.constant_initializer(0.1)
        wgt2 = tf.get_variable('wgts', [2,2])
        bias2 = tf.get_variable('biases', [2,2])

print wgt2.name, bias2.name
# >>> lv1/lv2/wgts:0 lv1/lv2/biases:0

 

当 reuse=True 时，tf.get_variable会查找该命名变量，如果没有找到，则会报错；所以设置reuse=True之前，要保证该命名变量已存在。

with tf.variable_scope('lv1', reuse=True):
    with tf.variable_scope('lv2'):
        init = tf.constant_initializer(0.1)
        wgt1 = tf.get_variable('wgts', [2,2])
        bias1 = tf.get_variable('biases', [2,2])

print wgt1.name, bias1.name
# >>> ValueError: Variable lv1/lv2/wgts does not exist,
# or was not created with tf.get_variable(). Did you mean
# to set reuse=tf.AUTO_REUSE in VarScope?

命名变量已存在：

with tf.variable_scope('lv1'):
    with tf.variable_scope('lv2'):
        init = tf.constant_initializer(0.1)
        wgt1 = tf.get_variable('wgts', [2,2])
        bias1 = tf.get_variable('biases', [2,2])

print wgt1.name, bias1.name
# >>> lv1/lv2/wgts:0 lv1/lv2/biases:0

# case 2
with tf.variable_scope('lv1', reuse=True):
    with tf.variable_scope('lv2'):
        init = tf.constant_initializer(0.1)
        wgt1 = tf.get_variable('wgts', [2,2])
        bias1 = tf.get_variable('biases', [2,2])

print wgt1.name, bias1.name
# >>> lv1/lv2/wgts:0 lv1/lv2/biases:0

当 reuse=False 时，tf.get_variable会调用tf.Variable来创建变量，并检查创建的变量是否以存在，如果已存在，则报错；

with tf.variable_scope('lv1'):
    with tf.variable_scope('lv2'):
        init = tf.constant_initializer(0.1)
        wgt1 = tf.get_variable('wgts', [2,2])
        bias1 = tf.get_variable('biases', [2,2])

print wgt1.name, bias1.name
# >>> lv1/lv2/wgts:0 lv1/lv2/biases:0

# case 2
with tf.variable_scope('lv1', reuse=False):
    with tf.variable_scope('lv2'):
        init = tf.constant_initializer(0.1)
        wgt1 = tf.get_variable('wgts', [2,2])
        bias1 = tf.get_variable('biases', [2,2])

print wgt1.name, bias1.name
# ValueError: Variable lv1/lv2/wgts already exists, disallowed.
# Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope?