tensorflow中命名空間、變量命名的問題

1.簡介

對比分析tf.Variable / tf.get_variable | tf.name_scope / tf.variable_scope的異同

2.說明

• tf.Variable創建變量；tf.get_variable創建與獲取變量
• tf.Variable自動檢測命名沖突並且處理；tf.get_variable在沒有設置reuse時會報錯
• tf.name_scope沒有reuse功能，tf.get_variable在變量沖突時報錯；tf.variable_scope有reuse功能，可配合tf.get_variable實現變量共享
• tf.get_variable變量命名不受tf.name_scope的影響；tf.Variable受兩者的影響

3.代碼示例

3.1 tf.Variable

tf.Variable在命名沖突時自動處理沖突問題

import tensorflow as tf
a1 = tf.Variable(tf.constant(1.0, shape=[1]),name="a")
a2 = tf.Variable(tf.constant(1.0, shape=[1]),name="a")
print(a1)
print(a2)
print(a1==a2)


###
10 <tf.Variable 'a:0' shape=(1,) dtype=float32_ref>
11 <tf.Variable 'a_1:0' shape=(1,) dtype=float32_ref>
12 False

3.2 tf.get_variable

tf.get_variable在沒有設置命名空間reuse的情況下變量命名沖突時報錯

import tensorflow as tf
a3 = tf.get_variable("a", shape=[1], initializer=tf.constant_initializer(1.0))
a4 = tf.get_variable("a", shape=[1], initializer=tf.constant_initializer(1.0))


###
7 ValueError: Variable a already exists, disallowed.
8 Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope?

3.3 tf.name_scope

tf.name_scope沒有reuse功能，tf.get_variable命名不受它影響，並且命名沖突時報錯；tf.Variable命名受它影響

import tensorflow as tf
a = tf.Variable(tf.constant(1.0, shape=[1]),name="a")
with tf.name_scope('layer2'):
    a1 = tf.Variable(tf.constant(1.0, shape=[1]),name="a")
    a2 = tf.Variable(tf.constant(1.0, shape=[1]),name="a")
    a3 = tf.get_variable("a", shape=[1], initializer=tf.constant_initializer(1.0))
 7 #     a4 = tf.get_variable("a", shape=[1], initializer=tf.constant_initializer(1.0))   該句會報錯
    print(a)
    print(a1) 
    print(a2)
    print(a3)
    print(a1==a2)


###
16 <tf.Variable 'a:0' shape=(1,) dtype=float32_ref>
17 <tf.Variable 'layer2/a:0' shape=(1,) dtype=float32_ref>
18 <tf.Variable 'layer2/a_1:0' shape=(1,) dtype=float32_ref>
19 <tf.Variable 'a_1:0' shape=(1,) dtype=float32_ref>
20 False

3.4 tf.variable_scope

tf.variable_scope可以配tf.get_variable實現變量共享；reuse默認為None，有False/True/tf.AUTO_REUSE可選：

• 設置reuse = None/False時tf.get_variable創建新變量，變量存在則報錯
• 設置reuse = True時tf.get_variable只講獲取已存在的變量，變量不存在時報錯
• 設置reuse = tf.AUTO_REUSE時tf.get_variable在變量已存在則自動復用，不存在則創建

import tensorflow as tf
with tf.variable_scope('layer1',reuse=tf.AUTO_REUSE):
    a1 = tf.Variable(tf.constant(1.0, shape=[1]),name="a")
    a2 = tf.Variable(tf.constant(1.0, shape=[1]),name="a")
    a3 = tf.get_variable("a", shape=[1], initializer=tf.constant_initializer(1.0))
    a4 = tf.get_variable("a", shape=[1], initializer=tf.constant_initializer(1.0))
    print(a1) 
    print(a2)
    print(a1==a2)
    print(a3)
    print(a4)
    print(a3==a4)


### 
16 <tf.Variable 'layer1_1/a:0' shape=(1,) dtype=float32_ref>
17 <tf.Variable 'layer1_1/a_1:0' shape=(1,) dtype=float32_ref>
18 False
19 <tf.Variable 'layer1/a_2:0' shape=(1,) dtype=float32_ref>
20 <tf.Variable 'layer1/a_2:0' shape=(1,) dtype=float32_ref>
21 True

!!!