Tensorflow 实战google深度学习框架 08 变量域

1. 在上下文管理器“foo”中创建变量“v”。

import tensorflow as tf

In [3]:

with tf.variable_scope("foo"):
    v = tf.get_variable("v", [1], initializer=tf.constant_initializer(1.0))

#with tf.variable_scope("foo"):
   # v = tf.get_variable("v", [1])

with tf.variable_scope("foo", reuse=True):
    v1 = tf.get_variable("v", [1])
print( v == v1)
​
#with tf.variable_scope("bar", reuse=True):
   # v = tf.get_variable("v", [1])
True

2. 嵌套上下文管理器中的reuse参数的使用。

In [5]:

with tf.variable_scope("root"):
    print(tf.get_variable_scope().reuse)

    with tf.variable_scope("foo", reuse=True):
        print (tf.get_variable_scope().reuse)

        with tf.variable_scope("bar"):
            print( tf.get_variable_scope().reuse)

    print( tf.get_variable_scope().reuse)
False
True
True
False

3. 通过variable_scope来管理变量。

In [6]:

v1 = tf.get_variable("v", [1])
print(v1.name)
​
with tf.variable_scope("foo",reuse=True):
    v2 = tf.get_variable("v", [1])
print (v2.name)
​
with tf.variable_scope("foo"):
    with tf.variable_scope("bar"):
        v3 = tf.get_variable("v", [1])
        print (v3.name)

v4 = tf.get_variable("v1", [1])
print (v4.name)
v:0
foo/v:0
foo/bar/v:0
v1:0

4. 我们可以通过变量的名称来获取变量。

In [8]:

with tf.variable_scope("",reuse=True):
    v5 = tf.get_variable("foo/bar/v", [1])
    print( v5 == v3)
    print( v2 == v3)
    v6 = tf.get_variable("v1", [1])     
    print (v6 == v4)
True
False
True

5. 获取全局变量

v = tf.Variable(0, dtype=tf.float32, name="v")
for variables in tf.global_variables(): print( variables.name)

ema = tf.train.ExponentialMovingAverage(0.99)
maintain_averages_op = ema.apply(tf.global_variables())
for variables in tf.global_variables(): print( variables.name)