tensorflow_scope作用

tensorflow中有两个关于variable的op，tf.Variable()与tf.get_variable()下面介绍这两个的区别

区别

1. 使用tf.Variable时，如果检测到命名冲突，系统会自己处理。使用tf.get_variable()时，系统不会处理冲突，而会报错

import tensorflow as tfw_1 = tf.Variable(3,name="w_1")w_2 = tf.Variable(1,name="w_1")print w_1.nameprint w_2.name#输出#w_1:0#w_1_1:

import tensorflow as tfw_1 = tf.get_variable(name="w_1",initializer=1)w_2 = tf.get_variable(name="w_1",initializer=2)#错误信息#ValueError: Variable w_1 already exists, disallowed. Did#you mean to set reuse=True in VarScope?

1. 基于这两个函数的特性，当我们需要共享变量的时候，需要使用tf.get_variable()。在其他情况下，这两个的用法是一样的

get_variable()与Variable的实质区别

来看下面一段代码：

import tensorflow as tfwith tf.variable_scope("scope1"):    w1 = tf.get_variable("w1", shape=[])    w2 = tf.Variable(0.0, name="w2")with tf.variable_scope("scope1", reuse=True):    w1_p = tf.get_variable("w1", shape=[])    w2_p = tf.Variable(1.0, name="w2")print(w1 is w1_p, w2 is w2_p)#输出#True  False

看到这，就可以明白官网上说的参数复用的真面目了。由于tf.Variable() 每次都在创建新对象，所有reuse=True 和它并没有什么关系。对于get_variable()，来说，如果已经创建的变量对象，就把那个对象返回，如果没有创建变量对象的话，就创建一个新的。

实例：

import tensorflow as tf
#print(dir(tf))
#print(help(tf.Variable))
#with tf.name_scope("a_name_scope") as scope:
with tf.variable_scope("a_variable_scope") as scope:
    var1 = tf.get_variable(name = 'var1', initializer=[[1.,2.],[3.,4.]], dtype = tf.float32)
    #scope.reuse_variables()
    #print(dir(scope))
with tf.variable_scope("a_variable_scope", reuse = True) as scope:
    var2 = tf.get_variable(name='var1', initializer=[2])
with tf.variable_scope("a_variable_scope", reuse = None) as scope:
    var6 = tf.get_variable(name='var2', initializer=[2])
    var3 = tf.Variable(initial_value = [3], name='var3')
    var4 = tf.Variable(initial_value = [4], name='var3')
    var5 = tf.Variable(initial_value = [5], name='var3')

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    print(var1.name)
    print(sess.run(var1))
    print(var2.name)
    print(sess.run(var2))
    print(var3.name)
    print(sess.run(var3))
    print(var4.name)
    print(sess.run(var4))
    print(var5.name)
    print(sess.run(var5))

输出：

a_variable_scope/var1:0
[[ 1.  2.]
 [ 3.  4.]]
a_variable_scope/var1:0
[[ 1.  2.]
 [ 3.  4.]]
a_variable_scope_2/var3:0
[3]
a_variable_scope_2/var3_1:0
[4]
a_variable_scope_2/var3_2:0
[5]