tf.get_collection的使用方法

àì夳堔傛蜴生んèń 2021-12-09 06:04 269阅读 0赞

### tf.get\_collection的使用方法 ###

*  参数数量及其作用
 *  例子

# 参数数量及其作用 #

该函数共有两个参数，分别是key和scope。

def get_collection(key, scope=None)
     Wrapper for Graph.get_collection() using the default graph.
     See tf.Graph.get_collection for more details.
     Args:
       key: The key for the collection. For example, the `GraphKeys` class  
         contains many standard names for collections.  
       scope: (Optional.) If supplied, the resulting list is filtered to include  
         only items whose `name` attribute matches using `re.match`. Items  
         without a `name` attribute are never returned if a scope is supplied and  
         the choice or `re.match` means that a `scope` without special tokens  
         filters by prefix.  
     Returns:
       The list of values in the collection with the given `name`, or  
       an empty list if no value has been added to that collection. The  
       list contains the values in the order under which they were  
       collected.

该函数的作用是从一个collection中取出全部变量，形成列个列表，key参数中输入的是collection的名称。该函数常常与tf.get\_variable和tf.add\_to\_collection配合使用。

# 例子 #

该例子将分别举例tf.get\_collection与tf.get\_variable和tf.add\_to\_collection的配合使用方法。

import tensorflow as tf;  
     import numpy as np;  
     
     c1 = ['c1', tf.GraphKeys.GLOBAL_VARIABLES]
     
     v1 = tf.get_variable('v1', [1], initializer=tf.constant_initializer(1),collections=c1)
     
     v2 = tf.get_variable('v2', [1], initializer=tf.constant_initializer(2))
     tf.add_to_collection('c2', v2)
      
     with tf.Session() as sess:
         sess.run(tf.global_variables_initializer())
         print(tf.get_collection('c1'))
         print(tf.get_collection('c2'))

其输出为：

[<tf.Variable 'v1:0' shape=(1,) dtype=float32_ref>]
     [<tf.Variable 'v2:0' shape=(1,) dtype=float32_ref>]

tf.get\_variable的用法可以参照我的另一篇博文：[https://blog.csdn.net/weixin\_44791964/article/details/96134474][https_blog.csdn.net_weixin_44791964_article_details_96134474]

[https_blog.csdn.net_weixin_44791964_article_details_96134474]: https://blog.csdn.net/weixin_44791964/article/details/96134474