tf.initialize_all_variables() 和 tf.global_variables_initializer() 有什么区别 [英] What are the differences between tf.initialize_all_variables() and tf.global_variables_initializer()

问题描述

在Tensorflow官网上，对tf.initialize_all_variables()和tf.global_variables_initializer()函数的解释如下

On Tensorflow official website, it gives explantions of the tf.initialize_all_variables() and tf.global_variables_initializer() functions as follow

返回一个初始化所有变量的操作.

tf.initialize_all_variables():

Returns an op that initializes all variables.

添加一个操作来初始化模型中的所有变量

Adds an op to initialize all variables in the model

似乎两者都可以用来初始化图中的所有变量.我们可以交换使用这两个函数吗?如果不是，会有什么区别?

It seems like both can be used to initialize all variables in graphs. Can we use these two functions exchangbly? If not, what would be the differences?

推荐答案

很遗憾，您忘记阅读 tf.initialize_all_variables.

Unfortunately, you forgot to read an important line in the documentation of tf.initialize_all_variables.

此功能已弃用.它将在 2017-03-02 之后移除.更新说明:改用tf.global_variables_initializer.

THIS FUNCTION IS DEPRECATED. It will be removed after 2017-03-02. Instructions for updating: Use tf.global_variables_initializer instead.

这篇关于tf.initialize_all_variables() 和 tf.global_variables_initializer() 有什么区别的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！