tensorflow - tf.global_variables_initializer 的目的是什么？

Question

我想更详细地了解 tf.global_variables_initializer 的作用。一个sparse description is given here :

Returns an Op that initializes global variables.

但这并没有真正帮助我。我知道该操作对于初始化图形是必要的，但这实际上意味着什么？这是编译图表的步骤吗？

Answer 1

给出了更完整的描述here 。

只有在 session 中运行 tf.global_variables_initializer() 后，您的变量才会保存您在声明它们时告诉它们保存的值 (tf.Variable(tf.zeros(.. .)), tf.Variable(tf.random_normal(...)),...).

来自 TF 文档:

Calling tf.Variable() adds several ops to the graph:

• A variable op that holds the variable value.
• An initializer op that sets the variable to its initial value. This is actually a tf.assign op.
• The ops for the initial value, such as the zeros op for the biases variable in the example are also added to the graph.

还有:

Variable initializers must be run explicitly before other ops in your model can be run. The easiest way to do that is to add an op that runs all the variable initializers, and run that op before using the model.