tf.name_scope——tf2.1 Document

参考自tf2.1官方文档:
https://www.tensorflow.org/api_docs/python/tf/name_scope


A context manager for use when defining a Python op.
用于定义Python操作op的上下文管理器

tf.name_scope(
    name
)

This context manager pushes a name scope, which will make the name of all operations added within it have a prefix.
这个上下文管理器将创建一个名字作用域(或翻译为范围、或翻译为上下文,不太明白的可以看例子)(scope),使得在其中的所有(operations)操作,都加上一个给定的前缀



For example, to define a new Python op called my_op:

举个例子,我们定义一个叫my_op的Python操作(Python op):

def my_op(a, b, c, name=None):

    with tf.name_scope("MyOp") as scope:
        a = tf.convert_to_tensor(a, name="a")
        b = tf.convert_to_tensor(b, name="b")
        c = tf.convert_to_tensor(c, name="c")
        # Define some computation that uses `a`, `b`, and `c`.(在接下来的代码中,
        # 可以定义一些使用a, b, c 张量的操作)
        return foo_op(..., name=scope)

When executed, the Tensors a, b, c, will have names MyOp/a, MyOp/b, and MyOp/c
在执行时,张量abc,将被命名为MyOp/aMyOp/bMyOp/c
(注:即在前原当定义名字中加上前缀)



If the scope name already exists, the name will be made unique by appending `_n`. For example, calling `my_op` the second time will generate `MyOp_1/a`, etc.

如果在当前命名域(scope)内名称已经存在,则通过追加将使名称唯一 _n
例如,若MyOp/a已经存在,在将生成:MyOp_1/a,若仍然存在,则生成MyOp_2/a,直到不重名为止

原创文章 66 获赞 14 访问量 9090

猜你喜欢

转载自blog.csdn.net/HaoZiHuang/article/details/105209024
今日推荐