未验证 提交 15f39b7e 编写于 作者: X Xin Pan 提交者: GitHub

Merge pull request #13978 from sneaxiy/release/1.0.0

Cherry-pick #13944 to release/1.0.0
......@@ -2302,19 +2302,28 @@ def layer_norm(input,
Args:
input(Variable): The input tensor variable.
scale(bool): Whether to learn the adaptive gain :math:`g` after
normalization.
normalization. Default True.
shift(bool): Whether to learn the adaptive bias :math:`b` after
normalization.
begin_norm_axis(bool): The normalization will be performed along
normalization. Default True.
begin_norm_axis(int): The normalization will be performed along
dimensions from :attr:`begin_norm_axis` to :attr:`rank(input)`.
Default 1.
epsilon(float): The small value added to the variance to prevent
division by zero.
division by zero. Default 1e-05.
param_attr(ParamAttr|None): The parameter attribute for the learnable
gain :math:`g`.
gain :math:`g`. If :attr:`scale` is False, :attr:`param_attr` is
omitted. If :attr:`scale` is True and :attr:`param_attr` is None,
a default :code:`ParamAttr` would be added as scale. The
:attr:`param_attr` is initialized as 1 if it is added. Default None.
bias_attr(ParamAttr|None): The parameter attribute for the learnable
bias :math:`b`.
bias :math:`b`. If :attr:`shift` is False, :attr:`bias_attr` is
omitted. If :attr:`shift` is True and :attr:`param_attr` is None,
a default :code:`ParamAttr` would be added as bias. The
:attr:`bias_attr` is initialized as 0 if it is added. Default None.
act(str): Activation to be applied to the output of layer normalizaiton.
name (str): The name of this layer. It is optional.
Default None.
name(str): The name of this layer. It is optional. Default None, and a
unique name would be generated automatically.
Returns:
${y_comment}
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册