Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

修复 paddle.assign 等 API 的文档 #4850

Merged
merged 15 commits into from
Jun 6, 2022
Prev Previous commit
Next Next commit
Update XavierUniform_cn.rst
  • Loading branch information
BrilliantYuKaimin committed Jun 2, 2022
commit 0ad8aff4ec045a1760acbab0e895a321741bd4cb
2 changes: 1 addition & 1 deletion docs/api/paddle/nn/initializer/XavierUniform_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ XavierUniform
.. py:class:: paddle.nn.initializer.XavierUniform(fan_in=None, fan_out=None, name=None)


使用均匀分布的泽维尔权重初始化方法。泽维尔权重初始化方法出自泽维尔·格洛特和约书亚·本吉奥的论文 `Understanding the difficulty of training deep feedforward neural networks <http://proceedings.mlr.press/v9/glorot10a/glorot10a.pdf>`_
使用均匀分布的泽维尔权重初始化方法。泽维尔权重初始化方法出自泽维尔·格洛特和约书亚·本吉奥的论文 `Understanding the difficulty of training deep feedforward neural networks <http://proceedings.mlr.press/v9/glorot10a/glorot10a.pdf>`_

该初始化函数用于保持所有层的梯度尺度几乎一致。在均匀分布的情况下,取值范围为 :math:`[-x,x]`,其中

Expand Down