p47068915
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

mode_init_bug

This commit is contained in:
baiyangfan 2020-09-11 13:16:58 +08:00
parent c021f2379e
commit b7c1fbb4dc
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
mindspore/common/initializer.py
View File

@ -268,10 +268,10 @@ class XavierUniform(Initializer):
Initialize the array with xavier uniform algorithm, and from a uniform distribution collect samples within
U[-boundary, boundary] The boundary is defined as :
math:`boundary = gain * \sqrt{\frac{6}{n_{in} + n_{out}}}`.
where :math:`boundary = gain * \sqrt{\frac{6}{n_{in} + n_{out}}}`.
math:`n_{in}` is the number of input units in the weight tensor.
math:`n_{out}` is the number of output units in the weight tensor.
where :math:`n_{in}` is the number of input units in the weight tensor.
where :math:`n_{out}` is the number of output units in the weight tensor.
Args:
gain (Array): The array to be assigned. Default: 1.
@ -298,9 +298,9 @@ class HeUniform(Initializer):
Initialize the array with He kaiming uniform algorithm, and from a uniform distribution collect samples within
U[-boundary, boundary] The boundary is defined as :
math:`boundary = \sqrt{\frac{6}{n_{in}}}`
where :math:`boundary = \sqrt{\frac{6}{n_{in}}}`.
math:`n_{in}` is the number of input units in the weight tensor.
where :math:`n_{in}` is the number of input units in the weight tensor.
Args:
arr (Array): The array to be assigned.