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

!49425 update max_unpool2d/3d doc 

Merge pull request !49425 from liuchao/code_docs_maxunpool
This commit is contained in:
i-robot 2023-02-27 03:54:30 +00:00 committed by Gitee
parent 8254a39e40 86775d40da
commit 81e98d3f82
No known key found for this signature in database
GPG Key ID: 173E9B9CA92EEF8F
3 changed files with 17 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
mindspore/python/mindspore/nn/layer/pooling.py
View File

@ -1470,12 +1470,9 @@ class MaxUnpool1d(Cell):
class MaxUnpool2d(Cell):
r"""
Computes a partial inverse of MaxPool2d.
Computes inverse of MaxPool2d.
MaxPool2d is not fully invertible, since the non-maximal values are lost.
MaxUnpool2d takes in as input the output of MaxPool2d including the indices of the maximal values
and computes a partial inverse in which all non-maximal values are set to zero. Typically the input
MaxUnpool2d keeps the maximal value and set all position of non-maximal values to zero. Typically the input
is of shape :math:`(N, C, H_{in}, W_{in})` or :math:`(C, H_{in}, W_{in})`, and the output is of
shape :math:`(N, C, H_{out}, W_{out})` or :math:`(C, H_{out}, W_{out})`. The operation is as follows.
@ -1560,12 +1557,9 @@ class MaxUnpool2d(Cell):
class MaxUnpool3d(Cell):
r"""
Computes a partial inverse of MaxPool3d.
Computes inverse of MaxPool3d.
MaxPool3d is not fully invertible, since the non-maximal values are lost.
MaxUnpool3d takes in as input the output of MaxPool3d including the indices of the maximal
values and computes a partial inverse in which all non-maximal values are set to zero.
MaxUnpool3d keeps the maximal value and set all position of non-maximal values to zero.
Typically the input is of shape :math:`(N, C, D_{in}, H_{in}, W_{in})` or :math:`(C, D_{in}, H_{in}, W_{in})`,
and the output is of shape :math:`(N, C, D_{out}, H_{out}, W_{out})` or :math:`(C, D_{out}, H_{out}, W_{out})`.
The operation is as follows.

19
mindspore/python/mindspore/ops/function/nn_func.py
View File

@ -864,12 +864,9 @@ def max_unpool1d(x, indices, kernel_size, stride=None, padding=0, output_size=No
def max_unpool2d(x, indices, kernel_size, stride=None, padding=0, output_size=None):
r"""
Computes a partial inverse of maxpool2d.
Computes inverse of maxpool2d.
maxpool2d is not fully invertible, since the non-maximal values are lost.
max_unpool2d takes the output of maxpool2d as inputs including the indices of the maximal values
and computes a partial inverse in which all non-maximal values are set to zero. Typically the input
max_unpool2d keeps the maximal value and set all position of non-maximal values to zero. Typically the input
is of shape :math:`(N, C, H_{in}, W_{in})` or :math:`(C, H_{in}, W_{in})`, and the output is of
shape :math:`(N, C, H_{out}, W_{out})` or :math:`(C, H_{out}, W_{out})`. The operation is as follows.
@ -971,14 +968,12 @@ def max_unpool2d(x, indices, kernel_size, stride=None, padding=0, output_size=No
def max_unpool3d(x, indices, kernel_size, stride=None, padding=0, output_size=None):
r"""
Computes a partial inverse of maxpool3d.
Computes inverse of maxpool3d.
maxpool3d is not fully invertible, since the non-maximal values are lost.
max_unpool3d takes the output of maxpool3d as input including the indices of the maximal values and computes a
partial inverse in which all non-maximal values are set to zero. Typically the input is of shape
:math:`(N, C, D_{in}, H_{in}, W_{in})` or :math:`(C, D_{in}, H_{in}, W_{in})`, and the output is of shape
:math:`(N, C, D_{out}, H_{out}, W_{out})` or :math:`(C, D_{out}, H_{out}, W_{out})`. The operation is as follows.
max_unpool3d keeps the maximal value and set all position of non-maximal values to zero.
Typically the input is of shape :math:`(N, C, D_{in}, H_{in}, W_{in})` or :math:`(C, D_{in}, H_{in}, W_{in})`,
and the output is of shape :math:`(N, C, D_{out}, H_{out}, W_{out})` or :math:`(C, D_{out}, H_{out}, W_{out})`.
The operation is as follows.
.. math::
\begin{array}{ll} \\

18
mindspore/python/mindspore/ops/operations/nn_ops.py
View File

@ -2001,14 +2001,11 @@ class MaxPool3D(Primitive):
class MaxUnpool2D(Primitive):
r"""
Computes a partial inverse of MaxPool2D.
Computes inverse of MaxPool2D.
MaxPool2D is not fully invertible, since the non-maximal values are lost.
MaxUnpool2D takes in as input the output of MaxPool2D including the indices of
the maximal values and computes a partial inverse in which all non-maximal values
are set to zero. Typically the input is of shape :math:`(N, C, H_{in}, W_{in})` ,
the output is of shape :math:`(N, C, H_{out}, W_{out})` , the operation is as follows:
MaxUnpool2D keeps the maximal value and set all position of non-maximal values to zero.
Typically the input is of shape :math:`(N, C, H_{in}, W_{in})` , the output is of
shape :math:`(N, C, H_{out}, W_{out})` , the operation is as follows:
.. math::
\begin{array}{ll} \\
@ -2104,12 +2101,9 @@ class MaxUnpool2D(Primitive):
class MaxUnpool3D(Primitive):
r"""
Computes a partial inverse of MaxUnpool3D.
Computes inverse of MaxUnpool3D.
MaxUnpool3D is not fully invertible, since the non-maximal values are lost.
MaxUnpool3D takes in as input the output of MaxUnpool3D including the indices of the maximal
values and computes a partial inverse in which all non-maximal values are set to zero.
MaxUnpool3D keeps the maximal value and set all position of non-maximal values to zero.
Typically the input is of shape :math:`(N, C, D_{in}, H_{in}, W_{in})`, the output is of
shape :math:`(N, C, D_{out}, H_{out}, W_{out})`, the operation is as follows.