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

!48253 modify the name and samples of nn function multilabel_margin_loss. 

Merge pull request !48253 from 朱家兴/master
This commit is contained in:
i-robot 2023-02-10 01:34:41 +00:00 committed by Gitee
parent a8852757af 7ff743df1f
commit 9bb62cb742
No known key found for this signature in database
GPG Key ID: 173E9B9CA92EEF8F
7 changed files with 11 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/api/api_python/mindspore.ops.rst
View File

@ -65,7 +65,7 @@ mindspore.ops
mindspore.ops.margin_ranking_loss
mindspore.ops.mse_loss
mindspore.ops.multi_margin_loss
mindspore.ops.multi_label_margin_loss
mindspore.ops.multilabel_margin_loss
mindspore.ops.multilabel_soft_margin_loss
mindspore.ops.nll_loss
mindspore.ops.smooth_l1_loss

2
docs/api/api_python/ops/mindspore.ops.MultilabelMarginLoss.rst
View File

@ -8,4 +8,4 @@ mindspore.ops.MultilabelMarginLoss
创建一个标准，用于优化输入 :math:`x` （一个2D小批量Tensor）
和输出 :math:`y` （一个目标类别索引的2DTensor）之间的多类分类铰链损失（基于边距的损失）。
更多细节请参考 :func:`mindspore.ops.multi_label_margin_loss` 。
更多细节请参考 :func:`mindspore.ops.multilabel_margin_loss` 。

4
docs/api/api_python/ops/mindspore.ops.func_multi_label_margin_loss.rst
View File

@ -1,7 +1,7 @@
mindspore.ops.multi_label_margin_loss
mindspore.ops.multilabel_margin_loss
======================================
.. py:function:: mindspore.ops.multi_label_margin_loss(inputs, target, reduction='mean')
.. py:function:: mindspore.ops.multilabel_margin_loss(inputs, target, reduction='mean')
用于优化多标签分类问题的铰链损失。

2
docs/api/api_python_en/mindspore.ops.rst
View File

@ -65,7 +65,7 @@ Loss Functions
mindspore.ops.margin_ranking_loss
mindspore.ops.mse_loss
mindspore.ops.multi_margin_loss
mindspore.ops.multi_label_margin_loss
mindspore.ops.multilabel_margin_loss
mindspore.ops.multilabel_soft_margin_loss
mindspore.ops.nll_loss
mindspore.ops.smooth_l1_loss

2
mindspore/python/mindspore/ops/function/__init__.py
View File

@ -468,7 +468,7 @@ from .nn_func import (
conv3d,
glu,
multi_margin_loss,
multi_label_margin_loss,
multilabel_margin_loss,
multilabel_soft_margin_loss,
elu,
gelu,

9
mindspore/python/mindspore/ops/function/nn_func.py
View File

@ -5197,7 +5197,7 @@ def multi_margin_loss(inputs, target, p=1, margin=1, weight=None, reduction='mea
return outputs
def multi_label_margin_loss(inputs, target, reduction='mean'):
def multilabel_margin_loss(inputs, target, reduction='mean'):
r"""
Hinge loss for optimizing a multi-label classification.
@ -5248,10 +5248,9 @@ def multi_label_margin_loss(inputs, target, reduction='mean'):
Examples:
>>> inputs = Tensor(np.array([[0.1, 0.2, 0.4, 0.8], [0.2, 0.3, 0.5, 0.7]]), mindspore.float32)
>>> target = Tensor(np.array([[1, 2, 0, 3], [2, 3, -1, 1]]), mindspore.int32)
>>> output, _ = ops.multi_label_margin_loss(inputs, target)
>>> output = ops.multilabel_margin_loss(inputs, target)
>>> print(output)
(Tensor(shape=[], dtype=Float32, value= 0.325), Tensor(shape=[2, 4], dtype=Int32, value=
[[1, 1, 1, 1], [0, 0, 1, 1]]))
0.325
"""
loss = _get_cache_prim(P.MultilabelMarginLoss)(reduction)
@ -5851,7 +5850,7 @@ __all__ = [
'glu',
'margin_ranking_loss',
'multi_margin_loss',
'multi_label_margin_loss',
'multilabel_margin_loss',
'multilabel_soft_margin_loss',
'elu',
'gelu',

2
mindspore/python/mindspore/ops/operations/nn_ops.py
View File

@ -8808,7 +8808,7 @@ class MultilabelMarginLoss(Primitive):
hinge loss (margin-based loss) between input :math:`x` (a 2D mini-batch `Tensor`)
and output :math:`y` (which is a 2D `Tensor` of target class indices).
Refer to :func:`mindspore.ops.multi_label_margin_loss` for more details.
Refer to :func:`mindspore.ops.multilabel_margin_loss` for more details.
Supported Platforms:
``Ascend`` ``GPU``