Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
wmsofts
Paddle
提交
0032b4a4
P
Paddle
项目概览
wmsofts
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
未验证
提交
0032b4a4
编写于
4月 16, 2018
作者:
G
Guo Sheng
提交者:
GitHub
4月 16, 2018
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #9940 from guoshengCS/add-python-label-smooth
Add python wrapper for label smoothing
上级
a097d082
f086ccb7
变更
3
显示空白变更内容
内联
并排
Showing
3 changed file
with
82 addition
and
0 deletion
+82
-0
doc/fluid/api/layers.rst
doc/fluid/api/layers.rst
+6
-0
python/paddle/fluid/layers/nn.py
python/paddle/fluid/layers/nn.py
+66
-0
python/paddle/fluid/tests/unittests/test_layers.py
python/paddle/fluid/tests/unittests/test_layers.py
+10
-0
未找到文件。
doc/fluid/api/layers.rst
浏览文件 @
0032b4a4
...
...
@@ -473,6 +473,12 @@ multiplex
.. autofunction:: paddle.fluid.layers.multiplex
:noindex:
label_smooth
------------
.. autofunction:: paddle.fluid.layers.label_smooth
:noindex:
ops
===
...
...
python/paddle/fluid/layers/nn.py
浏览文件 @
0032b4a4
...
...
@@ -77,6 +77,7 @@ __all__ = [
'lod_reset'
,
'lrn'
,
'pad'
,
'label_smooth'
,
]
...
...
@@ -3678,3 +3679,68 @@ def pad(x, paddings, pad_value=0., name=None):
attrs
=
{
'paddings'
:
paddings
,
'pad_value'
:
float
(
pad_value
)})
return
out
def
label_smooth
(
label
,
prior_dist
=
None
,
epsilon
=
0.1
,
dtype
=
"float32"
,
name
=
None
):
"""
Label smoothing is a mechanism to regularize the classifier layer and is
called label-smoothing regularization (LSR).
Label smoothing is proposed to encourage the model to be less confident,
since optimizing the log-likelihood of the correct label directly may
cause overfitting and reduce the ability of the model to adapt. Label
smoothing replaces the ground-truth label :math:`y` with the weighted sum
of itself and some fixed distribution :math:`\mu`. For class :math:`k`,
i.e.
.. math::
\\
tilde{y_k} = (1 - \epsilon) * y_k + \epsilon * \mu_k,
where :math:`1 - \epsilon` and :math:`\epsilon` are the weights
respectively, and :math:`
\\
tilde{y}_k` is the smoothed label. Usually
uniform distribution is used for :math:`\mu`.
See more details about label smoothing in https://arxiv.org/abs/1512.00567.
Args:
label(Variable): The input variable containing the label data. The
label data should use one-hot representation.
prior_dist(Variable): The prior distribution to be used to smooth
labels. If not provided, an uniform distribution
is used. The shape of :attr:`prior_dist` should
be :math:`(1, class\_num)`.
epsilon(float): The weight used to mix up the original ground-truth
distribution and the fixed distribution.
dtype(np.dtype|core.VarDesc.VarType|str): The type of data : float32,
float_64, int etc.
name(str|None): A name for this layer(optional). If set None, the layer
will be named automatically.
Returns:
Variable: The tensor variable containing the smoothed labels.
Examples:
.. code-block:: python
label = layers.data(name="label", shape=[1], dtype="float32")
one_hot_label = layers.one_hot(input=label, depth=10)
smooth_label = layers.label_smooth(
label=one_hot_label, epsilon=0.1, dtype="float32")
"""
if
epsilon
>
1.
or
epsilon
<
0.
:
raise
ValueError
(
"The value of epsilon must be between 0 and 1."
)
helper
=
LayerHelper
(
"label_smooth"
,
**
locals
())
label
.
stop_gradient
=
True
smooth_label
=
helper
.
create_tmp_variable
(
dtype
)
helper
.
append_op
(
type
=
"label_smooth"
,
inputs
=
{
"X"
:
label
,
"PriorDist"
:
prior_dist
}
if
prior_dist
else
{
"X"
:
label
},
outputs
=
{
"Out"
:
smooth_label
},
attrs
=
{
"epsilon"
:
float
(
epsilon
)})
return
smooth_label
python/paddle/fluid/tests/unittests/test_layers.py
浏览文件 @
0032b4a4
...
...
@@ -340,6 +340,16 @@ class TestBook(unittest.TestCase):
print
(
layers
.
lod_reset
(
x
=
x
,
y
=
y
))
print
(
str
(
program
))
def
test_label_smooth
(
self
):
program
=
Program
()
with
program_guard
(
program
):
label
=
layers
.
data
(
name
=
"label"
,
shape
=
[
1
],
dtype
=
"float32"
)
one_hot_label
=
layers
.
one_hot
(
input
=
label
,
depth
=
10
)
smooth_label
=
layers
.
label_smooth
(
label
=
one_hot_label
,
epsilon
=
0.1
,
dtype
=
"float32"
)
self
.
assertIsNotNone
(
smooth_label
)
print
(
str
(
program
))
if
__name__
==
'__main__'
:
unittest
.
main
()
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录