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
PaddlePaddle
PaddleDetection
提交
b92ef45f
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
大约 1 年 前同步成功
通知
695
Star
11112
Fork
2696
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
184
列表
看板
标记
里程碑
合并请求
40
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleDetection
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
184
Issue
184
列表
看板
标记
里程碑
合并请求
40
合并请求
40
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
未验证
提交
b92ef45f
编写于
2月 27, 2019
作者:
J
jerrywgz
提交者:
GitHub
2月 27, 2019
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #15678 from jerrywgz/refine_softmax_with_cross_entropy
change default option related to softmax, test=develop
上级
558f94cd
b53fdbed
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
9 addition
and
8 deletion
+9
-8
paddle/fluid/API.spec
paddle/fluid/API.spec
+2
-2
paddle/fluid/operators/softmax_with_cross_entropy_op.cc
paddle/fluid/operators/softmax_with_cross_entropy_op.cc
+2
-2
python/paddle/fluid/layers/nn.py
python/paddle/fluid/layers/nn.py
+5
-4
未找到文件。
paddle/fluid/API.spec
浏览文件 @
b92ef45f
...
@@ -86,7 +86,7 @@ paddle.fluid.layers.conv2d ArgSpec(args=['input', 'num_filters', 'filter_size',
...
@@ -86,7 +86,7 @@ paddle.fluid.layers.conv2d ArgSpec(args=['input', 'num_filters', 'filter_size',
paddle.fluid.layers.conv3d ArgSpec(args=['input', 'num_filters', 'filter_size', 'stride', 'padding', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name'], varargs=None, keywords=None, defaults=(1, 0, 1, None, None, None, True, None, None))
paddle.fluid.layers.conv3d ArgSpec(args=['input', 'num_filters', 'filter_size', 'stride', 'padding', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name'], varargs=None, keywords=None, defaults=(1, 0, 1, None, None, None, True, None, None))
paddle.fluid.layers.sequence_pool ArgSpec(args=['input', 'pool_type', 'is_test'], varargs=None, keywords=None, defaults=(False,))
paddle.fluid.layers.sequence_pool ArgSpec(args=['input', 'pool_type', 'is_test'], varargs=None, keywords=None, defaults=(False,))
paddle.fluid.layers.sequence_softmax ArgSpec(args=['input', 'use_cudnn', 'name'], varargs=None, keywords=None, defaults=(False, None))
paddle.fluid.layers.sequence_softmax ArgSpec(args=['input', 'use_cudnn', 'name'], varargs=None, keywords=None, defaults=(False, None))
paddle.fluid.layers.softmax ArgSpec(args=['input', 'use_cudnn', 'name'], varargs=None, keywords=None, defaults=(
Tru
e, None))
paddle.fluid.layers.softmax ArgSpec(args=['input', 'use_cudnn', 'name'], varargs=None, keywords=None, defaults=(
Fals
e, None))
paddle.fluid.layers.pool2d ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True))
paddle.fluid.layers.pool2d ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True))
paddle.fluid.layers.pool3d ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True))
paddle.fluid.layers.pool3d ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True))
paddle.fluid.layers.adaptive_pool2d ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None))
paddle.fluid.layers.adaptive_pool2d ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None))
...
@@ -128,7 +128,7 @@ paddle.fluid.layers.row_conv ArgSpec(args=['input', 'future_context_size', 'para
...
@@ -128,7 +128,7 @@ paddle.fluid.layers.row_conv ArgSpec(args=['input', 'future_context_size', 'para
paddle.fluid.layers.multiplex ArgSpec(args=['inputs', 'index'], varargs=None, keywords=None, defaults=None)
paddle.fluid.layers.multiplex ArgSpec(args=['inputs', 'index'], varargs=None, keywords=None, defaults=None)
paddle.fluid.layers.layer_norm ArgSpec(args=['input', 'scale', 'shift', 'begin_norm_axis', 'epsilon', 'param_attr', 'bias_attr', 'act', 'name'], varargs=None, keywords=None, defaults=(True, True, 1, 1e-05, None, None, None, None))
paddle.fluid.layers.layer_norm ArgSpec(args=['input', 'scale', 'shift', 'begin_norm_axis', 'epsilon', 'param_attr', 'bias_attr', 'act', 'name'], varargs=None, keywords=None, defaults=(True, True, 1, 1e-05, None, None, None, None))
paddle.fluid.layers.group_norm ArgSpec(args=['input', 'groups', 'epsilon', 'param_attr', 'bias_attr', 'act', 'data_layout', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None, 'NCHW', None))
paddle.fluid.layers.group_norm ArgSpec(args=['input', 'groups', 'epsilon', 'param_attr', 'bias_attr', 'act', 'data_layout', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None, 'NCHW', None))
paddle.fluid.layers.softmax_with_cross_entropy ArgSpec(args=['logits', 'label', 'soft_label', 'ignore_index', 'numeric_stable_mode', 'return_softmax'], varargs=None, keywords=None, defaults=(False, -100,
Fals
e, False))
paddle.fluid.layers.softmax_with_cross_entropy ArgSpec(args=['logits', 'label', 'soft_label', 'ignore_index', 'numeric_stable_mode', 'return_softmax'], varargs=None, keywords=None, defaults=(False, -100,
Tru
e, False))
paddle.fluid.layers.smooth_l1 ArgSpec(args=['x', 'y', 'inside_weight', 'outside_weight', 'sigma'], varargs=None, keywords=None, defaults=(None, None, None))
paddle.fluid.layers.smooth_l1 ArgSpec(args=['x', 'y', 'inside_weight', 'outside_weight', 'sigma'], varargs=None, keywords=None, defaults=(None, None, None))
paddle.fluid.layers.one_hot ArgSpec(args=['input', 'depth'], varargs=None, keywords=None, defaults=None)
paddle.fluid.layers.one_hot ArgSpec(args=['input', 'depth'], varargs=None, keywords=None, defaults=None)
paddle.fluid.layers.autoincreased_step_counter ArgSpec(args=['counter_name', 'begin', 'step'], varargs=None, keywords=None, defaults=(None, 1, 1))
paddle.fluid.layers.autoincreased_step_counter ArgSpec(args=['counter_name', 'begin', 'step'], varargs=None, keywords=None, defaults=(None, 1, 1))
...
...
paddle/fluid/operators/softmax_with_cross_entropy_op.cc
浏览文件 @
b92ef45f
...
@@ -46,10 +46,10 @@ class SoftmaxWithCrossEntropyOpMaker
...
@@ -46,10 +46,10 @@ class SoftmaxWithCrossEntropyOpMaker
.
SetDefault
(
false
);
.
SetDefault
(
false
);
AddAttr
<
bool
>
(
AddAttr
<
bool
>
(
"numeric_stable_mode"
,
"numeric_stable_mode"
,
"(bool, default:
fals
e), A flag to indicate whether to use more "
"(bool, default:
tru
e), A flag to indicate whether to use more "
"numerically stable algorithm. This flag is only valid when "
"numerically stable algorithm. This flag is only valid when "
"soft_label is false and GPU is used."
)
"soft_label is false and GPU is used."
)
.
SetDefault
(
fals
e
);
.
SetDefault
(
tru
e
);
AddAttr
<
int
>
(
AddAttr
<
int
>
(
"ignore_index"
,
"ignore_index"
,
"(int, default -100), Specifies a target value that is ignored and"
"(int, default -100), Specifies a target value that is ignored and"
...
...
python/paddle/fluid/layers/nn.py
浏览文件 @
b92ef45f
...
@@ -1767,7 +1767,7 @@ def sequence_softmax(input, use_cudnn=False, name=None):
...
@@ -1767,7 +1767,7 @@ def sequence_softmax(input, use_cudnn=False, name=None):
return
softmax_out
return
softmax_out
def
softmax
(
input
,
use_cudnn
=
Tru
e
,
name
=
None
):
def
softmax
(
input
,
use_cudnn
=
Fals
e
,
name
=
None
):
"""
"""
The input of the softmax operator is a tensor of any rank. The output tensor
The input of the softmax operator is a tensor of any rank. The output tensor
has the same shape as the input.
has the same shape as the input.
...
@@ -1795,7 +1795,8 @@ def softmax(input, use_cudnn=True, name=None):
...
@@ -1795,7 +1795,8 @@ def softmax(input, use_cudnn=True, name=None):
Args:
Args:
input (Variable): The input variable.
input (Variable): The input variable.
use_cudnn (bool): Use cudnn kernel or not, it is valid only when the cudnn
\
use_cudnn (bool): Use cudnn kernel or not, it is valid only when the cudnn
\
library is installed.
library is installed. To improve numerical stablity, set use_cudnn to
\
False by default. Default: False
name (str|None): A name for this layer(optional). If set None, the layer
name (str|None): A name for this layer(optional). If set None, the layer
will be named automatically. Default: None.
will be named automatically. Default: None.
...
@@ -5753,7 +5754,7 @@ def softmax_with_cross_entropy(logits,
...
@@ -5753,7 +5754,7 @@ def softmax_with_cross_entropy(logits,
label
,
label
,
soft_label
=
False
,
soft_label
=
False
,
ignore_index
=
kIgnoreIndex
,
ignore_index
=
kIgnoreIndex
,
numeric_stable_mode
=
Fals
e
,
numeric_stable_mode
=
Tru
e
,
return_softmax
=
False
):
return_softmax
=
False
):
"""
"""
**Softmax With Cross Entropy Operator.**
**Softmax With Cross Entropy Operator.**
...
@@ -5817,7 +5818,7 @@ def softmax_with_cross_entropy(logits,
...
@@ -5817,7 +5818,7 @@ def softmax_with_cross_entropy(logits,
When soft_label is True or CPU is used,
When soft_label is True or CPU is used,
the algorithm is always numerically stable.
the algorithm is always numerically stable.
Note that the speed may be slower when use
Note that the speed may be slower when use
stable algorithm. Default:
Fals
e
stable algorithm. Default:
Tru
e
return_softmax (bool): A flag indicating whether to return the softmax
return_softmax (bool): A flag indicating whether to return the softmax
along with the cross entropy loss. Default: False
along with the cross entropy loss. Default: False
...
...
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