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
csdn_franckjun
Paddle
提交
7dbc77ba
P
Paddle
项目概览
csdn_franckjun
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1
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
1
Issue
1
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 >>
提交
7dbc77ba
编写于
3月 17, 2017
作者:
L
Luo Tao
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
rename regression_cost to mse_cost
上级
56fcf9c1
变更
12
隐藏空白更改
内联
并排
Showing
12 changed file
with
34 addition
and
29 deletion
+34
-29
demo/introduction/api_train_v2.py
demo/introduction/api_train_v2.py
+1
-1
demo/introduction/trainer_config.py
demo/introduction/trainer_config.py
+1
-1
demo/recommendation/api_train_v2.py
demo/recommendation/api_train_v2.py
+1
-1
demo/recommendation/trainer_config.py
demo/recommendation/trainer_config.py
+1
-4
doc/api/v1/trainer_config_helpers/layers.rst
doc/api/v1/trainer_config_helpers/layers.rst
+12
-6
doc/getstarted/basic_usage/index_cn.rst
doc/getstarted/basic_usage/index_cn.rst
+2
-2
doc/getstarted/basic_usage/index_en.rst
doc/getstarted/basic_usage/index_en.rst
+1
-1
doc/howto/usage/k8s/k8s_distributed_cn.md
doc/howto/usage/k8s/k8s_distributed_cn.md
+1
-1
python/paddle/trainer_config_helpers/layers.py
python/paddle/trainer_config_helpers/layers.py
+7
-4
python/paddle/trainer_config_helpers/tests/configs/protostr/test_cost_layers_with_weight.protostr
...ts/configs/protostr/test_cost_layers_with_weight.protostr
+4
-4
python/paddle/trainer_config_helpers/tests/configs/test_cost_layers_with_weight.py
...fig_helpers/tests/configs/test_cost_layers_with_weight.py
+1
-1
python/paddle/v2/tests/test_layer.py
python/paddle/v2/tests/test_layer.py
+2
-3
未找到文件。
demo/introduction/api_train_v2.py
浏览文件 @
7dbc77ba
...
...
@@ -14,7 +14,7 @@ def main():
act
=
paddle
.
activation
.
Linear
(),
bias_attr
=
paddle
.
attr
.
Param
(
name
=
'b'
))
y
=
paddle
.
layer
.
data
(
name
=
'y'
,
type
=
paddle
.
data_type
.
dense_vector
(
1
))
cost
=
paddle
.
layer
.
regression
_cost
(
input
=
y_predict
,
label
=
y
)
cost
=
paddle
.
layer
.
mse
_cost
(
input
=
y_predict
,
label
=
y
)
# create parameters
parameters
=
paddle
.
parameters
.
create
(
cost
)
...
...
demo/introduction/trainer_config.py
浏览文件 @
7dbc77ba
...
...
@@ -34,5 +34,5 @@ y_predict = fc_layer(
size
=
1
,
act
=
LinearActivation
(),
bias_attr
=
ParamAttr
(
name
=
'b'
))
cost
=
regression
_cost
(
input
=
y_predict
,
label
=
y
)
cost
=
mse
_cost
(
input
=
y_predict
,
label
=
y
)
outputs
(
cost
)
demo/recommendation/api_train_v2.py
浏览文件 @
7dbc77ba
...
...
@@ -61,7 +61,7 @@ def main():
inference
=
paddle
.
layer
.
cos_sim
(
a
=
usr_combined_features
,
b
=
mov_combined_features
,
size
=
1
,
scale
=
5
)
cost
=
paddle
.
layer
.
regression
_cost
(
cost
=
paddle
.
layer
.
mse
_cost
(
input
=
inference
,
label
=
paddle
.
layer
.
data
(
name
=
'score'
,
type
=
paddle
.
data_type
.
dense_vector
(
1
)))
...
...
demo/recommendation/trainer_config.py
浏览文件 @
7dbc77ba
...
...
@@ -86,10 +86,7 @@ movie_feature = construct_feature("movie")
user_feature
=
construct_feature
(
"user"
)
similarity
=
cos_sim
(
a
=
movie_feature
,
b
=
user_feature
)
if
not
is_predict
:
outputs
(
regression_cost
(
input
=
similarity
,
label
=
data_layer
(
'rating'
,
size
=
1
)))
outputs
(
mse_cost
(
input
=
similarity
,
label
=
data_layer
(
'rating'
,
size
=
1
)))
define_py_data_sources2
(
'data/train.list'
,
...
...
doc/api/v1/trainer_config_helpers/layers.rst
浏览文件 @
7dbc77ba
...
...
@@ -432,6 +432,12 @@ multi_binary_label_cross_entropy
:members: multi_binary_label_cross_entropy
:noindex:
mse_cost
---------
.. automodule:: paddle.trainer_config_helpers.layers
:members: mse_cost
:noindex:
huber_cost
----------
.. automodule:: paddle.trainer_config_helpers.layers
...
...
@@ -450,6 +456,12 @@ rank_cost
:members: rank_cost
:noindex:
sum_cost
---------
.. automodule:: paddle.trainer_config_helpers.layers
:members: sum_cost
:noindex:
crf_layer
-----------------
.. automodule:: paddle.trainer_config_helpers.layers
...
...
@@ -486,12 +498,6 @@ hsigmoid
:members: hsigmoid
:noindex:
sum_cost
---------
.. automodule:: paddle.trainer_config_helpers.layers
:members: sum_cost
:noindex:
Check Layer
============
...
...
doc/getstarted/basic_usage/index_cn.rst
浏览文件 @
7dbc77ba
...
...
@@ -55,7 +55,7 @@ PaddlePaddle是源于百度的一个深度学习平台。这份简短的介绍
# 线性计算网络层: ȳ = wx + b
ȳ = fc_layer(input=x, param_attr=ParamAttr(name='w'), size=1, act=LinearActivation(), bias_attr=ParamAttr(name='b'))
# 计算误差函数,即 ȳ 和真实 y 之间的距离
cost =
regression
_cost(input= ȳ, label=y)
cost =
mse
_cost(input= ȳ, label=y)
outputs(cost)
...
...
@@ -69,7 +69,7 @@ PaddlePaddle是源于百度的一个深度学习平台。这份简短的介绍
- **数据层**:数据层 `data_layer` 是神经网络的入口,它读入数据并将它们传输到接下来的网络层。这里数据层有两个,分别对应于变量 `x` 和 `y`。
- **全连接层**:全连接层 `fc_layer` 是基础的计算单元,这里利用它建模变量之间的线性关系。计算单元是神经网络的核心,PaddlePaddle支持大量的计算单元和任意深度的网络连接,从而可以拟合任意的函数来学习复杂的数据关系。
- **回归误差代价层**:回归误差代价层 `
regression
_cost` 是众多误差代价函数层的一种,它们在训练过程作为网络的出口,用来计算模型的误差,是模型参数优化的目标函数。
- **回归误差代价层**:回归误差代价层 `
mse
_cost` 是众多误差代价函数层的一种,它们在训练过程作为网络的出口,用来计算模型的误差,是模型参数优化的目标函数。
定义了网络结构并保存为 `trainer_config.py` 之后,运行以下训练命令:
...
...
doc/getstarted/basic_usage/index_en.rst
浏览文件 @
7dbc77ba
...
...
@@ -49,7 +49,7 @@ To recover this relationship between ``X`` and ``Y``, we use a neural network wi
x = data_layer(name='x', size=1)
y = data_layer(name='y', size=1)
y_predict = fc_layer(input=x, param_attr=ParamAttr(name='w'), size=1, act=LinearActivation(), bias_attr=ParamAttr(name='b'))
cost =
regression
_cost(input=y_predict, label=y)
cost =
mse
_cost(input=y_predict, label=y)
outputs(cost)
Some of the most fundamental usages of PaddlePaddle are demonstrated:
...
...
doc/howto/usage/k8s/k8s_distributed_cn.md
浏览文件 @
7dbc77ba
...
...
@@ -213,7 +213,7 @@ I1116 09:10:17.123440 50 Util.cpp:130] Calling runInitFunctions
I1116 09:10:17.123764 50 Util.cpp:143] Call runInitFunctions
done
.
[
WARNING 2016-11-16 09:10:17,227 default_decorators.py:40] please use keyword arguments
in
paddle config.
[
INFO 2016-11-16 09:10:17,239 networks.py:1282] The input order is
[
movie_id, title, genres, user_id, gender, age, occupation, rating]
[
INFO 2016-11-16 09:10:17,239 networks.py:1289] The output order is
[
__
regression
_cost_0__]
[
INFO 2016-11-16 09:10:17,239 networks.py:1289] The output order is
[
__
mse
_cost_0__]
I1116 09:10:17.392917 50 Trainer.cpp:170] trainer mode: Normal
I1116 09:10:17.613910 50 PyDataProvider2.cpp:257] loading dataprovider dataprovider::process
I1116 09:10:17.680917 50 PyDataProvider2.cpp:257] loading dataprovider dataprovider::process
...
...
python/paddle/trainer_config_helpers/layers.py
浏览文件 @
7dbc77ba
...
...
@@ -52,7 +52,7 @@ __all__ = [
"cos_sim"
,
"hsigmoid"
,
"conv_projection"
,
"
regression
_cost"
,
"
mse
_cost"
,
'classification_cost'
,
"LayerOutput"
,
'img_conv_layer'
,
...
...
@@ -3572,11 +3572,14 @@ def __cost_input__(input, label, weight=None):
@
wrap_name_default
()
@
layer_support
()
def
regression
_cost
(
input
,
label
,
weight
=
None
,
name
=
None
,
layer_attr
=
None
):
def
mse
_cost
(
input
,
label
,
weight
=
None
,
name
=
None
,
layer_attr
=
None
):
"""
Regression Layer.
mean squared error cost:
.. math::
$
\f
rac{1}{N}\sum_{i=1}^N(t _i- y_i)^2$
TODO(yuyang18): Complete this method.
:param name: layer name.
:type name: basestring
...
...
python/paddle/trainer_config_helpers/tests/configs/protostr/test_cost_layers_with_weight.protostr
浏览文件 @
7dbc77ba
...
...
@@ -45,7 +45,7 @@ layers {
coeff: 1.0
}
layers {
name: "__
regression
_cost_0__"
name: "__
mse
_cost_0__"
type: "square_error"
size: 1
active_type: ""
...
...
@@ -84,7 +84,7 @@ input_layer_names: "input"
input_layer_names: "label"
input_layer_names: "weight"
output_layer_names: "__cost_0__"
output_layer_names: "__
regression
_cost_0__"
output_layer_names: "__
mse
_cost_0__"
evaluators {
name: "classification_error_evaluator"
type: "classification_error"
...
...
@@ -99,12 +99,12 @@ sub_models {
layer_names: "weight"
layer_names: "__fc_layer_0__"
layer_names: "__cost_0__"
layer_names: "__
regression
_cost_0__"
layer_names: "__
mse
_cost_0__"
input_layer_names: "input"
input_layer_names: "label"
input_layer_names: "weight"
output_layer_names: "__cost_0__"
output_layer_names: "__
regression
_cost_0__"
output_layer_names: "__
mse
_cost_0__"
evaluator_names: "classification_error_evaluator"
is_recurrent_layer_group: false
}
...
...
python/paddle/trainer_config_helpers/tests/configs/test_cost_layers_with_weight.py
浏览文件 @
7dbc77ba
...
...
@@ -10,5 +10,5 @@ fc = fc_layer(input=data, size=10, act=SoftmaxActivation())
outputs
(
classification_cost
(
input
=
fc
,
label
=
lbl
,
weight
=
wt
),
regression
_cost
(
mse
_cost
(
input
=
fc
,
label
=
lbl
,
weight
=
wt
))
python/paddle/v2/tests/test_layer.py
浏览文件 @
7dbc77ba
...
...
@@ -126,9 +126,8 @@ class CostLayerTest(unittest.TestCase):
cost3
=
layer
.
cross_entropy_cost
(
input
=
inference
,
label
=
label
)
cost4
=
layer
.
cross_entropy_with_selfnorm_cost
(
input
=
inference
,
label
=
label
)
cost5
=
layer
.
regression_cost
(
input
=
inference
,
label
=
label
)
cost6
=
layer
.
regression_cost
(
input
=
inference
,
label
=
label
,
weight
=
weight
)
cost5
=
layer
.
mse_cost
(
input
=
inference
,
label
=
label
)
cost6
=
layer
.
mse_cost
(
input
=
inference
,
label
=
label
,
weight
=
weight
)
cost7
=
layer
.
multi_binary_label_cross_entropy_cost
(
input
=
inference
,
label
=
label
)
cost8
=
layer
.
rank_cost
(
left
=
score
,
right
=
score
,
label
=
score
)
...
...
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