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
BaiXuePrincess
Paddle
提交
3a0919ba
P
Paddle
项目概览
BaiXuePrincess
/
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
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
提交
3a0919ba
编写于
6月 29, 2017
作者:
Y
yangyaming
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Add test for configuration and add doc.
上级
b5ab4b69
变更
4
显示空白变更内容
内联
并排
Showing
4 changed file
with
62 addition
and
1 deletion
+62
-1
doc/api/v2/config/layer.rst
doc/api/v2/config/layer.rst
+13
-0
python/paddle/trainer_config_helpers/tests/configs/file_list.sh
.../paddle/trainer_config_helpers/tests/configs/file_list.sh
+1
-1
python/paddle/trainer_config_helpers/tests/configs/test_detection_output_layer.py
...nfig_helpers/tests/configs/test_detection_output_layer.py
+23
-0
python/paddle/trainer_config_helpers/tests/configs/test_multibox_loss_layer.py
..._config_helpers/tests/configs/test_multibox_loss_layer.py
+25
-0
未找到文件。
doc/api/v2/config/layer.rst
浏览文件 @
3a0919ba
...
@@ -445,6 +445,11 @@ smooth_l1_cost
...
@@ -445,6 +445,11 @@ smooth_l1_cost
.. autoclass:: paddle.v2.layer.smooth_l1_cost
.. autoclass:: paddle.v2.layer.smooth_l1_cost
:noindex:
:noindex:
multibox_loss
--------------
.. autoclass:: paddle.v2.layer.multibox_loss
:noindex:
Check Layer
Check Layer
============
============
...
@@ -468,3 +473,11 @@ prelu
...
@@ -468,3 +473,11 @@ prelu
--------
--------
.. autoclass:: paddle.v2.layer.prelu
.. autoclass:: paddle.v2.layer.prelu
:noindex:
:noindex:
Detection output Layer
======================
detection_output
---
.. autoclass:: paddle.v2.layer.detection_output
:noindex:
python/paddle/trainer_config_helpers/tests/configs/file_list.sh
浏览文件 @
3a0919ba
...
@@ -6,6 +6,6 @@ img_layers img_trans_layers util_layers simple_rnn_layers unused_layers test_cos
...
@@ -6,6 +6,6 @@ img_layers img_trans_layers util_layers simple_rnn_layers unused_layers test_cos
test_rnn_group shared_fc shared_lstm shared_gru test_cost_layers_with_weight
test_rnn_group shared_fc shared_lstm shared_gru test_cost_layers_with_weight
test_spp_layer test_bilinear_interp test_maxout test_bi_grumemory math_ops
test_spp_layer test_bilinear_interp test_maxout test_bi_grumemory math_ops
test_seq_concat_reshape test_pad test_smooth_l1 test_multiplex_layer
test_seq_concat_reshape test_pad test_smooth_l1 test_multiplex_layer
test_prelu_layer test_row_conv
)
test_prelu_layer test_row_conv
test_detection_output_layer test_multibox_loss_layer
)
export
whole_configs
=(
test_split_datasource
)
export
whole_configs
=(
test_split_datasource
)
python/paddle/trainer_config_helpers/tests/configs/test_detection_output_layer.py
0 → 100644
浏览文件 @
3a0919ba
from
paddle.trainer_config_helpers
import
*
settings
(
batch_size
=
1000
,
learning_rate
=
1e-5
)
input_loc
=
data_layer
(
name
=
'input_loc'
,
size
=
16
,
height
=
16
,
width
=
1
)
input_conf
=
data_layer
(
name
=
'input_conf'
,
size
=
8
,
height
=
1
,
width
=
8
)
priorbox
=
data_layer
(
name
=
'priorbox'
,
size
=
32
,
height
=
4
,
width
=
8
)
detout
=
detection_output_layer
(
input_loc
=
input_loc
,
input_conf
=
input_conf
,
priorbox
=
priorbox
,
num_classes
=
21
,
nms_threshold
=
0.45
,
nms_top_k
=
400
,
keep_top_k
=
200
,
confidence_threshold
=
0.01
,
background_id
=
0
,
name
=
'test_detection_output'
)
outputs
(
detout
)
python/paddle/trainer_config_helpers/tests/configs/test_multibox_loss_layer.py
0 → 100644
浏览文件 @
3a0919ba
from
paddle.trainer_config_helpers
import
*
settings
(
batch_size
=
1000
,
learning_rate
=
1e-5
)
input_loc
=
data_layer
(
name
=
'input_loc'
,
size
=
16
,
height
=
16
,
width
=
1
)
input_conf
=
data_layer
(
name
=
'input_conf'
,
size
=
8
,
height
=
1
,
width
=
8
)
priorbox
=
data_layer
(
name
=
'priorbox'
,
size
=
32
,
height
=
4
,
width
=
8
)
label
=
data_layer
(
name
=
'label'
,
size
=
24
,
height
=
4
,
width
=
6
)
multibox_loss
=
multibox_loss_layer
(
input_loc
=
input_loc
,
input_conf
=
input_conf
,
priorbox
=
priorbox
,
label
=
label
,
num_classes
=
21
,
overlap_threshold
=
0.5
,
neg_pos_ratio
=
3.0
,
neg_overlap
=
0.5
,
background_id
=
0
,
name
=
'test_multibox_loss'
)
outputs
(
multibox_loss
)
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