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
a785496b
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
大约 1 年 前同步成功
通知
694
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
体验新版 GitCode,发现更多精彩内容 >>
提交
a785496b
编写于
12月 22, 2017
作者:
T
tensor-tang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix logical error
上级
86b8bdc0
变更
5
显示空白变更内容
内联
并排
Showing
5 changed file
with
14 addition
and
26 deletion
+14
-26
benchmark/paddle/image/alexnet.py
benchmark/paddle/image/alexnet.py
+10
-22
benchmark/paddle/image/run_mkl_infer.sh
benchmark/paddle/image/run_mkl_infer.sh
+1
-1
benchmark/paddle/image/run_mkl_train.sh
benchmark/paddle/image/run_mkl_train.sh
+1
-1
benchmark/paddle/image/run_openblas_infer.sh
benchmark/paddle/image/run_openblas_infer.sh
+1
-1
benchmark/paddle/image/run_openblas_train.sh
benchmark/paddle/image/run_openblas_train.sh
+1
-1
未找到文件。
benchmark/paddle/image/alexnet.py
浏览文件 @
a785496b
...
...
@@ -6,7 +6,7 @@ height = 227
width
=
227
num_class
=
1000
batch_size
=
get_config_arg
(
'batch_size'
,
int
,
128
)
use_mkldnn
=
get_config_arg
(
'use_mkldnn'
,
bool
,
False
)
gp
=
get_config_arg
(
'layer_num'
,
int
,
1
)
is_infer
=
get_config_arg
(
"is_infer"
,
bool
,
False
)
num_samples
=
get_config_arg
(
'num_samples'
,
int
,
2560
)
...
...
@@ -41,12 +41,7 @@ net = img_pool_layer(input=net, pool_size=3, stride=2)
# conv2
net
=
img_conv_layer
(
input
=
net
,
filter_size
=
5
,
num_filters
=
256
,
stride
=
1
,
padding
=
2
,
groups
=
2
if
use_mkldnn
else
1
)
input
=
net
,
filter_size
=
5
,
num_filters
=
256
,
stride
=
1
,
padding
=
2
,
groups
=
gp
)
net
=
img_cmrnorm_layer
(
input
=
net
,
size
=
5
,
scale
=
0.0001
,
power
=
0.75
)
net
=
img_pool_layer
(
input
=
net
,
pool_size
=
3
,
stride
=
2
)
...
...
@@ -55,21 +50,11 @@ net = img_conv_layer(
input
=
net
,
filter_size
=
3
,
num_filters
=
384
,
stride
=
1
,
padding
=
1
)
# conv4
net
=
img_conv_layer
(
input
=
net
,
filter_size
=
3
,
num_filters
=
384
,
stride
=
1
,
padding
=
1
,
groups
=
2
if
use_mkldnn
else
1
)
input
=
net
,
filter_size
=
3
,
num_filters
=
384
,
stride
=
1
,
padding
=
1
,
groups
=
gp
)
# conv5
net
=
img_conv_layer
(
input
=
net
,
filter_size
=
3
,
num_filters
=
256
,
stride
=
1
,
padding
=
1
,
groups
=
2
if
use_mkldnn
else
1
)
input
=
net
,
filter_size
=
3
,
num_filters
=
256
,
stride
=
1
,
padding
=
1
,
groups
=
gp
)
net
=
img_pool_layer
(
input
=
net
,
pool_size
=
3
,
stride
=
2
)
net
=
fc_layer
(
...
...
@@ -84,6 +69,9 @@ net = fc_layer(
layer_attr
=
ExtraAttr
(
drop_rate
=
0.5
))
net
=
fc_layer
(
input
=
net
,
size
=
1000
,
act
=
SoftmaxActivation
())
lab
=
data_layer
(
'label'
,
num_class
)
loss
=
cross_entropy
(
input
=
net
,
label
=
lab
)
outputs
(
loss
)
if
is_infer
:
outputs
(
net
)
else
:
lab
=
data_layer
(
'label'
,
num_class
)
loss
=
cross_entropy
(
input
=
net
,
label
=
lab
)
outputs
(
loss
)
benchmark/paddle/image/run_mkl_infer.sh
浏览文件 @
a785496b
...
...
@@ -79,7 +79,7 @@ fi
# inference benchmark
for
use_mkldnn
in
True False
;
do
for
batchsize
in
1 2 4 8 16
;
do
infer alexnet
group
2
$batchsize
$use_mkldnn
infer alexnet 2
$batchsize
$use_mkldnn
infer googlenet v1
$batchsize
$use_mkldnn
infer resnet 50
$batchsize
$use_mkldnn
infer vgg 19
$batchsize
$use_mkldnn
...
...
benchmark/paddle/image/run_mkl_train.sh
浏览文件 @
a785496b
...
...
@@ -47,6 +47,6 @@ for use_mkldnn in True False; do
train vgg 19
$batchsize
$use_mkldnn
train resnet 50
$batchsize
$use_mkldnn
train googlenet v1
$batchsize
$use_mkldnn
train alexnet
group
2
$batchsize
$use_mkldnn
train alexnet 2
$batchsize
$use_mkldnn
done
done
benchmark/paddle/image/run_openblas_infer.sh
浏览文件 @
a785496b
...
...
@@ -56,7 +56,7 @@ fi
# inference benchmark
for
batchsize
in
1 2 4 8 16
;
do
infer alexnet
group
2
$batchsize
$use_mkldnn
infer alexnet 2
$batchsize
$use_mkldnn
infer googlenet v1
$batchsize
infer resnet 50
$batchsize
infer vgg 19
$batchsize
...
...
benchmark/paddle/image/run_openblas_train.sh
浏览文件 @
a785496b
...
...
@@ -36,5 +36,5 @@ for batchsize in 64 128 256; do
train vgg 19
$batchsize
train resnet 50
$batchsize
train googlenet v1
$batchsize
train alexnet
group
2
$batchsize
$use_mkldnn
train alexnet 2
$batchsize
$use_mkldnn
done
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