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
机器未来
Paddle
提交
e9b48863
P
Paddle
项目概览
机器未来
/
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
提交
e9b48863
编写于
3月 02, 2018
作者:
H
Helin Wang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Fix vgg16 fc layer size: 4096 rather than 512
上级
d43469b7
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
6 addition
and
6 deletion
+6
-6
benchmark/cluster/vgg16/vgg16_fluid.py
benchmark/cluster/vgg16/vgg16_fluid.py
+2
-2
python/paddle/fluid/tests/book/test_image_classification.py
python/paddle/fluid/tests/book/test_image_classification.py
+2
-2
python/paddle/fluid/tests/book_memory_optimization/test_memopt_image_classification_train.py
...ry_optimization/test_memopt_image_classification_train.py
+2
-2
未找到文件。
benchmark/cluster/vgg16/vgg16_fluid.py
浏览文件 @
e9b48863
...
...
@@ -106,10 +106,10 @@ def vgg16_bn_drop(input):
conv5
=
conv_block
(
conv4
,
512
,
3
,
[
0.4
,
0.4
,
0
])
drop
=
fluid
.
layers
.
dropout
(
x
=
conv5
,
dropout_prob
=
0.5
)
fc1
=
fluid
.
layers
.
fc
(
input
=
drop
,
size
=
512
,
act
=
None
)
fc1
=
fluid
.
layers
.
fc
(
input
=
drop
,
size
=
4096
,
act
=
None
)
bn
=
fluid
.
layers
.
batch_norm
(
input
=
fc1
,
act
=
'relu'
)
drop2
=
fluid
.
layers
.
dropout
(
x
=
bn
,
dropout_prob
=
0.5
)
fc2
=
fluid
.
layers
.
fc
(
input
=
drop2
,
size
=
512
,
act
=
None
)
fc2
=
fluid
.
layers
.
fc
(
input
=
drop2
,
size
=
4096
,
act
=
None
)
return
fc2
...
...
python/paddle/fluid/tests/book/test_image_classification.py
浏览文件 @
e9b48863
...
...
@@ -86,10 +86,10 @@ def vgg16_bn_drop(input):
conv5
=
conv_block
(
conv4
,
512
,
3
,
[
0.4
,
0.4
,
0
])
drop
=
fluid
.
layers
.
dropout
(
x
=
conv5
,
dropout_prob
=
0.5
)
fc1
=
fluid
.
layers
.
fc
(
input
=
drop
,
size
=
512
,
act
=
None
)
fc1
=
fluid
.
layers
.
fc
(
input
=
drop
,
size
=
4096
,
act
=
None
)
bn
=
fluid
.
layers
.
batch_norm
(
input
=
fc1
,
act
=
'relu'
)
drop2
=
fluid
.
layers
.
dropout
(
x
=
bn
,
dropout_prob
=
0.5
)
fc2
=
fluid
.
layers
.
fc
(
input
=
drop2
,
size
=
512
,
act
=
None
)
fc2
=
fluid
.
layers
.
fc
(
input
=
drop2
,
size
=
4096
,
act
=
None
)
return
fc2
...
...
python/paddle/fluid/tests/book_memory_optimization/test_memopt_image_classification_train.py
浏览文件 @
e9b48863
...
...
@@ -89,10 +89,10 @@ def vgg16_bn_drop(input):
conv5
=
conv_block
(
conv4
,
512
,
3
,
[
0.4
,
0.4
,
0
])
drop
=
fluid
.
layers
.
dropout
(
x
=
conv5
,
dropout_prob
=
0.5
)
fc1
=
fluid
.
layers
.
fc
(
input
=
drop
,
size
=
512
,
act
=
None
)
fc1
=
fluid
.
layers
.
fc
(
input
=
drop
,
size
=
4096
,
act
=
None
)
bn
=
fluid
.
layers
.
batch_norm
(
input
=
fc1
,
act
=
'relu'
)
drop2
=
fluid
.
layers
.
dropout
(
x
=
bn
,
dropout_prob
=
0.5
)
fc2
=
fluid
.
layers
.
fc
(
input
=
drop2
,
size
=
512
,
act
=
None
)
fc2
=
fluid
.
layers
.
fc
(
input
=
drop2
,
size
=
4096
,
act
=
None
)
return
fc2
...
...
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