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
wzpei9
Paddle
提交
7a557040
P
Paddle
项目概览
wzpei9
/
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
7a557040
编写于
5月 23, 2018
作者:
Y
Yibing Liu
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Expose param group in conv2d_transpose api
上级
6e13c86d
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
9 addition
and
1 deletion
+9
-1
python/paddle/fluid/layers/nn.py
python/paddle/fluid/layers/nn.py
+9
-1
未找到文件。
python/paddle/fluid/layers/nn.py
浏览文件 @
7a557040
...
@@ -1706,6 +1706,7 @@ def conv2d_transpose(input,
...
@@ -1706,6 +1706,7 @@ def conv2d_transpose(input,
padding
=
0
,
padding
=
0
,
stride
=
1
,
stride
=
1
,
dilation
=
1
,
dilation
=
1
,
groups
=
None
,
param_attr
=
None
,
param_attr
=
None
,
bias_attr
=
None
,
bias_attr
=
None
,
use_cudnn
=
True
,
use_cudnn
=
True
,
...
@@ -1776,6 +1777,12 @@ def conv2d_transpose(input,
...
@@ -1776,6 +1777,12 @@ def conv2d_transpose(input,
dilation(int|tuple): The dilation size. If dilation is a tuple, it must
dilation(int|tuple): The dilation size. If dilation is a tuple, it must
contain two integers, (dilation_H, dilation_W). Otherwise, the
contain two integers, (dilation_H, dilation_W). Otherwise, the
dilation_H = dilation_W = dilation. Default: dilation = 1.
dilation_H = dilation_W = dilation. Default: dilation = 1.
groups(int): The groups number of the Conv2d transpose layer. Inspired by
grouped convolution in Alex Krizhevsky's Deep CNN paper, in which
when group=2, the first half of the filters is only connected to the
first half of the input channels, while the second half of the
filters is only connected to the second half of the input channels.
Default: groups=1
param_attr(ParamAttr): The parameters to the Conv2d_transpose Layer.
param_attr(ParamAttr): The parameters to the Conv2d_transpose Layer.
Default: None
Default: None
bias_attr(ParamAttr): Bias parameter for the Conv2d layer. Default: None
bias_attr(ParamAttr): Bias parameter for the Conv2d layer. Default: None
...
@@ -1830,7 +1837,8 @@ def conv2d_transpose(input,
...
@@ -1830,7 +1837,8 @@ def conv2d_transpose(input,
filter_size
=
utils
.
convert_to_list
(
filter_size
,
2
,
filter_size
=
utils
.
convert_to_list
(
filter_size
,
2
,
'conv2d_transpose.filter_size'
)
'conv2d_transpose.filter_size'
)
filter_shape
=
[
input_channel
,
num_filters
]
+
filter_size
groups
=
1
if
groups
is
None
else
groups
filter_shape
=
[
input_channel
,
num_filters
/
groups
]
+
filter_size
img_filter
=
helper
.
create_parameter
(
img_filter
=
helper
.
create_parameter
(
dtype
=
input
.
dtype
,
shape
=
filter_shape
,
attr
=
helper
.
param_attr
)
dtype
=
input
.
dtype
,
shape
=
filter_shape
,
attr
=
helper
.
param_attr
)
...
...
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