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
迷途归一
Paddle
提交
7eb19abc
P
Paddle
项目概览
迷途归一
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
0
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
体验新版 GitCode,发现更多精彩内容 >>
提交
7eb19abc
编写于
1月 25, 2018
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
Refine the doc.
上级
a249c0ca
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
15 addition
and
15 deletion
+15
-15
python/paddle/v2/fluid/layers/nn.py
python/paddle/v2/fluid/layers/nn.py
+15
-15
未找到文件。
python/paddle/v2/fluid/layers/nn.py
浏览文件 @
7eb19abc
...
@@ -2714,21 +2714,21 @@ def multiplex(inputs, index):
...
@@ -2714,21 +2714,21 @@ def multiplex(inputs, index):
"""
"""
**Multiplex Layer**
**Multiplex Layer**
Referring to the given index variable, this layer
gathers from the input
Referring to the given index variable, this layer
selects rows from the
variables to output a multiplex variable. Assuming that there are :math:`m`
input variables to construct a multiplex variable. Assuming that there are
input variables and let :math:`I_i` represents the i-th input variable and i
:math:`m` input variables and :math:`I_i` represents the i-th input
is in [0, :math:`m`). All input variables are tensors with same shap
e
variable and :math:`i` is in [0, :math:`m`). All input variables ar
e
[:math:`d_0`, :math:`d_1`, ..., :math:`d_R`]. Please note that rank of the
tensors with same shape [:math:`d_0`, :math:`d_1`, ..., :math:`d_R`].
input tensor should be at least 2. Each input variable will be treated as a
Please note that rank of the input tensor should be at least 2. Each input
2-D matrix with shape [:math:`M`, :math:`N`] where :math:`M` for :math:`d_0`
variable will be treated as a 2-D matrix with shape [:math:`M`, :math:`N`]
and :math:`N` for :math:`d_1` * :math:`d_2` * ... * :math:`d_R`. Let
where :math:`M` for :math:`d_0` and :math:`N` for :math:`d_1` * :math:`d_2`
:math:`I_i[j]` be the j-th row of the i-th input variable. The given index
* ... * :math:`d_R`. Let :math:`I_i[j]` be the j-th row of the i-th input
variable
should be a 2-D tensor with shape [:math:`M`, 1]. Let `ID[i]` b
e
variable
. The given index variable should be a 2-D tensor with shap
e
the i-th index value of the index variable. Then the output variable will
[:math:`M`, 1]. Let `ID[i]` be the i-th index value of the index variable.
be a tensor with shape [:math:`d_0`, :math:`d_1`, ..., :math:`d_R`]. If we
Then the output variable will be a tensor with shape [:math:`d_0`,
treat the output tensor as a 2-D matrix with shape [:math:`M`, :math:`N`]
:math:`d_1`, ..., :math:`d_R`]. If we treat the output tensor as a 2-D
and let :math:`O[i]` be the i-th row of the matrix, then `O[i]` is equal to
matrix with shape [:math:`M`, :math:`N`] and let :math:`O[i]` be the i-th
:math:`I_{ID[i]}[i]`.
row of the matrix, then `O[i]` is equal to
:math:`I_{ID[i]}[i]`.
Args:
Args:
inputs (list): A list of variables to gather from. All variables have the
inputs (list): A list of variables to gather from. All variables have the
...
...
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