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
Paddle
提交
e7b071f3
P
Paddle
项目概览
PaddlePaddle
/
Paddle
11 个月 前同步成功
通知
2292
Star
20931
Fork
5422
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1423
列表
看板
标记
里程碑
合并请求
543
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
1,423
Issue
1,423
列表
看板
标记
里程碑
合并请求
543
合并请求
543
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
e7b071f3
编写于
7月 05, 2017
作者:
L
Luo Tao
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
update annotation with comments
上级
3b073fdc
变更
5
隐藏空白更改
内联
并排
Showing
5 changed file
with
20 addition
and
14 deletion
+20
-14
paddle/gserver/layers/AverageLayer.h
paddle/gserver/layers/AverageLayer.h
+4
-0
paddle/gserver/layers/MaxLayer.h
paddle/gserver/layers/MaxLayer.h
+3
-4
paddle/gserver/layers/SequenceLastInstanceLayer.cpp
paddle/gserver/layers/SequenceLastInstanceLayer.cpp
+3
-4
paddle/gserver/layers/SequencePoolLayer.h
paddle/gserver/layers/SequencePoolLayer.h
+3
-2
python/paddle/trainer_config_helpers/layers.py
python/paddle/trainer_config_helpers/layers.py
+7
-4
未找到文件。
paddle/gserver/layers/AverageLayer.h
浏览文件 @
e7b071f3
...
@@ -25,6 +25,10 @@ namespace paddle {
...
@@ -25,6 +25,10 @@ namespace paddle {
* If SequenceLevel = kNonSeq:
* If SequenceLevel = kNonSeq:
* Output: output size is the number of input sequences (NOT input instances)
* Output: output size is the number of input sequences (NOT input instances)
* output[i] = average_{for each instance in this sequence}{input[i]}
* output[i] = average_{for each instance in this sequence}{input[i]}
* If stride_ > 0:
* Output: a shorten sequence. Stride is the step size by which we slide a
* window upon the input sequence, and the average pooling
* operation is then applied to each interval independently.
* If SequenceLevel = kSeq:
* If SequenceLevel = kSeq:
* Check input sequence must has sub-sequence
* Check input sequence must has sub-sequence
* Output: output size is the number of input sub-sequences
* Output: output size is the number of input sub-sequences
...
...
paddle/gserver/layers/MaxLayer.h
浏览文件 @
e7b071f3
...
@@ -27,10 +27,9 @@ namespace paddle {
...
@@ -27,10 +27,9 @@ namespace paddle {
* Output: output size is the number of input sequences (NOT input instances)
* Output: output size is the number of input sequences (NOT input instances)
* output[i] = max_{for each instance in this sequence}{input[i]}
* output[i] = max_{for each instance in this sequence}{input[i]}
* If stride_ > 0:
* If stride_ > 0:
* Output: a shorten sequence. The operation of getting max instance of a
* Output: a shorten sequence. Stride is the step size by which we slide a
* sequence is independently performed on every slice of the input
* window upon the input sequence, and the max pooling operation is
* sequence, which is obtained by sliding a window with the window
* then applied to each interval independently.
* size set to stride_.
* If SequenceLevel = kSeq:
* If SequenceLevel = kSeq:
* Check input sequence must has sub-sequence
* Check input sequence must has sub-sequence
* Output: output size is the number of input sub-sequences
* Output: output size is the number of input sub-sequences
...
...
paddle/gserver/layers/SequenceLastInstanceLayer.cpp
浏览文件 @
e7b071f3
...
@@ -26,10 +26,9 @@ namespace paddle {
...
@@ -26,10 +26,9 @@ namespace paddle {
* If SequenceLevel = kNonseq:
* If SequenceLevel = kNonseq:
* Output: a sequence containing only the last instance of the input sequence
* Output: a sequence containing only the last instance of the input sequence
* If stride_ > 0:
* If stride_ > 0:
* Output: a shorten sequence. The operation of getting last instance of a
* Output: a shorten sequence. Stride is the step size by which we slide a
* sequence is independently performed on every slice of the input
* window upon the input sequence, and getting last instance
* sequence, which is obtained by sliding a window with the window
* operation is then applied to each interval independently.
* size set to stride_.
* If SequenceLevel = kSeq:
* If SequenceLevel = kSeq:
* Check input sequence must has sub-sequence
* Check input sequence must has sub-sequence
* Output: a sequence containing only the last instance of each sub-sequence
* Output: a sequence containing only the last instance of each sub-sequence
...
...
paddle/gserver/layers/SequencePoolLayer.h
浏览文件 @
e7b071f3
...
@@ -28,8 +28,9 @@ namespace paddle {
...
@@ -28,8 +28,9 @@ namespace paddle {
* sequence}{input[i]}
* sequence}{input[i]}
* If stride_ > 0:
* If stride_ > 0:
* Check input sequence must not have sub-sequence
* Check input sequence must not have sub-sequence
* Output: a shorten sequence, pooling is performed upon a small local
* Output: a shorten sequence. Stride is the step size by which we slide
* area
* a window upon the input sequence, and the pooling operation
* is then applied to each interval independently.
* If SequenceLevel = kSeq:
* If SequenceLevel = kSeq:
* Check input sequence must has sub-sequence
* Check input sequence must has sub-sequence
* Output: output size is the number of input sub-sequences
* Output: output size is the number of input sub-sequences
...
...
python/paddle/trainer_config_helpers/layers.py
浏览文件 @
e7b071f3
...
@@ -1097,7 +1097,10 @@ def pooling_layer(input,
...
@@ -1097,7 +1097,10 @@ def pooling_layer(input,
If stride > 0, this layer slides a window whose size is determined by stride,
If stride > 0, this layer slides a window whose size is determined by stride,
and return the pooling value of the window as the output. Thus, a long sequence
and return the pooling value of the window as the output. Thus, a long sequence
will be shorten. Note that for sequence with sub-sequence, the default value
will be shorten.
The parameter stride specifies the intervals at which to apply the pooling
operation. Note that for sequence with sub-sequence, the default value
of stride is -1.
of stride is -1.
The example usage is:
The example usage is:
...
@@ -1118,7 +1121,7 @@ def pooling_layer(input,
...
@@ -1118,7 +1121,7 @@ def pooling_layer(input,
:param pooling_type: Type of pooling, MaxPooling(default), AvgPooling,
:param pooling_type: Type of pooling, MaxPooling(default), AvgPooling,
SumPooling, SquareRootNPooling.
SumPooling, SquareRootNPooling.
:type pooling_type: BasePoolingType|None
:type pooling_type: BasePoolingType|None
:param stride:
window size
.
:param stride:
The step size between successive pooling regions
.
:type stride: Int
:type stride: Int
:param bias_attr: Bias parameter attribute. False if no bias.
:param bias_attr: Bias parameter attribute. False if no bias.
:type bias_attr: ParameterAttribute|None|False
:type bias_attr: ParameterAttribute|None|False
...
@@ -1408,7 +1411,7 @@ def last_seq(input,
...
@@ -1408,7 +1411,7 @@ def last_seq(input,
:type name: basestring
:type name: basestring
:param input: Input layer name.
:param input: Input layer name.
:type input: LayerOutput
:type input: LayerOutput
:param stride:
window size
.
:param stride:
The step size between successive pooling regions
.
:type stride: Int
:type stride: Int
:param layer_attr: extra layer attributes.
:param layer_attr: extra layer attributes.
:type layer_attr: ExtraLayerAttribute.
:type layer_attr: ExtraLayerAttribute.
...
@@ -1464,7 +1467,7 @@ def first_seq(input,
...
@@ -1464,7 +1467,7 @@ def first_seq(input,
:type name: basestring
:type name: basestring
:param input: Input layer name.
:param input: Input layer name.
:type input: LayerOutput
:type input: LayerOutput
:param stride:
window size
.
:param stride:
The step size between successive pooling regions
.
:type stride: Int
:type stride: Int
:param layer_attr: extra layer attributes.
:param layer_attr: extra layer attributes.
:type layer_attr: ExtraLayerAttribute.
:type layer_attr: ExtraLayerAttribute.
...
...
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