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
76f0bd83
P
Paddle
项目概览
PaddlePaddle
/
Paddle
12 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
76f0bd83
编写于
12月 15, 2017
作者:
R
ranqiu
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Update annotations of layers.py
上级
322bf3fe
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
68 addition
and
60 deletion
+68
-60
python/paddle/trainer_config_helpers/layers.py
python/paddle/trainer_config_helpers/layers.py
+68
-60
未找到文件。
python/paddle/trainer_config_helpers/layers.py
浏览文件 @
76f0bd83
...
@@ -791,10 +791,9 @@ class MixedLayerType(LayerOutput):
...
@@ -791,10 +791,9 @@ class MixedLayerType(LayerOutput):
def
__init__
(
self
,
name
,
size
,
act
,
bias_attr
,
layer_attr
,
parents
=
None
):
def
__init__
(
self
,
name
,
size
,
act
,
bias_attr
,
layer_attr
,
parents
=
None
):
"""
"""
Ctor.
:param name: The name of this layer.
:param name: layer name.
:type name: basestring
:type name: basestring
:param size:
layer size
.
:param size:
The dimension of this layer
.
:type size: int
:type size: int
:param act: Activation type.
:param act: Activation type.
:type act: BaseActivation
:type act: BaseActivation
...
@@ -802,8 +801,9 @@ class MixedLayerType(LayerOutput):
...
@@ -802,8 +801,9 @@ class MixedLayerType(LayerOutput):
whose type is not ParameterAttribute, no bias is defined. If the
whose type is not ParameterAttribute, no bias is defined. If the
parameter is set to True, the bias is initialized to zero.
parameter is set to True, the bias is initialized to zero.
:type bias_attr: ParameterAttribute | None | bool | Any
:type bias_attr: ParameterAttribute | None | bool | Any
:param layer_attr: Extra Layer Attribute.
:param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
:type layer_attr: ExtraLayerAttribute or None
details.
:type layer_attr: ExtraLayerAttribute | None
"""
"""
LayerOutput
.
__init__
(
LayerOutput
.
__init__
(
self
,
self
,
...
@@ -868,12 +868,12 @@ def mixed_layer(size=0,
...
@@ -868,12 +868,12 @@ def mixed_layer(size=0,
bias_attr
=
False
,
bias_attr
=
False
,
layer_attr
=
None
):
layer_attr
=
None
):
"""
"""
Mixed Layer. A mixed layer will add all inputs together, then activate.
Mixed Layer. A mixed layer will add all inputs together, then activate
the sum
.
Each input
s
is a projection or operator.
Each input is a projection or operator.
There are two styles of usages.
There are two styles of usages.
1. When
not set inputs parameter
, use mixed_layer like this:
1. When
the parameter input is not set
, use mixed_layer like this:
.. code-block:: python
.. code-block:: python
...
@@ -889,21 +889,21 @@ def mixed_layer(size=0,
...
@@ -889,21 +889,21 @@ def mixed_layer(size=0,
input=[full_matrix_projection(input=layer1),
input=[full_matrix_projection(input=layer1),
full_matrix_projection(input=layer2)])
full_matrix_projection(input=layer2)])
:param name:
mixed layer name. Can be referenced by other layer
.
:param name:
The name of this layer. It is optional
.
:type name: basestring
:type name: basestring
:param size:
layer size
.
:param size:
The dimension of this layer
.
:type size: int
:type size: int
:param input: The input of this layer. It is an optional parameter. If set,
:param input: The input of this layer. It is an optional parameter.
then this function will just return layer's name.
:param act: Activation Type. LinearActivation is the default activation.
:param act: Activation Type. LinearActivation is the default activation.
:type act: BaseActivation
:type act: BaseActivation
:param bias_attr: The bias attribute. If the parameter is set to False or an object
:param bias_attr: The bias attribute. If the parameter is set to False or an object
whose type is not ParameterAttribute, no bias is defined. If the
whose type is not ParameterAttribute, no bias is defined. If the
parameter is set to True, the bias is initialized to zero.
parameter is set to True, the bias is initialized to zero.
:type bias_attr: ParameterAttribute | None | bool | Any
:type bias_attr: ParameterAttribute | None | bool | Any
:param layer_attr: The extra layer config. Default is None.
:param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
details.
:type layer_attr: ExtraLayerAttribute
:type layer_attr: ExtraLayerAttribute
:return: MixedLayerType object
can add inputs or layer name
.
:return: MixedLayerType object.
:rtype: MixedLayerType
:rtype: MixedLayerType
"""
"""
...
@@ -938,14 +938,15 @@ def data_layer(name, size, depth=None, height=None, width=None,
...
@@ -938,14 +938,15 @@ def data_layer(name, size, depth=None, height=None, width=None,
:param name: The name of this layer.
:param name: The name of this layer.
:type name: basestring
:type name: basestring
:param size:
Size
of this data layer.
:param size:
The dimension
of this data layer.
:type size: int
:type size: int
:param height:
Height of this data layer, used for image
:param height:
The height of the input image data.
:type height: int | None
:type height: int | None
:param width:
Width of this data layer, used for image
:param width:
The width of the input image data.
:type width: int | None
:type width: int | None
:param layer_attr: Extra Layer Attribute.
:param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
:type layer_attr: ExtraLayerAttribute.
details.
:type layer_attr: ExtraLayerAttribute
:return: LayerOutput object.
:return: LayerOutput object.
:rtype: LayerOutput
:rtype: LayerOutput
"""
"""
...
@@ -978,14 +979,15 @@ def embedding_layer(input, size, name=None, param_attr=None, layer_attr=None):
...
@@ -978,14 +979,15 @@ def embedding_layer(input, size, name=None, param_attr=None, layer_attr=None):
:param name: The name of this layer. It is optional.
:param name: The name of this layer. It is optional.
:type name: basestring
:type name: basestring
:param input: The input of this layer, wh
ich
must be Index Data.
:param input: The input of this layer, wh
ose type
must be Index Data.
:type input: LayerOutput
:type input: LayerOutput
:param size: The
embedding dimension
.
:param size: The
dimension of the embedding vector
.
:type size: int
:type size: int
:param param_attr: The embedding parameter attribute. See ParameterAttribute
:param param_attr: The embedding parameter attribute. See ParameterAttribute
for details.
for details.
:type param_attr: ParameterAttribute | None
:type param_attr: ParameterAttribute
:param layer_attr: Extra layer Config. Default is None.
:param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
details.
:type layer_attr: ExtraLayerAttribute | None
:type layer_attr: ExtraLayerAttribute | None
:return: LayerOutput object.
:return: LayerOutput object.
:rtype: LayerOutput
:rtype: LayerOutput
...
@@ -1013,7 +1015,7 @@ def fc_layer(input,
...
@@ -1013,7 +1015,7 @@ def fc_layer(input,
bias_attr
=
None
,
bias_attr
=
None
,
layer_attr
=
None
):
layer_attr
=
None
):
"""
"""
Helper for declar
e fully connected layer.
Th
e fully connected layer.
The example usage is:
The example usage is:
...
@@ -1035,17 +1037,18 @@ def fc_layer(input,
...
@@ -1035,17 +1037,18 @@ def fc_layer(input,
:type name: basestring
:type name: basestring
:param input: The input of this layer.
:param input: The input of this layer.
:type input: LayerOutput | list | tuple
:type input: LayerOutput | list | tuple
:param size: The
layer dimension
.
:param size: The
dimension of this layer
.
:type size: int
:type size: int
:param act: Activation Type. TanhActivation is the default activation.
:param act: Activation Type. TanhActivation is the default activation.
:type act: BaseActivation
:type act: BaseActivation
:param param_attr: The
Parameter Attribute|list
.
:param param_attr: The
parameter attribute. See ParameterAttribute for details
.
:type param_attr: ParameterAttribute
:type param_attr: ParameterAttribute
:param bias_attr: The bias attribute. If the parameter is set to False or an object
:param bias_attr: The bias attribute. If the parameter is set to False or an object
whose type is not ParameterAttribute, no bias is defined. If the
whose type is not ParameterAttribute, no bias is defined. If the
parameter is set to True, the bias is initialized to zero.
parameter is set to True, the bias is initialized to zero.
:type bias_attr: ParameterAttribute | None | bool | Any
:type bias_attr: ParameterAttribute | None | bool | Any
:param layer_attr: Extra Layer config.
:param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
details.
:type layer_attr: ExtraLayerAttribute | None
:type layer_attr: ExtraLayerAttribute | None
:return: LayerOutput object.
:return: LayerOutput object.
:rtype: LayerOutput
:rtype: LayerOutput
...
@@ -1086,13 +1089,15 @@ def fc_layer(input,
...
@@ -1086,13 +1089,15 @@ def fc_layer(input,
@
wrap_name_default
(
"print"
)
@
wrap_name_default
(
"print"
)
def
printer_layer
(
input
,
format
=
None
,
name
=
None
):
def
printer_layer
(
input
,
format
=
None
,
name
=
None
):
"""
"""
Print the output value of input layers. This layer is useful for debugging.
Print the output value of the layers specified by the parameter input.
This layer is useful for debugging.
:param name: The name of this layer. It is optional.
:param name: The name of this layer. It is optional.
:type name: basestring
:type name: basestring
:param input: The input of this layer.
:param input: The input of this layer.
:type input: LayerOutput | list | tuple
:type input: LayerOutput | list | tuple
:return: LayerOutput
:return: LayerOutput object.
:rtype: LayerOutput
"""
"""
if
isinstance
(
input
,
LayerOutput
):
if
isinstance
(
input
,
LayerOutput
):
input
=
[
input
]
input
=
[
input
]
...
@@ -1135,11 +1140,12 @@ def priorbox_layer(input,
...
@@ -1135,11 +1140,12 @@ def priorbox_layer(input,
:param aspect_ratio: The aspect ratio.
:param aspect_ratio: The aspect ratio.
:type aspect_ratio: list
:type aspect_ratio: list
:param variance: The bounding box variance.
:param variance: The bounding box variance.
:type min_size: The min size of the priorbox width/height.
:type min_size: The min
imum
size of the priorbox width/height.
:param min_size: list
:param min_size: list
:type max_size: The max
size of the priorbox width/height. C
ould be NULL.
:type max_size: The max
imum size of the priorbox width/height. It c
ould be NULL.
:param max_size: list
:param max_size: list
:return: LayerOutput
:return: LayerOutput object.
:rtype: LayerOutput
"""
"""
# plus one for ratio 1.
# plus one for ratio 1.
num_filters
=
(
len
(
aspect_ratio
)
*
2
+
1
+
len
(
max_size
))
*
4
num_filters
=
(
len
(
aspect_ratio
)
*
2
+
1
+
len
(
max_size
))
*
4
...
@@ -1177,7 +1183,7 @@ def multibox_loss_layer(input_loc,
...
@@ -1177,7 +1183,7 @@ def multibox_loss_layer(input_loc,
:param name: The name of this layer. It is optional.
:param name: The name of this layer. It is optional.
:type name: basestring
:type name: basestring
:param input_loc: The input predict locations.
:param input_loc: The input predict
ed
locations.
:type input_loc: LayerOutput | List of LayerOutput
:type input_loc: LayerOutput | List of LayerOutput
:param input_conf: The input priorbox confidence.
:param input_conf: The input priorbox confidence.
:type input_conf: LayerOutput | List of LayerOutput
:type input_conf: LayerOutput | List of LayerOutput
...
@@ -1189,13 +1195,15 @@ def multibox_loss_layer(input_loc,
...
@@ -1189,13 +1195,15 @@ def multibox_loss_layer(input_loc,
:type num_classes: int
:type num_classes: int
:param overlap_threshold: The threshold of the overlap.
:param overlap_threshold: The threshold of the overlap.
:type overlap_threshold: float
:type overlap_threshold: float
:param neg_pos_ratio: The ratio of the negative bbox to the positive bbox.
:param neg_pos_ratio: The ratio of the negative bounding box to
the positive bounding box.
:type neg_pos_ratio: float
:type neg_pos_ratio: float
:param neg_overlap: The negative bbox overlap threshold.
:param neg_overlap: The negative b
ounding
box overlap threshold.
:type neg_overlap: float
:type neg_overlap: float
:param background_id: The background class index.
:param background_id: The background class index.
:type background_id: int
:type background_id: int
:return: LayerOutput
:return: LayerOutput object.
:rtype: LayerOutput
"""
"""
if
isinstance
(
input_loc
,
LayerOutput
):
if
isinstance
(
input_loc
,
LayerOutput
):
input_loc
=
[
input_loc
]
input_loc
=
[
input_loc
]
...
@@ -1258,19 +1266,20 @@ def detection_output_layer(input_loc,
...
@@ -1258,19 +1266,20 @@ def detection_output_layer(input_loc,
:type input_conf: LayerOutput | List of LayerOutput.
:type input_conf: LayerOutput | List of LayerOutput.
:param priorbox: The input priorbox location and the variance.
:param priorbox: The input priorbox location and the variance.
:type priorbox: LayerOutput
:type priorbox: LayerOutput
:param num_classes: The number of the class
ification
.
:param num_classes: The number of the class
es
.
:type num_classes: int
:type num_classes: int
:param nms_threshold: The Non-maximum suppression threshold.
:param nms_threshold: The Non-maximum suppression threshold.
:type nms_threshold: float
:type nms_threshold: float
:param nms_top_k: The b
box number kept of the NMS's output
:param nms_top_k: The b
ounding boxes number kept of the NMS's output.
:type nms_top_k: int
:type nms_top_k: int
:param keep_top_k: The b
box number kept of the layer's output
:param keep_top_k: The b
ounding boxes number kept of the layer's output.
:type keep_top_k: int
:type keep_top_k: int
:param confidence_threshold: The classification confidence threshold
:param confidence_threshold: The classification confidence threshold
.
:type confidence_threshold: float
:type confidence_threshold: float
:param background_id: The background class index.
:param background_id: The background class index.
:type background_id: int
:type background_id: int
:return: LayerOutput
:return: LayerOutput object.
:rtype: LayerOutput
"""
"""
if
isinstance
(
input_loc
,
LayerOutput
):
if
isinstance
(
input_loc
,
LayerOutput
):
input_loc
=
[
input_loc
]
input_loc
=
[
input_loc
]
...
@@ -1326,7 +1335,7 @@ def roi_pool_layer(input,
...
@@ -1326,7 +1335,7 @@ def roi_pool_layer(input,
A layer used by Fast R-CNN to extract feature maps of ROIs from the last
A layer used by Fast R-CNN to extract feature maps of ROIs from the last
feature map.
feature map.
:param name: The
Layer Name
.
:param name: The
name of this layer. It is optional
.
:type name: basestring
:type name: basestring
:param input: The input layer.
:param input: The input layer.
:type input: LayerOutput.
:type input: LayerOutput.
...
@@ -1338,9 +1347,10 @@ def roi_pool_layer(input,
...
@@ -1338,9 +1347,10 @@ def roi_pool_layer(input,
:type pooled_height: int
:type pooled_height: int
:param spatial_scale: The spatial scale between the image and feature map.
:param spatial_scale: The spatial scale between the image and feature map.
:type spatial_scale: float
:type spatial_scale: float
:param num_channels:
number of input channel
.
:param num_channels:
The number of the input channels
.
:type num_channels: int
:type num_channels: int
:return: LayerOutput
:return: LayerOutput object.
:rtype: LayerOutput
"""
"""
if
num_channels
is
None
:
if
num_channels
is
None
:
assert
input
.
num_filters
is
not
None
assert
input
.
num_filters
is
not
None
...
@@ -1361,18 +1371,19 @@ def roi_pool_layer(input,
...
@@ -1361,18 +1371,19 @@ def roi_pool_layer(input,
@
wrap_name_default
(
"cross_channel_norm"
)
@
wrap_name_default
(
"cross_channel_norm"
)
def
cross_channel_norm_layer
(
input
,
name
=
None
,
param_attr
=
None
):
def
cross_channel_norm_layer
(
input
,
name
=
None
,
param_attr
=
None
):
"""
"""
Normalize a layer's output. This layer is necessary for ssd.
Normalize a layer's output. This layer is necessary for ssd.
This
This layer applys normalize
across the channels of each sample to
layer applys normalization
across the channels of each sample to
a conv
layer's output and scale the output by a group of trainable
a conv
olutional layer's output and scales the output by a group of
factors which
dimensions equal to the channel's number.
trainable factors whose
dimensions equal to the channel's number.
:param name: The name of this layer. It is optional.
:param name: The name of this layer. It is optional.
:type name: basestring
:type name: basestring
:param input: The input of this layer.
:param input: The input of this layer.
:type input: LayerOutput
:type input: LayerOutput
:param param_attr: The
Parameter Attribute|list
.
:param param_attr: The
parameter attribute. See ParameterAttribute for details
.
:type param_attr: ParameterAttribute
:type param_attr: ParameterAttribute
:return: LayerOutput
:return: LayerOutput object.
:rtype: LayerOutput
"""
"""
assert
input
.
num_filters
is
not
None
assert
input
.
num_filters
is
not
None
Layer
(
Layer
(
...
@@ -1413,12 +1424,9 @@ def pooling_layer(input,
...
@@ -1413,12 +1424,9 @@ def pooling_layer(input,
Pooling layer for sequence inputs, not used for Image.
Pooling layer for sequence inputs, not used for Image.
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 returns the pooling value of the sequence in the window as the output. Thus,
will be shorten.
a long sequence will be shortened. Note that for sequence with sub-sequence, the
default value of stride is -1.
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.
The example usage is:
The example usage is:
...
@@ -1435,16 +1443,16 @@ def pooling_layer(input,
...
@@ -1435,16 +1443,16 @@ def pooling_layer(input,
:type name: basestring
:type name: basestring
:param input: The input of this layer.
:param input: The input of this layer.
:type input: LayerOutput
:type input: LayerOutput
:param pooling_type: Type of pooling, MaxPooling(default), AvgPooling,
:param pooling_type: Type of pooling. MaxPooling is the default pooling.
SumPooling, SquareRootNPooling.
:type pooling_type: BasePoolingType | None
:type pooling_type: BasePoolingType | None
:param stride: The step size between successive pooling regions.
:param stride: The step size between successive pooling regions.
:type stride:
I
nt
:type stride:
i
nt
:param bias_attr: The bias attribute. If the parameter is set to False or an object
:param bias_attr: The bias attribute. If the parameter is set to False or an object
whose type is not ParameterAttribute, no bias is defined. If the
whose type is not ParameterAttribute, no bias is defined. If the
parameter is set to True, the bias is initialized to zero.
parameter is set to True, the bias is initialized to zero.
:type bias_attr: ParameterAttribute | None | bool | Any
:type bias_attr: ParameterAttribute | None | bool | Any
:param layer_attr: The Extra Attributes for layer, such as dropout.
:param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
details.
:type layer_attr: ExtraLayerAttribute | None
:type layer_attr: ExtraLayerAttribute | None
:return: LayerOutput object.
:return: LayerOutput object.
:rtype: LayerOutput
:rtype: LayerOutput
...
...
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