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
634faab1
P
Paddle
项目概览
PaddlePaddle
/
Paddle
大约 1 年 前同步成功
通知
2298
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
提交
634faab1
编写于
1月 28, 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
Format doc & add unit test for dynamic_lstmp api
上级
cc82ff0d
变更
4
隐藏空白更改
内联
并排
Showing
4 changed file
with
48 addition
and
27 deletion
+48
-27
doc/api/v2/fluid/layers.rst
doc/api/v2/fluid/layers.rst
+2
-2
paddle/operators/CMakeLists.txt
paddle/operators/CMakeLists.txt
+1
-0
python/paddle/v2/fluid/layers/nn.py
python/paddle/v2/fluid/layers/nn.py
+33
-25
python/paddle/v2/fluid/tests/test_layers.py
python/paddle/v2/fluid/tests/test_layers.py
+12
-0
未找到文件。
doc/api/v2/fluid/layers.rst
浏览文件 @
634faab1
...
...
@@ -19,11 +19,11 @@ dynamic_lstm
:noindex:
dynamic_lstmp
------------
------------
-
.. autofunction:: paddle.v2.fluid.layers.dynamic_lstmp
:noindex:
dynamic_gru
dynamic_gru
-----------
.. autofunction:: paddle.v2.fluid.layers.dynamic_gru
:noindex:
...
...
paddle/operators/CMakeLists.txt
浏览文件 @
634faab1
...
...
@@ -147,6 +147,7 @@ op_library(max_sequence_len_op DEPS lod_rank_table)
op_library
(
sequence_conv_op DEPS context_project
)
op_library
(
sequence_pool_op DEPS sequence_pooling
)
op_library
(
lstm_op DEPS sequence2batch lstm_compute
)
op_library
(
lstmp_op DEPS sequence2batch lstm_compute
)
op_library
(
gru_op DEPS sequence2batch gru_compute
)
op_library
(
recurrent_op DEPS executor
)
op_library
(
warpctc_op DEPS dynload_warpctc sequence_padding sequence_scale math_function
)
...
...
python/paddle/v2/fluid/layers/nn.py
浏览文件 @
634faab1
...
...
@@ -257,7 +257,8 @@ def dynamic_lstm(input,
gate_activation
=
'sigmoid'
,
cell_activation
=
'tanh'
,
candidate_activation
=
'tanh'
,
dtype
=
'float32'
):
dtype
=
'float32'
,
name
=
None
):
"""
**Dynamic LSTM Layer**
...
...
@@ -309,25 +310,25 @@ def dynamic_lstm(input,
(T X 4D), where T is the total time steps in this
mini-batch, D is the hidden size.
size(int): 4 * hidden size.
param_attr(ParamAttr): The parameter attribute for the learnable
param_attr(ParamAttr
|None
): The parameter attribute for the learnable
hidden-hidden weights.
- The shape is (D x 4D), where D is the hidden
size.
- Weights = {:math:`W_{ch}, W_{ih},
\
W_{fh}, W_{oh}`}
bias_attr(ParamAttr): The bias attribute for the learnable bias
- The shape is (D x 4D), where D is the hidden
size.
bias_attr(ParamAttr|None): The bias attribute for the learnable bias
weights, which contains two parts, input-hidden
bias weights and peephole connections weights if
setting `use_peepholes` to `True`.
1. `use_peepholes = False`
- The shape is (1 x 4D).
- Biases = {:math:`b_c, b_i, b_f, b_o`}.
- The shape is (1 x 4D).
2. `use_peepholes = True`
- The shape is (1 x 7D).
- Biases = { :math:`b_c, b_i, b_f, b_o, W_{ic},
\
W_{fc}, W_{oc}`}.
- The shape is (1 x 7D).
use_peepholes(bool): Whether to enable diagonal/peephole connections,
default `True`.
is_reverse(bool): Whether to compute reversed LSTM, default `False`.
...
...
@@ -340,6 +341,8 @@ def dynamic_lstm(input,
Choices = ["sigmoid", "tanh", "relu", "identity"],
default "tanh".
dtype(str): Data type. Choices = ["float32", "float64"], default "float32".
name(str|None): A name for this layer(optional). If set None, the layer
will be named automatically.
Returns:
tuple: The hidden state, and cell state of LSTM. The shape of both
\
...
...
@@ -354,6 +357,7 @@ def dynamic_lstm(input,
forward, _ = fluid.layers.dynamic_lstm(
input=forward_proj, size=hidden_dim * 4, use_peepholes=False)
"""
helper
=
LayerHelper
(
'lstm'
,
**
locals
())
size
=
size
/
4
weight
=
helper
.
create_parameter
(
...
...
@@ -401,7 +405,8 @@ def dynamic_lstmp(input,
cell_activation
=
'tanh'
,
candidate_activation
=
'tanh'
,
proj_activation
=
'tanh'
,
dtype
=
'float32'
):
dtype
=
'float32'
,
name
=
None
):
"""
**Dynamic LSTMP Layer**
...
...
@@ -416,19 +421,19 @@ def dynamic_lstmp(input,
.. math::
i_t
= \sigma(W_{ix}x_{t} + W_{ir}r_{t-1} + W_{ic}c_{t-1} + b_i)
\\
i_t
& = \sigma(W_{ix}x_{t} + W_{ir}r_{t-1} + W_{ic}c_{t-1} + b_i)
f_t
= \sigma(W_{fx}x_{t} + W_{fr}r_{t-1} + W_{fc}c_{t-1} + b_f)
\\
f_t
& = \sigma(W_{fx}x_{t} + W_{fr}r_{t-1} + W_{fc}c_{t-1} + b_f)
\
t
ilde{c_t} = act_g(W_{cx}x_t + W_{cr}r_{t-1} + b_c)
\\
\
\
tilde{c_t} & = act_g(W_{cx}x_t + W_{cr}r_{t-1} + b_c)
o_t
= \sigma(W_{ox}x_{t} + W_{or}r_{t-1} + W_{oc}c_t + b_o)
\\
o_t
& = \sigma(W_{ox}x_{t} + W_{or}r_{t-1} + W_{oc}c_t + b_o)
c_t
= f_t \odot c_{t-1} + i_t \odot
\t
ilde{c_t}
\\
c_t
& = f_t \odot c_{t-1} + i_t \odot
\\
tilde{c_t}
h_t
= o_t \odot act_h(c_t)
\\
h_t
& = o_t \odot act_h(c_t)
r_t = \overline{act_h}(W_{rh}h_t)
r_t
&
= \overline{act_h}(W_{rh}h_t)
where the :math:`W` terms denote weight matrices (e.g. :math:`W_{xi}` is
the matrix of weights from the input gate to the input), :math:`W_{ic}`,
...
...
@@ -441,7 +446,7 @@ def dynamic_lstmp(input,
vectors, respectively, all of which have the same size as the cell output
activation vector :math:`h`. Here :math:`h` is usually called the hidden
state and :math:`r` denotes its recurrent projection. And
:math:`
\t
ilde{c_t}` is also called the candidate hidden state, whose
:math:`
\
\
tilde{c_t}` is also called the candidate hidden state, whose
computation is based on the current input and previous hidden state.
The :math:`\odot` is the element-wise product of the vectors. :math:`act_g`
...
...
@@ -466,28 +471,28 @@ def dynamic_lstmp(input,
mini-batch, D is the hidden size.
size(int): 4 * hidden size.
proj_size(int): The size of projection output.
param_attr(ParamAttr): The parameter attribute for the learnable
param_attr(ParamAttr
|None
): The parameter attribute for the learnable
hidden-hidden weight and projection weight.
- Hidden-hidden weight = {:math:`W_{ch}, W_{ih},
\
W_{fh}, W_{oh}`}.
- The shape of hidden-hidden weight is (P x 4D),
where P is the projection size and D the hidden
size.
- The shape of projection weight is (D x P).
- Hidden-hidden weight = {:math:`W_{ch}, W_{ih},
\
W_{fh}, W_{oh}`}.
- Projection weight = {:math:`W_{rh}`}.
bias_attr(ParamAttr): The bias attribute for the learnable bias
- The shape of projection weight is (D x P).
bias_attr(ParamAttr|None): The bias attribute for the learnable bias
weights, which contains two parts, input-hidden
bias weights and peephole connections weights if
setting `use_peepholes` to `True`.
1. `use_peepholes = False`
- The shape is (1 x 4D).
- Biases = {:math:`b_c, b_i, b_f, b_o`}.
- The shape is (1 x 4D).
2. `use_peepholes = True`
- The shape is (1 x 7D).
- Biases = { :math:`b_c, b_i, b_f, b_o, W_{ic},
\
W_{fc}, W_{oc}`}.
- The shape is (1 x 7D).
use_peepholes(bool): Whether to enable diagonal/peephole connections,
default `True`.
is_reverse(bool): Whether to compute reversed LSTM, default `False`.
...
...
@@ -503,10 +508,12 @@ def dynamic_lstmp(input,
Choices = ["sigmoid", "tanh", "relu", "identity"],
default "tanh".
dtype(str): Data type. Choices = ["float32", "float64"], default "float32".
name(str|None): A name for this layer(optional). If set None, the layer
will be named automatically.
Returns:
tuple: The projection of hidden state, and cell state of LSTMP. The
shape of projection is (T x P), for the cell state which is
tuple: The projection of hidden state, and cell state of LSTMP. The
\
shape of projection is (T x P), for the cell state which is
\
(T x D), and both LoD is the same with the `input`.
Examples:
...
...
@@ -519,6 +526,7 @@ def dynamic_lstmp(input,
proj_out, _ = fluid.layers.dynamic_lstmp(input=fc_out,
size=hidden_dim * 4, proj_size=proj_dim, use_peepholes=False)
"""
helper
=
LayerHelper
(
'lstmp'
,
**
locals
())
size
=
size
/
4
weight
=
helper
.
create_parameter
(
...
...
python/paddle/v2/fluid/tests/test_layers.py
浏览文件 @
634faab1
...
...
@@ -202,6 +202,18 @@ class TestBook(unittest.TestCase):
x_t
=
x_t
,
hidden_t_prev
=
prev_hidden
,
cell_t_prev
=
prev_cell
))
print
(
str
(
program
))
def
test_dynamic_lstmp
(
self
):
program
=
Program
()
with
program_guard
(
program
):
hidden_dim
,
proj_dim
=
16
,
8
seq_data
=
layers
.
data
(
name
=
'seq_data'
,
shape
=
[
10
,
10
],
dtype
=
'float32'
,
lod_level
=
1
)
fc_out
=
layers
.
fc
(
input
=
seq_data
,
size
=
4
*
hidden_dim
)
self
.
assertIsNotNone
(
layers
.
dynamic_lstmp
(
input
=
fc_out
,
size
=
4
*
hidden_dim
,
proj_size
=
proj_dim
))
print
(
str
(
program
))
def
test_sequence_softmax
(
self
):
program
=
Program
()
with
program_guard
(
program
):
...
...
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