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
OPTHREE
Paddle
提交
c6482444
P
Paddle
项目概览
OPTHREE
/
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 >>
未验证
提交
c6482444
编写于
1月 23, 2018
作者:
G
Guo Sheng
提交者:
GitHub
1月 23, 2018
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #7766 from guoshengCS/add-python-GRU
Add python wrapper for GRU
上级
b4555028
8cfb3e55
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
113 addition
and
0 deletion
+113
-0
doc/api/v2/fluid/layers.rst
doc/api/v2/fluid/layers.rst
+5
-0
python/paddle/v2/fluid/layers/nn.py
python/paddle/v2/fluid/layers/nn.py
+108
-0
未找到文件。
doc/api/v2/fluid/layers.rst
浏览文件 @
c6482444
...
...
@@ -18,6 +18,11 @@ dynamic_lstm
.. autofunction:: paddle.v2.fluid.layers.dynamic_lstm
:noindex:
dynamic_gru
-----------
.. autofunction:: paddle.v2.fluid.layers.dynamic_gru
:noindex:
data
----
.. autofunction:: paddle.v2.fluid.layers.data
...
...
python/paddle/v2/fluid/layers/nn.py
浏览文件 @
c6482444
...
...
@@ -26,6 +26,7 @@ __all__ = [
'fc'
,
'embedding'
,
'dynamic_lstm'
,
'dynamic_gru'
,
'gru_unit'
,
'linear_chain_crf'
,
'crf_decoding'
,
...
...
@@ -368,6 +369,113 @@ def dynamic_lstm(input,
return
hidden
,
cell
def
dynamic_gru
(
input
,
size
,
param_attr
=
None
,
bias_attr
=
None
,
is_reverse
=
False
,
gate_activation
=
'sigmoid'
,
candidate_activation
=
'tanh'
,
h_0
=
None
):
"""
**Dynamic GRU Layer**
Refer to `Empirical Evaluation of Gated Recurrent Neural Networks on
Sequence Modeling <https://arxiv.org/abs/1412.3555>`_
The formula is as follows:
.. math::
u_t & = act_g(W_{ux}x_{t} + W_{uh}h_{t-1} + b_u)
r_t & = act_g(W_{rx}x_{t} + W_{rh}h_{t-1} + b_r)
\\
tilde{h_t} & = act_c(W_{cx}x_{t} + W_{ch}(r_t \odot h_{t-1}) + b_c)
h_t & = (1-u_t) \odot h_{t-1} + u_t \odot
\\
tilde{h_t}
The :math:`\odot` is the element-wise product of the vectors. :math:`act_g`
is the update gate and reset gate activation function and :math:`sigmoid`
is usually used for it. :math:`act_c` is the activation function for
candidate hidden state and :math:`tanh` is usually used for it.
Note that these :math:`W_{ux}x_{t}, W_{rx}x_{t}, W_{cx}x_{t}` operations on
the input :math:`x_{t}` are NOT included in this operator. Users can choose
to use fully-connect layer before GRU layer.
Args:
input(Variable): The input of dynamic_gru layer, which supports
variable-time length input sequence. The underlying tensor in this
Variable is a matrix with shape :math:`(T
\\
times 3D)`, where
:math:`T` is the total time steps in this mini-batch, :math:`D`
is the hidden size.
size(int): The dimension of the gru cell.
param_attr(ParamAttr|None): The parameter attribute for the learnable
hidden-hidden weight matrix. Note:
- The shape of the weight matrix is :math:`(T
\\
times 3D)`, where
:math:`D` is the hidden size.
- All elements in the weight matrix can be divided into two parts.
The first part are weights of the update gate and reset gate with
shape :math:`(D
\\
times 2D)`, and the second part are weights for
candidate hidden state with shape :math:`(D
\\
times D)`.
bias_attr(ParamAttr): The parameter attribute for learnable the
hidden-hidden bias.
is_reverse(bool): Whether to compute reversed GRU, default
:attr:`False`.
gate_activation(str): The activation for update gate and reset gate.
Choices = ["sigmoid", "tanh", "relu", "identity"], default "sigmoid".
activation(str): The activation for candidate hidden state.
Choices = ["sigmoid", "tanh", "relu", "identity"], default "tanh".
Returns:
Variable: The hidden state of GRU. The shape is (T
\\
times D), and lod
\
is the same with the input.
Examples:
.. code-block:: python
hidden_dim = 512
x = fluid.layers.fc(input=data, size=hidden_dim * 3)
hidden = fluid.layers.dynamic_gru(input=x, dim=hidden_dim)
"""
helper
=
LayerHelper
(
'gru'
,
**
locals
())
dtype
=
helper
.
input_dtype
()
weight
=
helper
.
create_parameter
(
attr
=
helper
.
param_attr
,
shape
=
[
size
,
3
*
size
],
dtype
=
dtype
)
bias
=
helper
.
create_parameter
(
attr
=
helper
.
bias_attr
,
shape
=
[
1
,
3
*
size
],
dtype
=
dtype
,
is_bias
=
True
)
inputs
=
{
'Input'
:
input
,
'Weight'
:
weight
,
'Bias'
:
bias
}
if
h_0
!=
None
:
assert
h_0
.
shape
==
(
size
,
size
),
'The shape of h0 should be(%d, %d)'
%
(
size
,
size
)
inputs
[
'h0'
]
=
h_0
hidden
=
helper
.
create_tmp_variable
(
dtype
)
batch_gate
=
helper
.
create_tmp_variable
(
dtype
)
batch_reset_hidden_prev
=
helper
.
create_tmp_variable
(
dtype
)
batch_hidden
=
helper
.
create_tmp_variable
(
dtype
)
helper
.
append_op
(
type
=
'gru'
,
inputs
=
inputs
,
outputs
=
{
'Hidden'
:
hidden
,
'BatchGate'
:
batch_gate
,
'BatchResetHiddenPrev'
:
batch_reset_hidden_prev
,
'BatchHidden'
:
batch_hidden
},
attrs
=
{
'is_reverse'
:
is_reverse
,
'gate_activation'
:
gate_activation
,
'activation'
:
candidate_activation
})
return
hidden
def
gru_unit
(
input
,
hidden
,
size
,
...
...
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