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
wmsofts
Paddle
提交
e641ffe7
P
Paddle
项目概览
wmsofts
/
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
e641ffe7
编写于
1月 13, 2019
作者:
Q
Qiao Longfei
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
change interface and api spec for dynamic_gru test=develop
上级
4c7be265
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
46 addition
and
8 deletion
+46
-8
paddle/fluid/API.spec
paddle/fluid/API.spec
+1
-1
paddle/fluid/operators/gru_unit_op.cc
paddle/fluid/operators/gru_unit_op.cc
+4
-1
python/paddle/fluid/layers/nn.py
python/paddle/fluid/layers/nn.py
+41
-6
未找到文件。
paddle/fluid/API.spec
浏览文件 @
e641ffe7
...
...
@@ -68,7 +68,7 @@ paddle.fluid.layers.fc ArgSpec(args=['input', 'size', 'num_flatten_dims', 'param
paddle.fluid.layers.embedding ArgSpec(args=['input', 'size', 'is_sparse', 'is_distributed', 'padding_idx', 'param_attr', 'dtype'], varargs=None, keywords=None, defaults=(False, False, None, None, 'float32'))
paddle.fluid.layers.dynamic_lstm ArgSpec(args=['input', 'size', 'h_0', 'c_0', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, None, None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'float32', None))
paddle.fluid.layers.dynamic_lstmp ArgSpec(args=['input', 'size', 'proj_size', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'proj_activation', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'tanh', 'float32', None))
paddle.fluid.layers.dynamic_gru ArgSpec(args=['input', 'size', 'param_attr', 'bias_attr', 'is_reverse', 'gate_activation', 'candidate_activation', 'h_0'
], varargs=None, keywords=None, defaults=(None, None, False, 'sigmoid', 'tanh', Non
e))
paddle.fluid.layers.dynamic_gru ArgSpec(args=['input', 'size', 'param_attr', 'bias_attr', 'is_reverse', 'gate_activation', 'candidate_activation', 'h_0'
, 'origin_mode'], varargs=None, keywords=None, defaults=(None, None, False, 'sigmoid', 'tanh', None, Fals
e))
paddle.fluid.layers.gru_unit ArgSpec(args=['input', 'hidden', 'size', 'param_attr', 'bias_attr', 'activation', 'gate_activation', 'origin_mode'], varargs=None, keywords=None, defaults=(None, None, 'tanh', 'sigmoid', False))
paddle.fluid.layers.linear_chain_crf ArgSpec(args=['input', 'label', 'param_attr'], varargs=None, keywords=None, defaults=(None,))
paddle.fluid.layers.crf_decoding ArgSpec(args=['input', 'param_attr', 'label'], varargs=None, keywords=None, defaults=(None,))
...
...
paddle/fluid/operators/gru_unit_op.cc
浏览文件 @
e641ffe7
...
...
@@ -113,7 +113,10 @@ class GRUUnitOpMaker : public framework::OpProtoAndCheckerMaker {
.
InEnum
({
identity
,
sigmoid
,
tanh
,
relu
});
AddAttr
<
bool
>
(
"origin_mode"
,
"bool"
"use origin mode in article https://arxiv.org/abs/1412.3555"
)
"use origin mode in article <Learning Phrase Representations "
"using RNN Encoder–Decoder
\n
"
"for Statistical Machine "
"Translation>(https://arxiv.org/pdf/1406.1078.pdf)"
)
.
SetDefault
(
false
);
AddComment
(
R"DOC(
GRUUnit Operator implements partial calculations of the GRU unit as following:
...
...
python/paddle/fluid/layers/nn.py
浏览文件 @
e641ffe7
...
...
@@ -864,12 +864,14 @@ def dynamic_gru(input,
is_reverse
=
False
,
gate_activation
=
'sigmoid'
,
candidate_activation
=
'tanh'
,
h_0
=
None
):
h_0
=
None
,
origin_mode
=
False
):
"""
**Gated Recurrent Unit (GRU) Layer**
Refer to `Empirical Evaluation of Gated Recurrent Neural Networks on
Sequence Modeling <https://arxiv.org/abs/1412.3555>`_ .
if origin_mode is False, then the equation of a gru step is from paper
`Empirical Evaluation of Gated Recurrent Neural Networks on Sequence
Modeling <https://arxiv.org/pdf/1412.3555.pdf>`_ .
The formula is as follows:
...
...
@@ -883,6 +885,20 @@ def dynamic_gru(input,
h_t & = (1-u_t) \odot h_{t-1} + u_t \odot
\\
tilde{h_t}
if origin_mode is True, then the equation is from paper
`Learning Phrase Representations using RNN Encoder–Decoder for Statistical
Machine Translation <https://arxiv.org/pdf/1406.1078.pdf>`_
.. 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 & = u_t \odot h_{t-1} + (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
...
...
@@ -980,7 +996,8 @@ def dynamic_gru(input,
attrs
=
{
'is_reverse'
:
is_reverse
,
'gate_activation'
:
gate_activation
,
'activation'
:
candidate_activation
'activation'
:
candidate_activation
,
'origin_mode'
:
origin_mode
})
return
hidden
...
...
@@ -994,7 +1011,11 @@ def gru_unit(input,
gate_activation
=
'sigmoid'
,
origin_mode
=
False
):
"""
GRU unit layer. The equation of a gru step is:
**GRU unit layer**
if origin_mode is True, then the equation of a gru step is from paper
`Learning Phrase Representations using RNN Encoder–Decoder for Statistical
Machine Translation <https://arxiv.org/pdf/1406.1078.pdf>`_
.. math::
u_t & = actGate(xu_{t} + W_u h_{t-1} + b_u)
...
...
@@ -1003,7 +1024,21 @@ def gru_unit(input,
m_t & = actNode(xm_t + W_c dot(r_t, h_{t-1}) + b_m)
h_t & = dot((1-u_t), m_t) + dot(u_t, h_{t-1})
h_t & = dot(u_t, h_{t-1}) + dot((1-u_t), m_t)
if origin_mode is False, then the equation of a gru step is from paper
`Empirical Evaluation of Gated Recurrent Neural Networks on Sequence
Modeling <https://arxiv.org/pdf/1412.3555.pdf>`_
.. math::
u_t & = actGate(xu_{t} + W_u h_{t-1} + b_u)
r_t & = actGate(xr_{t} + W_r h_{t-1} + b_r)
m_t & = actNode(xm_t + W_c dot(r_t, h_{t-1}) + b_m)
h_t & = dot((1-u_t), h_{t-1}) + dot(u_t, m_t)
The inputs of gru unit includes :math:`z_t`, :math:`h_{t-1}`. In terms
of the equation above, the :math:`z_t` is split into 3 parts -
...
...
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