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
0fbfd2dc
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
0fbfd2dc
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
Simplify the symbol description
上级
634faab1
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
29 addition
and
22 deletion
+29
-22
python/paddle/v2/fluid/layers/nn.py
python/paddle/v2/fluid/layers/nn.py
+29
-22
未找到文件。
python/paddle/v2/fluid/layers/nn.py
浏览文件 @
0fbfd2dc
...
...
@@ -435,25 +435,28 @@ def dynamic_lstmp(input,
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}`,
:math:`W_{fc}`, :math:`W_{oc}` are diagonal weight matrices for peephole
connections. In our implementation, we use vectors to reprenset these
diagonal weight matrices. The :math:`b` terms denote bias vectors
(:math:`b_i` is the input gate bias vector), :math:`\sigma` is the
activation, such as logistic sigmoid function, and :math:`i, f, o` and
:math:`c` are the input gate, forget gate, output gate, and cell activation
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:`
\\
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`
and :math:`act_h` are the cell input and cell output activation functions
and `tanh` is usually used for them. :math:`\overline{act_h}` is the
activation function for the projection output, usually using `identity` or
same as :math:`act_h`.
In the above formula:
* :math:`W`: Denotes weight matrices (e.g. :math:`W_{xi}` is
\
the matrix of weights from the input gate to the input).
* :math:`W_{ic}`, :math:`W_{fc}`, :math:`W_{oc}`: Diagonal weight
\
matrices for peephole connections. In our implementation,
\
we use vectors to reprenset these diagonal weight matrices.
* :math:`b`: Denotes bias vectors (e.g. :math:`b_i` is the input gate
\
bias vector).
* :math:`\sigma`: The activation, such as logistic sigmoid function.
* :math:`i, f, o` and :math:`c`: The input gate, forget gate, output
\
gate, and cell activation vectors, respectively, all of which have
\
the same size as the cell output activation vector :math:`h`.
* :math:`h`: The hidden state.
* :math:`r`: The recurrent projection of the hidden state.
* :math:`
\\
tilde{c_t}`: The candidate hidden state, whose
\
computation is based on the current input and previous hidden state.
* :math:`\odot`: The element-wise product of the vectors.
* :math:`act_g` and :math:`act_h`: The cell input and cell output
\
activation functions and `tanh` is usually used for them.
* :math:`\overline{act_h}`: The activation function for the projection
\
output, usually using `identity` or same as :math:`act_h`.
Set `use_peepholes` to `False` to disable peephole connection. The formula
is omitted here, please refer to the paper
...
...
@@ -519,12 +522,16 @@ def dynamic_lstmp(input,
Examples:
.. code-block:: python
hidden_dim = 512
proj_dim = 256
hidden_dim, proj_dim = 512, 256
fc_out = fluid.layers.fc(input=input_seq, size=hidden_dim * 4,
act=None, bias_attr=None)
proj_out, _ = fluid.layers.dynamic_lstmp(input=fc_out,
size=hidden_dim * 4, proj_size=proj_dim, use_peepholes=False)
size=hidden_dim * 4,
proj_size=proj_dim,
use_peepholes=False,
is_reverse=True,
cell_activation="tanh",
proj_activation="tanh")
"""
helper
=
LayerHelper
(
'lstmp'
,
**
locals
())
...
...
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