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
models
提交
a07e5b4e
M
models
项目概览
PaddlePaddle
/
models
1 年多 前同步成功
通知
222
Star
6828
Fork
2962
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
602
列表
看板
标记
里程碑
合并请求
255
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
M
models
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
602
Issue
602
列表
看板
标记
里程碑
合并请求
255
合并请求
255
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
a07e5b4e
编写于
10月 25, 2017
作者:
P
Peng Li
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix typos
上级
ffa2568a
变更
4
隐藏空白更改
内联
并排
Showing
4 changed file
with
6 addition
and
6 deletion
+6
-6
neural_seq_qa/README.md
neural_seq_qa/README.md
+1
-1
neural_seq_qa/index.html
neural_seq_qa/index.html
+1
-1
neural_seq_qa/network.py
neural_seq_qa/network.py
+3
-3
neural_seq_qa/train.py
neural_seq_qa/train.py
+1
-1
未找到文件。
neural_seq_qa/README.md
浏览文件 @
a07e5b4e
...
...
@@ -45,7 +45,7 @@ PYTHONPATH=data/evaluation:$PYTHONPATH python train.py 2>&1 | tee train.log
```
# Validation and Test
WebQA prov
oides two versions of validation and test sets. Automatic vali
ation and test can be lauched by
WebQA prov
ides two versions of validation and test sets. Automatic valid
ation and test can be lauched by
```
bash
PYTHONPATH
=
data/evaluation:
$PYTHONPATH
python val_and_test.py models
[
ann|ir]
...
...
neural_seq_qa/index.html
浏览文件 @
a07e5b4e
...
...
@@ -87,7 +87,7 @@ PYTHONPATH=data/evaluation:$PYTHONPATH python train.py 2>&1 | tee train.log
```
# Validation and Test
WebQA prov
oides two versions of validation and test sets. Automatic vali
ation and test can be lauched by
WebQA prov
ides two versions of validation and test sets. Automatic valid
ation and test can be lauched by
```bash
PYTHONPATH=data/evaluation:$PYTHONPATH python val_and_test.py models [ann|ir]
...
...
neural_seq_qa/network.py
浏览文件 @
a07e5b4e
...
...
@@ -16,7 +16,7 @@ feeding = {
def
get_embedding
(
input
,
word_vec_dim
,
wordvecs
):
"""
Define
d
word embedding
Define word embedding
:param input: layer input
:type input: LayerOutput
...
...
@@ -51,7 +51,7 @@ def encoding_question(question, q_lstm_dim, latent_chain_dim, word_vec_dim,
:type drop_rate: float
:param wordvecs: word embedding matrix
:type wordvecs: numpy array
:param default_init_std: default initial st
d
:param default_init_std: default initial st
andard deviation
:type default_init_std: float
:param default_l2_rate: default l2 rate
:type default_l2_rate: float
...
...
@@ -131,7 +131,7 @@ def encoding_evidence(evidence, qe_comm, ee_comm, q_encoding, e_lstm_dim,
:type drop_rate: float
:param wordvecs: word embedding matrix
:type wordvecs: numpy array
:param default_init_std: default initial st
d
:param default_init_std: default initial st
andard deviation
:type default_init_std: float
:param default_l2_rate: default l2 rate
:type default_l2_rate: float
...
...
neural_seq_qa/train.py
浏览文件 @
a07e5b4e
...
...
@@ -21,7 +21,7 @@ def save_model(trainer, model_save_dir, parameters, pass_id):
def
show_parameter_init_info
(
parameters
):
"""
Print the information of initialization mean and st
d
of parameters
Print the information of initialization mean and st
andard deviation
of parameters
:param parameters: the parameters created in a model
"""
...
...
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