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
ujs_wantz
Paddle
提交
e60d94b3
P
Paddle
项目概览
ujs_wantz
/
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 >>
提交
e60d94b3
编写于
3月 03, 2017
作者:
Q
qiaolongfei
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
correct data_type
上级
495861f5
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
9 addition
and
9 deletion
+9
-9
demo/seqToseq/api_train_v2.py
demo/seqToseq/api_train_v2.py
+6
-6
demo/seqToseq/seqToseq_net_v2.py
demo/seqToseq/seqToseq_net_v2.py
+3
-3
未找到文件。
demo/seqToseq/api_train_v2.py
浏览文件 @
e60d94b3
...
...
@@ -4,7 +4,8 @@ import paddle.v2 as paddle
from
seqToseq_net_v2
import
seqToseq_net_v2
### Data Definiation
# Data Definiation.
# TODO:This code should be merged to dataset package.
data_dir
=
"./data/pre-wmt14"
src_lang_dict
=
os
.
path
.
join
(
data_dir
,
'src.dict'
)
trg_lang_dict
=
os
.
path
.
join
(
data_dir
,
'trg.dict'
)
...
...
@@ -68,15 +69,14 @@ def train_reader(file_name):
def
main
():
paddle
.
init
(
use_gpu
=
False
,
trainer_count
=
1
)
# reader = train_reader("data/pre-wmt14/train/train")
# define network topology
cost
=
seqToseq_net_v2
(
source_dict_dim
,
target_dict_dim
)
parameters
=
paddle
.
parameters
.
create
(
cost
)
optimizer
=
paddle
.
optimizer
.
Adam
(
batch_size
=
50
,
learning_rate
=
5
e-4
)
optimizer
=
paddle
.
optimizer
.
Adam
(
learning_rate
=
1
e-4
)
def
event_handler
(
event
):
if
isinstance
(
event
,
paddle
.
event
.
EndIteration
):
if
event
.
batch_id
%
10
0
==
0
:
if
event
.
batch_id
%
10
==
0
:
print
"Pass %d, Batch %d, Cost %f, %s"
%
(
event
.
pass_id
,
event
.
batch_id
,
event
.
cost
,
event
.
metrics
)
...
...
@@ -93,12 +93,12 @@ def main():
trn_reader
=
paddle
.
reader
.
batched
(
paddle
.
reader
.
shuffle
(
train_reader
(
"data/pre-wmt14/train/train"
),
buf_size
=
8192
),
batch_size
=
10
)
batch_size
=
10
000
)
trainer
.
train
(
reader
=
trn_reader
,
event_handler
=
event_handler
,
num_passes
=
10
000
,
num_passes
=
10
,
reader_dict
=
reader_dict
)
...
...
demo/seqToseq/seqToseq_net_v2.py
浏览文件 @
e60d94b3
...
...
@@ -14,7 +14,7 @@ def seqToseq_net_v2(source_dict_dim, target_dict_dim):
#### Encoder
src_word_id
=
layer
.
data
(
name
=
'source_language_word'
,
type
=
data_type
.
dense_vector
(
source_dict_dim
))
type
=
data_type
.
integer_value_sequence
(
source_dict_dim
))
src_embedding
=
layer
.
embedding
(
input
=
src_word_id
,
size
=
word_vector_dim
,
...
...
@@ -67,7 +67,7 @@ def seqToseq_net_v2(source_dict_dim, target_dict_dim):
trg_embedding
=
layer
.
embedding
(
input
=
layer
.
data
(
name
=
'target_language_word'
,
type
=
data_type
.
dense_vector
(
target_dict_dim
)),
type
=
data_type
.
integer_value_sequence
(
target_dict_dim
)),
size
=
word_vector_dim
,
param_attr
=
attr
.
ParamAttr
(
name
=
'_target_language_embedding'
))
group_inputs
.
append
(
trg_embedding
)
...
...
@@ -84,7 +84,7 @@ def seqToseq_net_v2(source_dict_dim, target_dict_dim):
lbl
=
layer
.
data
(
name
=
'target_language_next_word'
,
type
=
data_type
.
dense_vector
(
target_dict_dim
))
type
=
data_type
.
integer_value_sequence
(
target_dict_dim
))
cost
=
layer
.
classification_cost
(
input
=
decoder
,
label
=
lbl
)
return
cost
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