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
csdn_franckjun
Paddle
提交
9827a5c6
P
Paddle
项目概览
csdn_franckjun
/
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
9827a5c6
编写于
3月 03, 2017
作者:
Q
qingqing01
提交者:
GitHub
3月 03, 2017
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #1504 from qingqing01/srl_api_v2
semantic_role_labeling v2 api
上级
8bbf3539
e7c23989
变更
3
显示空白变更内容
内联
并排
Showing
3 changed file
with
187 addition
and
20 deletion
+187
-20
demo/semantic_role_labeling/api_train_v2.py
demo/semantic_role_labeling/api_train_v2.py
+175
-0
python/paddle/v2/dataset/__init__.py
python/paddle/v2/dataset/__init__.py
+2
-1
python/paddle/v2/dataset/conll05.py
python/paddle/v2/dataset/conll05.py
+10
-19
未找到文件。
demo/semantic_role_labeling/api_train_v2.py
0 → 100644
浏览文件 @
9827a5c6
import
sys
import
math
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.dataset.conll05
as
conll05
def
db_lstm
():
word_dict
,
verb_dict
,
label_dict
=
conll05
.
get_dict
()
word_dict_len
=
len
(
word_dict
)
label_dict_len
=
len
(
label_dict
)
pred_len
=
len
(
verb_dict
)
mark_dict_len
=
2
word_dim
=
32
mark_dim
=
5
hidden_dim
=
512
depth
=
8
#8 features
def
d_type
(
size
):
return
paddle
.
data_type
.
integer_value_sequence
(
size
)
word
=
paddle
.
layer
.
data
(
name
=
'word_data'
,
type
=
d_type
(
word_dict_len
))
predicate
=
paddle
.
layer
.
data
(
name
=
'verb_data'
,
type
=
d_type
(
pred_len
))
ctx_n2
=
paddle
.
layer
.
data
(
name
=
'ctx_n2_data'
,
type
=
d_type
(
word_dict_len
))
ctx_n1
=
paddle
.
layer
.
data
(
name
=
'ctx_n1_data'
,
type
=
d_type
(
word_dict_len
))
ctx_0
=
paddle
.
layer
.
data
(
name
=
'ctx_0_data'
,
type
=
d_type
(
word_dict_len
))
ctx_p1
=
paddle
.
layer
.
data
(
name
=
'ctx_p1_data'
,
type
=
d_type
(
word_dict_len
))
ctx_p2
=
paddle
.
layer
.
data
(
name
=
'ctx_p2_data'
,
type
=
d_type
(
word_dict_len
))
mark
=
paddle
.
layer
.
data
(
name
=
'mark_data'
,
type
=
d_type
(
mark_dict_len
))
target
=
paddle
.
layer
.
data
(
name
=
'target'
,
type
=
d_type
(
label_dict_len
))
default_std
=
1
/
math
.
sqrt
(
hidden_dim
)
/
3.0
emb_para
=
paddle
.
attr
.
Param
(
name
=
'emb'
,
initial_std
=
0.
,
learning_rate
=
0.
)
std_0
=
paddle
.
attr
.
Param
(
initial_std
=
0.
)
std_default
=
paddle
.
attr
.
Param
(
initial_std
=
default_std
)
predicate_embedding
=
paddle
.
layer
.
embedding
(
size
=
word_dim
,
input
=
predicate
,
param_attr
=
paddle
.
attr
.
Param
(
name
=
'vemb'
,
initial_std
=
default_std
))
mark_embedding
=
paddle
.
layer
.
embedding
(
size
=
mark_dim
,
input
=
mark
,
param_attr
=
std_0
)
word_input
=
[
word
,
ctx_n2
,
ctx_n1
,
ctx_0
,
ctx_p1
,
ctx_p2
]
emb_layers
=
[
paddle
.
layer
.
embedding
(
size
=
word_dim
,
input
=
x
,
param_attr
=
emb_para
)
for
x
in
word_input
]
emb_layers
.
append
(
predicate_embedding
)
emb_layers
.
append
(
mark_embedding
)
hidden_0
=
paddle
.
layer
.
mixed
(
size
=
hidden_dim
,
bias_attr
=
std_default
,
input
=
[
paddle
.
layer
.
full_matrix_projection
(
input
=
emb
,
param_attr
=
std_default
)
for
emb
in
emb_layers
])
mix_hidden_lr
=
1e-3
lstm_para_attr
=
paddle
.
attr
.
Param
(
initial_std
=
0.0
,
learning_rate
=
1.0
)
hidden_para_attr
=
paddle
.
attr
.
Param
(
initial_std
=
default_std
,
learning_rate
=
mix_hidden_lr
)
lstm_0
=
paddle
.
layer
.
lstmemory
(
input
=
hidden_0
,
act
=
paddle
.
activation
.
Relu
(),
gate_act
=
paddle
.
activation
.
Sigmoid
(),
state_act
=
paddle
.
activation
.
Sigmoid
(),
bias_attr
=
std_0
,
param_attr
=
lstm_para_attr
)
#stack L-LSTM and R-LSTM with direct edges
input_tmp
=
[
hidden_0
,
lstm_0
]
for
i
in
range
(
1
,
depth
):
mix_hidden
=
paddle
.
layer
.
mixed
(
size
=
hidden_dim
,
bias_attr
=
std_default
,
input
=
[
paddle
.
layer
.
full_matrix_projection
(
input
=
input_tmp
[
0
],
param_attr
=
hidden_para_attr
),
paddle
.
layer
.
full_matrix_projection
(
input
=
input_tmp
[
1
],
param_attr
=
lstm_para_attr
)
])
lstm
=
paddle
.
layer
.
lstmemory
(
input
=
mix_hidden
,
act
=
paddle
.
activation
.
Relu
(),
gate_act
=
paddle
.
activation
.
Sigmoid
(),
state_act
=
paddle
.
activation
.
Sigmoid
(),
reverse
=
((
i
%
2
)
==
1
),
bias_attr
=
std_0
,
param_attr
=
lstm_para_attr
)
input_tmp
=
[
mix_hidden
,
lstm
]
feature_out
=
paddle
.
layer
.
mixed
(
size
=
label_dict_len
,
bias_attr
=
std_default
,
input
=
[
paddle
.
layer
.
full_matrix_projection
(
input
=
input_tmp
[
0
],
param_attr
=
hidden_para_attr
),
paddle
.
layer
.
full_matrix_projection
(
input
=
input_tmp
[
1
],
param_attr
=
lstm_para_attr
)
],
)
crf_cost
=
paddle
.
layer
.
crf
(
size
=
label_dict_len
,
input
=
feature_out
,
label
=
target
,
param_attr
=
paddle
.
attr
.
Param
(
name
=
'crfw'
,
initial_std
=
default_std
,
learning_rate
=
mix_hidden_lr
))
crf_dec
=
paddle
.
layer
.
crf_decoding
(
name
=
'crf_dec_l'
,
size
=
label_dict_len
,
input
=
feature_out
,
label
=
target
,
param_attr
=
paddle
.
attr
.
Param
(
name
=
'crfw'
))
return
crf_cost
,
crf_dec
def
load_parameter
(
file_name
,
h
,
w
):
with
open
(
file_name
,
'rb'
)
as
f
:
f
.
read
(
16
)
# skip header.
return
np
.
fromfile
(
f
,
dtype
=
np
.
float32
).
reshape
(
h
,
w
)
def
main
():
paddle
.
init
(
use_gpu
=
False
,
trainer_count
=
1
)
# define network topology
crf_cost
,
crf_dec
=
db_lstm
()
# create parameters
parameters
=
paddle
.
parameters
.
create
([
crf_cost
,
crf_dec
])
# create optimizer
optimizer
=
paddle
.
optimizer
.
Momentum
(
momentum
=
0
,
learning_rate
=
2e-2
,
regularization
=
paddle
.
optimizer
.
L2Regularization
(
rate
=
8e-4
),
model_average
=
paddle
.
optimizer
.
ModelAverage
(
average_window
=
0.5
,
max_average_window
=
10000
),
)
def
event_handler
(
event
):
if
isinstance
(
event
,
paddle
.
event
.
EndIteration
):
if
event
.
batch_id
%
100
==
0
:
print
"Pass %d, Batch %d, Cost %f, %s"
%
(
event
.
pass_id
,
event
.
batch_id
,
event
.
cost
,
event
.
metrics
)
trainer
=
paddle
.
trainer
.
SGD
(
cost
=
crf_cost
,
parameters
=
parameters
,
update_equation
=
optimizer
)
parameters
.
set
(
'emb'
,
load_parameter
(
conll05
.
get_embedding
(),
44068
,
32
))
trn_reader
=
paddle
.
reader
.
batched
(
paddle
.
reader
.
shuffle
(
conll05
.
test
(),
buf_size
=
8192
),
batch_size
=
10
)
trainer
.
train
(
reader
=
trn_reader
,
event_handler
=
event_handler
,
num_passes
=
10000
)
if
__name__
==
'__main__'
:
main
()
python/paddle/v2/dataset/__init__.py
浏览文件 @
9827a5c6
...
@@ -17,5 +17,6 @@ import imikolov
...
@@ -17,5 +17,6 @@ import imikolov
import
imdb
import
imdb
import
cifar
import
cifar
import
movielens
import
movielens
import
conll05
__all__
=
[
'mnist'
,
'imikolov'
,
'imdb'
,
'cifar'
,
'movielens'
]
__all__
=
[
'mnist'
,
'imikolov'
,
'imdb'
,
'cifar'
,
'movielens'
,
'conll05'
]
python/paddle/v2/dataset/conll05.py
浏览文件 @
9827a5c6
...
@@ -12,10 +12,10 @@
...
@@ -12,10 +12,10 @@
# See the License for the specific language governing permissions and
# See the License for the specific language governing permissions and
# limitations under the License.
# limitations under the License.
import
paddle.v2.dataset.common
import
tarfile
import
tarfile
import
gzip
import
gzip
import
itertools
import
itertools
from
common
import
download
__all__
=
[
'test, get_dict'
,
'get_embedding'
]
__all__
=
[
'test, get_dict'
,
'get_embedding'
]
"""
"""
...
@@ -160,7 +160,6 @@ def reader_creator(corpus_reader,
...
@@ -160,7 +160,6 @@ def reader_creator(corpus_reader,
ctx_p2
=
'eos'
ctx_p2
=
'eos'
word_idx
=
[
word_dict
.
get
(
w
,
UNK_IDX
)
for
w
in
sentence
]
word_idx
=
[
word_dict
.
get
(
w
,
UNK_IDX
)
for
w
in
sentence
]
pred_idx
=
[
predicate_dict
.
get
(
predicate
)]
*
sen_len
ctx_n2_idx
=
[
word_dict
.
get
(
ctx_n2
,
UNK_IDX
)]
*
sen_len
ctx_n2_idx
=
[
word_dict
.
get
(
ctx_n2
,
UNK_IDX
)]
*
sen_len
ctx_n1_idx
=
[
word_dict
.
get
(
ctx_n1
,
UNK_IDX
)]
*
sen_len
ctx_n1_idx
=
[
word_dict
.
get
(
ctx_n1
,
UNK_IDX
)]
*
sen_len
...
@@ -168,38 +167,30 @@ def reader_creator(corpus_reader,
...
@@ -168,38 +167,30 @@ def reader_creator(corpus_reader,
ctx_p1_idx
=
[
word_dict
.
get
(
ctx_p1
,
UNK_IDX
)]
*
sen_len
ctx_p1_idx
=
[
word_dict
.
get
(
ctx_p1
,
UNK_IDX
)]
*
sen_len
ctx_p2_idx
=
[
word_dict
.
get
(
ctx_p2
,
UNK_IDX
)]
*
sen_len
ctx_p2_idx
=
[
word_dict
.
get
(
ctx_p2
,
UNK_IDX
)]
*
sen_len
pred_idx
=
[
predicate_dict
.
get
(
predicate
)]
*
sen_len
label_idx
=
[
label_dict
.
get
(
w
)
for
w
in
labels
]
label_idx
=
[
label_dict
.
get
(
w
)
for
w
in
labels
]
yield
word_idx
,
pred_idx
,
ctx_n2_idx
,
ctx_n1_idx
,
\
yield
word_idx
,
ctx_n2_idx
,
ctx_n1_idx
,
\
ctx_0_idx
,
ctx_p1_idx
,
ctx_p2_idx
,
mark
,
label_idx
ctx_0_idx
,
ctx_p1_idx
,
ctx_p2_idx
,
pred_idx
,
mark
,
label_idx
return
reader
()
return
reader
def
get_dict
():
def
get_dict
():
word_dict
=
load_dict
(
word_dict
=
load_dict
(
download
(
WORDDICT_URL
,
'conll05st'
,
WORDDICT_MD5
))
common
.
download
(
WORDDICT_URL
,
'conll05st'
,
WORDDICT_MD5
))
verb_dict
=
load_dict
(
download
(
VERBDICT_URL
,
'conll05st'
,
VERBDICT_MD5
))
verb_dict
=
load_dict
(
label_dict
=
load_dict
(
download
(
TRGDICT_URL
,
'conll05st'
,
TRGDICT_MD5
))
common
.
download
(
VERBDICT_URL
,
'conll05st'
,
VERBDICT_MD5
))
label_dict
=
load_dict
(
common
.
download
(
TRGDICT_URL
,
'conll05st'
,
TRGDICT_MD5
))
return
word_dict
,
verb_dict
,
label_dict
return
word_dict
,
verb_dict
,
label_dict
def
get_embedding
():
def
get_embedding
():
return
common
.
download
(
EMB_URL
,
'conll05st'
,
EMB_MD5
)
return
download
(
EMB_URL
,
'conll05st'
,
EMB_MD5
)
def
test
():
def
test
():
word_dict
,
verb_dict
,
label_dict
=
get_dict
()
word_dict
,
verb_dict
,
label_dict
=
get_dict
()
reader
=
corpus_reader
(
reader
=
corpus_reader
(
common
.
download
(
DATA_URL
,
'conll05st'
,
DATA_MD5
),
download
(
DATA_URL
,
'conll05st'
,
DATA_MD5
),
words_name
=
'conll05st-release/test.wsj/words/test.wsj.words.gz'
,
words_name
=
'conll05st-release/test.wsj/words/test.wsj.words.gz'
,
props_name
=
'conll05st-release/test.wsj/props/test.wsj.props.gz'
)
props_name
=
'conll05st-release/test.wsj/props/test.wsj.props.gz'
)
return
reader_creator
(
reader
,
word_dict
,
verb_dict
,
label_dict
)
return
reader_creator
(
reader
,
word_dict
,
verb_dict
,
label_dict
)
if
__name__
==
'__main__'
:
print
get_embedding
()
for
f
in
test
():
print
f
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