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
迷途归一
Paddle
提交
0531edf9
P
Paddle
项目概览
迷途归一
/
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 >>
未验证
提交
0531edf9
编写于
1月 26, 2018
作者:
K
kavyasrinet
提交者:
GitHub
1月 26, 2018
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Adding distributed training for dynamic_lstm (#7903)
上级
9b6387e7
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
135 addition
and
0 deletion
+135
-0
python/paddle/v2/fluid/tests/book_distribute/notest_understand_sentiment_dynamic_lstm.py
...ok_distribute/notest_understand_sentiment_dynamic_lstm.py
+135
-0
未找到文件。
python/paddle/v2/fluid/tests/book_distribute/notest_understand_sentiment_dynamic_lstm.py
0 → 100644
浏览文件 @
0531edf9
# Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import
numpy
as
np
import
os
import
paddle.v2
as
paddle
import
paddle.v2.fluid
as
fluid
def
stacked_lstm_net
(
data
,
label
,
input_dim
,
class_dim
=
2
,
emb_dim
=
128
,
hid_dim
=
512
,
stacked_num
=
3
):
assert
stacked_num
%
2
==
1
emb
=
fluid
.
layers
.
embedding
(
input
=
data
,
size
=
[
input_dim
,
emb_dim
])
# add bias attr
# TODO(qijun) linear act
fc1
=
fluid
.
layers
.
fc
(
input
=
emb
,
size
=
hid_dim
)
lstm1
,
cell1
=
fluid
.
layers
.
dynamic_lstm
(
input
=
fc1
,
size
=
hid_dim
)
inputs
=
[
fc1
,
lstm1
]
for
i
in
range
(
2
,
stacked_num
+
1
):
fc
=
fluid
.
layers
.
fc
(
input
=
inputs
,
size
=
hid_dim
)
lstm
,
cell
=
fluid
.
layers
.
dynamic_lstm
(
input
=
fc
,
size
=
hid_dim
,
is_reverse
=
(
i
%
2
)
==
0
)
inputs
=
[
fc
,
lstm
]
fc_last
=
fluid
.
layers
.
sequence_pool
(
input
=
inputs
[
0
],
pool_type
=
'max'
)
lstm_last
=
fluid
.
layers
.
sequence_pool
(
input
=
inputs
[
1
],
pool_type
=
'max'
)
prediction
=
fluid
.
layers
.
fc
(
input
=
[
fc_last
,
lstm_last
],
size
=
class_dim
,
act
=
'softmax'
)
cost
=
fluid
.
layers
.
cross_entropy
(
input
=
prediction
,
label
=
label
)
avg_cost
=
fluid
.
layers
.
mean
(
x
=
cost
)
adam_optimizer
=
fluid
.
optimizer
.
Adam
(
learning_rate
=
0.002
)
optimize_ops
,
params_grads
=
adam_optimizer
.
minimize
(
avg_cost
)
accuracy
=
fluid
.
evaluator
.
Accuracy
(
input
=
prediction
,
label
=
label
)
return
avg_cost
,
accuracy
,
accuracy
.
metrics
[
0
],
optimize_ops
,
params_grads
def
to_lodtensor
(
data
,
place
):
seq_lens
=
[
len
(
seq
)
for
seq
in
data
]
cur_len
=
0
lod
=
[
cur_len
]
for
l
in
seq_lens
:
cur_len
+=
l
lod
.
append
(
cur_len
)
flattened_data
=
np
.
concatenate
(
data
,
axis
=
0
).
astype
(
"int64"
)
flattened_data
=
flattened_data
.
reshape
([
len
(
flattened_data
),
1
])
res
=
fluid
.
LoDTensor
()
res
.
set
(
flattened_data
,
place
)
res
.
set_lod
([
lod
])
return
res
def
main
():
BATCH_SIZE
=
100
PASS_NUM
=
5
word_dict
=
paddle
.
dataset
.
imdb
.
word_dict
()
print
"loaded word dict successfully"
dict_dim
=
len
(
word_dict
)
class_dim
=
2
data
=
fluid
.
layers
.
data
(
name
=
"words"
,
shape
=
[
1
],
dtype
=
"int64"
,
lod_level
=
1
)
label
=
fluid
.
layers
.
data
(
name
=
"label"
,
shape
=
[
1
],
dtype
=
"int64"
)
cost
,
accuracy
,
acc_out
,
optimize_ops
,
params_grads
=
stacked_lstm_net
(
data
,
label
,
input_dim
=
dict_dim
,
class_dim
=
class_dim
)
train_data
=
paddle
.
batch
(
paddle
.
reader
.
shuffle
(
paddle
.
dataset
.
imdb
.
train
(
word_dict
),
buf_size
=
1000
),
batch_size
=
BATCH_SIZE
)
place
=
fluid
.
CPUPlace
()
exe
=
fluid
.
Executor
(
place
)
feeder
=
fluid
.
DataFeeder
(
feed_list
=
[
data
,
label
],
place
=
place
)
t
=
fluid
.
DistributeTranspiler
()
# all parameter server endpoints list for spliting parameters
pserver_endpoints
=
os
.
getenv
(
"PSERVERS"
)
# server endpoint for current node
current_endpoint
=
os
.
getenv
(
"SERVER_ENDPOINT"
)
# run as trainer or parameter server
training_role
=
os
.
getenv
(
"TRAINING_ROLE"
,
"TRAINER"
)
# get the training role: trainer/pserver
t
.
transpile
(
optimize_ops
,
params_grads
,
pservers
=
pserver_endpoints
,
trainers
=
2
)
if
training_role
==
"PSERVER"
:
if
not
current_endpoint
:
print
(
"need env SERVER_ENDPOINT"
)
exit
(
1
)
pserver_prog
=
t
.
get_pserver_program
(
current_endpoint
)
pserver_startup
=
t
.
get_startup_program
(
current_endpoint
,
pserver_prog
)
exe
.
run
(
pserver_startup
)
exe
.
run
(
pserver_prog
)
elif
training_role
==
"TRAINER"
:
exe
.
run
(
fluid
.
default_startup_program
())
trainer_prog
=
t
.
get_trainer_program
()
for
pass_id
in
xrange
(
PASS_NUM
):
accuracy
.
reset
(
exe
)
for
data
in
train_data
():
cost_val
,
acc_val
=
exe
.
run
(
trainer_prog
,
feed
=
feeder
.
feed
(
data
),
fetch_list
=
[
cost
,
acc_out
])
pass_acc
=
accuracy
.
eval
(
exe
)
print
(
"cost="
+
str
(
cost_val
)
+
" acc="
+
str
(
acc_val
)
+
" pass_acc="
+
str
(
pass_acc
))
if
cost_val
<
1.0
and
acc_val
>
0.8
:
exit
(
0
)
else
:
print
(
"environment var TRAINER_ROLE should be TRAINER os PSERVER"
)
if
__name__
==
'__main__'
:
main
()
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