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
Serving
提交
28368f7d
S
Serving
项目概览
PaddlePaddle
/
Serving
大约 1 年 前同步成功
通知
185
Star
833
Fork
253
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
105
列表
看板
标记
里程碑
合并请求
10
Wiki
2
Wiki
分析
仓库
DevOps
项目成员
Pages
S
Serving
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
105
Issue
105
列表
看板
标记
里程碑
合并请求
10
合并请求
10
Pages
分析
分析
仓库分析
DevOps
Wiki
2
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
28368f7d
编写于
4月 10, 2020
作者:
B
barrierye
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add imdb_reader
上级
96ef959b
变更
1
显示空白变更内容
内联
并排
Showing
1 changed file
with
92 addition
and
0 deletion
+92
-0
ensemble-demo/imdb_reader.py
ensemble-demo/imdb_reader.py
+92
-0
未找到文件。
ensemble-demo/imdb_reader.py
0 → 100644
浏览文件 @
28368f7d
# Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.
#
# 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.
# pylint: disable=doc-string-missing
import
sys
import
os
import
paddle
import
re
import
paddle.fluid.incubate.data_generator
as
dg
py_version
=
sys
.
version_info
[
0
]
class
IMDBDataset
(
dg
.
MultiSlotDataGenerator
):
def
load_resource
(
self
,
dictfile
):
self
.
_vocab
=
{}
wid
=
0
if
py_version
==
2
:
with
open
(
dictfile
)
as
f
:
for
line
in
f
:
self
.
_vocab
[
line
.
strip
()]
=
wid
wid
+=
1
else
:
with
open
(
dictfile
,
encoding
=
"utf-8"
)
as
f
:
for
line
in
f
:
self
.
_vocab
[
line
.
strip
()]
=
wid
wid
+=
1
self
.
_unk_id
=
len
(
self
.
_vocab
)
self
.
_pattern
=
re
.
compile
(
r
'(;|,|\.|\?|!|\s|\(|\))'
)
self
.
return_value
=
(
"words"
,
[
1
,
2
,
3
,
4
,
5
,
6
]),
(
"label"
,
[
0
])
def
get_words_only
(
self
,
line
):
sent
=
line
.
lower
().
replace
(
"<br />"
,
" "
).
strip
()
words
=
[
x
for
x
in
self
.
_pattern
.
split
(
sent
)
if
x
and
x
!=
" "
]
feas
=
[
self
.
_vocab
[
x
]
if
x
in
self
.
_vocab
else
self
.
_unk_id
for
x
in
words
]
return
feas
def
get_words_and_label
(
self
,
line
):
send
=
'|'
.
join
(
line
.
split
(
'|'
)[:
-
1
]).
lower
().
replace
(
"<br />"
,
" "
).
strip
()
label
=
[
int
(
line
.
split
(
'|'
)[
-
1
])]
words
=
[
x
for
x
in
self
.
_pattern
.
split
(
send
)
if
x
and
x
!=
" "
]
feas
=
[
self
.
_vocab
[
x
]
if
x
in
self
.
_vocab
else
self
.
_unk_id
for
x
in
words
]
return
feas
,
label
def
infer_reader
(
self
,
infer_filelist
,
batch
,
buf_size
):
def
local_iter
():
for
fname
in
infer_filelist
:
with
open
(
fname
,
"r"
)
as
fin
:
for
line
in
fin
:
feas
,
label
=
self
.
get_words_and_label
(
line
)
yield
feas
,
label
import
paddle
batch_iter
=
paddle
.
batch
(
paddle
.
reader
.
shuffle
(
local_iter
,
buf_size
=
buf_size
),
batch_size
=
batch
)
return
batch_iter
def
generate_sample
(
self
,
line
):
def
memory_iter
():
for
i
in
range
(
1000
):
yield
self
.
return_value
def
data_iter
():
feas
,
label
=
self
.
get_words_and_label
(
line
)
yield
(
"words"
,
feas
),
(
"label"
,
label
)
return
data_iter
if
__name__
==
"__main__"
:
imdb
=
IMDBDataset
()
imdb
.
load_resource
(
"imdb.vocab"
)
imdb
.
run_from_stdin
()
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