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
ccf6d601
S
Serving
项目概览
PaddlePaddle
/
Serving
大约 1 年 前同步成功
通知
186
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
提交
ccf6d601
编写于
1月 14, 2022
作者:
F
felixhjh
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add ocr postprocess
上级
ecd70aef
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
106 addition
and
0 deletion
+106
-0
python/paddle_serving_app/reader/ocr_reader.py
python/paddle_serving_app/reader/ocr_reader.py
+106
-0
未找到文件。
python/paddle_serving_app/reader/ocr_reader.py
浏览文件 @
ccf6d601
...
...
@@ -118,6 +118,111 @@ class CharacterOps(object):
%
(
self
.
loss_type
)
assert
False
,
err
class
BaseRecLabelDecode
(
object
):
""" Convert between text-label and text-index """
def
__init__
(
self
,
config
):
support_character_type
=
[
'ch'
,
'en'
,
'EN_symbol'
,
'french'
,
'german'
,
'japan'
,
'korean'
,
'it'
,
'xi'
,
'pu'
,
'ru'
,
'ar'
,
'ta'
,
'ug'
,
'fa'
,
'ur'
,
'rs'
,
'oc'
,
'rsc'
,
'bg'
,
'uk'
,
'be'
,
'te'
,
'ka'
,
'chinese_cht'
,
'hi'
,
'mr'
,
'ne'
,
'EN'
]
character_type
=
config
[
'character_type'
]
character_dict_path
=
config
[
'character_dict_path'
]
use_space_char
=
True
assert
character_type
in
support_character_type
,
"Only {} are supported now but get {}"
.
format
(
support_character_type
,
character_type
)
self
.
beg_str
=
"sos"
self
.
end_str
=
"eos"
if
character_type
==
"en"
:
self
.
character_str
=
"0123456789abcdefghijklmnopqrstuvwxyz"
dict_character
=
list
(
self
.
character_str
)
elif
character_type
==
"EN_symbol"
:
# same with ASTER setting (use 94 char).
self
.
character_str
=
string
.
printable
[:
-
6
]
dict_character
=
list
(
self
.
character_str
)
elif
character_type
in
support_character_type
:
self
.
character_str
=
""
assert
character_dict_path
is
not
None
,
"character_dict_path should not be None when character_type is {}"
.
format
(
character_type
)
with
open
(
character_dict_path
,
"rb"
)
as
fin
:
lines
=
fin
.
readlines
()
for
line
in
lines
:
line
=
line
.
decode
(
'utf-8'
).
strip
(
"
\n
"
).
strip
(
"
\r\n
"
)
self
.
character_str
+=
line
if
use_space_char
:
self
.
character_str
+=
" "
dict_character
=
list
(
self
.
character_str
)
else
:
raise
NotImplementedError
self
.
character_type
=
character_type
dict_character
=
self
.
add_special_char
(
dict_character
)
self
.
dict
=
{}
for
i
,
char
in
enumerate
(
dict_character
):
self
.
dict
[
char
]
=
i
self
.
character
=
dict_character
def
add_special_char
(
self
,
dict_character
):
return
dict_character
def
decode
(
self
,
text_index
,
text_prob
=
None
,
is_remove_duplicate
=
False
):
""" convert text-index into text-label. """
result_list
=
[]
ignored_tokens
=
self
.
get_ignored_tokens
()
batch_size
=
len
(
text_index
)
for
batch_idx
in
range
(
batch_size
):
char_list
=
[]
conf_list
=
[]
for
idx
in
range
(
len
(
text_index
[
batch_idx
])):
if
text_index
[
batch_idx
][
idx
]
in
ignored_tokens
:
continue
if
is_remove_duplicate
:
# only for predict
if
idx
>
0
and
text_index
[
batch_idx
][
idx
-
1
]
==
text_index
[
batch_idx
][
idx
]:
continue
char_list
.
append
(
self
.
character
[
int
(
text_index
[
batch_idx
][
idx
])])
if
text_prob
is
not
None
:
conf_list
.
append
(
text_prob
[
batch_idx
][
idx
])
else
:
conf_list
.
append
(
1
)
text
=
''
.
join
(
char_list
)
result_list
.
append
((
text
,
np
.
mean
(
conf_list
)))
return
result_list
def
get_ignored_tokens
(
self
):
return
[
0
]
# for ctc blank
class
CTCLabelDecode
(
BaseRecLabelDecode
):
""" Convert between text-label and text-index """
def
__init__
(
self
,
config
,
#character_dict_path=None,
#character_type='ch',
#use_space_char=False,
**
kwargs
):
super
(
CTCLabelDecode
,
self
).
__init__
(
config
)
def
__call__
(
self
,
preds
,
label
=
None
,
*
args
,
**
kwargs
):
preds_idx
=
preds
.
argmax
(
axis
=
2
)
preds_prob
=
preds
.
max
(
axis
=
2
)
text
=
self
.
decode
(
preds_idx
,
preds_prob
,
is_remove_duplicate
=
True
)
if
label
is
None
:
return
text
label
=
self
.
decode
(
label
)
return
text
,
label
def
add_special_char
(
self
,
dict_character
):
dict_character
=
[
'blank'
]
+
dict_character
return
dict_character
class
OCRReader
(
object
):
def
__init__
(
self
,
...
...
@@ -134,6 +239,7 @@ class OCRReader(object):
char_ops_params
[
"character_dict_path"
]
=
char_dict_path
char_ops_params
[
'loss_type'
]
=
'ctc'
self
.
char_ops
=
CharacterOps
(
char_ops_params
)
self
.
label_ops
=
CTCLabelDecode
(
char_ops_params
)
def
resize_norm_img
(
self
,
img
,
max_wh_ratio
):
imgC
,
imgH
,
imgW
=
self
.
rec_image_shape
...
...
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