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
PaddleOCR
提交
5cce398e
P
PaddleOCR
项目概览
PaddlePaddle
/
PaddleOCR
大约 1 年 前同步成功
通知
1528
Star
32962
Fork
6643
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
108
列表
看板
标记
里程碑
合并请求
7
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleOCR
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
108
Issue
108
列表
看板
标记
里程碑
合并请求
7
合并请求
7
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
提交
5cce398e
编写于
6月 10, 2021
作者:
W
WenmuZhou
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix structure pipeline infer bug
上级
330f08ff
变更
5
隐藏空白更改
内联
并排
Showing
5 changed file
with
18 addition
and
10 deletion
+18
-10
paddleocr.py
paddleocr.py
+2
-2
ppocr/utils/logging.py
ppocr/utils/logging.py
+1
-1
ppstructure/paddlestructure.py
ppstructure/paddlestructure.py
+2
-2
ppstructure/predict_system.py
ppstructure/predict_system.py
+6
-2
tools/infer/predict_system.py
tools/infer/predict_system.py
+7
-3
未找到文件。
paddleocr.py
浏览文件 @
5cce398e
...
@@ -151,8 +151,8 @@ class PaddleOCR(predict_system.TextSystem):
...
@@ -151,8 +151,8 @@ class PaddleOCR(predict_system.TextSystem):
"""
"""
params
=
parse_args
(
mMain
=
False
)
params
=
parse_args
(
mMain
=
False
)
params
.
__dict__
.
update
(
**
kwargs
)
params
.
__dict__
.
update
(
**
kwargs
)
if
params
.
show_log
:
if
not
params
.
show_log
:
logger
.
setLevel
(
logging
.
DEBUG
)
logger
.
setLevel
(
logging
.
INFO
)
self
.
use_angle_cls
=
params
.
use_angle_cls
self
.
use_angle_cls
=
params
.
use_angle_cls
lang
=
params
.
lang
lang
=
params
.
lang
latin_lang
=
[
latin_lang
=
[
...
...
ppocr/utils/logging.py
浏览文件 @
5cce398e
...
@@ -22,7 +22,7 @@ logger_initialized = {}
...
@@ -22,7 +22,7 @@ logger_initialized = {}
@
functools
.
lru_cache
()
@
functools
.
lru_cache
()
def
get_logger
(
name
=
'root'
,
log_file
=
None
,
log_level
=
logging
.
INFO
):
def
get_logger
(
name
=
'root'
,
log_file
=
None
,
log_level
=
logging
.
DEBUG
):
"""Initialize and get a logger by name.
"""Initialize and get a logger by name.
If the logger has not been initialized, this method will initialize the
If the logger has not been initialized, this method will initialize the
logger by adding one or two handlers, otherwise the initialized logger will
logger by adding one or two handlers, otherwise the initialized logger will
...
...
ppstructure/paddlestructure.py
浏览文件 @
5cce398e
...
@@ -66,8 +66,8 @@ class PaddleStructure(OCRSystem):
...
@@ -66,8 +66,8 @@ class PaddleStructure(OCRSystem):
def
__init__
(
self
,
**
kwargs
):
def
__init__
(
self
,
**
kwargs
):
params
=
parse_args
(
mMain
=
False
)
params
=
parse_args
(
mMain
=
False
)
params
.
__dict__
.
update
(
**
kwargs
)
params
.
__dict__
.
update
(
**
kwargs
)
if
params
.
show_log
:
if
not
params
.
show_log
:
logger
.
setLevel
(
logging
.
DEBUG
)
logger
.
setLevel
(
logging
.
INFO
)
params
.
use_angle_cls
=
False
params
.
use_angle_cls
=
False
# init model dir
# init model dir
params
.
det_model_dir
,
det_url
=
confirm_model_dir_url
(
params
.
det_model_dir
,
params
.
det_model_dir
,
det_url
=
confirm_model_dir_url
(
params
.
det_model_dir
,
...
...
ppstructure/predict_system.py
浏览文件 @
5cce398e
...
@@ -24,6 +24,7 @@ os.environ["FLAGS_allocator_strategy"] = 'auto_growth'
...
@@ -24,6 +24,7 @@ os.environ["FLAGS_allocator_strategy"] = 'auto_growth'
import
cv2
import
cv2
import
numpy
as
np
import
numpy
as
np
import
time
import
time
import
logging
import
layoutparser
as
lp
import
layoutparser
as
lp
...
@@ -31,7 +32,7 @@ from ppocr.utils.utility import get_image_file_list, check_and_read_gif
...
@@ -31,7 +32,7 @@ from ppocr.utils.utility import get_image_file_list, check_and_read_gif
from
ppocr.utils.logging
import
get_logger
from
ppocr.utils.logging
import
get_logger
from
tools.infer.predict_system
import
TextSystem
from
tools.infer.predict_system
import
TextSystem
from
ppstructure.table.predict_table
import
TableSystem
,
to_excel
from
ppstructure.table.predict_table
import
TableSystem
,
to_excel
from
ppstructure.utility
import
parse_args
,
draw_result
from
ppstructure.utility
import
parse_args
,
draw_result
logger
=
get_logger
()
logger
=
get_logger
()
...
@@ -40,6 +41,8 @@ class OCRSystem(object):
...
@@ -40,6 +41,8 @@ class OCRSystem(object):
def
__init__
(
self
,
args
):
def
__init__
(
self
,
args
):
args
.
det_limit_type
=
'resize_long'
args
.
det_limit_type
=
'resize_long'
args
.
drop_score
=
0
args
.
drop_score
=
0
if
not
args
.
show_log
:
logger
.
setLevel
(
logging
.
INFO
)
self
.
text_system
=
TextSystem
(
args
)
self
.
text_system
=
TextSystem
(
args
)
self
.
table_system
=
TableSystem
(
args
,
self
.
text_system
.
text_detector
,
self
.
text_system
.
text_recognizer
)
self
.
table_system
=
TableSystem
(
args
,
self
.
text_system
.
text_detector
,
self
.
text_system
.
text_recognizer
)
self
.
table_layout
=
lp
.
PaddleDetectionLayoutModel
(
"lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config"
,
self
.
table_layout
=
lp
.
PaddleDetectionLayoutModel
(
"lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config"
,
...
@@ -67,6 +70,7 @@ class OCRSystem(object):
...
@@ -67,6 +70,7 @@ class OCRSystem(object):
res_list
.
append
({
'type'
:
region
.
type
,
'bbox'
:
[
x1
,
y1
,
x2
,
y2
],
'res'
:
res
})
res_list
.
append
({
'type'
:
region
.
type
,
'bbox'
:
[
x1
,
y1
,
x2
,
y2
],
'res'
:
res
})
return
res_list
return
res_list
def
save_res
(
res
,
save_folder
,
img_name
):
def
save_res
(
res
,
save_folder
,
img_name
):
excel_save_folder
=
os
.
path
.
join
(
save_folder
,
img_name
)
excel_save_folder
=
os
.
path
.
join
(
save_folder
,
img_name
)
os
.
makedirs
(
excel_save_folder
,
exist_ok
=
True
)
os
.
makedirs
(
excel_save_folder
,
exist_ok
=
True
)
...
@@ -105,7 +109,7 @@ def main(args):
...
@@ -105,7 +109,7 @@ def main(args):
starttime
=
time
.
time
()
starttime
=
time
.
time
()
res
=
structure_sys
(
img
)
res
=
structure_sys
(
img
)
save_res
(
res
,
save_folder
,
img_name
)
save_res
(
res
,
save_folder
,
img_name
)
draw_img
=
draw_result
(
img
,
res
,
args
.
vis_font_path
)
draw_img
=
draw_result
(
img
,
res
,
args
.
vis_font_path
)
cv2
.
imwrite
(
os
.
path
.
join
(
save_folder
,
img_name
,
'show.jpg'
),
draw_img
)
cv2
.
imwrite
(
os
.
path
.
join
(
save_folder
,
img_name
,
'show.jpg'
),
draw_img
)
logger
.
info
(
'result save to {}'
.
format
(
os
.
path
.
join
(
save_folder
,
img_name
)))
logger
.
info
(
'result save to {}'
.
format
(
os
.
path
.
join
(
save_folder
,
img_name
)))
elapse
=
time
.
time
()
-
starttime
elapse
=
time
.
time
()
-
starttime
...
...
tools/infer/predict_system.py
浏览文件 @
5cce398e
...
@@ -24,6 +24,7 @@ import cv2
...
@@ -24,6 +24,7 @@ import cv2
import
copy
import
copy
import
numpy
as
np
import
numpy
as
np
import
time
import
time
import
logging
from
PIL
import
Image
from
PIL
import
Image
import
tools.infer.utility
as
utility
import
tools.infer.utility
as
utility
import
tools.infer.predict_rec
as
predict_rec
import
tools.infer.predict_rec
as
predict_rec
...
@@ -38,6 +39,9 @@ logger = get_logger()
...
@@ -38,6 +39,9 @@ logger = get_logger()
class
TextSystem
(
object
):
class
TextSystem
(
object
):
def
__init__
(
self
,
args
):
def
__init__
(
self
,
args
):
if
not
args
.
show_log
:
logger
.
setLevel
(
logging
.
INFO
)
self
.
text_detector
=
predict_det
.
TextDetector
(
args
)
self
.
text_detector
=
predict_det
.
TextDetector
(
args
)
self
.
text_recognizer
=
predict_rec
.
TextRecognizer
(
args
)
self
.
text_recognizer
=
predict_rec
.
TextRecognizer
(
args
)
self
.
use_angle_cls
=
args
.
use_angle_cls
self
.
use_angle_cls
=
args
.
use_angle_cls
...
@@ -88,7 +92,7 @@ class TextSystem(object):
...
@@ -88,7 +92,7 @@ class TextSystem(object):
ori_im
=
img
.
copy
()
ori_im
=
img
.
copy
()
dt_boxes
,
elapse
=
self
.
text_detector
(
img
)
dt_boxes
,
elapse
=
self
.
text_detector
(
img
)
logger
.
info
(
"dt_boxes num : {}, elapse : {}"
.
format
(
logger
.
debug
(
"dt_boxes num : {}, elapse : {}"
.
format
(
len
(
dt_boxes
),
elapse
))
len
(
dt_boxes
),
elapse
))
if
dt_boxes
is
None
:
if
dt_boxes
is
None
:
...
@@ -104,11 +108,11 @@ class TextSystem(object):
...
@@ -104,11 +108,11 @@ class TextSystem(object):
if
self
.
use_angle_cls
and
cls
:
if
self
.
use_angle_cls
and
cls
:
img_crop_list
,
angle_list
,
elapse
=
self
.
text_classifier
(
img_crop_list
,
angle_list
,
elapse
=
self
.
text_classifier
(
img_crop_list
)
img_crop_list
)
logger
.
info
(
"cls num : {}, elapse : {}"
.
format
(
logger
.
debug
(
"cls num : {}, elapse : {}"
.
format
(
len
(
img_crop_list
),
elapse
))
len
(
img_crop_list
),
elapse
))
rec_res
,
elapse
=
self
.
text_recognizer
(
img_crop_list
)
rec_res
,
elapse
=
self
.
text_recognizer
(
img_crop_list
)
logger
.
info
(
"rec_res num : {}, elapse : {}"
.
format
(
logger
.
debug
(
"rec_res num : {}, elapse : {}"
.
format
(
len
(
rec_res
),
elapse
))
len
(
rec_res
),
elapse
))
# self.print_draw_crop_rec_res(img_crop_list, rec_res)
# self.print_draw_crop_rec_res(img_crop_list, rec_res)
filter_boxes
,
filter_rec_res
=
[],
[]
filter_boxes
,
filter_rec_res
=
[],
[]
...
...
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