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
90260649
P
PaddleOCR
项目概览
PaddlePaddle
/
PaddleOCR
大约 1 年 前同步成功
通知
1525
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
体验新版 GitCode,发现更多精彩内容 >>
提交
90260649
编写于
12月 01, 2020
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
add predict_cls to predict_system
上级
1c43e8bb
变更
2
显示空白变更内容
内联
并排
Showing
2 changed file
with
33 addition
and
13 deletion
+33
-13
tools/infer/predict_system.py
tools/infer/predict_system.py
+22
-7
tools/infer/utility.py
tools/infer/utility.py
+11
-6
未找到文件。
tools/infer/predict_system.py
浏览文件 @
90260649
...
...
@@ -23,17 +23,21 @@ import numpy as np
import
time
from
PIL
import
Image
import
tools.infer.utility
as
utility
from
tools.infer.utility
import
draw_ocr
import
tools.infer.predict_rec
as
predict_rec
import
tools.infer.predict_det
as
predict_det
import
tools.infer.predict_cls
as
predict_cls
from
ppocr.utils.utility
import
get_image_file_list
,
check_and_read_gif
from
ppocr.utils.logging
import
get_logger
from
tools.infer.utility
import
draw_ocr_box_txt
class
TextSystem
(
object
):
def
__init__
(
self
,
args
):
self
.
text_detector
=
predict_det
.
TextDetector
(
args
)
self
.
text_recognizer
=
predict_rec
.
TextRecognizer
(
args
)
self
.
use_angle_cls
=
args
.
use_angle_cls
if
self
.
use_angle_cls
:
self
.
text_classifier
=
predict_cls
.
TextClassifier
(
args
)
def
get_rotate_crop_image
(
self
,
img
,
points
):
'''
...
...
@@ -88,6 +92,15 @@ class TextSystem(object):
tmp_box
=
copy
.
deepcopy
(
dt_boxes
[
bno
])
img_crop
=
self
.
get_rotate_crop_image
(
ori_im
,
tmp_box
)
img_crop_list
.
append
(
img_crop
)
cv2
.
imwrite
(
'/home/zhoujun20/dygraph/PaddleOCR_rc/inference_results/{}.jpg'
.
format
(
bno
),
img_crop
)
if
self
.
use_angle_cls
:
img_crop_list
,
angle_list
,
elapse
=
self
.
text_classifier
(
img_crop_list
)
print
(
"cls num : {}, elapse : {}"
.
format
(
len
(
img_crop_list
),
elapse
))
rec_res
,
elapse
=
self
.
text_recognizer
(
img_crop_list
)
print
(
"rec_res num : {}, elapse : {}"
.
format
(
len
(
rec_res
),
elapse
))
# self.print_draw_crop_rec_res(img_crop_list, rec_res)
...
...
@@ -119,7 +132,7 @@ def main(args):
image_file_list
=
get_image_file_list
(
args
.
image_dir
)
text_sys
=
TextSystem
(
args
)
is_visualize
=
True
tackle_img_num
=
0
font_path
=
args
.
vis_font_path
for
image_file
in
image_file_list
:
img
,
flag
=
check_and_read_gif
(
image_file
)
if
not
flag
:
...
...
@@ -128,9 +141,6 @@ def main(args):
logger
.
info
(
"error in loading image:{}"
.
format
(
image_file
))
continue
starttime
=
time
.
time
()
tackle_img_num
+=
1
if
not
args
.
use_gpu
and
args
.
enable_mkldnn
and
tackle_img_num
%
30
==
0
:
text_sys
=
TextSystem
(
args
)
dt_boxes
,
rec_res
=
text_sys
(
img
)
elapse
=
time
.
time
()
-
starttime
print
(
"Predict time of %s: %.3fs"
%
(
image_file
,
elapse
))
...
...
@@ -149,8 +159,13 @@ def main(args):
txts
=
[
rec_res
[
i
][
0
]
for
i
in
range
(
len
(
rec_res
))]
scores
=
[
rec_res
[
i
][
1
]
for
i
in
range
(
len
(
rec_res
))]
draw_img
=
draw_ocr
(
image
,
boxes
,
txts
,
scores
,
drop_score
=
drop_score
)
draw_img
=
draw_ocr_box_txt
(
image
,
boxes
,
txts
,
scores
,
drop_score
=
drop_score
,
font_path
=
font_path
)
draw_img_save
=
"./inference_results/"
if
not
os
.
path
.
exists
(
draw_img_save
):
os
.
makedirs
(
draw_img_save
)
...
...
tools/infer/utility.py
浏览文件 @
90260649
...
...
@@ -202,7 +202,12 @@ def draw_ocr(image,
return
image
def
draw_ocr_box_txt
(
image
,
boxes
,
txts
):
def
draw_ocr_box_txt
(
image
,
boxes
,
txts
,
scores
=
None
,
drop_score
=
0.5
,
font_path
=
"./doc/simfang.ttf"
):
h
,
w
=
image
.
height
,
image
.
width
img_left
=
image
.
copy
()
img_right
=
Image
.
new
(
'RGB'
,
(
w
,
h
),
(
255
,
255
,
255
))
...
...
@@ -212,7 +217,9 @@ def draw_ocr_box_txt(image, boxes, txts):
random
.
seed
(
0
)
draw_left
=
ImageDraw
.
Draw
(
img_left
)
draw_right
=
ImageDraw
.
Draw
(
img_right
)
for
(
box
,
txt
)
in
zip
(
boxes
,
txts
):
for
idx
,
(
box
,
txt
)
in
enumerate
(
zip
(
boxes
,
txts
)):
if
scores
is
not
None
and
scores
[
idx
]
<
drop_score
:
continue
color
=
(
random
.
randint
(
0
,
255
),
random
.
randint
(
0
,
255
),
random
.
randint
(
0
,
255
))
draw_left
.
polygon
(
box
,
fill
=
color
)
...
...
@@ -228,8 +235,7 @@ def draw_ocr_box_txt(image, boxes, txts):
1
])
**
2
)
if
box_height
>
2
*
box_width
:
font_size
=
max
(
int
(
box_width
*
0.9
),
10
)
font
=
ImageFont
.
truetype
(
"./doc/simfang.ttf"
,
font_size
,
encoding
=
"utf-8"
)
font
=
ImageFont
.
truetype
(
font_path
,
font_size
,
encoding
=
"utf-8"
)
cur_y
=
box
[
0
][
1
]
for
c
in
txt
:
char_size
=
font
.
getsize
(
c
)
...
...
@@ -238,8 +244,7 @@ def draw_ocr_box_txt(image, boxes, txts):
cur_y
+=
char_size
[
1
]
else
:
font_size
=
max
(
int
(
box_height
*
0.8
),
10
)
font
=
ImageFont
.
truetype
(
"./doc/simfang.ttf"
,
font_size
,
encoding
=
"utf-8"
)
font
=
ImageFont
.
truetype
(
font_path
,
font_size
,
encoding
=
"utf-8"
)
draw_right
.
text
(
[
box
[
0
][
0
],
box
[
0
][
1
]],
txt
,
fill
=
(
0
,
0
,
0
),
font
=
font
)
img_left
=
Image
.
blend
(
image
,
img_left
,
0.5
)
...
...
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