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
znstj
PaddleOCR
提交
a621bef8
P
PaddleOCR
项目概览
znstj
/
PaddleOCR
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleOCR
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1
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
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
1
Issue
1
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 >>
提交
a621bef8
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
90260649
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
14 addition
and
34 deletion
+14
-34
tools/infer/predict_cls.py
tools/infer/predict_cls.py
+1
-1
tools/infer/predict_system.py
tools/infer/predict_system.py
+7
-22
tools/infer/utility.py
tools/infer/utility.py
+6
-11
未找到文件。
tools/infer/predict_cls.py
浏览文件 @
a621bef8
...
@@ -37,7 +37,7 @@ logger = get_logger()
...
@@ -37,7 +37,7 @@ logger = get_logger()
class
TextClassifier
(
object
):
class
TextClassifier
(
object
):
def
__init__
(
self
,
args
):
def
__init__
(
self
,
args
):
self
.
cls_image_shape
=
[
int
(
v
)
for
v
in
args
.
cls_image_shape
.
split
(
","
)]
self
.
cls_image_shape
=
[
int
(
v
)
for
v
in
args
.
cls_image_shape
.
split
(
","
)]
self
.
cls_batch_num
=
args
.
rec
_batch_num
self
.
cls_batch_num
=
args
.
cls
_batch_num
self
.
cls_thresh
=
args
.
cls_thresh
self
.
cls_thresh
=
args
.
cls_thresh
self
.
use_zero_copy_run
=
args
.
use_zero_copy_run
self
.
use_zero_copy_run
=
args
.
use_zero_copy_run
postprocess_params
=
{
postprocess_params
=
{
...
...
tools/infer/predict_system.py
浏览文件 @
a621bef8
...
@@ -23,21 +23,17 @@ import numpy as np
...
@@ -23,21 +23,17 @@ import numpy as np
import
time
import
time
from
PIL
import
Image
from
PIL
import
Image
import
tools.infer.utility
as
utility
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_rec
as
predict_rec
import
tools.infer.predict_det
as
predict_det
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.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.utility
import
draw_ocr_box_txt
class
TextSystem
(
object
):
class
TextSystem
(
object
):
def
__init__
(
self
,
args
):
def
__init__
(
self
,
args
):
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
if
self
.
use_angle_cls
:
self
.
text_classifier
=
predict_cls
.
TextClassifier
(
args
)
def
get_rotate_crop_image
(
self
,
img
,
points
):
def
get_rotate_crop_image
(
self
,
img
,
points
):
'''
'''
...
@@ -92,15 +88,6 @@ class TextSystem(object):
...
@@ -92,15 +88,6 @@ class TextSystem(object):
tmp_box
=
copy
.
deepcopy
(
dt_boxes
[
bno
])
tmp_box
=
copy
.
deepcopy
(
dt_boxes
[
bno
])
img_crop
=
self
.
get_rotate_crop_image
(
ori_im
,
tmp_box
)
img_crop
=
self
.
get_rotate_crop_image
(
ori_im
,
tmp_box
)
img_crop_list
.
append
(
img_crop
)
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
)
rec_res
,
elapse
=
self
.
text_recognizer
(
img_crop_list
)
print
(
"rec_res num : {}, elapse : {}"
.
format
(
len
(
rec_res
),
elapse
))
print
(
"rec_res num : {}, elapse : {}"
.
format
(
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)
...
@@ -132,7 +119,7 @@ def main(args):
...
@@ -132,7 +119,7 @@ def main(args):
image_file_list
=
get_image_file_list
(
args
.
image_dir
)
image_file_list
=
get_image_file_list
(
args
.
image_dir
)
text_sys
=
TextSystem
(
args
)
text_sys
=
TextSystem
(
args
)
is_visualize
=
True
is_visualize
=
True
font_path
=
args
.
vis_font_path
tackle_img_num
=
0
for
image_file
in
image_file_list
:
for
image_file
in
image_file_list
:
img
,
flag
=
check_and_read_gif
(
image_file
)
img
,
flag
=
check_and_read_gif
(
image_file
)
if
not
flag
:
if
not
flag
:
...
@@ -141,6 +128,9 @@ def main(args):
...
@@ -141,6 +128,9 @@ def main(args):
logger
.
info
(
"error in loading image:{}"
.
format
(
image_file
))
logger
.
info
(
"error in loading image:{}"
.
format
(
image_file
))
continue
continue
starttime
=
time
.
time
()
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
)
dt_boxes
,
rec_res
=
text_sys
(
img
)
elapse
=
time
.
time
()
-
starttime
elapse
=
time
.
time
()
-
starttime
print
(
"Predict time of %s: %.3fs"
%
(
image_file
,
elapse
))
print
(
"Predict time of %s: %.3fs"
%
(
image_file
,
elapse
))
...
@@ -159,13 +149,8 @@ def main(args):
...
@@ -159,13 +149,8 @@ def main(args):
txts
=
[
rec_res
[
i
][
0
]
for
i
in
range
(
len
(
rec_res
))]
txts
=
[
rec_res
[
i
][
0
]
for
i
in
range
(
len
(
rec_res
))]
scores
=
[
rec_res
[
i
][
1
]
for
i
in
range
(
len
(
rec_res
))]
scores
=
[
rec_res
[
i
][
1
]
for
i
in
range
(
len
(
rec_res
))]
draw_img
=
draw_ocr_box_txt
(
draw_img
=
draw_ocr
(
image
,
image
,
boxes
,
txts
,
scores
,
drop_score
=
drop_score
)
boxes
,
txts
,
scores
,
drop_score
=
drop_score
,
font_path
=
font_path
)
draw_img_save
=
"./inference_results/"
draw_img_save
=
"./inference_results/"
if
not
os
.
path
.
exists
(
draw_img_save
):
if
not
os
.
path
.
exists
(
draw_img_save
):
os
.
makedirs
(
draw_img_save
)
os
.
makedirs
(
draw_img_save
)
...
...
tools/infer/utility.py
浏览文件 @
a621bef8
...
@@ -202,12 +202,7 @@ def draw_ocr(image,
...
@@ -202,12 +202,7 @@ def draw_ocr(image,
return
image
return
image
def
draw_ocr_box_txt
(
image
,
def
draw_ocr_box_txt
(
image
,
boxes
,
txts
):
boxes
,
txts
,
scores
=
None
,
drop_score
=
0.5
,
font_path
=
"./doc/simfang.ttf"
):
h
,
w
=
image
.
height
,
image
.
width
h
,
w
=
image
.
height
,
image
.
width
img_left
=
image
.
copy
()
img_left
=
image
.
copy
()
img_right
=
Image
.
new
(
'RGB'
,
(
w
,
h
),
(
255
,
255
,
255
))
img_right
=
Image
.
new
(
'RGB'
,
(
w
,
h
),
(
255
,
255
,
255
))
...
@@ -217,9 +212,7 @@ def draw_ocr_box_txt(image,
...
@@ -217,9 +212,7 @@ def draw_ocr_box_txt(image,
random
.
seed
(
0
)
random
.
seed
(
0
)
draw_left
=
ImageDraw
.
Draw
(
img_left
)
draw_left
=
ImageDraw
.
Draw
(
img_left
)
draw_right
=
ImageDraw
.
Draw
(
img_right
)
draw_right
=
ImageDraw
.
Draw
(
img_right
)
for
idx
,
(
box
,
txt
)
in
enumerate
(
zip
(
boxes
,
txts
)):
for
(
box
,
txt
)
in
zip
(
boxes
,
txts
):
if
scores
is
not
None
and
scores
[
idx
]
<
drop_score
:
continue
color
=
(
random
.
randint
(
0
,
255
),
random
.
randint
(
0
,
255
),
color
=
(
random
.
randint
(
0
,
255
),
random
.
randint
(
0
,
255
),
random
.
randint
(
0
,
255
))
random
.
randint
(
0
,
255
))
draw_left
.
polygon
(
box
,
fill
=
color
)
draw_left
.
polygon
(
box
,
fill
=
color
)
...
@@ -235,7 +228,8 @@ def draw_ocr_box_txt(image,
...
@@ -235,7 +228,8 @@ def draw_ocr_box_txt(image,
1
])
**
2
)
1
])
**
2
)
if
box_height
>
2
*
box_width
:
if
box_height
>
2
*
box_width
:
font_size
=
max
(
int
(
box_width
*
0.9
),
10
)
font_size
=
max
(
int
(
box_width
*
0.9
),
10
)
font
=
ImageFont
.
truetype
(
font_path
,
font_size
,
encoding
=
"utf-8"
)
font
=
ImageFont
.
truetype
(
"./doc/simfang.ttf"
,
font_size
,
encoding
=
"utf-8"
)
cur_y
=
box
[
0
][
1
]
cur_y
=
box
[
0
][
1
]
for
c
in
txt
:
for
c
in
txt
:
char_size
=
font
.
getsize
(
c
)
char_size
=
font
.
getsize
(
c
)
...
@@ -244,7 +238,8 @@ def draw_ocr_box_txt(image,
...
@@ -244,7 +238,8 @@ def draw_ocr_box_txt(image,
cur_y
+=
char_size
[
1
]
cur_y
+=
char_size
[
1
]
else
:
else
:
font_size
=
max
(
int
(
box_height
*
0.8
),
10
)
font_size
=
max
(
int
(
box_height
*
0.8
),
10
)
font
=
ImageFont
.
truetype
(
font_path
,
font_size
,
encoding
=
"utf-8"
)
font
=
ImageFont
.
truetype
(
"./doc/simfang.ttf"
,
font_size
,
encoding
=
"utf-8"
)
draw_right
.
text
(
draw_right
.
text
(
[
box
[
0
][
0
],
box
[
0
][
1
]],
txt
,
fill
=
(
0
,
0
,
0
),
font
=
font
)
[
box
[
0
][
0
],
box
[
0
][
1
]],
txt
,
fill
=
(
0
,
0
,
0
),
font
=
font
)
img_left
=
Image
.
blend
(
image
,
img_left
,
0.5
)
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