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
bf1a7168
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
bf1a7168
编写于
6月 23, 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
rename structure 2 table
上级
01c4ee5d
变更
9
隐藏空白更改
内联
并排
Showing
9 changed file
with
58 addition
and
34 deletion
+58
-34
test1/api.md
test1/api.md
+6
-4
test1/api_ch.md
test1/api_ch.md
+6
-4
test1/layoutparser-0.0.0-py3-none-any.whl
test1/layoutparser-0.0.0-py3-none-any.whl
+0
-0
test1/paddlestructure.py
test1/paddlestructure.py
+31
-11
test1/table/README.md
test1/table/README.md
+2
-2
test1/table/README_ch.md
test1/table/README_ch.md
+2
-2
test1/table/predict_structure.py
test1/table/predict_structure.py
+4
-4
test1/utility.py
test1/utility.py
+4
-4
tools/infer/utility.py
tools/infer/utility.py
+3
-3
未找到文件。
test1/api.md
浏览文件 @
bf1a7168
...
...
@@ -36,16 +36,18 @@ Types 1-4 follow the traditional OCR process, and 5 follow the Table OCR process
4.
1.1 Use by code
```
python
import
os
import
cv2
from
paddlestructure
import
PaddleStructure
,
draw_result
from
paddlestructure
import
PaddleStructure
,
draw_result
,
save_res
table_engine
=
PaddleStructure
(
output
=
'./output/table'
,
show_log
=
True
)
table_engine
=
PaddleStructure
(
show_log
=
True
)
save_folder
=
'./output/table'
img_path
=
'../doc/table/1.png'
img
=
cv2
.
imread
(
img_path
)
result
=
table_engine
(
img
)
save_res
(
result
,
save_folder
,
os
.
path
.
basename
(
img_path
).
split
(
'.'
)[
0
])
for
line
in
result
:
print
(
line
)
...
...
test1/api_ch.md
浏览文件 @
bf1a7168
...
...
@@ -36,16 +36,18 @@ PaddleStructure 是一个用于复杂板式文字OCR的工具包,流程如下
4.
1.1 代码使用
```
python
import
os
import
cv2
from
paddlestructure
import
PaddleStructure
,
draw_result
from
paddlestructure
import
PaddleStructure
,
draw_result
,
save_res
table_engine
=
PaddleStructure
(
output
=
'./output/table'
,
show_log
=
True
)
table_engine
=
PaddleStructure
(
show_log
=
True
)
save_folder
=
'./output/table'
img_path
=
'../doc/table/1.png'
img
=
cv2
.
imread
(
img_path
)
result
=
table_engine
(
img
)
save_res
(
result
,
save_folder
,
os
.
path
.
basename
(
img_path
).
split
(
'.'
)[
0
])
for
line
in
result
:
print
(
line
)
...
...
test1/layoutparser-0.0.0-py3-none-any.whl
已删除
100644 → 0
浏览文件 @
01c4ee5d
文件已删除
test1/paddlestructure.py
浏览文件 @
bf1a7168
...
...
@@ -32,7 +32,7 @@ logger = get_logger()
from
ppocr.utils.utility
import
check_and_read_gif
,
get_image_file_list
from
ppocr.utils.network
import
maybe_download
,
download_with_progressbar
,
confirm_model_dir_url
,
is_link
__all__
=
[
'PaddleStructure'
,
'draw_result'
,
'
to_excel
'
]
__all__
=
[
'PaddleStructure'
,
'draw_result'
,
'
save_res
'
]
VERSION
=
'2.1'
BASE_DIR
=
os
.
path
.
expanduser
(
"~/.paddlestructure/"
)
...
...
@@ -40,7 +40,7 @@ BASE_DIR = os.path.expanduser("~/.paddlestructure/")
model_urls
=
{
'det'
:
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar'
,
'rec'
:
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar'
,
'
structur
e'
:
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar'
'
tabl
e'
:
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar'
}
...
...
@@ -51,7 +51,7 @@ def parse_args(mMain=True):
parser
.
add_help
=
mMain
for
action
in
parser
.
_actions
:
if
action
.
dest
in
[
'rec_char_dict_path'
,
'
structur
e_char_dict_path'
]:
if
action
.
dest
in
[
'rec_char_dict_path'
,
'
tabl
e_char_dict_path'
]:
action
.
default
=
None
if
mMain
:
return
parser
.
parse_args
()
...
...
@@ -76,13 +76,13 @@ class PaddleStructure(OCRSystem):
params
.
rec_model_dir
,
rec_url
=
confirm_model_dir_url
(
params
.
rec_model_dir
,
os
.
path
.
join
(
BASE_DIR
,
VERSION
,
'rec'
),
model_urls
[
'rec'
])
params
.
structure_model_dir
,
structure_url
=
confirm_model_dir_url
(
params
.
structur
e_model_dir
,
os
.
path
.
join
(
BASE_DIR
,
VERSION
,
'
structur
e'
),
model_urls
[
'
structur
e'
])
params
.
table_model_dir
,
table_url
=
confirm_model_dir_url
(
params
.
tabl
e_model_dir
,
os
.
path
.
join
(
BASE_DIR
,
VERSION
,
'
tabl
e'
),
model_urls
[
'
tabl
e'
])
# download model
maybe_download
(
params
.
det_model_dir
,
det_url
)
maybe_download
(
params
.
rec_model_dir
,
rec_url
)
maybe_download
(
params
.
structure_model_dir
,
structur
e_url
)
maybe_download
(
params
.
table_model_dir
,
tabl
e_url
)
if
params
.
rec_char_dict_path
is
None
:
params
.
rec_char_type
=
'EN'
...
...
@@ -90,12 +90,12 @@ class PaddleStructure(OCRSystem):
params
.
rec_char_dict_path
=
str
(
Path
(
__file__
).
parent
/
'ppocr/utils/dict/table_dict.txt'
)
else
:
params
.
rec_char_dict_path
=
str
(
Path
(
__file__
).
parent
.
parent
/
'ppocr/utils/dict/table_dict.txt'
)
if
params
.
structur
e_char_dict_path
is
None
:
if
params
.
tabl
e_char_dict_path
is
None
:
if
os
.
path
.
exists
(
str
(
Path
(
__file__
).
parent
/
'ppocr/utils/dict/table_structure_dict.txt'
)):
params
.
structur
e_char_dict_path
=
str
(
params
.
tabl
e_char_dict_path
=
str
(
Path
(
__file__
).
parent
/
'ppocr/utils/dict/table_structure_dict.txt'
)
else
:
params
.
structur
e_char_dict_path
=
str
(
params
.
tabl
e_char_dict_path
=
str
(
Path
(
__file__
).
parent
.
parent
/
'ppocr/utils/dict/table_structure_dict.txt'
)
print
(
params
)
...
...
@@ -145,4 +145,24 @@ def main():
for
item
in
result
:
logger
.
info
(
item
[
'res'
])
save_res
(
result
,
save_folder
,
img_name
)
logger
.
info
(
'result save to {}'
.
format
(
os
.
path
.
join
(
save_folder
,
img_name
)))
\ No newline at end of file
logger
.
info
(
'result save to {}'
.
format
(
os
.
path
.
join
(
save_folder
,
img_name
)))
if
__name__
==
'__main__'
:
table_engine
=
PaddleStructure
(
show_log
=
True
)
img_path
=
'../test/test_imgs/PMC1173095_006_00.png'
img
=
cv2
.
imread
(
img_path
)
result
=
table_engine
(
img
)
save_res
(
result
,
'/Users/zhoujun20/Desktop/工作相关/table/table_pr/PaddleOCR/output/table'
,
os
.
path
.
basename
(
img_path
).
split
(
'.'
)[
0
])
for
line
in
result
:
print
(
line
)
from
PIL
import
Image
font_path
=
'../doc/fonts/simfang.ttf'
image
=
Image
.
open
(
img_path
).
convert
(
'RGB'
)
im_show
=
draw_result
(
image
,
result
,
font_path
=
font_path
)
im_show
=
Image
.
fromarray
(
im_show
)
im_show
.
save
(
'result.jpg'
)
\ No newline at end of file
test1/table/README.md
浏览文件 @
bf1a7168
...
...
@@ -36,7 +36,7 @@ In gt json, the key is the image name, the value is the corresponding gt, and gt
Use the following command to evaluate. After the evaluation is completed, the teds indicator will be output.
```
python
python3
table
/
eval_table
.
py
--
det_model_dir
=
path
/
to
/
det_model_dir
--
rec_model_dir
=
path
/
to
/
rec_model_dir
--
structure_model_dir
=
path
/
to
/
structure_model_dir
--
image_dir
=
..
/
doc
/
table
/
1.
png
--
rec_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_dict
.
txt
--
structur
e_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_structure_dict
.
txt
--
rec_char_type
=
EN
--
det_limit_side_len
=
736
--
det_limit_type
=
min
--
gt_path
=
path
/
to
/
gt
.
json
python3
table
/
eval_table
.
py
--
det_model_dir
=
path
/
to
/
det_model_dir
--
rec_model_dir
=
path
/
to
/
rec_model_dir
--
table_model_dir
=
path
/
to
/
table_model_dir
--
image_dir
=
..
/
doc
/
table
/
1.
png
--
rec_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_dict
.
txt
--
tabl
e_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_structure_dict
.
txt
--
rec_char_type
=
EN
--
det_limit_side_len
=
736
--
det_limit_type
=
min
--
gt_path
=
path
/
to
/
gt
.
json
```
...
...
@@ -44,6 +44,6 @@ python3 table/eval_table.py --det_model_dir=path/to/det_model_dir --rec_model_di
First cd to the PaddleOCR/ppstructure directory
```
python
python3
table
/
predict_table
.
py
--
det_model_dir
=
path
/
to
/
det_model_dir
--
rec_model_dir
=
path
/
to
/
rec_model_dir
--
structure_model_dir
=
path
/
to
/
structure_model_dir
--
image_dir
=
..
/
doc
/
table
/
1.
png
--
rec_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_dict
.
txt
--
structur
e_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_structure_dict
.
txt
--
rec_char_type
=
EN
--
det_limit_side_len
=
736
--
det_limit_type
=
min
--
output
..
/
output
/
table
python3
table
/
predict_table
.
py
--
det_model_dir
=
path
/
to
/
det_model_dir
--
rec_model_dir
=
path
/
to
/
rec_model_dir
--
table_model_dir
=
path
/
to
/
table_model_dir
--
image_dir
=
..
/
doc
/
table
/
1.
png
--
rec_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_dict
.
txt
--
tabl
e_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_structure_dict
.
txt
--
rec_char_type
=
EN
--
det_limit_side_len
=
736
--
det_limit_type
=
min
--
output
..
/
output
/
table
```
After running, the excel sheet of each picture will be saved in the directory specified by the table_output field
\ No newline at end of file
test1/table/README_ch.md
浏览文件 @
bf1a7168
...
...
@@ -36,7 +36,7 @@ json 中,key为图片名,value为对于的gt,gt是一个由四个item组
准备完成后使用如下命令进行评估,评估完成后会输出teds指标。
```
python
python3
table
/
eval_table
.
py
--
det_model_dir
=
path
/
to
/
det_model_dir
--
rec_model_dir
=
path
/
to
/
rec_model_dir
--
structure_model_dir
=
path
/
to
/
structure_model_dir
--
image_dir
=
..
/
doc
/
table
/
1.
png
--
rec_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_dict
.
txt
--
structur
e_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_structure_dict
.
txt
--
rec_char_type
=
EN
--
det_limit_side_len
=
736
--
det_limit_type
=
min
--
gt_path
=
path
/
to
/
gt
.
json
python3
table
/
eval_table
.
py
--
det_model_dir
=
path
/
to
/
det_model_dir
--
rec_model_dir
=
path
/
to
/
rec_model_dir
--
table_model_dir
=
path
/
to
/
table_model_dir
--
image_dir
=
..
/
doc
/
table
/
1.
png
--
rec_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_dict
.
txt
--
tabl
e_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_structure_dict
.
txt
--
rec_char_type
=
EN
--
det_limit_side_len
=
736
--
det_limit_type
=
min
--
gt_path
=
path
/
to
/
gt
.
json
```
...
...
@@ -44,6 +44,6 @@ python3 table/eval_table.py --det_model_dir=path/to/det_model_dir --rec_model_di
先cd到PaddleOCR/ppstructure目录下
```
python
python3
table
/
predict_table
.
py
--
det_model_dir
=
path
/
to
/
det_model_dir
--
rec_model_dir
=
path
/
to
/
rec_model_dir
--
structure_model_dir
=
path
/
to
/
structure_model_dir
--
image_dir
=
..
/
doc
/
table
/
1.
png
--
rec_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_dict
.
txt
--
structur
e_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_structure_dict
.
txt
--
rec_char_type
=
EN
--
det_limit_side_len
=
736
--
det_limit_type
=
min
--
output
..
/
output
/
table
python3
table
/
predict_table
.
py
--
det_model_dir
=
path
/
to
/
det_model_dir
--
rec_model_dir
=
path
/
to
/
rec_model_dir
--
table_model_dir
=
path
/
to
/
table_model_dir
--
image_dir
=
..
/
doc
/
table
/
1.
png
--
rec_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_dict
.
txt
--
tabl
e_char_dict_path
=
..
/
ppocr
/
utils
/
dict
/
table_structure_dict
.
txt
--
rec_char_type
=
EN
--
det_limit_side_len
=
736
--
det_limit_type
=
min
--
output
..
/
output
/
table
```
运行完成后,每张图片的excel表格会保存到table_output字段指定的目录下
test1/table/predict_structure.py
浏览文件 @
bf1a7168
...
...
@@ -41,7 +41,7 @@ class TableStructurer(object):
def
__init__
(
self
,
args
):
pre_process_list
=
[{
'ResizeTableImage'
:
{
'max_len'
:
args
.
structur
e_max_len
'max_len'
:
args
.
tabl
e_max_len
}
},
{
'NormalizeImage'
:
{
...
...
@@ -61,14 +61,14 @@ class TableStructurer(object):
}]
postprocess_params
=
{
'name'
:
'TableLabelDecode'
,
"character_type"
:
args
.
structur
e_char_type
,
"character_dict_path"
:
args
.
structur
e_char_dict_path
,
"character_type"
:
args
.
tabl
e_char_type
,
"character_dict_path"
:
args
.
tabl
e_char_dict_path
,
}
self
.
preprocess_op
=
create_operators
(
pre_process_list
)
self
.
postprocess_op
=
build_post_process
(
postprocess_params
)
self
.
predictor
,
self
.
input_tensor
,
self
.
output_tensors
,
self
.
config
=
\
utility
.
create_predictor
(
args
,
'
structur
e'
,
logger
)
utility
.
create_predictor
(
args
,
'
tabl
e'
,
logger
)
def
__call__
(
self
,
img
):
ori_im
=
img
.
copy
()
...
...
test1/utility.py
浏览文件 @
bf1a7168
...
...
@@ -23,10 +23,10 @@ def init_args():
# params for output
parser
.
add_argument
(
"--output"
,
type
=
str
,
default
=
'./output/table'
)
# params for table structure
parser
.
add_argument
(
"--
structur
e_max_len"
,
type
=
int
,
default
=
488
)
parser
.
add_argument
(
"--
structur
e_model_dir"
,
type
=
str
)
parser
.
add_argument
(
"--
structur
e_char_type"
,
type
=
str
,
default
=
'en'
)
parser
.
add_argument
(
"--
structur
e_char_dict_path"
,
type
=
str
,
default
=
"../ppocr/utils/dict/table_structure_dict.txt"
)
parser
.
add_argument
(
"--
tabl
e_max_len"
,
type
=
int
,
default
=
488
)
parser
.
add_argument
(
"--
tabl
e_model_dir"
,
type
=
str
)
parser
.
add_argument
(
"--
tabl
e_char_type"
,
type
=
str
,
default
=
'en'
)
parser
.
add_argument
(
"--
tabl
e_char_dict_path"
,
type
=
str
,
default
=
"../ppocr/utils/dict/table_structure_dict.txt"
)
return
parser
...
...
tools/infer/utility.py
浏览文件 @
bf1a7168
...
...
@@ -201,8 +201,8 @@ def create_predictor(args, mode, logger):
model_dir
=
args
.
cls_model_dir
elif
mode
==
'rec'
:
model_dir
=
args
.
rec_model_dir
elif
mode
==
'
structur
e'
:
model_dir
=
args
.
structur
e_model_dir
elif
mode
==
'
tabl
e'
:
model_dir
=
args
.
tabl
e_model_dir
else
:
model_dir
=
args
.
e2e_model_dir
...
...
@@ -331,7 +331,7 @@ def create_predictor(args, mode, logger):
config
.
disable_glog_info
()
config
.
delete_pass
(
"conv_transpose_eltwiseadd_bn_fuse_pass"
)
if
mode
==
'
structur
e'
:
if
mode
==
'
tabl
e'
:
config
.
delete_pass
(
"fc_fuse_pass"
)
# not supported for table
config
.
switch_use_feed_fetch_ops
(
False
)
config
.
switch_ir_optim
(
True
)
...
...
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