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
s920243400
PaddleOCR
提交
73ca6c2e
P
PaddleOCR
项目概览
s920243400
/
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
0
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
0
Issue
0
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
提交
73ca6c2e
编写于
8月 10, 2022
作者:
文幕地方
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add PP-Structurev2 to hubserving
上级
4ac17fca
变更
12
显示空白变更内容
内联
并排
Showing
12 changed file
with
63 addition
and
73 deletion
+63
-73
deploy/hubserving/readme.md
deploy/hubserving/readme.md
+2
-1
deploy/hubserving/readme_en.md
deploy/hubserving/readme_en.md
+2
-1
deploy/hubserving/structure_system/module.py
deploy/hubserving/structure_system/module.py
+2
-2
deploy/hubserving/structure_system/params.py
deploy/hubserving/structure_system/params.py
+4
-2
deploy/hubserving/structure_table/module.py
deploy/hubserving/structure_table/module.py
+3
-3
doc/doc_en/quickstart_en.md
doc/doc_en/quickstart_en.md
+7
-13
ppstructure/docs/installation.md
ppstructure/docs/installation.md
+2
-10
ppstructure/docs/quickstart.md
ppstructure/docs/quickstart.md
+16
-18
ppstructure/docs/quickstart_en.md
ppstructure/docs/quickstart_en.md
+16
-18
ppstructure/predict_system.py
ppstructure/predict_system.py
+3
-2
ppstructure/table/predict_table.py
ppstructure/table/predict_table.py
+1
-1
ppstructure/utility.py
ppstructure/utility.py
+5
-2
未找到文件。
deploy/hubserving/readme.md
浏览文件 @
73ca6c2e
...
@@ -59,6 +59,7 @@ pip3 install paddlehub==2.1.0 --upgrade -i https://mirror.baidu.com/pypi/simple
...
@@ -59,6 +59,7 @@ pip3 install paddlehub==2.1.0 --upgrade -i https://mirror.baidu.com/pypi/simple
检测模型:./inference/ch_PP-OCRv3_det_infer/
检测模型:./inference/ch_PP-OCRv3_det_infer/
识别模型:./inference/ch_PP-OCRv3_rec_infer/
识别模型:./inference/ch_PP-OCRv3_rec_infer/
方向分类器:./inference/ch_ppocr_mobile_v2.0_cls_infer/
方向分类器:./inference/ch_ppocr_mobile_v2.0_cls_infer/
版面分析模型:
表格结构识别模型:./inference/en_ppocr_mobile_v2.0_table_structure_infer/
表格结构识别模型:./inference/en_ppocr_mobile_v2.0_table_structure_infer/
```
```
...
@@ -172,7 +173,7 @@ hub serving start -c deploy/hubserving/ocr_system/config.json
...
@@ -172,7 +173,7 @@ hub serving start -c deploy/hubserving/ocr_system/config.json
## 3. 发送预测请求
## 3. 发送预测请求
配置好服务端,可使用以下命令发送预测请求,获取预测结果:
配置好服务端,可使用以下命令发送预测请求,获取预测结果:
```
python tools/test_hubserving.py
server_url
image_path
```
```
python tools/test_hubserving.py
--server_url=server_url --image_dir=
image_path
```
需要给脚本传递2个参数:
需要给脚本传递2个参数:
- **server_url**:服务地址,格式为
- **server_url**:服务地址,格式为
...
...
deploy/hubserving/readme_en.md
浏览文件 @
73ca6c2e
...
@@ -61,6 +61,7 @@ Before installing the service module, you need to prepare the inference model an
...
@@ -61,6 +61,7 @@ Before installing the service module, you need to prepare the inference model an
text detection model: ./inference/ch_PP-OCRv3_det_infer/
text detection model: ./inference/ch_PP-OCRv3_det_infer/
text recognition model: ./inference/ch_PP-OCRv3_rec_infer/
text recognition model: ./inference/ch_PP-OCRv3_rec_infer/
text angle classifier: ./inference/ch_ppocr_mobile_v2.0_cls_infer/
text angle classifier: ./inference/ch_ppocr_mobile_v2.0_cls_infer/
layout parse model:
tanle recognition: ./inference/en_ppocr_mobile_v2.0_table_structure_infer/
tanle recognition: ./inference/en_ppocr_mobile_v2.0_table_structure_infer/
```
```
...
@@ -177,7 +178,7 @@ hub serving start -c deploy/hubserving/ocr_system/config.json
...
@@ -177,7 +178,7 @@ hub serving start -c deploy/hubserving/ocr_system/config.json
## 3. Send prediction requests
## 3. Send prediction requests
After the service starts, you can use the following command to send a prediction request to obtain the prediction result:
After the service starts, you can use the following command to send a prediction request to obtain the prediction result:
```
shell
```
shell
python tools/test_hubserving.py
server_url
image_path
python tools/test_hubserving.py
--server_url
=
server_url
--image_dir
=
image_path
```
```
Two parameters need to be passed to the script:
Two parameters need to be passed to the script:
...
...
deploy/hubserving/structure_system/module.py
浏览文件 @
73ca6c2e
...
@@ -119,7 +119,7 @@ class StructureSystem(hub.Module):
...
@@ -119,7 +119,7 @@ class StructureSystem(hub.Module):
all_results
.
append
([])
all_results
.
append
([])
continue
continue
starttime
=
time
.
time
()
starttime
=
time
.
time
()
res
=
self
.
table_sys
(
img
)
res
,
_
=
self
.
table_sys
(
img
)
elapse
=
time
.
time
()
-
starttime
elapse
=
time
.
time
()
-
starttime
logger
.
info
(
"Predict time: {}"
.
format
(
elapse
))
logger
.
info
(
"Predict time: {}"
.
format
(
elapse
))
...
@@ -144,6 +144,6 @@ class StructureSystem(hub.Module):
...
@@ -144,6 +144,6 @@ class StructureSystem(hub.Module):
if
__name__
==
'__main__'
:
if
__name__
==
'__main__'
:
structure_system
=
StructureSystem
()
structure_system
=
StructureSystem
()
structure_system
.
_initialize
()
structure_system
.
_initialize
()
image_path
=
[
'./
doc
/table/1.png'
]
image_path
=
[
'./
ppstructure/docs
/table/1.png'
]
res
=
structure_system
.
predict
(
paths
=
image_path
)
res
=
structure_system
.
predict
(
paths
=
image_path
)
print
(
res
)
print
(
res
)
deploy/hubserving/structure_system/params.py
浏览文件 @
73ca6c2e
...
@@ -23,8 +23,10 @@ def read_params():
...
@@ -23,8 +23,10 @@ def read_params():
cfg
=
table_read_params
()
cfg
=
table_read_params
()
# params for layout parser model
# params for layout parser model
cfg
.
layout_path_model
=
'lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config'
cfg
.
layout_model_dir
=
''
cfg
.
layout_label_map
=
None
cfg
.
layout_dict_path
=
'./ppocr/utils/dict/layout_publaynet_dict.txt'
cfg
.
layout_score_threshold
=
0.5
cfg
.
layout_nms_threshold
=
0.5
cfg
.
mode
=
'structure'
cfg
.
mode
=
'structure'
cfg
.
output
=
'./output'
cfg
.
output
=
'./output'
...
...
deploy/hubserving/structure_table/module.py
浏览文件 @
73ca6c2e
...
@@ -118,11 +118,11 @@ class TableSystem(hub.Module):
...
@@ -118,11 +118,11 @@ class TableSystem(hub.Module):
all_results
.
append
([])
all_results
.
append
([])
continue
continue
starttime
=
time
.
time
()
starttime
=
time
.
time
()
pred_html
=
self
.
table_sys
(
img
)
res
,
_
=
self
.
table_sys
(
img
)
elapse
=
time
.
time
()
-
starttime
elapse
=
time
.
time
()
-
starttime
logger
.
info
(
"Predict time: {}"
.
format
(
elapse
))
logger
.
info
(
"Predict time: {}"
.
format
(
elapse
))
all_results
.
append
({
'html'
:
pred_html
})
all_results
.
append
({
'html'
:
res
[
'html'
]
})
return
all_results
return
all_results
@
serving
@
serving
...
@@ -138,6 +138,6 @@ class TableSystem(hub.Module):
...
@@ -138,6 +138,6 @@ class TableSystem(hub.Module):
if
__name__
==
'__main__'
:
if
__name__
==
'__main__'
:
table_system
=
TableSystem
()
table_system
=
TableSystem
()
table_system
.
_initialize
()
table_system
.
_initialize
()
image_path
=
[
'./
doc
/table/table.jpg'
]
image_path
=
[
'./
ppstructure/docs
/table/table.jpg'
]
res
=
table_system
.
predict
(
paths
=
image_path
)
res
=
table_system
.
predict
(
paths
=
image_path
)
print
(
res
)
print
(
res
)
doc/doc_en/quickstart_en.md
浏览文件 @
73ca6c2e
...
@@ -51,12 +51,6 @@ pip install "paddleocr>=2.0.1" # Recommend to use version 2.0.1+
...
@@ -51,12 +51,6 @@ pip install "paddleocr>=2.0.1" # Recommend to use version 2.0.1+
Reference:
[
Solve shapely installation on windows
](
https://stackoverflow.com/questions/44398265/install-shapely-oserror-winerror-126-the-specified-module-could-not-be-found
)
Reference:
[
Solve shapely installation on windows
](
https://stackoverflow.com/questions/44398265/install-shapely-oserror-winerror-126-the-specified-module-could-not-be-found
)
-
**For layout analysis users**
, run the following command to install
**Layout-Parser**
```
bash
pip3
install
-U
https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
```
<a
name=
"2-easy-to-use"
></a>
<a
name=
"2-easy-to-use"
></a>
## 2. Easy-to-Use
## 2. Easy-to-Use
...
...
ppstructure/docs/installation.md
浏览文件 @
73ca6c2e
-
[
快速安装
](
#快速安装
)
-
[
快速安装
](
#快速安装
)
-
[
1. PaddlePaddle 和 PaddleOCR
](
#1-paddlepaddle-和-paddleocr
)
-
[
1. PaddlePaddle 和 PaddleOCR
](
#1-paddlepaddle-和-paddleocr
)
-
[
2. 安装其他依赖
](
#2-安装其他依赖
)
-
[
2. 安装其他依赖
](
#2-安装其他依赖
)
-
[
2.1 版面分析所需 Layout-Parser
](
#21-版面分析所需--layout-parser
)
-
[
2.1 VQA所需依赖
](
#21--vqa所需依赖
)
-
[
2.2 VQA所需依赖
](
#22--vqa所需依赖
)
# 快速安装
# 快速安装
...
@@ -12,14 +11,7 @@
...
@@ -12,14 +11,7 @@
## 2. 安装其他依赖
## 2. 安装其他依赖
### 2.1 版面分析所需 Layout-Parser
### 2.1 VQA所需依赖
Layout-Parser 可通过如下命令安装
```
bash
pip3
install
-U
https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
```
### 2.2 VQA所需依赖
*
paddleocr
*
paddleocr
```
bash
```
bash
...
...
ppstructure/docs/quickstart.md
浏览文件 @
73ca6c2e
# PP-Structure 快速开始
# PP-Structure 快速开始
-
[
1. 安装依赖包
](
#1
)
-
[
1. 安装依赖包
](
#1
-安装依赖包
)
-
[
2. 便捷使用
](
#2
)
-
[
2. 便捷使用
](
#2
-便捷使用
)
-
[
2.1 命令行使用
](
#21
)
-
[
2.1 命令行使用
](
#21-命令行使用
)
-
[
2.1.1 版面分析+表格识别
](
#211
)
-
[
2.1.1 版面分析+表格识别
](
#211-版面分析表格识别
)
-
[
2.1.2 版面分析
](
#212
)
-
[
2.1.2 版面分析
](
#212-版面分析
)
-
[
2.1.3 表格识别
](
#213
)
-
[
2.1.3 表格识别
](
#213-表格识别
)
-
[
2.1.4 DocVQA
](
#214
)
-
[
2.1.4 DocVQA
](
#214-docvqa
)
-
[
2.2 代码使用
](
#22
)
-
[
2.2 代码使用
](
#22-代码使用
)
-
[
2.2.1 版面分析+表格识别
](
#221
)
-
[
2.2.1 版面分析+表格识别
](
#221-版面分析表格识别
)
-
[
2.2.2 版面分析
](
#222
)
-
[
2.2.2 版面分析
](
#222-版面分析
)
-
[
2.2.3 表格识别
](
#223
)
-
[
2.2.3 表格识别
](
#223-表格识别
)
-
[
2.2.4 DocVQA
](
#224
)
-
[
2.2.4 DocVQA
](
#224-docvqa
)
-
[
2.3 返回结果说明
](
#23
)
-
[
2.3 返回结果说明
](
#23-返回结果说明
)
-
[
2.3.1 版面分析+表格识别
](
#231
)
-
[
2.3.1 版面分析+表格识别
](
#231-版面分析表格识别
)
-
[
2.3.2 DocVQA
](
#232
)
-
[
2.3.2 DocVQA
](
#232-docvqa
)
-
[
2.4 参数说明
](
#24
)
-
[
2.4 参数说明
](
#24-参数说明
)
<a
name=
"1"
></a>
<a
name=
"1"
></a>
...
@@ -24,8 +24,6 @@
...
@@ -24,8 +24,6 @@
```
bash
```
bash
# 安装 paddleocr,推荐使用2.5+版本
# 安装 paddleocr,推荐使用2.5+版本
pip3
install
"paddleocr>=2.5"
pip3
install
"paddleocr>=2.5"
# 安装 版面分析依赖包layoutparser(如不需要版面分析功能,可跳过)
pip3
install
-U
https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
# 安装 DocVQA依赖包paddlenlp(如不需要DocVQA功能,可跳过)
# 安装 DocVQA依赖包paddlenlp(如不需要DocVQA功能,可跳过)
pip
install
paddlenlp
pip
install
paddlenlp
...
...
ppstructure/docs/quickstart_en.md
浏览文件 @
73ca6c2e
# PP-Structure Quick Start
# PP-Structure Quick Start
-
[
1. Install package
](
#1
)
-
[
1. Install package
](
#1
-install-package
)
-
[
2. Use
](
#2
)
-
[
2. Use
](
#2
-use
)
-
[
2.1 Use by command line
](
#21
)
-
[
2.1 Use by command line
](
#21-use-by-command-line
)
-
[
2.1.1 layout analysis + table recognition
](
#211
)
-
[
2.1.1 layout analysis + table recognition
](
#211-layout-analysis--table-recognition
)
-
[
2.1.2 layout analysis
](
#212
)
-
[
2.1.2 layout analysis
](
#212-layout-analysis
)
-
[
2.1.3 table recognition
](
#213
)
-
[
2.1.3 table recognition
](
#213-table-recognition
)
-
[
2.1.4 DocVQA
](
#214
)
-
[
2.1.4 DocVQA
](
#214-docvqa
)
-
[
2.2 Use by code
](
#22
)
-
[
2.2 Use by code
](
#22-use-by-code
)
-
[
2.2.1 layout analysis + table recognition
](
#221
)
-
[
2.2.1 layout analysis + table recognition
](
#221-layout-analysis--table-recognition
)
-
[
2.2.2 layout analysis
](
#222
)
-
[
2.2.2 layout analysis
](
#222-layout-analysis
)
-
[
2.2.3 table recognition
](
#223
)
-
[
2.2.3 table recognition
](
#223-table-recognition
)
-
[
2.2.4 DocVQA
](
#224
)
-
[
2.2.4 DocVQA
](
#224-docvqa
)
-
[
2.3 Result description
](
#23
)
-
[
2.3 Result description
](
#23-result-description
)
-
[
2.3.1 layout analysis + table recognition
](
#231
)
-
[
2.3.1 layout analysis + table recognition
](
#231-layout-analysis--table-recognition
)
-
[
2.3.2 DocVQA
](
#232
)
-
[
2.3.2 DocVQA
](
#232-docvqa
)
-
[
2.4 Parameter Description
](
#24
)
-
[
2.4 Parameter Description
](
#24-parameter-description
)
<a
name=
"1"
></a>
<a
name=
"1"
></a>
...
@@ -24,8 +24,6 @@
...
@@ -24,8 +24,6 @@
```
bash
```
bash
# Install paddleocr, version 2.5+ is recommended
# Install paddleocr, version 2.5+ is recommended
pip3
install
"paddleocr>=2.5"
pip3
install
"paddleocr>=2.5"
# Install layoutparser (if you do not use the layout analysis, you can skip it)
pip3
install
-U
https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
# Install the DocVQA dependency package paddlenlp (if you do not use the DocVQA, you can skip it)
# Install the DocVQA dependency package paddlenlp (if you do not use the DocVQA, you can skip it)
pip
install
paddlenlp
pip
install
paddlenlp
...
...
ppstructure/predict_system.py
浏览文件 @
73ca6c2e
...
@@ -43,6 +43,7 @@ logger = get_logger()
...
@@ -43,6 +43,7 @@ logger = get_logger()
class
StructureSystem
(
object
):
class
StructureSystem
(
object
):
def
__init__
(
self
,
args
):
def
__init__
(
self
,
args
):
self
.
mode
=
args
.
mode
self
.
mode
=
args
.
mode
self
.
recovery
=
args
.
recovery
if
self
.
mode
==
'structure'
:
if
self
.
mode
==
'structure'
:
if
not
args
.
show_log
:
if
not
args
.
show_log
:
logger
.
setLevel
(
logging
.
INFO
)
logger
.
setLevel
(
logging
.
INFO
)
...
@@ -110,7 +111,7 @@ class StructureSystem(object):
...
@@ -110,7 +111,7 @@ class StructureSystem(object):
time_dict
[
'rec'
]
+=
table_time_dict
[
'rec'
]
time_dict
[
'rec'
]
+=
table_time_dict
[
'rec'
]
else
:
else
:
if
self
.
text_system
is
not
None
:
if
self
.
text_system
is
not
None
:
if
args
.
recovery
:
if
self
.
recovery
:
wht_im
=
np
.
ones
(
ori_im
.
shape
,
dtype
=
ori_im
.
dtype
)
wht_im
=
np
.
ones
(
ori_im
.
shape
,
dtype
=
ori_im
.
dtype
)
wht_im
[
y1
:
y2
,
x1
:
x2
,
:]
=
roi_img
wht_im
[
y1
:
y2
,
x1
:
x2
,
:]
=
roi_img
filter_boxes
,
filter_rec_res
,
ocr_time_dict
=
self
.
text_system
(
filter_boxes
,
filter_rec_res
,
ocr_time_dict
=
self
.
text_system
(
...
@@ -133,7 +134,7 @@ class StructureSystem(object):
...
@@ -133,7 +134,7 @@ class StructureSystem(object):
for
token
in
style_token
:
for
token
in
style_token
:
if
token
in
rec_str
:
if
token
in
rec_str
:
rec_str
=
rec_str
.
replace
(
token
,
''
)
rec_str
=
rec_str
.
replace
(
token
,
''
)
if
not
args
.
recovery
:
if
not
self
.
recovery
:
box
+=
[
x1
,
y1
]
box
+=
[
x1
,
y1
]
res
.
append
({
res
.
append
({
'text'
:
rec_str
,
'text'
:
rec_str
,
...
...
ppstructure/table/predict_table.py
浏览文件 @
73ca6c2e
...
@@ -101,7 +101,7 @@ class TableSystem(object):
...
@@ -101,7 +101,7 @@ class TableSystem(object):
start
=
time
.
time
()
start
=
time
.
time
()
structure_res
,
elapse
=
self
.
_structure
(
copy
.
deepcopy
(
img
))
structure_res
,
elapse
=
self
.
_structure
(
copy
.
deepcopy
(
img
))
result
[
'cell_bbox'
]
=
structure_res
[
1
]
result
[
'cell_bbox'
]
=
structure_res
[
1
]
.
tolist
()
time_dict
[
'table'
]
=
elapse
time_dict
[
'table'
]
=
elapse
dt_boxes
,
rec_res
,
det_elapse
,
rec_elapse
=
self
.
_ocr
(
dt_boxes
,
rec_res
,
det_elapse
,
rec_elapse
=
self
.
_ocr
(
...
...
ppstructure/utility.py
浏览文件 @
73ca6c2e
...
@@ -38,14 +38,17 @@ def init_args():
...
@@ -38,14 +38,17 @@ def init_args():
parser
.
add_argument
(
parser
.
add_argument
(
"--layout_dict_path"
,
"--layout_dict_path"
,
type
=
str
,
type
=
str
,
default
=
"../ppocr/utils/dict/layout_pub
al
ynet_dict.txt"
)
default
=
"../ppocr/utils/dict/layout_pub
la
ynet_dict.txt"
)
parser
.
add_argument
(
parser
.
add_argument
(
"--layout_score_threshold"
,
"--layout_score_threshold"
,
type
=
float
,
type
=
float
,
default
=
0.5
,
default
=
0.5
,
help
=
"Threshold of score."
)
help
=
"Threshold of score."
)
parser
.
add_argument
(
parser
.
add_argument
(
"--layout_nms_threshold"
,
type
=
float
,
default
=
0.5
,
help
=
"Threshold of nms."
)
"--layout_nms_threshold"
,
type
=
float
,
default
=
0.5
,
help
=
"Threshold of nms."
)
# params for vqa
# params for vqa
parser
.
add_argument
(
"--vqa_algorithm"
,
type
=
str
,
default
=
'LayoutXLM'
)
parser
.
add_argument
(
"--vqa_algorithm"
,
type
=
str
,
default
=
'LayoutXLM'
)
parser
.
add_argument
(
"--ser_model_dir"
,
type
=
str
)
parser
.
add_argument
(
"--ser_model_dir"
,
type
=
str
)
...
...
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