Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
wangsen
paddle_dbnet
Commits
edd1222f
Commit
edd1222f
authored
Dec 03, 2021
by
littletomatodonkey
Browse files
fix place
parent
765cee61
Changes
14
Hide whitespace changes
Inline
Side-by-side
Showing
14 changed files
with
6 additions
and
6 deletions
+6
-6
ppstructure/vqa/README.md
ppstructure/vqa/README.md
+6
-6
ppstructure/vqa/helper/eval_with_label_end2end.py
ppstructure/vqa/helper/eval_with_label_end2end.py
+0
-0
ppstructure/vqa/helper/trans_xfun_data.py
ppstructure/vqa/helper/trans_xfun_data.py
+0
-0
ppstructure/vqa/images/input/zh_val_0.jpg
ppstructure/vqa/images/input/zh_val_0.jpg
+0
-0
ppstructure/vqa/images/input/zh_val_42.jpg
ppstructure/vqa/images/input/zh_val_42.jpg
+0
-0
ppstructure/vqa/images/result_ser/zh_val_0_ser.jpg
ppstructure/vqa/images/result_ser/zh_val_0_ser.jpg
+0
-0
ppstructure/vqa/images/result_ser/zh_val_42_ser.jpg
ppstructure/vqa/images/result_ser/zh_val_42_ser.jpg
+0
-0
ppstructure/vqa/infer_ser.py
ppstructure/vqa/infer_ser.py
+0
-0
ppstructure/vqa/infer_ser_e2e.py
ppstructure/vqa/infer_ser_e2e.py
+0
-0
ppstructure/vqa/labels/labels_ser.txt
ppstructure/vqa/labels/labels_ser.txt
+0
-0
ppstructure/vqa/requirements.txt
ppstructure/vqa/requirements.txt
+0
-0
ppstructure/vqa/train_ser.py
ppstructure/vqa/train_ser.py
+0
-0
ppstructure/vqa/utils.py
ppstructure/vqa/utils.py
+0
-0
ppstructure/vqa/xfun.py
ppstructure/vqa/xfun.py
+0
-0
No files found.
pp
layout
/README.md
→
pp
structure/vqa
/README.md
View file @
edd1222f
#
PP-Layout
#
视觉问答(VQA)
PP-Layout是一个针对图像文本内容进行语义实体识别与关系抽取的OCR工具包,
主要特性如下:
VQA
主要特性如下:
-
集成
[
LayoutXLM
](
https://arxiv.org/pdf/2104.08836.pdf
)
模型以及PP-OCR预测引擎。
-
集成
[
LayoutXLM
](
https://arxiv.org/pdf/2104.08836.pdf
)
模型以及PP-OCR预测引擎。
-
支持基于多模态方法的语义实体识别 (Semantic Entity Recognition, SER) 以及关系抽取 (Relation Extraction, RE) 任务。基于 SER 任务,可以完成对图像中的文本识别与分类;基于 RE 任务,可以完成对图象中的文本内容的关系提取(比如判断问题对)
-
支持基于多模态方法的语义实体识别 (Semantic Entity Recognition, SER) 以及关系抽取 (Relation Extraction, RE) 任务。基于 SER 任务,可以完成对图像中的文本识别与分类;基于 RE 任务,可以完成对图象中的文本内容的关系提取(比如判断问题对)
...
@@ -22,7 +22,7 @@ PP-Layout是一个针对图像文本内容进行语义实体识别与关系抽
...
@@ -22,7 +22,7 @@ PP-Layout是一个针对图像文本内容进行语义实体识别与关系抽
</div>
</div>
<div
align=
"center"
>
<div
align=
"center"
>
<img
src=
"./images/result_ser/zh_val_
1
_ser.jpg"
width =
"600"
/>
<img
src=
"./images/result_ser/zh_val_
42
_ser.jpg"
width =
"600"
/>
</div>
</div>
其中不同颜色的框表示不同的类别,对于XFUN数据集,有
`QUESTION`
,
`ANSWER`
,
`HEADER`
3种类别,在OCR检测框的左上方也标出了对应的类别和OCR识别结果。
其中不同颜色的框表示不同的类别,对于XFUN数据集,有
`QUESTION`
,
`ANSWER`
,
`HEADER`
3种类别,在OCR检测框的左上方也标出了对应的类别和OCR识别结果。
...
@@ -53,7 +53,7 @@ python3 -m pip install paddlepaddle==2.2 -i https://mirror.baidu.com/pypi/simple
...
@@ -53,7 +53,7 @@ python3 -m pip install paddlepaddle==2.2 -i https://mirror.baidu.com/pypi/simple
更多需求,请参照
[
安装文档
](
https://www.paddlepaddle.org.cn/install/quick
)
中的说明进行操作。
更多需求,请参照
[
安装文档
](
https://www.paddlepaddle.org.cn/install/quick
)
中的说明进行操作。
### 2.2 安装PaddleOCR(包含PP-OCR
和PP-Layout
)
### 2.2 安装PaddleOCR(包含
PP-OCR
和 VQA
)
-
**(1)pip快速安装PaddleOCR whl包(仅预测)**
-
**(1)pip快速安装PaddleOCR whl包(仅预测)**
...
@@ -61,7 +61,7 @@ python3 -m pip install paddlepaddle==2.2 -i https://mirror.baidu.com/pypi/simple
...
@@ -61,7 +61,7 @@ python3 -m pip install paddlepaddle==2.2 -i https://mirror.baidu.com/pypi/simple
pip
install
"paddleocr>=2.2"
# 推荐使用2.2+版本
pip
install
"paddleocr>=2.2"
# 推荐使用2.2+版本
```
```
-
**(2)下载
PP-Layout
源码(预测+训练)**
-
**(2)下载
VQA
源码(预测+训练)**
```
bash
```
bash
【推荐】git clone https://github.com/PaddlePaddle/PaddleOCR
【推荐】git clone https://github.com/PaddlePaddle/PaddleOCR
...
@@ -82,7 +82,7 @@ pip install -e .
...
@@ -82,7 +82,7 @@ pip install -e .
```
```
-
**(4)安装
PP-Layout
的`requirements`**
-
**(4)安装
VQA
的`requirements`**
```
bash
```
bash
pip
install
-r
requirements.txt
pip
install
-r
requirements.txt
...
...
pp
layout
/helper/eval_with_label_end2end.py
→
pp
structure/vqa
/helper/eval_with_label_end2end.py
View file @
edd1222f
File moved
pp
layout
/helper/trans_xfun_data.py
→
pp
structure/vqa
/helper/trans_xfun_data.py
View file @
edd1222f
File moved
pp
layout
/images/input/zh_val_0.jpg
→
pp
structure/vqa
/images/input/zh_val_0.jpg
View file @
edd1222f
File moved
pp
layout
/images/input/zh_val_42.jpg
→
pp
structure/vqa
/images/input/zh_val_42.jpg
View file @
edd1222f
File moved
pp
layout
/images/result_ser/zh_val_0_ser.jpg
→
pp
structure/vqa
/images/result_ser/zh_val_0_ser.jpg
View file @
edd1222f
File moved
pp
layout
/images/result_ser/zh_val_42_ser.jpg
→
pp
structure/vqa
/images/result_ser/zh_val_42_ser.jpg
View file @
edd1222f
File moved
pp
layout
/infer_ser.py
→
pp
structure/vqa
/infer_ser.py
View file @
edd1222f
File moved
pp
layout
/infer_ser_e2e.py
→
pp
structure/vqa
/infer_ser_e2e.py
View file @
edd1222f
File moved
pp
layout
/labels/labels_ser.txt
→
pp
structure/vqa
/labels/labels_ser.txt
View file @
edd1222f
File moved
pp
layout
/requirements.txt
→
pp
structure/vqa
/requirements.txt
View file @
edd1222f
File moved
pp
layout
/train_ser.py
→
pp
structure/vqa
/train_ser.py
View file @
edd1222f
File moved
pp
layout
/utils.py
→
pp
structure/vqa
/utils.py
View file @
edd1222f
File moved
pp
layout
/xfun.py
→
pp
structure/vqa
/xfun.py
View file @
edd1222f
File moved
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment