This commit is contained in:
WenmuZhou 2021-06-23 12:45:05 +08:00
parent bf1a716855
commit 2fab904538
4 changed files with 26 additions and 10 deletions

View File

@ -30,11 +30,19 @@ Types 1-4 follow the traditional OCR process, and 5 follow the Table OCR process
[doc](table/README.md)
## 4. PaddleStructure whl package introduction
## 4. Predictive by inference engine
### 4.1 Use
Use the following commands to complete the inference
```python
python3 table/predict_system.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 --table_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, each image will have a directory with the same name under the directory specified in the output field. Each table in the picture will be stored as an excel, and the excel file name will be the coordinates of the table in the image.
4.1.1 Use by code
## 5. PaddleStructure whl package introduction
### 5.1 Use
5.1.1 Use by code
```python
import os
import cv2
@ -60,7 +68,7 @@ im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
4.1.2 Use by command line
5.1.2 Use by command line
```bash
paddlestructure --image_dir=../doc/table/1.png
```

View File

@ -30,11 +30,19 @@ PaddleStructure 是一个用于复杂板式文字OCR的工具包流程如下
[文档](table/README_ch.md)
## 4. PaddleStructure whl包介绍
## 4. 预测引擎推理
### 4.1 使用
使用如下命令即可完成预测引擎的推理
```python
python3 table/predict_system.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 --table_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会output字段指定的目录下有一个同名目录图片里的每个表格会存储为一个excelexcel文件名为表格在图片里的坐标。
4.1.1 代码使用
## 5. PaddleStructure whl包介绍
### 5.1 使用
5.1.1 代码使用
```python
import os
import cv2
@ -60,7 +68,7 @@ im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
4.1.2 命令行使用
5.1.2 命令行使用
```bash
paddlestructure --image_dir=../doc/table/1.png
```

View File

@ -46,4 +46,4 @@ 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 --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_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
After running, the excel sheet of each picture will be saved in the directory specified by the output field

View File

@ -46,4 +46,4 @@ python3 table/eval_table.py --det_model_dir=path/to/det_model_dir --rec_model_di
```python
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 --table_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
运行完成后每张图片的excel表格会保存到output字段指定的目录下