未验证 提交 08de694a 编写于 作者: M MissPenguin 提交者: GitHub

Merge pull request #3442 from WenmuZhou/table2

rename test1 2 ppstructure
...@@ -5,5 +5,5 @@ recursive-include ppocr/utils *.txt utility.py logging.py network.py ...@@ -5,5 +5,5 @@ recursive-include ppocr/utils *.txt utility.py logging.py network.py
recursive-include ppocr/data/ *.py recursive-include ppocr/data/ *.py
recursive-include ppocr/postprocess *.py recursive-include ppocr/postprocess *.py
recursive-include tools/infer *.py recursive-include tools/infer *.py
recursive-include test1 *.py recursive-include ppstructure *.py
...@@ -10,7 +10,7 @@ pip3 install layoutparser-0.0.0-py3-none-any.whl ...@@ -10,7 +10,7 @@ pip3 install layoutparser-0.0.0-py3-none-any.whl
PaddleStructure is a toolkit for complex layout text OCR, the process is as follows PaddleStructure is a toolkit for complex layout text OCR, the process is as follows
![pipeline](../doc/table/pipeline.png) ![pipeline](../doc/table/pipeline.jpg)
In PaddleStructure, the image will be analyzed by layoutparser first. In the layout analysis, the area in the image will be classified, and the OCR process will be carried out according to the category. In PaddleStructure, the image will be analyzed by layoutparser first. In the layout analysis, the area in the image will be classified, and the OCR process will be carried out according to the category.
......
...@@ -9,7 +9,7 @@ pip3 install layoutparser-0.0.0-py3-none-any.whl ...@@ -9,7 +9,7 @@ pip3 install layoutparser-0.0.0-py3-none-any.whl
## 1. pipeline介绍 ## 1. pipeline介绍
PaddleStructure 是一个用于复杂板式文字OCR的工具包,流程如下 PaddleStructure 是一个用于复杂板式文字OCR的工具包,流程如下
![pipeline](../doc/table/pipeline.png) ![pipeline](../doc/table/pipeline.jpg)
在PaddleStructure中,图片会先经由layoutparser进行版面分析,在版面分析中,会对图片里的区域进行分类,根据根据类别进行对于的ocr流程。 在PaddleStructure中,图片会先经由layoutparser进行版面分析,在版面分析中,会对图片里的区域进行分类,根据根据类别进行对于的ocr流程。
......
...@@ -24,9 +24,9 @@ import numpy as np ...@@ -24,9 +24,9 @@ import numpy as np
from pathlib import Path from pathlib import Path
from ppocr.utils.logging import get_logger from ppocr.utils.logging import get_logger
from test1.predict_system import OCRSystem, save_res from ppstructure.predict_system import OCRSystem, save_res
from test1.table.predict_table import to_excel from ppstructure.table.predict_table import to_excel
from test1.utility import init_args, draw_result from ppstructure.utility import init_args, draw_result
logger = get_logger() logger = get_logger()
from ppocr.utils.utility import check_and_read_gif, get_image_file_list from ppocr.utils.utility import check_and_read_gif, get_image_file_list
...@@ -145,4 +145,4 @@ def main(): ...@@ -145,4 +145,4 @@ def main():
for item in result: for item in result:
logger.info(item['res']) logger.info(item['res'])
save_res(result, save_folder, img_name) save_res(result, save_folder, img_name)
logger.info('result save to {}'.format(os.path.join(save_folder, img_name))) logger.info('result save to {}'.format(os.path.join(save_folder, img_name)))
\ No newline at end of file
...@@ -31,8 +31,8 @@ import layoutparser as lp ...@@ -31,8 +31,8 @@ import layoutparser as lp
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.predict_system import TextSystem from tools.infer.predict_system import TextSystem
from test1.table.predict_table import TableSystem, to_excel from ppstructure.table.predict_table import TableSystem, to_excel
from test1.utility import parse_args, draw_result from ppstructure.utility import parse_args, draw_result
logger = get_logger() logger = get_logger()
......
...@@ -23,14 +23,14 @@ with open('../requirements.txt', encoding="utf-8-sig") as f: ...@@ -23,14 +23,14 @@ with open('../requirements.txt', encoding="utf-8-sig") as f:
def readme(): def readme():
with open('api_ch.md', encoding="utf-8-sig") as f: with open('README_ch.md', encoding="utf-8-sig") as f:
README = f.read() README = f.read()
return README return README
shutil.copytree('./table', './test1/table') shutil.copytree('./table', './ppstructure/table')
shutil.copyfile('./predict_system.py', './test1/predict_system.py') shutil.copyfile('./predict_system.py', './ppstructure/predict_system.py')
shutil.copyfile('./utility.py', './test1/utility.py') shutil.copyfile('./utility.py', './ppstructure/utility.py')
shutil.copytree('../ppocr', './ppocr') shutil.copytree('../ppocr', './ppocr')
shutil.copytree('../tools', './tools') shutil.copytree('../tools', './tools')
shutil.copyfile('../LICENSE', './LICENSE') shutil.copyfile('../LICENSE', './LICENSE')
...@@ -66,5 +66,5 @@ setup( ...@@ -66,5 +66,5 @@ setup(
shutil.rmtree('ppocr') shutil.rmtree('ppocr')
shutil.rmtree('tools') shutil.rmtree('tools')
shutil.rmtree('test1') shutil.rmtree('ppstructure')
os.remove('LICENSE') os.remove('LICENSE')
...@@ -20,9 +20,9 @@ sys.path.append(os.path.abspath(os.path.join(__dir__, '../..'))) ...@@ -20,9 +20,9 @@ sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
import cv2 import cv2
import json import json
from tqdm import tqdm from tqdm import tqdm
from test1.table.table_metric import TEDS from ppstructure.table.table_metric import TEDS
from test1.table.predict_table import TableSystem from ppstructure.table.predict_table import TableSystem
from test1.utility import init_args from ppstructure.utility import init_args
from ppocr.utils.logging import get_logger from ppocr.utils.logging import get_logger
logger = get_logger() logger = get_logger()
......
...@@ -22,17 +22,14 @@ os.environ["FLAGS_allocator_strategy"] = 'auto_growth' ...@@ -22,17 +22,14 @@ os.environ["FLAGS_allocator_strategy"] = 'auto_growth'
import cv2 import cv2
import numpy as np import numpy as np
import math
import time import time
import traceback
import paddle
import tools.infer.utility as utility import tools.infer.utility as utility
from ppocr.data import create_operators, transform from ppocr.data import create_operators, transform
from ppocr.postprocess import build_post_process from ppocr.postprocess import build_post_process
from ppocr.utils.logging import get_logger from ppocr.utils.logging import get_logger
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 test1.utility import parse_args from ppstructure.utility import parse_args
logger = get_logger() logger = get_logger()
......
...@@ -30,9 +30,9 @@ import tools.infer.predict_rec as predict_rec ...@@ -30,9 +30,9 @@ import tools.infer.predict_rec as predict_rec
import tools.infer.predict_det as predict_det import tools.infer.predict_det as predict_det
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 test1.table.matcher import distance, compute_iou from ppstructure.table.matcher import distance, compute_iou
from test1.utility import parse_args from ppstructure.utility import parse_args
import test1.table.predict_structure as predict_strture import ppstructure.table.predict_structure as predict_strture
logger = get_logger() logger = get_logger()
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册