forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

rename structure 2 table

This commit is contained in:
WenmuZhou 2021-06-23 12:28:32 +08:00
parent 01c4ee5de0
commit bf1a716855
9 changed files with 58 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
test1/api.md
View File

@ -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)

10
test1/api_ch.md
View File

@ -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)

BIN
test1/layoutparser-0.0.0-py3-none-any.whl
View File

Binary file not shown.

42
test1/paddlestructure.py
View File

@ -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',
'structure': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar'
'table': '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', 'structure_char_dict_path']:
if action.dest in ['rec_char_dict_path', 'table_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.structure_model_dir,
os.path.join(BASE_DIR, VERSION, 'structure'),
model_urls['structure'])
params.table_model_dir, table_url = confirm_model_dir_url(params.table_model_dir,
os.path.join(BASE_DIR, VERSION, 'table'),
model_urls['table'])
# download model
maybe_download(params.det_model_dir, det_url)
maybe_download(params.rec_model_dir, rec_url)
maybe_download(params.structure_model_dir, structure_url)
maybe_download(params.table_model_dir, table_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.structure_char_dict_path is None:
if params.table_char_dict_path is None:
if os.path.exists(str(Path(__file__).parent / 'ppocr/utils/dict/table_structure_dict.txt')):
params.structure_char_dict_path = str(
params.table_char_dict_path = str(
Path(__file__).parent / 'ppocr/utils/dict/table_structure_dict.txt')
else:
params.structure_char_dict_path = str(
params.table_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)))
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')

4
test1/table/README.md
View File

@ -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 --structure_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 --table_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 --structure_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 --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

4
test1/table/README_ch.md
View File

@ -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 --structure_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 --table_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 --structure_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 --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

8
test1/table/predict_structure.py
View File

@ -41,7 +41,7 @@ class TableStructurer(object):
def __init__(self, args):
pre_process_list = [{
'ResizeTableImage': {
'max_len': args.structure_max_len
'max_len': args.table_max_len
}
}, {
'NormalizeImage': {
@ -61,14 +61,14 @@ class TableStructurer(object):
}]
postprocess_params = {
'name': 'TableLabelDecode',
"character_type": args.structure_char_type,
"character_dict_path": args.structure_char_dict_path,
"character_type": args.table_char_type,
"character_dict_path": args.table_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, 'structure', logger)
utility.create_predictor(args, 'table', logger)
def __call__(self, img):
ori_im = img.copy()

8
test1/utility.py
View File

@ -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("--structure_max_len", type=int, default=488)
parser.add_argument("--structure_model_dir", type=str)
parser.add_argument("--structure_char_type", type=str, default='en')
parser.add_argument("--structure_char_dict_path", type=str, default="../ppocr/utils/dict/table_structure_dict.txt")
parser.add_argument("--table_max_len", type=int, default=488)
parser.add_argument("--table_model_dir", type=str)
parser.add_argument("--table_char_type", type=str, default='en')
parser.add_argument("--table_char_dict_path", type=str, default="../ppocr/utils/dict/table_structure_dict.txt")
return parser

6
tools/infer/utility.py
View File

@ -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 == 'structure':
model_dir = args.structure_model_dir
elif mode == 'table':
model_dir = args.table_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 == 'structure':
if mode == 'table':
config.delete_pass("fc_fuse_pass") # not supported for table
config.switch_use_feed_fetch_ops(False)
config.switch_ir_optim(True)