From 4030fd1e82ff38b24d8e9edc248fff14744ac47f Mon Sep 17 00:00:00 2001 From: WenmuZhou Date: Mon, 2 Aug 2021 15:28:07 +0800 Subject: [PATCH] merge paddlestructure whl to paddleocr whl --- MANIFEST.in | 3 +- __init__.py | 5 +- paddleocr.py | 116 ++++++++++++++++++++++---- ppstructure/MANIFEST.in | 9 -- ppstructure/__init__.py | 4 - ppstructure/paddlestructure.py | 147 --------------------------------- ppstructure/predict_system.py | 11 ++- ppstructure/setup.py | 70 ---------------- ppstructure/utility.py | 2 +- setup.py | 3 +- 10 files changed, 111 insertions(+), 259 deletions(-) delete mode 100644 ppstructure/MANIFEST.in delete mode 100644 ppstructure/paddlestructure.py delete mode 100644 ppstructure/setup.py diff --git a/MANIFEST.in b/MANIFEST.in index 1ca129b1..d674fabc 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -5,4 +5,5 @@ recursive-include ppocr/utils *.txt utility.py logging.py network.py recursive-include ppocr/data *.py recursive-include ppocr/postprocess *.py recursive-include tools/infer *.py -recursive-include ppocr/utils/e2e_utils *.py \ No newline at end of file +recursive-include ppocr/utils/e2e_utils *.py +recursive-include ppstructure *.py \ No newline at end of file diff --git a/__init__.py b/__init__.py index 7d94f66b..6db6dcfe 100644 --- a/__init__.py +++ b/__init__.py @@ -11,7 +11,6 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. +from .paddleocr import * -__all__ = ['PaddleOCR', 'draw_ocr'] -from .paddleocr import PaddleOCR -from .tools.infer.utility import draw_ocr +__all__ = ['PaddleOCR', 'PPStructure', 'draw_ocr', 'draw_structure_result', 'save_structure_res'] diff --git a/paddleocr.py b/paddleocr.py index f2a34968..80fe0b98 100644 --- a/paddleocr.py +++ b/paddleocr.py @@ -29,16 +29,19 @@ from ppocr.utils.logging import get_logger 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, is_link, confirm_model_dir_url -from tools.infer.utility import draw_ocr, init_args, str2bool +from tools.infer.utility import draw_ocr, str2bool +from ppstructure.utility import init_args, draw_structure_result +from ppstructure.predict_system import OCRSystem, save_structure_res -__all__ = ['PaddleOCR'] +__all__ = ['PaddleOCR','PPStructure','draw_ocr','draw_structure_result','save_structure_res'] model_urls = { 'det': { 'ch': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar', 'en': - 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar' + 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar', + 'structure': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar' }, 'rec': { 'ch': { @@ -110,10 +113,17 @@ model_urls = { 'url': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar', 'dict_path': './ppocr/utils/dict/devanagari_dict.txt' + }, + 'structure': { + 'url': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar', + 'dict_path': 'ppocr/utils/dict/table_dict.txt' } }, - 'cls': - 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar' + 'cls': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar', + 'table': { + 'url': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar', + 'dict_path': 'ppocr/utils/dict/table_structure_dict.txt' + } } SUPPORT_DET_MODEL = ['DB'] @@ -129,9 +139,10 @@ def parse_args(mMain=True): parser.add_argument("--lang", type=str, default='ch') parser.add_argument("--det", type=str2bool, default=True) parser.add_argument("--rec", type=str2bool, default=True) + parser.add_argument("--type", type=str, default='ocr') for action in parser._actions: - if action.dest == 'rec_char_dict_path': + if action.dest in ['rec_char_dict_path', 'table_char_dict_path']: action.default = None if mMain: return parser.parse_args() @@ -193,13 +204,13 @@ class PaddleOCR(predict_system.TextSystem): # init model dir params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir, - os.path.join(BASE_DIR, VERSION, 'det', det_lang), + os.path.join(BASE_DIR, VERSION, 'ocr', 'det', det_lang), model_urls['det'][det_lang]) params.rec_model_dir, rec_url = confirm_model_dir_url(params.rec_model_dir, - os.path.join(BASE_DIR, VERSION, 'rec', lang), + os.path.join(BASE_DIR, VERSION, 'ocr', 'rec', lang), model_urls['rec'][lang]['url']) params.cls_model_dir, cls_url = confirm_model_dir_url(params.cls_model_dir, - os.path.join(BASE_DIR, VERSION, 'cls'), + os.path.join(BASE_DIR, VERSION, 'ocr', 'cls'), model_urls['cls']) # download model maybe_download(params.det_model_dir, det_url) @@ -272,6 +283,65 @@ class PaddleOCR(predict_system.TextSystem): return rec_res +class PPStructure(OCRSystem): + def __init__(self, **kwargs): + params = parse_args(mMain=False) + params.__dict__.update(**kwargs) + if not params.show_log: + logger.setLevel(logging.INFO) + params.use_angle_cls = False + # init model dir + params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir, + os.path.join(BASE_DIR, VERSION, 'structure', 'det'), + model_urls['det']['structure']) + params.rec_model_dir, rec_url = confirm_model_dir_url(params.rec_model_dir, + os.path.join(BASE_DIR, VERSION, 'structure', 'rec'), + model_urls['rec']['structure']['url']) + params.table_model_dir, table_url = confirm_model_dir_url(params.table_model_dir, + os.path.join(BASE_DIR, VERSION, 'structure', 'table'), + model_urls['table']['url']) + # download model + maybe_download(params.det_model_dir, det_url) + maybe_download(params.rec_model_dir, rec_url) + maybe_download(params.table_model_dir, table_url) + + if params.rec_char_dict_path is None: + params.rec_char_type = 'EN' + if os.path.exists(str(Path(__file__).parent / model_urls['rec']['structure']['dict_path'])): + params.rec_char_dict_path = str(Path(__file__).parent / model_urls['rec']['structure']['dict_path']) + else: + params.rec_char_dict_path = str(Path(__file__).parent.parent / model_urls['rec']['structure']['dict_path']) + if params.table_char_dict_path is None: + if os.path.exists(str(Path(__file__).parent / model_urls['table']['dict_path'])): + params.table_char_dict_path = str(Path(__file__).parent / model_urls['table']['dict_path']) + else: + params.table_char_dict_path = str(Path(__file__).parent.parent / model_urls['table']['dict_path']) + + print(params) + super().__init__(params) + + def __call__(self, img): + if isinstance(img, str): + # download net image + if img.startswith('http'): + download_with_progressbar(img, 'tmp.jpg') + img = 'tmp.jpg' + image_file = img + img, flag = check_and_read_gif(image_file) + if not flag: + with open(image_file, 'rb') as f: + np_arr = np.frombuffer(f.read(), dtype=np.uint8) + img = cv2.imdecode(np_arr, cv2.IMREAD_COLOR) + if img is None: + logger.error("error in loading image:{}".format(image_file)) + return None + if isinstance(img, np.ndarray) and len(img.shape) == 2: + img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR) + + res = super().__call__(img) + return res + + def main(): # for cmd args = parse_args(mMain=True) @@ -284,14 +354,26 @@ def main(): if len(image_file_list) == 0: logger.error('no images find in {}'.format(args.image_dir)) return + if args.type=='ocr': + engine = PaddleOCR(**(args.__dict__)) + elif args.type=='structure': + engine = PPStructure(**(args.__dict__)) + else: + raise NotImplementedError - ocr_engine = PaddleOCR(**(args.__dict__)) for img_path in image_file_list: + img_name = os.path.basename(img_path).split('.')[0] logger.info('{}{}{}'.format('*' * 10, img_path, '*' * 10)) - result = ocr_engine.ocr(img_path, - det=args.det, - rec=args.rec, - cls=args.use_angle_cls) - if result is not None: - for line in result: - logger.info(line) + if args.type == 'ocr': + result = engine.ocr(img_path, + det=args.det, + rec=args.rec, + cls=args.use_angle_cls) + if result is not None: + for line in result: + logger.info(line) + elif args.type == 'structure': + result = engine(img_path) + for item in result: + logger.info(item['res']) + save_structure_res(result, args.output, img_name) \ No newline at end of file diff --git a/ppstructure/MANIFEST.in b/ppstructure/MANIFEST.in deleted file mode 100644 index 713e4b06..00000000 --- a/ppstructure/MANIFEST.in +++ /dev/null @@ -1,9 +0,0 @@ -include LICENSE -include README.md - -recursive-include ppocr/utils *.txt utility.py logging.py network.py -recursive-include ppocr/data *.py -recursive-include ppocr/postprocess *.py -recursive-include tools/infer *.py -recursive-include ppstructure *.py - diff --git a/ppstructure/__init__.py b/ppstructure/__init__.py index 3952b5ff..1d11e265 100644 --- a/ppstructure/__init__.py +++ b/ppstructure/__init__.py @@ -11,7 +11,3 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. - -from .paddlestructure import PaddleStructure, draw_result, save_res - -__all__ = ['PaddleStructure', 'draw_result', 'save_res'] diff --git a/ppstructure/paddlestructure.py b/ppstructure/paddlestructure.py deleted file mode 100644 index d0009ae8..00000000 --- a/ppstructure/paddlestructure.py +++ /dev/null @@ -1,147 +0,0 @@ -# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved. -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. -import logging -import os -import sys - -__dir__ = os.path.dirname(__file__) -sys.path.append(__dir__) -sys.path.append(os.path.join(__dir__, '..')) - -import cv2 -import numpy as np -from pathlib import Path - -from ppocr.utils.logging import get_logger -from ppstructure.predict_system import OCRSystem, save_res -from ppstructure.utility import init_args, draw_result - -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', 'save_res'] - -VERSION = '2.1' -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', - 'table': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar' - -} - - -def parse_args(mMain=True): - import argparse - parser = init_args() - parser.add_help = mMain - - for action in parser._actions: - if action.dest in ['rec_char_dict_path', 'table_char_dict_path']: - action.default = None - if mMain: - return parser.parse_args() - else: - inference_args_dict = {} - for action in parser._actions: - inference_args_dict[action.dest] = action.default - return argparse.Namespace(**inference_args_dict) - - -class PaddleStructure(OCRSystem): - def __init__(self, **kwargs): - params = parse_args(mMain=False) - params.__dict__.update(**kwargs) - if not params.show_log: - logger.setLevel(logging.INFO) - params.use_angle_cls = False - # init model dir - params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir, - os.path.join(BASE_DIR, VERSION, 'det'), - model_urls['det']) - 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.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.table_model_dir, table_url) - - if params.rec_char_dict_path is None: - params.rec_char_type = 'EN' - if os.path.exists(str(Path(__file__).parent / 'ppocr/utils/dict/table_dict.txt')): - 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.table_char_dict_path is None: - if os.path.exists(str(Path(__file__).parent / 'ppocr/utils/dict/table_structure_dict.txt')): - params.table_char_dict_path = str( - Path(__file__).parent / 'ppocr/utils/dict/table_structure_dict.txt') - else: - params.table_char_dict_path = str( - Path(__file__).parent.parent / 'ppocr/utils/dict/table_structure_dict.txt') - - print(params) - super().__init__(params) - - def __call__(self, img): - if isinstance(img, str): - # download net image - if img.startswith('http'): - download_with_progressbar(img, 'tmp.jpg') - img = 'tmp.jpg' - image_file = img - img, flag = check_and_read_gif(image_file) - if not flag: - with open(image_file, 'rb') as f: - np_arr = np.frombuffer(f.read(), dtype=np.uint8) - img = cv2.imdecode(np_arr, cv2.IMREAD_COLOR) - if img is None: - logger.error("error in loading image:{}".format(image_file)) - return None - if isinstance(img, np.ndarray) and len(img.shape) == 2: - img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR) - - res = super().__call__(img) - return res - - -def main(): - # for cmd - args = parse_args(mMain=True) - image_dir = args.image_dir - save_folder = args.output - if image_dir.startswith('http'): - download_with_progressbar(image_dir, 'tmp.jpg') - image_file_list = ['tmp.jpg'] - else: - image_file_list = get_image_file_list(args.image_dir) - if len(image_file_list) == 0: - logger.error('no images find in {}'.format(args.image_dir)) - return - - structure_engine = PaddleStructure(**(args.__dict__)) - for img_path in image_file_list: - img_name = os.path.basename(img_path).split('.')[0] - logger.info('{}{}{}'.format('*' * 10, img_path, '*' * 10)) - result = structure_engine(img_path) - 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))) \ No newline at end of file diff --git a/ppstructure/predict_system.py b/ppstructure/predict_system.py index 60e25745..1bae8973 100644 --- a/ppstructure/predict_system.py +++ b/ppstructure/predict_system.py @@ -26,19 +26,18 @@ import numpy as np import time import logging -import layoutparser as lp - from ppocr.utils.utility import get_image_file_list, check_and_read_gif from ppocr.utils.logging import get_logger from tools.infer.predict_system import TextSystem from ppstructure.table.predict_table import TableSystem, to_excel -from ppstructure.utility import parse_args, draw_result +from ppstructure.utility import parse_args, draw_structure_result logger = get_logger() class OCRSystem(object): def __init__(self, args): + import layoutparser as lp args.det_limit_type = 'resize_long' args.drop_score = 0 if not args.show_log: @@ -80,7 +79,7 @@ class OCRSystem(object): return res_list -def save_res(res, save_folder, img_name): +def save_structure_res(res, save_folder, img_name): excel_save_folder = os.path.join(save_folder, img_name) os.makedirs(excel_save_folder, exist_ok=True) # save res @@ -115,8 +114,8 @@ def main(args): continue starttime = time.time() res = structure_sys(img) - save_res(res, save_folder, img_name) - draw_img = draw_result(img, res, args.vis_font_path) + save_structure_res(res, save_folder, img_name) + draw_img = draw_structure_result(img, res, args.vis_font_path) cv2.imwrite(os.path.join(save_folder, img_name, 'show.jpg'), draw_img) logger.info('result save to {}'.format(os.path.join(save_folder, img_name))) elapse = time.time() - starttime diff --git a/ppstructure/setup.py b/ppstructure/setup.py deleted file mode 100644 index c99d71fe..00000000 --- a/ppstructure/setup.py +++ /dev/null @@ -1,70 +0,0 @@ -# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved. -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. -import os - -from setuptools import setup -from io import open -import shutil - -with open('../requirements.txt', encoding="utf-8-sig") as f: - requirements = f.readlines() - requirements.append('tqdm') - - -def readme(): - with open('README_ch.md', encoding="utf-8-sig") as f: - README = f.read() - return README - - -shutil.copytree('./table', './ppstructure/table') -shutil.copyfile('./predict_system.py', './ppstructure/predict_system.py') -shutil.copyfile('./utility.py', './ppstructure/utility.py') -shutil.copytree('../ppocr', './ppocr') -shutil.copytree('../tools', './tools') -shutil.copyfile('../LICENSE', './LICENSE') - -setup( - name='paddlestructure', - packages=['paddlestructure'], - package_dir={'paddlestructure': ''}, - include_package_data=True, - entry_points={"console_scripts": ["paddlestructure= paddlestructure.paddlestructure:main"]}, - version='1.0', - install_requires=requirements, - license='Apache License 2.0', - description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices', - long_description=readme(), - long_description_content_type='text/markdown', - url='https://github.com/PaddlePaddle/PaddleOCR', - download_url='https://github.com/PaddlePaddle/PaddleOCR.git', - keywords=[ - 'ocr textdetection textrecognition paddleocr crnn east star-net rosetta ocrlite db chineseocr chinesetextdetection chinesetextrecognition' - ], - classifiers=[ - 'Intended Audience :: Developers', 'Operating System :: OS Independent', - 'Natural Language :: Chinese (Simplified)', - 'Programming Language :: Python :: 3', - 'Programming Language :: Python :: 3.2', - 'Programming Language :: Python :: 3.3', - 'Programming Language :: Python :: 3.4', - 'Programming Language :: Python :: 3.5', - 'Programming Language :: Python :: 3.6', - 'Programming Language :: Python :: 3.7', 'Topic :: Utilities' - ], ) - -shutil.rmtree('ppocr') -shutil.rmtree('tools') -shutil.rmtree('ppstructure') -os.remove('LICENSE') diff --git a/ppstructure/utility.py b/ppstructure/utility.py index 29daeef4..bfb11a9c 100644 --- a/ppstructure/utility.py +++ b/ppstructure/utility.py @@ -36,7 +36,7 @@ def parse_args(): return parser.parse_args() -def draw_result(image, result, font_path): +def draw_structure_result(image, result, font_path): if isinstance(image, np.ndarray): image = Image.fromarray(image) boxes, txts, scores = [], [], [] diff --git a/setup.py b/setup.py index a1ddbbb6..7d4d871d 100644 --- a/setup.py +++ b/setup.py @@ -14,6 +14,7 @@ from setuptools import setup from io import open +from paddleocr import VERSION with open('requirements.txt', encoding="utf-8-sig") as f: requirements = f.readlines() @@ -32,7 +33,7 @@ setup( package_dir={'paddleocr': ''}, include_package_data=True, entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]}, - version='2.0.6', + version=VERSION, install_requires=requirements, license='Apache License 2.0', description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',