Skip to content

P
PaddleOCR

PaddlePaddle / PaddleOCR
大约 1 年 前同步成功

通知 1528
Star 32962
Fork 6643
P
PaddleOCR
未验证 提交 96c8c004 编写于 作者: Z zhoujun 提交者： GitHub
浏览文件
操作

add desc of version params (#3929) 

* add desc of version params
上级 b6a21419
隐藏空白更改
内联 并排
Showing with 219 addition and 150 deletion
MANIFEST.in
浏览文件 @ 96c8c004
...@@ -5,5 +5,6 @@ recursive-include ppocr/utils *.txt utility.py logging.py network.py ...@@ -5,5 +5,6 @@ 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 tools __init__.py
recursive-include ppocr/utils/e2e_utils *.py recursive-include ppocr/utils/e2e_utils *.py
recursive-include ppstructure *.py recursive-include ppstructure *.py
\ No newline at end of file
doc/doc_ch/whl.md
浏览文件 @ 96c8c004
...@@ -420,3 +420,5 @@ im_show.save('result.jpg') ...@@ -420,3 +420,5 @@ im_show.save('result.jpg')
| cls | 前向时是否启动分类 (命令行模式下使用use_angle_cls控制前向是否启动分类) | FALSE | | cls | 前向时是否启动分类 (命令行模式下使用use_angle_cls控制前向是否启动分类) | FALSE |
| show_log | 是否打印det和rec等信息 | FALSE | | show_log | 是否打印det和rec等信息 | FALSE |
| type | 执行ocr或者表格结构化, 值可选['ocr','structure'] | ocr | | type | 执行ocr或者表格结构化, 值可选['ocr','structure'] | ocr |
| ocr_version | OCR模型版本，可选PP-OCRv2, PP-OCR。PP-OCRv2 目前仅支持中文的检测和识别模型，PP-OCR支持中文的检测，识别，多语种识别，方向分类器等模型 | PP-OCRv2 |
| structure_version | 表格结构化模型版本，可选 STRUCTURE。STRUCTURE支持表格结构化模型 | STRUCTURE |
doc/doc_en/whl_en.md
浏览文件 @ 96c8c004
...@@ -366,4 +366,6 @@ im_show.save('result.jpg') ...@@ -366,4 +366,6 @@ im_show.save('result.jpg')
| rec | Enable recognition when `ppocr.ocr` func exec | TRUE | | rec | Enable recognition when `ppocr.ocr` func exec | TRUE |
| cls | Enable classification when `ppocr.ocr` func exec((Use use_angle_cls in command line mode to control whether to start classification in the forward direction) | FALSE | | cls | Enable classification when `ppocr.ocr` func exec((Use use_angle_cls in command line mode to control whether to start classification in the forward direction) | FALSE |
| show_log | Whether to print log in det and rec | FALSE | | show_log | Whether to print log in det and rec | FALSE |
| type | Perform ocr or table structuring, the value is selected in ['ocr','structure'] | ocr | | type | Perform ocr or table structuring, the value is selected in ['ocr','structure'] | ocr |
\ No newline at end of file | ocr_version | OCR Model version number, the current model support list is as follows: PP-OCRv2 support Chinese detection and recognition model, PP-OCR support Chinese detection, recognition and direction classifier, multilingual recognition model | PP-OCRv2 |
| structure_version | table structure Model version number, the current model support list is as follows: STRUCTURE support english table structure model | STRUCTURE |
paddleocr.py
浏览文件 @ 96c8c004
...@@ -16,6 +16,9 @@ import os ...@@ -16,6 +16,9 @@ import os
import sys import sys
__dir__ = os.path.dirname(__file__) __dir__ = os.path.dirname(__file__)
import paddle
sys.path.append(os.path.join(__dir__, '')) sys.path.append(os.path.join(__dir__, ''))
import cv2 import cv2
...@@ -29,7 +32,7 @@ from ppocr.utils.logging import get_logger ...@@ -29,7 +32,7 @@ from ppocr.utils.logging import get_logger
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
from ppocr.utils.network import maybe_download, download_with_progressbar, is_link, confirm_model_dir_url from ppocr.utils.network import maybe_download, download_with_progressbar, is_link, confirm_model_dir_url
from tools.infer.utility import draw_ocr, str2bool from tools.infer.utility import draw_ocr, str2bool, check_gpu
from ppstructure.utility import init_args, draw_structure_result from ppstructure.utility import init_args, draw_structure_result
from ppstructure.predict_system import OCRSystem, save_structure_res from ppstructure.predict_system import OCRSystem, save_structure_res
...@@ -39,130 +42,137 @@ __all__ = [ ...@@ -39,130 +42,137 @@ __all__ = [
] ]
SUPPORT_DET_MODEL = ['DB'] SUPPORT_DET_MODEL = ['DB']
VERSION = '2.2.1' VERSION = '2.3.0.1'
SUPPORT_REC_MODEL = ['CRNN'] SUPPORT_REC_MODEL = ['CRNN']
BASE_DIR = os.path.expanduser("~/.paddleocr/") BASE_DIR = os.path.expanduser("~/.paddleocr/")
DEFAULT_MODEL_VERSION = '2.0' DEFAULT_OCR_MODEL_VERSION = 'PP-OCR'
DEFAULT_STRUCTURE_MODEL_VERSION = 'STRUCTURE'
MODEL_URLS = { MODEL_URLS = {
'2.1': { 'OCR': {
'det': { 'PP-OCRv2': {
'ch': { 'det': {
'url': 'ch': {
'https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar', 'url':
}, 'https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar',
}, },
'rec': {
'ch': {
'url':
'https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar',
'dict_path': './ppocr/utils/ppocr_keys_v1.txt'
}
}
},
'2.0': {
'det': {
'ch': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar',
},
'en': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar',
}, },
'structure': { 'rec': {
'url': 'ch': {
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar' 'url':
'https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar',
'dict_path': './ppocr/utils/ppocr_keys_v1.txt'
}
} }
}, },
'rec': { DEFAULT_OCR_MODEL_VERSION: {
'ch': { 'det': {
'url': 'ch': {
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar', 'url':
'dict_path': './ppocr/utils/ppocr_keys_v1.txt' 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar',
}, },
'en': { 'en': {
'url': 'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar', 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar',
'dict_path': './ppocr/utils/en_dict.txt' },
}, 'structure': {
'french': { 'url':
'url': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar'
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_infer.tar', }
'dict_path': './ppocr/utils/dict/french_dict.txt'
},
'german': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/german_dict.txt'
},
'korean': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/korean_dict.txt'
},
'japan': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/japan_dict.txt'
},
'chinese_cht': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/chinese_cht_dict.txt'
},
'ta': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/ta_dict.txt'
}, },
'te': { 'rec': {
'url': 'ch': {
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_infer.tar', 'url':
'dict_path': './ppocr/utils/dict/te_dict.txt' 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/ppocr_keys_v1.txt'
},
'en': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/en_dict.txt'
},
'french': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/french_dict.txt'
},
'german': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/german_dict.txt'
},
'korean': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/korean_dict.txt'
},
'japan': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/japan_dict.txt'
},
'chinese_cht': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/chinese_cht_dict.txt'
},
'ta': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/ta_dict.txt'
},
'te': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/te_dict.txt'
},
'ka': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/ka_dict.txt'
},
'latin': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/latin_dict.txt'
},
'arabic': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/arabic_dict.txt'
},
'cyrillic': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/cyrillic_dict.txt'
},
'devanagari': {
'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'
}
}, },
'ka': { 'cls': {
'url': 'ch': {
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_infer.tar', 'url':
'dict_path': './ppocr/utils/dict/ka_dict.txt' 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar',
}
}, },
'latin': { }
'url': },
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_infer.tar', 'STRUCTURE': {
'dict_path': './ppocr/utils/dict/latin_dict.txt' DEFAULT_STRUCTURE_MODEL_VERSION: {
}, 'table': {
'arabic': { 'en': {
'url': 'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_infer.tar', 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar',
'dict_path': './ppocr/utils/dict/arabic_dict.txt' 'dict_path': 'ppocr/utils/dict/table_structure_dict.txt'
}, }
'cyrillic': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/cyrillic_dict.txt'
},
'devanagari': {
'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': {
'ch': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar',
}
},
'table': {
'en': {
'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'
} }
} }
} }
...@@ -177,7 +187,20 @@ def parse_args(mMain=True): ...@@ -177,7 +187,20 @@ def parse_args(mMain=True):
parser.add_argument("--det", type=str2bool, default=True) parser.add_argument("--det", type=str2bool, default=True)
parser.add_argument("--rec", type=str2bool, default=True) parser.add_argument("--rec", type=str2bool, default=True)
parser.add_argument("--type", type=str, default='ocr') parser.add_argument("--type", type=str, default='ocr')
parser.add_argument("--version", type=str, default='2.1') parser.add_argument(
"--ocr_version",
type=str,
default='PP-OCRv2',
help='OCR Model version, the current model support list is as follows: '
'1. PP-OCRv2 Support Chinese detection and recognition model. '
'2. PP-OCR support Chinese detection, recognition and direction classifier and multilingual recognition model.'
)
parser.add_argument(
"--structure_version",
type=str,
default='STRUCTURE',
help='Model version, the current model support list is as follows:'
' 1. STRUCTURE Support en table structure model.')
for action in parser._actions: for action in parser._actions:
if action.dest in ['rec_char_dict_path', 'table_char_dict_path']: if action.dest in ['rec_char_dict_path', 'table_char_dict_path']:
...@@ -215,9 +238,9 @@ def parse_lang(lang): ...@@ -215,9 +238,9 @@ def parse_lang(lang):
lang = "cyrillic" lang = "cyrillic"
elif lang in devanagari_lang: elif lang in devanagari_lang:
lang = "devanagari" lang = "devanagari"
assert lang in MODEL_URLS[DEFAULT_MODEL_VERSION][ assert lang in MODEL_URLS['OCR'][DEFAULT_OCR_MODEL_VERSION][
'rec'], 'param lang must in {}, but got {}'.format( 'rec'], 'param lang must in {}, but got {}'.format(
MODEL_URLS[DEFAULT_MODEL_VERSION]['rec'].keys(), lang) MODEL_URLS['OCR'][DEFAULT_OCR_MODEL_VERSION]['rec'].keys(), lang)
if lang == "ch": if lang == "ch":
det_lang = "ch" det_lang = "ch"
elif lang == 'structure': elif lang == 'structure':
...@@ -227,33 +250,41 @@ def parse_lang(lang): ...@@ -227,33 +250,41 @@ def parse_lang(lang):
return lang, det_lang return lang, det_lang
def get_model_config(version, model_type, lang): def get_model_config(type, version, model_type, lang):
if version not in MODEL_URLS: if type == 'OCR':
logger.warning('version {} not in {}, use version {} instead'.format( DEFAULT_MODEL_VERSION = DEFAULT_OCR_MODEL_VERSION
version, MODEL_URLS.keys(), DEFAULT_MODEL_VERSION)) elif type == 'STRUCTURE':
DEFAULT_MODEL_VERSION = DEFAULT_STRUCTURE_MODEL_VERSION
else:
raise NotImplementedError
model_urls = MODEL_URLS[type]
if version not in model_urls:
logger.warning('version {} not in {}, auto switch to version {}'.format(
version, model_urls.keys(), DEFAULT_MODEL_VERSION))
version = DEFAULT_MODEL_VERSION version = DEFAULT_MODEL_VERSION
if model_type not in MODEL_URLS[version]: if model_type not in model_urls[version]:
if model_type in MODEL_URLS[DEFAULT_MODEL_VERSION]: if model_type in model_urls[DEFAULT_MODEL_VERSION]:
logger.warning( logger.warning(
'version {} not support {} models, use version {} instead'. 'version {} not support {} models, auto switch to version {}'.
format(version, model_type, DEFAULT_MODEL_VERSION)) format(version, model_type, DEFAULT_MODEL_VERSION))
version = DEFAULT_MODEL_VERSION version = DEFAULT_MODEL_VERSION
else: else:
logger.error('{} models is not support, we only support {}'.format( logger.error('{} models is not support, we only support {}'.format(
model_type, MODEL_URLS[DEFAULT_MODEL_VERSION].keys())) model_type, model_urls[DEFAULT_MODEL_VERSION].keys()))
sys.exit(-1) sys.exit(-1)
if lang not in MODEL_URLS[version][model_type]: if lang not in model_urls[version][model_type]:
if lang in MODEL_URLS[DEFAULT_MODEL_VERSION][model_type]: if lang in model_urls[DEFAULT_MODEL_VERSION][model_type]:
logger.warning('lang {} is not support in {}, use {} instead'. logger.warning(
format(lang, version, DEFAULT_MODEL_VERSION)) 'lang {} is not support in {}, auto switch to version {}'.
format(lang, version, DEFAULT_MODEL_VERSION))
version = DEFAULT_MODEL_VERSION version = DEFAULT_MODEL_VERSION
else: else:
logger.error( logger.error(
'lang {} is not support, we only support {} for {} models'. 'lang {} is not support, we only support {} for {} models'.
format(lang, MODEL_URLS[DEFAULT_MODEL_VERSION][model_type].keys( format(lang, model_urls[DEFAULT_MODEL_VERSION][model_type].keys(
), model_type)) ), model_type))
sys.exit(-1) sys.exit(-1)
return MODEL_URLS[version][model_type][lang] return model_urls[version][model_type][lang]
class PaddleOCR(predict_system.TextSystem): class PaddleOCR(predict_system.TextSystem):
...@@ -265,23 +296,28 @@ class PaddleOCR(predict_system.TextSystem): ...@@ -265,23 +296,28 @@ class PaddleOCR(predict_system.TextSystem):
""" """
params = parse_args(mMain=False) params = parse_args(mMain=False)
params.__dict__.update(**kwargs) params.__dict__.update(**kwargs)
params.use_gpu = check_gpu(params.use_gpu)
if not params.show_log: if not params.show_log:
logger.setLevel(logging.INFO) logger.setLevel(logging.INFO)
self.use_angle_cls = params.use_angle_cls self.use_angle_cls = params.use_angle_cls
lang, det_lang = parse_lang(params.lang) lang, det_lang = parse_lang(params.lang)
# init model dir # init model dir
det_model_config = get_model_config(params.version, 'det', det_lang) det_model_config = get_model_config('OCR', params.ocr_version, 'det',
det_lang)
params.det_model_dir, det_url = confirm_model_dir_url( params.det_model_dir, det_url = confirm_model_dir_url(
params.det_model_dir, params.det_model_dir,
os.path.join(BASE_DIR, VERSION, 'ocr', 'det', det_lang), os.path.join(BASE_DIR, VERSION, 'ocr', 'det', det_lang),
det_model_config['url']) det_model_config['url'])
rec_model_config = get_model_config(params.version, 'rec', lang) rec_model_config = get_model_config('OCR', params.ocr_version, 'rec',
lang)
params.rec_model_dir, rec_url = confirm_model_dir_url( params.rec_model_dir, rec_url = confirm_model_dir_url(
params.rec_model_dir, params.rec_model_dir,
os.path.join(BASE_DIR, VERSION, 'ocr', 'rec', lang), os.path.join(BASE_DIR, VERSION, 'ocr', 'rec', lang),
rec_model_config['url']) rec_model_config['url'])
cls_model_config = get_model_config(params.version, 'cls', 'ch') cls_model_config = get_model_config('OCR', params.ocr_version, 'cls',
'ch')
params.cls_model_dir, cls_url = confirm_model_dir_url( params.cls_model_dir, cls_url = confirm_model_dir_url(
params.cls_model_dir, params.cls_model_dir,
os.path.join(BASE_DIR, VERSION, 'ocr', 'cls'), os.path.join(BASE_DIR, VERSION, 'ocr', 'cls'),
...@@ -362,22 +398,27 @@ class PPStructure(OCRSystem): ...@@ -362,22 +398,27 @@ class PPStructure(OCRSystem):
def __init__(self, **kwargs): def __init__(self, **kwargs):
params = parse_args(mMain=False) params = parse_args(mMain=False)
params.__dict__.update(**kwargs) params.__dict__.update(**kwargs)
params.use_gpu = check_gpu(params.use_gpu)
if not params.show_log: if not params.show_log:
logger.setLevel(logging.INFO) logger.setLevel(logging.INFO)
lang, det_lang = parse_lang(params.lang) lang, det_lang = parse_lang(params.lang)
# init model dir # init model dir
det_model_config = get_model_config(params.version, 'det', det_lang) det_model_config = get_model_config('OCR', params.ocr_version, 'det',
det_lang)
params.det_model_dir, det_url = confirm_model_dir_url( params.det_model_dir, det_url = confirm_model_dir_url(
params.det_model_dir, params.det_model_dir,
os.path.join(BASE_DIR, VERSION, 'ocr', 'det', det_lang), os.path.join(BASE_DIR, VERSION, 'ocr', 'det', det_lang),
det_model_config['url']) det_model_config['url'])
rec_model_config = get_model_config(params.version, 'rec', lang) rec_model_config = get_model_config('OCR', params.ocr_version, 'rec',
lang)
params.rec_model_dir, rec_url = confirm_model_dir_url( params.rec_model_dir, rec_url = confirm_model_dir_url(
params.rec_model_dir, params.rec_model_dir,
os.path.join(BASE_DIR, VERSION, 'ocr', 'rec', lang), os.path.join(BASE_DIR, VERSION, 'ocr', 'rec', lang),
rec_model_config['url']) rec_model_config['url'])
table_model_config = get_model_config(params.version, 'table', 'en') table_model_config = get_model_config(
'STRUCTURE', params.structure_version, 'table', 'en')
params.table_model_dir, table_url = confirm_model_dir_url( params.table_model_dir, table_url = confirm_model_dir_url(
params.table_model_dir, params.table_model_dir,
os.path.join(BASE_DIR, VERSION, 'ocr', 'table'), os.path.join(BASE_DIR, VERSION, 'ocr', 'table'),
......
ppocr/utils/network.py
浏览文件 @ 96c8c004
...@@ -24,15 +24,17 @@ from ppocr.utils.logging import get_logger ...@@ -24,15 +24,17 @@ from ppocr.utils.logging import get_logger
def download_with_progressbar(url, save_path): def download_with_progressbar(url, save_path):
logger = get_logger() logger = get_logger()
response = requests.get(url, stream=True) response = requests.get(url, stream=True)
total_size_in_bytes = int(response.headers.get('content-length', 0)) if response.status_code == 200:
block_size = 1024 # 1 Kibibyte total_size_in_bytes = int(response.headers.get('content-length', 1))
progress_bar = tqdm(total=total_size_in_bytes, unit='iB', unit_scale=True) block_size = 1024 # 1 Kibibyte
with open(save_path, 'wb') as file: progress_bar = tqdm(
for data in response.iter_content(block_size): total=total_size_in_bytes, unit='iB', unit_scale=True)
progress_bar.update(len(data)) with open(save_path, 'wb') as file:
file.write(data) for data in response.iter_content(block_size):
progress_bar.close() progress_bar.update(len(data))
if total_size_in_bytes == 0 or progress_bar.n != total_size_in_bytes: file.write(data)
progress_bar.close()
else:
logger.error("Something went wrong while downloading models") logger.error("Something went wrong while downloading models")
sys.exit(0) sys.exit(0)
...@@ -45,7 +47,7 @@ def maybe_download(model_storage_directory, url): ...@@ -45,7 +47,7 @@ def maybe_download(model_storage_directory, url):
if not os.path.exists( if not os.path.exists(
os.path.join(model_storage_directory, 'inference.pdiparams') os.path.join(model_storage_directory, 'inference.pdiparams')
) or not os.path.exists( ) or not os.path.exists(
os.path.join(model_storage_directory, 'inference.pdmodel')): os.path.join(model_storage_directory, 'inference.pdmodel')):
assert url.endswith('.tar'), 'Only supports tar compressed package' assert url.endswith('.tar'), 'Only supports tar compressed package'
tmp_path = os.path.join(model_storage_directory, url.split('/')[-1]) tmp_path = os.path.join(model_storage_directory, url.split('/')[-1])
print('download {} to {}'.format(url, tmp_path)) print('download {} to {}'.format(url, tmp_path))
......
tools/__init__.py 0 → 100644
浏览文件 @ 96c8c004
# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
#
# 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.
tools/infer/utility.py
浏览文件 @ 96c8c004
...@@ -17,7 +17,7 @@ import os ...@@ -17,7 +17,7 @@ import os
import sys import sys
import cv2 import cv2
import numpy as np import numpy as np
import json import paddle
from PIL import Image, ImageDraw, ImageFont from PIL import Image, ImageDraw, ImageFont
import math import math
from paddle import inference from paddle import inference
...@@ -601,5 +601,12 @@ def get_rotate_crop_image(img, points): ...@@ -601,5 +601,12 @@ def get_rotate_crop_image(img, points):
return dst_img return dst_img
def check_gpu(use_gpu):
if use_gpu and not paddle.is_compiled_with_cuda():
use_gpu = False
return use_gpu
if __name__ == '__main__': if __name__ == '__main__':
pass pass
Markdown is supported
0% 或 .
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 或