mirrors
/
PaddleOCR
mirror of https://github.com/PaddlePaddle/PaddleOCR.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #8073 from WenmuZhou/whl 

fix benckmark error when benckmark=false
pull/8087/head
zhoujun 2022-10-24 23:24:43 +08:00 committed by GitHub
parent b92501faf6 cad701d411
commit 210135cc94
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 120 additions and 93 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
paddleocr.py
View File

@ -47,7 +47,7 @@ __all__ = [
]
SUPPORT_DET_MODEL = ['DB']
VERSION = '2.6.0.3'
VERSION = '2.6.1.0'
SUPPORT_REC_MODEL = ['CRNN', 'SVTR_LCNet']
BASE_DIR = os.path.expanduser("~/.paddleocr/")

154
ppstructure/pdf2word/pdf2word.py
View File

@ -1,3 +1,17 @@
# copyright (c) 2022 PaddlePaddle Authors. All Rights Reserve.
#
# 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 sys
import tarfile
import os
@ -20,7 +34,6 @@ root = os.path.abspath(os.path.join(file, '../../'))
sys.path.append(file)
sys.path.insert(0, root)
from ppstructure.predict_system import StructureSystem, save_structure_res
from ppstructure.utility import parse_args, draw_structure_result
from ppocr.utils.network import download_with_progressbar
@ -32,13 +45,17 @@ __VERSION__ = "0.2.2"
URLs_EN = {
# 下载超英文轻量级PP-OCRv3模型的检测模型并解压
"en_PP-OCRv3_det_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar",
"en_PP-OCRv3_det_infer":
"https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar",
# 下载英文轻量级PP-OCRv3模型的识别模型并解压
"en_PP-OCRv3_rec_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar",
"en_PP-OCRv3_rec_infer":
"https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar",
# 下载超轻量级英文表格英文模型并解压
"en_ppstructure_mobile_v2.0_SLANet_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar",
"en_ppstructure_mobile_v2.0_SLANet_infer":
"https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar",
# 英文版面分析模型
"picodet_lcnet_x1_0_fgd_layout_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_infer.tar",
"picodet_lcnet_x1_0_fgd_layout_infer":
"https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_infer.tar",
}
DICT_EN = {
"rec_char_dict_path": "en_dict.txt",
@ -47,13 +64,17 @@ DICT_EN = {
URLs_CN = {
# 下载超中文轻量级PP-OCRv3模型的检测模型并解压
"cn_PP-OCRv3_det_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar",
"cn_PP-OCRv3_det_infer":
"https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar",
# 下载中文轻量级PP-OCRv3模型的识别模型并解压
"cn_PP-OCRv3_rec_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar",
"cn_PP-OCRv3_rec_infer":
"https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar",
# 下载超轻量级英文表格英文模型并解压
"cn_ppstructure_mobile_v2.0_SLANet_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar",
"cn_ppstructure_mobile_v2.0_SLANet_infer":
"https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar",
# 中文版面分析模型
"picodet_lcnet_x1_0_fgd_layout_cdla_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_cdla_infer.tar",
"picodet_lcnet_x1_0_fgd_layout_cdla_infer":
"https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_cdla_infer.tar",
}
DICT_CN = {
"rec_char_dict_path": "ppocr_keys_v1.txt",
@ -61,7 +82,6 @@ DICT_CN = {
}
def QImageToCvMat(incomingImage) -> np.array:
'''
Converts a QImage into an opencv MAT format
@ -167,8 +187,8 @@ class Worker(QThread):
try:
convert_info_docx(imgs, all_res, self.outputDir, img_name)
except Exception as ex:
print("error in layout recovery image:{}, err msg: {}".
format(img_name, ex))
print("error in layout recovery image:{}, err msg: {}".format(
img_name, ex))
print("Predict time : {:.3f}s".format(time_dict['all']))
print('result save to {}'.format(self.outputDir))
@ -185,10 +205,11 @@ class Worker(QThread):
and os.path.basename(image_file)[-3:] == 'pdf':
self.totalPageCnt += 1
self.progressBarRange.emit(self.totalPageCnt)
print('===============using use_pdf2docx_api===============')
print(
'===============using use_pdf2docx_api===============')
img_name = os.path.basename(image_file).split('.')[0]
docx_file = os.path.join(
self.outputDir, '{}.docx'.format(img_name))
docx_file = os.path.join(self.outputDir,
'{}.docx'.format(img_name))
cv = Converter(image_file)
cv.convert(docx_file)
cv.close()
@ -201,7 +222,8 @@ class Worker(QThread):
if len(imgs) == 0:
continue
img_name = os.path.basename(image_file).split('.')[0]
os.makedirs(os.path.join(self.outputDir, img_name), exist_ok=True)
os.makedirs(
os.path.join(self.outputDir, img_name), exist_ok=True)
self.ppocrPrecitor(imgs, img_name)
# file processed
self.endsignal.emit()
@ -222,8 +244,7 @@ class APP_Image2Doc(QWidget):
self.screenShot = None
self.save_pdf = False
self.output_dir = None
self.vis_font_path = os.path.join(root,
"doc", "fonts", "simfang.ttf")
self.vis_font_path = os.path.join(root, "doc", "fonts", "simfang.ttf")
self.use_pdf2docx_api = False
# ProgressBar
@ -245,8 +266,10 @@ class APP_Image2Doc(QWidget):
}
# 设置工作进程
self._thread = Worker(predictors, self.save_pdf, self.vis_font_path, self.use_pdf2docx_api)
self._thread.progressBarValue.connect(self.handleProgressBarUpdateSingal)
self._thread = Worker(predictors, self.save_pdf, self.vis_font_path,
self.use_pdf2docx_api)
self._thread.progressBarValue.connect(
self.handleProgressBarUpdateSingal)
self._thread.endsignal.connect(self.handleEndsignalSignal)
# self._thread.finished.connect(QObject.deleteLater)
self._thread.progressBarRange.connect(self.handleProgressBarRangeSingal)
@ -294,8 +317,7 @@ class APP_Image2Doc(QWidget):
# ProgressBar
layout.addWidget(self.pb, 2, 0, 1, 5)
# time estimate label
self.timeEstLabel = QLabel(
("Time Left: --"))
self.timeEstLabel = QLabel(("Time Left: --"))
layout.addWidget(self.timeEstLabel, 3, 0, 1, 5)
self.setLayout(layout)
@ -303,11 +325,8 @@ class APP_Image2Doc(QWidget):
def downloadModels(self, URLs):
# using custom model
tar_file_name_list = [
'inference.pdiparams',
'inference.pdiparams.info',
'inference.pdmodel',
'model.pdiparams',
'model.pdiparams.info',
'inference.pdiparams', 'inference.pdiparams.info',
'inference.pdmodel', 'model.pdiparams', 'model.pdiparams.info',
'model.pdmodel'
]
model_path = os.path.join(root, 'inference')
@ -325,7 +344,8 @@ class APP_Image2Doc(QWidget):
try:
download_with_progressbar(url, tarpath)
except Exception as e:
print("Error occurred when downloading file, error message:")
print(
"Error occurred when downloading file, error message:")
print(e)
# unzip model tar
@ -341,8 +361,7 @@ class APP_Image2Doc(QWidget):
if filename is None:
continue
file = tarObj.extractfile(member)
with open(
os.path.join(storage_dir, filename),
with open(os.path.join(storage_dir, filename),
'wb') as f:
f.write(file.read())
except Exception as e:
@ -356,37 +375,40 @@ class APP_Image2Doc(QWidget):
args.ocr = True
args.recovery = True
args.save_pdf = self.save_pdf
args.table_char_dict_path = os.path.join(root,
"ppocr", "utils", "dict", "table_structure_dict.txt")
args.table_char_dict_path = os.path.join(root, "ppocr", "utils", "dict",
"table_structure_dict.txt")
if lang == 'EN':
args.det_model_dir = os.path.join(root, # 此处从这里找到模型存放位置
"inference", "en_PP-OCRv3_det_infer")
args.rec_model_dir = os.path.join(root,
"inference", "en_PP-OCRv3_rec_infer")
args.table_model_dir = os.path.join(root,
"inference", "en_ppstructure_mobile_v2.0_SLANet_infer")
args.det_model_dir = os.path.join(
root, # 此处从这里找到模型存放位置
"inference",
"en_PP-OCRv3_det_infer")
args.rec_model_dir = os.path.join(root, "inference",
"en_PP-OCRv3_rec_infer")
args.table_model_dir = os.path.join(
root, "inference", "en_ppstructure_mobile_v2.0_SLANet_infer")
args.output = os.path.join(root, "output") # 结果保存路径
args.layout_model_dir = os.path.join(root,
"inference", "picodet_lcnet_x1_0_fgd_layout_infer")
args.layout_model_dir = os.path.join(
root, "inference", "picodet_lcnet_x1_0_fgd_layout_infer")
lang_dict = DICT_EN
elif lang == 'CN':
args.det_model_dir = os.path.join(root, # 此处从这里找到模型存放位置
"inference", "cn_PP-OCRv3_det_infer")
args.rec_model_dir = os.path.join(root,
"inference", "cn_PP-OCRv3_rec_infer")
args.table_model_dir = os.path.join(root,
"inference", "cn_ppstructure_mobile_v2.0_SLANet_infer")
args.det_model_dir = os.path.join(
root, # 此处从这里找到模型存放位置
"inference",
"cn_PP-OCRv3_det_infer")
args.rec_model_dir = os.path.join(root, "inference",
"cn_PP-OCRv3_rec_infer")
args.table_model_dir = os.path.join(
root, "inference", "cn_ppstructure_mobile_v2.0_SLANet_infer")
args.output = os.path.join(root, "output") # 结果保存路径
args.layout_model_dir = os.path.join(root,
"inference", "picodet_lcnet_x1_0_fgd_layout_cdla_infer")
args.layout_model_dir = os.path.join(
root, "inference", "picodet_lcnet_x1_0_fgd_layout_cdla_infer")
lang_dict = DICT_CN
else:
raise ValueError("Unsupported language")
args.rec_char_dict_path = os.path.join(root,
"ppocr", "utils",
args.rec_char_dict_path = os.path.join(root, "ppocr", "utils",
lang_dict['rec_char_dict_path'])
args.layout_dict_path = os.path.join(root,
"ppocr", "utils", "dict", "layout_dict",
args.layout_dict_path = os.path.join(root, "ppocr", "utils", "dict",
"layout_dict",
lang_dict['layout_dict_path'])
# init predictor
return StructureSystem(args)
@ -395,8 +417,8 @@ class APP_Image2Doc(QWidget):
'''
可以多选图像文件
'''
selectedFiles = QFileDialog.getOpenFileNames(self,
"多文件选择", "/", "图片文件 (*.png *.jpeg *.jpg *.bmp *.pdf)")[0]
selectedFiles = QFileDialog.getOpenFileNames(
self, "多文件选择", "/", "图片文件 (*.png *.jpeg *.jpg *.bmp *.pdf)")[0]
if len(selectedFiles) > 0:
self.imagePaths = selectedFiles
self.screenShot = None # discard screenshot temp image
@ -416,17 +438,18 @@ class APP_Image2Doc(QWidget):
def handleStartSignal(self, lang='EN', pdfParser=False):
if self.screenShot: # for screenShot
img_name = 'screenshot_' + time.strftime("%Y%m%d%H%M%S", time.localtime())
img_name = 'screenshot_' + time.strftime("%Y%m%d%H%M%S",
time.localtime())
image = QImageToCvMat(self.screenShot)
self.predictAndSave(image, img_name, lang)
# update Progress Bar
self.pb.setValue(1)
QMessageBox.information(self,
u'Information', "文档提取完成")
QMessageBox.information(self, u'Information', "文档提取完成")
elif len(self.imagePaths) > 0: # for image file selection
# Must set image path list and language before start
self.output_dir = os.path.join(
os.path.dirname(self.imagePaths[0]), "output") # output_dir shold be same as imagepath
os.path.dirname(self.imagePaths[0]),
"output") # output_dir shold be same as imagepath
self._thread.setOutputDir(self.output_dir)
self._thread.setImagePath(self.imagePaths)
self._thread.setLang(lang)
@ -439,11 +462,9 @@ class APP_Image2Doc(QWidget):
# 启动工作进程
self._thread.start()
self.time_start = time.time() # log start time
QMessageBox.information(self,
u'Information', "开始转换")
QMessageBox.information(self, u'Information', "开始转换")
else:
QMessageBox.warning(self,
u'Information', "请选择要识别的文件或截图")
QMessageBox.warning(self, u'Information', "请选择要识别的文件或截图")
def handleShowResultSignal(self):
if self.output_dir is None:
@ -454,15 +475,16 @@ class APP_Image2Doc(QWidget):
else:
os.system('open ' + os.path.normpath(self.output_dir))
else:
QMessageBox.information(self,
u'Information', "输出文件不存在")
QMessageBox.information(self, u'Information', "输出文件不存在")
def handleProgressBarUpdateSingal(self, i):
self.pb.setValue(i)
# calculate time left of recognition
lenbar = self.pb.maximum()
avg_time = (time.time() - self.time_start) / i # Use average time to prevent time fluctuations
time_left = str(datetime.timedelta(seconds=avg_time * (lenbar - i))).split(".")[0] # Remove microseconds
avg_time = (time.time() - self.time_start
) / i # Use average time to prevent time fluctuations
time_left = str(datetime.timedelta(seconds=avg_time * (
lenbar - i))).split(".")[0] # Remove microseconds
self.timeEstLabel.setText(f"Time Left: {time_left}") # show time left
def handleProgressBarRangeSingal(self, max):

1
ppstructure/recovery/requirements.txt
View File

@ -3,3 +3,4 @@ PyMuPDF==1.19.0
beautifulsoup4
fonttools>=4.24.0
fire>=0.3.0
pdf2docx

4
ppstructure/table/predict_table.py
View File

@ -60,11 +60,15 @@ class TableSystem(object):
self.args = args
if not args.show_log:
logger.setLevel(logging.INFO)
benchmark_tmp = False
if args.benchmark:
benchmark_tmp = args.benchmark
args.benchmark = False
self.text_detector = predict_det.TextDetector(copy.deepcopy(
args)) if text_detector is None else text_detector
self.text_recognizer = predict_rec.TextRecognizer(copy.deepcopy(
args)) if text_recognizer is None else text_recognizer
if benchmark_tmp:
args.benchmark = True
self.table_structurer = predict_strture.TableStructurer(args)
if args.table_algorithm in ['TableMaster']: