shiyutang e3fc6393e0
[Cherry-pick] Cherry-pick from release/2.6 ()
* Update recognition_en.md ()

ic15_dict.txt only have 36 digits

* Update ocr_rec.h ()

It is enough to include preprocess_op.h, we do not need to include ocr_cls.h.

* 补充num_classes注释说明 ()

ser_vi_layoutxlm_xfund_zh.yml中的Architecture.Backbone.num_classes所赋值会设置给Loss.num_classes,
由于采用BIO标注,假设字典中包含n个字段(包含other)时,则类别数为2n-1;假设字典中包含n个字段(不含other)时,则类别数为2n+1。

* Update algorithm_overview_en.md ()

Fix links to super-resolution algorithm docs

* 改进文档`deploy/hubserving/readme.md`和`doc/doc_ch/models_list.md` ()

* Update readme.md

* Update readme.md

* Update readme.md

* Update models_list.md

* trim trailling spaces @ `deploy/hubserving/readme_en.md`

* `s/shell/bash/` @ `deploy/hubserving/readme_en.md`

* Update `deploy/hubserving/readme_en.md` to sync with `deploy/hubserving/readme.md`

* Update deploy/hubserving/readme_en.md to sync with `deploy/hubserving/readme.md`

* Update deploy/hubserving/readme_en.md to sync with `deploy/hubserving/readme.md`

* Update `doc/doc_en/models_list_en.md` to sync with `doc/doc_ch/models_list_en.md`

* using Grammarly to weak `deploy/hubserving/readme_en.md`

* using Grammarly to tweak `doc/doc_en/models_list_en.md`

* `ocr_system` module will return with values of field `confidence`

* Update README_CN.md

* 修复测试服务中图片转Base64的引用地址错误。 ()

* Update application.md

* [Doc] Fix 404 link.  ()

* Update PP-OCRv3_det_train.md

* Update knowledge_distillation.md

* Update config.md

* Fix fitz camelCase deprecation and .PDF not being recognized as pdf file ()

* Fix fitz camelCase deprecation and .PDF not being recognized as pdf file

* refactor get_image_file_list function

* Update customize.md ()

* Update FAQ.md ()

* Update FAQ.md ()

* Don't break overall processing on a bad image ()

* Add preprocessing common to OCR tasks ()

Add preprocessing to options

* [MLU] add mlu device for infer ()

* Create newfeature.md

* Update newfeature.md

* remove unused imported module, so can avoid PyInstaller packaged binary's start-time not found module error. ()

* CV套件建设专项活动 - 文字识别返回单字识别坐标 ()

* modification of return word box

* update_implements

* Update rec_postprocess.py

* Update utility.py

* Update README_ch.md

* revert README_ch.md update

* Fixed Layout recovery README file ()

Co-authored-by: Shubham Chambhare <shubhamchambhare@zoop.one>

* update_doc

* bugfix

---------

Co-authored-by: ChuongLoc <89434232+ChuongLoc@users.noreply.github.com>
Co-authored-by: Wang Xin <xinwang614@gmail.com>
Co-authored-by: tanjh <dtdhinjapan@gmail.com>
Co-authored-by: Louis Maddox <lmmx@users.noreply.github.com>
Co-authored-by: n0099 <n@n0099.net>
Co-authored-by: zhenliang li <37922155+shouyong@users.noreply.github.com>
Co-authored-by: itasli <ilyas.tasli@outlook.fr>
Co-authored-by: UserUnknownFactor <63057995+UserUnknownFactor@users.noreply.github.com>
Co-authored-by: PeiyuLau <135964669+PeiyuLau@users.noreply.github.com>
Co-authored-by: kerneltravel <kjpioo2006@gmail.com>
Co-authored-by: ToddBear <43341135+ToddBear@users.noreply.github.com>
Co-authored-by: Ligoml <39876205+Ligoml@users.noreply.github.com>
Co-authored-by: Shubham Chambhare <59397280+Shubham654@users.noreply.github.com>
Co-authored-by: Shubham Chambhare <shubhamchambhare@zoop.one>
Co-authored-by: andyj <87074272+andyjpaddle@users.noreply.github.com>
2023-10-18 17:37:23 +08:00

65 lines
2.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# 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.
from setuptools import setup
from io import open
from paddleocr import VERSION
def load_requirements(file_list=None):
if file_list is None:
file_list = ['requirements.txt']
if isinstance(file_list,str):
file_list = [file_list]
requirements = []
for file in file_list:
with open(file, encoding="utf-8-sig") as f:
requirements.extend(f.readlines())
return requirements
def readme():
with open('doc/doc_en/whl_en.md', encoding="utf-8-sig") as f:
README = f.read()
return README
setup(
name='paddleocr',
packages=['paddleocr'],
package_dir={'paddleocr': ''},
include_package_data=True,
entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
version=VERSION,
install_requires=load_requirements(['requirements.txt', 'ppstructure/recovery/requirements.txt']),
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, embedded 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'
], )