Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into test_v11

201cb592 · LDOUBLEV · 9415f71d · ccd01cfe · 201cb592 · 201cb592
Commit 201cb592 authored Nov 16, 2021 by LDOUBLEV
20 changed files
--- a/.github/ISSUE_TEMPLATE/custom.md
+++ b/.github/ISSUE_TEMPLATE/custom.md
+---
+name: Issue template
+about: Issue template for code error.
+title: ''
+labels: ''
+assignees: ''
+---
+请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
+- 系统环境/System Environment：
+- 版本号/Version：Paddle：  PaddleOCR： 问题相关组件/Related components：
+- 运行指令/Command Code：
+- 完整报错/Complete Error Message：
--- a/PPOCRLabel/PPOCRLabel.py
+++ b/PPOCRLabel/PPOCRLabel.py
@@ -35,6 +35,7 @@ import numpy as np
 sys.path.append(__dir__)
 sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
+sys.path.append(os.path.abspath(os.path.join(__dir__, '../PaddleOCR')))
 sys.path.append("..")
 from paddleocr import PaddleOCR
@@ -390,7 +391,7 @@ class MainWindow(QMainWindow, WindowMixin):
                          'Ctrl+J', 'edit', u'Move and edit Boxs', enabled=False)
        create = action(getStr('crtBox'), self.createShape,
-                        'w', 'new', getStr('crtBoxDetail'), enabled=False)
+                        'w', 'objects', getStr('crtBoxDetail'), enabled=False)
        delete = action(getStr('delBox'), self.deleteSelectedShape,
                        'backspace', 'delete', getStr('delBoxDetail'), enabled=False)

--- a/PPOCRLabel/libs/stringBundle.py
+++ b/PPOCRLabel/libs/stringBundle.py
@@ -19,6 +19,9 @@ import sys
 import locale
 from libs.ustr import ustr
+__dir__ = os.path.dirname(os.path.abspath(__file__)) # 获取本程序文件路径
+__dirpath__ = os.path.abspath(os.path.join(__dir__, '../resources/strings'))
 try:
    from PyQt5.QtCore import *
 except ImportError:
@@ -57,14 +60,15 @@ class StringBundle:
    def __createLookupFallbackList(self, localeStr):
        resultPaths = []
-        basePath = ":/strings"
+        basePath = "\strings"
        resultPaths.append(basePath)
        if localeStr is not None:
            # Don't follow standard BCP47. Simple fallback
            tags = re.split('[^a-zA-Z]', localeStr)
            for tag in tags:
                lastPath = resultPaths[-1]
-                resultPaths.append(lastPath + '-' + tag)
+                resultPaths[-1] = lastPath + '-' + tag
+            resultPaths[-1] = __dirpath__ + resultPaths[-1] + ".properties"
        return resultPaths

--- a/PPOCRLabel/libs/utils.py
+++ b/PPOCRLabel/libs/utils.py
@@ -17,6 +17,10 @@ import re
 import sys
 import cv2
 import numpy as np
+import os
+__dir__ = os.path.dirname(os.path.abspath(__file__)) # 获取本程序文件路径
+__iconpath__ = os.path.abspath(os.path.join(__dir__, '../resources/icons'))
 try:
    from PyQt5.QtGui import *
@@ -29,9 +33,9 @@ except ImportError:
 def newIcon(icon, iconSize=None):
    if iconSize is not None:
-        return QIcon(QIcon(':/' + icon).pixmap(iconSize,iconSize))
+        return QIcon(QIcon(__iconpath__ + "\\" + icon + ".png").pixmap(iconSize,iconSize))
    else:
-        return QIcon(':/' + icon)
+        return QIcon(__iconpath__ + "\\" + icon + ".png")
 def newButton(text, icon=None, slot=None):

--- a/PPOCRLabel/requirements.txt
+++ b/PPOCRLabel/requirements.txt
+shapely
+scikit-image==0.17.2
+imgaug==0.4.0
+pyclipper
+lmdb
+tqdm
+numpy
+visualdl
+python-Levenshtein
+opencv-contrib-python==4.2.0.32
+PaddleOCR
\ No newline at end of file
--- a/PPOCRLabel/resources/strings/strings.properties
+++ b/PPOCRLabel/resources/strings/strings.properties
--- a/PPOCRLabel/setup.py
+++ b/PPOCRLabel/setup.py
-# Copyright (c) <2015-Present> Tzutalin
+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
-# Copyright (C) 2013  MIT, Computer Science and Artificial Intelligence Laboratory. Bryan Russell, Antonio Torralba,
+#
-# William T. Freeman. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and
+# Licensed under the Apache License, Version 2.0 (the "License");
-# associated documentation files (the "Software"), to deal in the Software without restriction, including without
+# you may not use this file except in compliance with the License.
-# limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the
+# You may obtain a copy of the License at
-# Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+#
-# The above copyright notice and this permission notice shall be included in all copies or substantial portions of
+#     http://www.apache.org/licenses/LICENSE-2.0
-# the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT
+#
-# NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
+# Unless required by applicable law or agreed to in writing, software
-# SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
+# distributed under the License is distributed on an "AS IS" BASIS,
-# CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# THE SOFTWARE.
+# See the License for the specific language governing permissions and
+# limitations under the License.
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
+from setuptools import setup
+from io import open
-from setuptools import setup, find_packages, Command
-from sys import platform as _platform
+with open('requirements.txt', encoding="utf-8-sig") as f:
-from shutil import rmtree
+    requirements = f.readlines()
-import sys
+    requirements.append('tqdm')
-import os
-here = os.path.abspath(os.path.dirname(__file__))
+def readme():
-NAME = 'labelImg'
+    with open('README.md', encoding="utf-8-sig") as f:
-REQUIRES_PYTHON = '>=3.0.0'
+        README = f.read()
-REQUIRED_DEP = ['pyqt5', 'lxml']
+    return README
-about = {}
-with open(os.path.join(here, 'libs', '__init__.py')) as f:
-    exec(f.read(), about)
-with open('README.rst') as readme_file:
-    readme = readme_file.read()
-with open('HISTORY.rst') as history_file:
-    history = history_file.read()
-# OS specific settings
-SET_REQUIRES = []
-if _platform == "linux" or _platform == "linux2":
-   # linux
-   print('linux')
-elif _platform == "darwin":
-   # MAC OS X
-   SET_REQUIRES.append('py2app')
-required_packages = find_packages()
-required_packages.append('labelImg')
-APP = [NAME + '.py']
-OPTIONS = {
-    'argv_emulation': True,
-    'iconfile': 'resources/icons/app.icns'
-}
-class UploadCommand(Command):
-    """Support setup.py upload."""
-    description=readme + '\n\n' + history,
-    user_options = []
-    @staticmethod
-    def status(s):
-        """Prints things in bold."""
-        print('\033[1m{0}\033[0m'.format(s))
-    def initialize_options(self):
-        pass
-    def finalize_options(self):
-        pass
-    def run(self):
-        try:
-            self.status('Removing previous builds…')
-            rmtree(os.path.join(here, 'dist'))
-        except OSError:
-            self.status('Fail to remove previous builds..')
-            pass
-        self.status('Building Source and Wheel (universal) distribution…')
-        os.system(
-            '{0} setup.py sdist bdist_wheel --universal'.format(sys.executable))
-        self.status('Uploading the package to PyPI via Twine…')
-        os.system('twine upload dist/*')
-        self.status('Pushing git tags…')
-        os.system('git tag -d v{0}'.format(about['__version__']))
-        os.system('git tag v{0}'.format(about['__version__']))
-        # os.system('git push --tags')
-        sys.exit()
 setup(
-    app=APP,
+    name='PPOCRLabel',
-    name=NAME,
+    packages=['PPOCRLabel'],
-    version=about['__version__'],
+    package_data = {'PPOCRLabel': ['libs/*','resources/strings/*','resources/icons/*']},
-    description="LabelImg is a graphical image annotation tool and label object bounding boxes in images",
+    package_dir={'PPOCRLabel': ''},
-    long_description=readme + '\n\n' + history,
-    author="TzuTa Lin",
-    author_email='tzu.ta.lin@gmail.com',
-    url='https://github.com/tzutalin/labelImg',
-    python_requires=REQUIRES_PYTHON,
-    package_dir={'labelImg': '.'},
-    packages=required_packages,
-    entry_points={
-        'console_scripts': [
-            'labelImg=labelImg.labelImg:main'
-        ]
-    },
    include_package_data=True,
-    install_requires=REQUIRED_DEP,
+    entry_points={"console_scripts": ["PPOCRLabel= PPOCRLabel.PPOCRLabel:main"]},
-    license="MIT license",
+    version='1.0.0',
-    zip_safe=False,
+    install_requires=requirements,
-    keywords='labelImg labelTool development annotation deeplearning',
+    license='Apache License 2.0',
+    description='PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, with built-in PPOCR model to automatically detect and re-recognize data. It is written in python3 and pyqt5, supporting rectangular box annotation and four-point annotation modes. Annotations can be directly used for the training of PPOCR detection and recognition models',
+    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=[
-        'Development Status :: 5 - Production/Stable',
+        'Intended Audience :: Developers', 'Operating System :: OS Independent',
-        'Intended Audience :: Developers',
-        'License :: OSI Approved :: MIT License',
        'Natural Language :: English',
-        'Programming Language :: Python :: 3',
-        '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',
+        'Programming Language :: Python :: 3.7', 'Topic :: Utilities'
-    ],
+    ], )
-    package_data={'data/predefined_classes.txt': ['data/predefined_classes.txt']},
\ No newline at end of file
-    options={'py2app': OPTIONS},
-    setup_requires=SET_REQUIRES,
-    # $ setup.py publish support.
-    cmdclass={
-        'upload': UploadCommand,
-    }
-)
--- a/README.md
+++ b/README.md
@@ -25,7 +25,7 @@ PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools
 **Recent updates**
- PaddleOCR R&D team would like to share the key points of PP-OCRv2, at 20:15 pm on September 8th, [Live Address](https://live.bilibili.com/21689802).
+- PaddleOCR R&D team would like to share the key points of PP-OCRv2, at 20:15 pm on September 8th, [Course Address](https://aistudio.baidu.com/aistudio/education/group/info/6758).
 - 2021.9.7 release PaddleOCR v2.3, [PP-OCRv2](#PP-OCRv2) is proposed. The inference speed of PP-OCRv2 is 220% higher than that of PP-OCR server in CPU device. The F-score of PP-OCRv2 is 7% higher than that of PP-OCR mobile.
 - 2021.8.3 released PaddleOCR v2.2, add a new structured documents analysis toolkit, i.e., [PP-Structure](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/ppstructure/README.md), support layout analysis and table recognition (One-key to export chart images to Excel files).
 - 2021.4.8 release end-to-end text recognition algorithm [PGNet](https://www.aaai.org/AAAI21Papers/AAAI-2885.WangP.pdf) which is published in AAAI 2021. Find tutorial [here](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/pgnet_en.md)；release multi language recognition [models](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md), support more than 80 languages recognition; especically, the performance of [English recognition model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/models_list_en.md#English) is Optimized.
@@ -86,9 +86,9 @@ Mobile DEMO experience (based on EasyEdge and Paddle-Lite, supports iOS and Andr
 | Model introduction                                           | Model name                   | Recommended scene | Detection model                                              | Direction classifier                                         | Recognition model                                            |
 | ------------------------------------------------------------ | ---------------------------- | ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
-| Chinese and English ultra-lightweight PP-OCRv2 model（11.6M） |  ch_PP-OCRv2_xx |Mobile&Server|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/ch/ch_PP-OCRv2_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
+| Chinese and English ultra-lightweight PP-OCRv2 model（11.6M） |  ch_PP-OCRv2_xx |Mobile & Server|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/ch/ch_PP-OCRv2_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
-| Chinese and English ultra-lightweight PP-OCR model (9.4M)       | ch_ppocr_mobile_v2.0_xx      | Mobile & server   |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar)      |
+| Chinese and English ultra-lightweight PP-OCR model (9.4M)       | ch_ppocr_mobile_v2.0_xx      | Mobile & server   |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar)      |
-| Chinese and English general PP-OCR model (143.4M)               | ch_ppocr_server_v2.0_xx      | Server            |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_traingit.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar)  |  
+| Chinese and English general PP-OCR model (143.4M)               | ch_ppocr_server_v2.0_xx      | Server            |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_traingit.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar)  |
 For more model downloads (including multiple languages), please refer to [PP-OCR series model downloads](./doc/doc_en/models_list_en.md).
@@ -102,7 +102,6 @@ For a new language request, please refer to [Guideline for new language_requests
 - PP-OCR Industry Landing: from Training to Deployment
    - [PP-OCR Model and Configuration](./doc/doc_en/models_and_config_en.md)
        - [PP-OCR Model Download](./doc/doc_en/models_list_en.md)
-        - [Yml Configuration](./doc/doc_en/config_en.md)
        - [Python Inference for PP-OCR Model Library](./doc/doc_en/inference_ppocr_en.md)
    - [PP-OCR Training](./doc/doc_en/training_en.md)
        - [Text Detection](./doc/doc_en/detection_en.md)

--- a/README_ch.md
+++ b/README_ch.md
@@ -24,7 +24,7 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 **近期更新**
- PaddleOCR研发团队对最新发版内容技术深入解读，9月8日晚上20:15，[直播地址](https://live.bilibili.com/21689802)。
+- PaddleOCR研发团队对最新发版内容技术深入解读，9月8日晚上20:15，[课程回放](https://aistudio.baidu.com/aistudio/education/group/info/6758)。
 - 2021.9.7 发布PaddleOCR v2.3，发布[PP-OCRv2](#PP-OCRv2)，CPU推理速度相比于PP-OCR server提升220%；效果相比于PP-OCR mobile 提升7%。
 - 2021.8.3 发布PaddleOCR v2.2，新增文档结构分析[PP-Structure](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/ppstructure/README_ch.md)工具包，支持版面分析与表格识别（含Excel导出）。
 - 2021.6.29 [FAQ](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/doc/doc_ch/FAQ.md)新增5个高频问题，总数248个，每周一都会更新，欢迎大家持续关注。
@@ -81,9 +81,9 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 | 模型简介     | 模型名称     |推荐场景          | 检测模型 | 方向分类器 | 识别模型 |
 | ------------ | --------------- | ----------------|---- | ---------- | -------- |
-| 中英文超轻量PP-OCRv2模型（13.0M） |  ch_PP-OCRv2_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
+| 中英文超轻量PP-OCRv2模型（13.0M） |  ch_PP-OCRv2_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
-| 中英文超轻量PP-OCR mobile模型（9.4M） | ch_ppocr_mobile_v2.0_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar)      |
+| 中英文超轻量PP-OCR mobile模型（9.4M） | ch_ppocr_mobile_v2.0_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar)      |
-| 中英文通用PP-OCR server模型（143.4M）   |ch_ppocr_server_v2.0_xx|服务器端 |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)    |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar)    |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar)  |  
+| 中英文通用PP-OCR server模型（143.4M）   |ch_ppocr_server_v2.0_xx|服务器端 |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)    |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar)    |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar)  |
 更多模型下载（包括多语言），可以参考[PP-OCR 系列模型下载](./doc/doc_ch/models_list.md)
@@ -94,7 +94,6 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 - PP-OCR产业落地：从训练到部署
    - [PP-OCR模型与配置文件](./doc/doc_ch/models_and_config.md)
        - [PP-OCR模型下载](./doc/doc_ch/models_list.md)
-        - [配置文件内容与生成](./doc/doc_ch/config.md)
        - [PP-OCR模型库快速推理](./doc/doc_ch/inference_ppocr.md)
    - [PP-OCR模型训练](./doc/doc_ch/training.md)
        - [文本检测](./doc/doc_ch/detection.md)

--- a/deploy/lite/ocr_db_crnn.cc
+++ b/deploy/lite/ocr_db_crnn.cc
@@ -307,21 +307,10 @@ RunDetModel(std::shared_ptr<PaddlePredictor> predictor, cv::Mat img,
  return filter_boxes;
 }
-std::shared_ptr<PaddlePredictor> loadModel(std::string model_file, std::string power_mode, int num_threads) {
+std::shared_ptr<PaddlePredictor> loadModel(std::string model_file, int num_threads) {
  MobileConfig config;
  config.set_model_from_file(model_file);
-  if (power_mode == "LITE_POWER_HIGH"){
-      config.set_power_mode(LITE_POWER_HIGH);
-  } else {
-      if (power_mode == "LITE_POWER_LOW") {
-          config.set_power_mode(LITE_POWER_HIGH);
-      } else {
-          std::cerr << "Only support LITE_POWER_HIGH or LITE_POWER_HIGH." << std::endl;
-          exit(1);
-      }
-  }
  config.set_threads(num_threads);
  std::shared_ptr<PaddlePredictor> predictor =
@@ -391,7 +380,7 @@ void check_params(int argc, char **argv) {
  if (strcmp(argv[1], "det") == 0) {
      if (argc < 9){
        std::cerr << "[ERROR] usage:" << argv[0]
-                  << " det det_model num_threads batchsize power_mode img_dir det_config lite_benchmark_value" << std::endl;
+                  << " det det_model runtime_device num_threads batchsize img_dir det_config lite_benchmark_value" << std::endl;
        exit(1);
      }
  }
@@ -399,7 +388,7 @@ void check_params(int argc, char **argv) {
  if (strcmp(argv[1], "rec") == 0) {
      if (argc < 9){
        std::cerr << "[ERROR] usage:" << argv[0]
-                  << " rec rec_model num_threads batchsize power_mode img_dir key_txt lite_benchmark_value" << std::endl;
+                  << " rec rec_model runtime_device num_threads batchsize img_dir key_txt lite_benchmark_value" << std::endl;
        exit(1);
      }
  }
@@ -407,7 +396,7 @@ void check_params(int argc, char **argv) {
  if (strcmp(argv[1], "system") == 0) {
      if (argc < 12){
        std::cerr << "[ERROR] usage:" << argv[0]
-                  << " system det_model rec_model clas_model num_threads batchsize power_mode img_dir det_config key_txt lite_benchmark_value" << std::endl;
+                  << " system det_model rec_model clas_model runtime_device num_threads batchsize img_dir det_config key_txt lite_benchmark_value" << std::endl;
        exit(1);
      }
  }
@@ -417,15 +406,15 @@ void system(char **argv){
  std::string det_model_file = argv[2];
  std::string rec_model_file = argv[3];
  std::string cls_model_file = argv[4];
-  std::string precision = argv[5];
+  std::string runtime_device = argv[5];
-  std::string num_threads = argv[6];
+  std::string precision = argv[6];
-  std::string batchsize = argv[7];
+  std::string num_threads = argv[7];
-  std::string power_mode = argv[8];
+  std::string batchsize = argv[8];
  std::string img_dir = argv[9];
  std::string det_config_path = argv[10];
  std::string dict_path = argv[11];
-  if (strcmp(argv[5], "FP32") != 0 && strcmp(argv[5], "INT8") != 0) {
+  if (strcmp(argv[6], "FP32") != 0 && strcmp(argv[6], "INT8") != 0) {
      std::cerr << "Only support FP32 or INT8." << std::endl;
      exit(1);
  }
@@ -441,9 +430,9 @@ void system(char **argv){
  charactor_dict.insert(charactor_dict.begin(), "#"); // blank char for ctc
  charactor_dict.push_back(" ");
-  auto det_predictor = loadModel(det_model_file, power_mode, std::stoi(num_threads));
+  auto det_predictor = loadModel(det_model_file, std::stoi(num_threads));
-  auto rec_predictor = loadModel(rec_model_file, power_mode, std::stoi(num_threads));
+  auto rec_predictor = loadModel(rec_model_file, std::stoi(num_threads));
-  auto cls_predictor = loadModel(cls_model_file, power_mode, std::stoi(num_threads));
+  auto cls_predictor = loadModel(cls_model_file, std::stoi(num_threads));
  for (int i = 0; i < cv_all_img_names.size(); ++i) {
    std::cout << "The predict img: " << cv_all_img_names[i] << std::endl;
@@ -477,14 +466,14 @@ void system(char **argv){
 void det(int argc, char **argv) {
  std::string det_model_file = argv[2];
-  std::string precision = argv[3];
+  std::string runtime_device = argv[3];
-  std::string num_threads = argv[4];
+  std::string precision = argv[4];
-  std::string batchsize = argv[5];
+  std::string num_threads = argv[5];
-  std::string power_mode = argv[6];
+  std::string batchsize = argv[6];
  std::string img_dir = argv[7];
  std::string det_config_path = argv[8];
-  if (strcmp(argv[3], "FP32") != 0 && strcmp(argv[3], "INT8") != 0) {
+  if (strcmp(argv[4], "FP32") != 0 && strcmp(argv[4], "INT8") != 0) {
      std::cerr << "Only support FP32 or INT8." << std::endl;
      exit(1);
  }
@@ -495,7 +484,7 @@ void det(int argc, char **argv) {
  //// load config from txt file
  auto Config = LoadConfigTxt(det_config_path);
-  auto det_predictor = loadModel(det_model_file, power_mode, std::stoi(num_threads));
+  auto det_predictor = loadModel(det_model_file, std::stoi(num_threads));
  std::vector<double> time_info = {0, 0, 0};
  for (int i = 0; i < cv_all_img_names.size(); ++i) {
@@ -530,14 +519,11 @@ void det(int argc, char **argv) {
  if (strcmp(argv[9], "True") == 0) {
    AutoLogger autolog(det_model_file, 
-                       0,
+                       runtime_device,
-                       0,
-                       0,
                       std::stoi(num_threads),
                       std::stoi(batchsize), 
                       "dynamic", 
                       precision, 
-                       power_mode,
                       time_info, 
                       cv_all_img_names.size());
    autolog.report();
@@ -546,14 +532,14 @@ void det(int argc, char **argv) {
 void rec(int argc, char **argv) {
  std::string rec_model_file = argv[2];
-  std::string precision = argv[3];
+  std::string runtime_device = argv[3];
-  std::string num_threads = argv[4];
+  std::string precision = argv[4];
-  std::string batchsize = argv[5];
+  std::string num_threads = argv[5];
-  std::string power_mode = argv[6];
+  std::string batchsize = argv[6];
  std::string img_dir = argv[7];
  std::string dict_path = argv[8];
-  if (strcmp(argv[3], "FP32") != 0 && strcmp(argv[3], "INT8") != 0) {
+  if (strcmp(argv[4], "FP32") != 0 && strcmp(argv[4], "INT8") != 0) {
      std::cerr << "Only support FP32 or INT8." << std::endl;
      exit(1);
  }
@@ -565,7 +551,7 @@ void rec(int argc, char **argv) {
  charactor_dict.insert(charactor_dict.begin(), "#"); // blank char for ctc
  charactor_dict.push_back(" ");
-  auto rec_predictor = loadModel(rec_model_file, power_mode, std::stoi(num_threads));
+  auto rec_predictor = loadModel(rec_model_file, std::stoi(num_threads));
  std::shared_ptr<PaddlePredictor> cls_predictor;
@@ -603,14 +589,11 @@ void rec(int argc, char **argv) {
  // TODO: support autolog
  if (strcmp(argv[9], "True") == 0) {
    AutoLogger autolog(rec_model_file, 
-                       0,
+                       runtime_device,
-                       0,
-                       0,
                       std::stoi(num_threads),
                       std::stoi(batchsize), 
                       "dynamic", 
                       precision, 
-                       power_mode,
                       time_info, 
                       cv_all_img_names.size());
    autolog.report();

--- a/deploy/slim/prune/export_prune_model.py
+++ b/deploy/slim/prune/export_prune_model.py
@@ -30,7 +30,7 @@ from ppocr.modeling.architectures import build_model
 from ppocr.postprocess import build_post_process
 from ppocr.metrics import build_metric
-from ppocr.utils.save_load import init_model
+from ppocr.utils.save_load import load_model
 import tools.program as program
@@ -89,7 +89,7 @@ def main(config, device, logger, vdl_writer):
    logger.info(f"FLOPs after pruning: {flops}")
    # load pretrain model
-    pre_best_model_dict = init_model(config, model, logger, None)
+    load_model(config, model)
    metric = program.eval(model, valid_dataloader, post_process_class,
                          eval_class)
    logger.info(f"metric['hmean']: {metric['hmean']}")

--- a/deploy/slim/prune/sensitivity_anal.py
+++ b/deploy/slim/prune/sensitivity_anal.py
@@ -32,7 +32,7 @@ from ppocr.losses import build_loss
 from ppocr.optimizer import build_optimizer
 from ppocr.postprocess import build_post_process
 from ppocr.metrics import build_metric
-from ppocr.utils.save_load import init_model
+from ppocr.utils.save_load import load_model
 import tools.program as program
 dist.get_world_size()
@@ -94,7 +94,7 @@ def main(config, device, logger, vdl_writer):
    # build metric
    eval_class = build_metric(config['Metric'])
    # load pretrain model
-    pre_best_model_dict = init_model(config, model, logger, optimizer)
+    pre_best_model_dict = load_model(config, model, optimizer)
    logger.info('train dataloader has {} iters, valid dataloader has {} iters'.
                format(len(train_dataloader), len(valid_dataloader)))

--- a/deploy/slim/quantization/export_model.py
+++ b/deploy/slim/quantization/export_model.py
@@ -28,7 +28,7 @@ from paddle.jit import to_static
 from ppocr.modeling.architectures import build_model
 from ppocr.postprocess import build_post_process
-from ppocr.utils.save_load import init_model
+from ppocr.utils.save_load import load_model
 from ppocr.utils.logging import get_logger
 from tools.program import load_config, merge_config, ArgsParser
 from ppocr.metrics import build_metric
@@ -101,7 +101,7 @@ def main():
    quanter = QAT(config=quant_config)
    quanter.quantize(model)
-    init_model(config, model)
+    load_model(config, model)
    model.eval()
    # build metric

--- a/deploy/slim/quantization/quant.py
+++ b/deploy/slim/quantization/quant.py
@@ -37,7 +37,7 @@ from ppocr.losses import build_loss
 from ppocr.optimizer import build_optimizer
 from ppocr.postprocess import build_post_process
 from ppocr.metrics import build_metric
-from ppocr.utils.save_load import init_model
+from ppocr.utils.save_load import load_model
 import tools.program as program
 from paddleslim.dygraph.quant import QAT
@@ -137,7 +137,7 @@ def main(config, device, logger, vdl_writer):
    # build metric
    eval_class = build_metric(config['Metric'])
    # load pretrain model
-    pre_best_model_dict = init_model(config, model, logger, optimizer)
+    pre_best_model_dict = load_model(config, model, optimizer)
    logger.info('train dataloader has {} iters, valid dataloader has {} iters'.
                format(len(train_dataloader), len(valid_dataloader)))

--- a/deploy/slim/quantization/quant_kl.py
+++ b/deploy/slim/quantization/quant_kl.py
@@ -37,7 +37,7 @@ from ppocr.losses import build_loss
 from ppocr.optimizer import build_optimizer
 from ppocr.postprocess import build_post_process
 from ppocr.metrics import build_metric
-from ppocr.utils.save_load import init_model
+from ppocr.utils.save_load import load_model
 import tools.program as program
 import paddleslim
 from paddleslim.dygraph.quant import QAT

--- a/doc/banner.png
+++ b/doc/banner.png
--- a/doc/doc_ch/algorithm_overview.md
+++ b/doc/doc_ch/algorithm_overview.md
-<a name="算法介绍"></a>
+# 两阶段算法
-## 算法介绍
+- [两阶段算法](#-----)
+  * [1. 算法介绍](#1)
+    + [1.1 文本检测算法](#11)
+    + [1.2 文本识别算法](#12)
+  * [2. 模型训练](#2)
+  * [3. 模型推理](#3)
+<a name="1"></a>
+## 1. 算法介绍
 本文给出了PaddleOCR已支持的文本检测算法和文本识别算法列表，以及每个算法在**英文公开数据集**上的模型和指标，主要用于算法简介和算法性能对比，更多包括中文在内的其他数据集上的模型请参考[PP-OCR v2.0 系列模型下载](./models_list.md)。
- [1.文本检测算法](#文本检测算法)
+<a name="11"></a>
- [2.文本识别算法](#文本识别算法)
-<a name="文本检测算法"></a>
+### 1.1 文本检测算法
-### 1.文本检测算法
 PaddleOCR开源的文本检测算法列表：
- [x]  DB([paper]( https://arxiv.org/abs/1911.08947))（ppocr推荐）
+- [x]  DB([paper]( https://arxiv.org/abs/1911.08947)) [2]（ppocr推荐）
- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))
+- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))[1]
- [x]  SAST([paper](https://arxiv.org/abs/1908.05498))
+- [x]  SAST([paper](https://arxiv.org/abs/1908.05498))[4]
 - [x]  PSENet([paper](https://arxiv.org/abs/1903.12473v2)）
 在ICDAR2015文本检测公开数据集上，算法效果如下：
 |模型|骨干网络|precision|recall|Hmean|下载链接|
 | --- | --- | --- | --- | --- | --- |
-|EAST|ResNet50_vd|85.80%|86.71%|86.25%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)|
+|EAST|ResNet50_vd|85.80%|86.71%|86.25%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)|
-|EAST|MobileNetV3|79.42%|80.64%|80.03%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_east_v2.0_train.tar)|
+|EAST|MobileNetV3|79.42%|80.64%|80.03%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_east_v2.0_train.tar)|
-|DB|ResNet50_vd|86.41%|78.72%|82.38%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)|
+|DB|ResNet50_vd|86.41%|78.72%|82.38%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)|
-|DB|MobileNetV3|77.29%|73.08%|75.12%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar)|
+|DB|MobileNetV3|77.29%|73.08%|75.12%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar)|
-|SAST|ResNet50_vd|91.39%|83.77%|87.42%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)|
+|SAST|ResNet50_vd|91.39%|83.77%|87.42%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)|
-|PSE|ResNet50_vd|85.81%|79.53%|82.55%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)|
+|PSE|ResNet50_vd|85.81%|79.53%|82.55%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)|
-|PSE|MobileNetV3|82.20%|70.48%|75.89%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)|
+|PSE|MobileNetV3|82.20%|70.48%|75.89%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)|
 在Total-text文本检测公开数据集上，算法效果如下：
 |模型|骨干网络|precision|recall|Hmean|下载链接|
 | --- | --- | --- | --- | --- | --- |
-|SAST|ResNet50_vd|89.63%|78.44%|83.66%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)|
+|SAST|ResNet50_vd|89.63%|78.44%|83.66%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)|
 **说明：** SAST模型训练额外加入了icdar2013、icdar2017、COCO-Text、ArT等公开数据集进行调优。PaddleOCR用到的经过整理格式的英文公开数据集下载：
 * [百度云地址](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (提取码: 2bpi)
 * [Google Drive下载地址](https://drive.google.com/drive/folders/1ll2-XEVyCQLpJjawLDiRlvo_i4BqHCJe?usp=sharing)
-PaddleOCR文本检测算法的训练和使用请参考文档教程中[模型训练/评估中的文本检测部分](./detection.md)。
+<a name="12"></a>
-<a name="文本识别算法"></a>
+### 1.2 文本识别算法
-### 2.文本识别算法
 PaddleOCR基于动态图开源的文本识别算法列表：
- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))（ppocr推荐）
+- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))[7]（ppocr推荐）
- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))
+- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))[10]
- [x]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))
+- [x]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11]
- [x]  RARE([paper](https://arxiv.org/abs/1603.03915v1))
+- [x]  RARE([paper](https://arxiv.org/abs/1603.03915v1))[12]
- [x]  SRN([paper](https://arxiv.org/abs/2003.12294))
+- [x]  SRN([paper](https://arxiv.org/abs/2003.12294))[5]
- [x]  NRTR([paper](https://arxiv.org/abs/1806.00926v2))
+- [x]  NRTR([paper](https://arxiv.org/abs/1806.00926v2))[13]
 - [x]  SAR([paper](https://arxiv.org/abs/1811.00751v2))
- [x]  SEED([paper](https://arxiv.org/pdf/2005.10977.pdf))
+- [x] SEED([paper](https://arxiv.org/pdf/2005.10977.pdf))
-参考[DTRB](https://arxiv.org/abs/1904.01906) 文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
+参考[DTRB][3](https://arxiv.org/abs/1904.01906)文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
 |模型|骨干网络|Avg Accuracy|模型存储命名|下载链接|
 |---|---|---|---|---|
-|Rosetta|Resnet34_vd|80.9%|rec_r34_vd_none_none_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_none_ctc_v2.0_train.tar)|
+|Rosetta|Resnet34_vd|80.9%|rec_r34_vd_none_none_ctc|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_none_ctc_v2.0_train.tar)|
-|Rosetta|MobileNetV3|78.05%|rec_mv3_none_none_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_none_ctc_v2.0_train.tar)|
+|Rosetta|MobileNetV3|78.05%|rec_mv3_none_none_ctc|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_none_ctc_v2.0_train.tar)|
-|CRNN|Resnet34_vd|82.76%|rec_r34_vd_none_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_bilstm_ctc_v2.0_train.tar)|
+|CRNN|Resnet34_vd|82.76%|rec_r34_vd_none_bilstm_ctc|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_bilstm_ctc_v2.0_train.tar)|
-|CRNN|MobileNetV3|79.97%|rec_mv3_none_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_bilstm_ctc_v2.0_train.tar)|
+|CRNN|MobileNetV3|79.97%|rec_mv3_none_bilstm_ctc|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_bilstm_ctc_v2.0_train.tar)|
-|StarNet|Resnet34_vd|84.44%|rec_r34_vd_tps_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_ctc_v2.0_train.tar)|
+|StarNet|Resnet34_vd|84.44%|rec_r34_vd_tps_bilstm_ctc|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_ctc_v2.0_train.tar)|
-|StarNet|MobileNetV3|81.42%|rec_mv3_tps_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_ctc_v2.0_train.tar)|
+|StarNet|MobileNetV3|81.42%|rec_mv3_tps_bilstm_ctc|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_ctc_v2.0_train.tar)|
-|RARE|MobileNetV3|82.5%|rec_mv3_tps_bilstm_att |[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_att_v2.0_train.tar)|
+|RARE|MobileNetV3|82.5%|rec_mv3_tps_bilstm_att |[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_att_v2.0_train.tar)|
-|RARE|Resnet34_vd|83.6%|rec_r34_vd_tps_bilstm_att |[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_att_v2.0_train.tar)|
+|RARE|Resnet34_vd|83.6%|rec_r34_vd_tps_bilstm_att |[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_att_v2.0_train.tar)|
-|SRN|Resnet50_vd_fpn| 88.52% | rec_r50fpn_vd_none_srn | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r50_vd_srn_train.tar) |
+|SRN|Resnet50_vd_fpn| 88.52% | rec_r50fpn_vd_none_srn | [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r50_vd_srn_train.tar) |
-|NRTR|NRTR_MTB| 84.3% | rec_mtb_nrtr | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) |
+|NRTR|NRTR_MTB| 84.3% | rec_mtb_nrtr | [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) |
-|SAR|Resnet31| 87.2% | rec_r31_sar | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_train.tar) |
+|SAR|Resnet31| 87.2% | rec_r31_sar | [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_train.tar) |
-|SEED| Aster_Resnet | 85.2% | rec_resnet_stn_bilstm_att | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_resnet_stn_bilstm_att.tar)|
+|SEED|Aster_Resnet| 85.2% | rec_resnet_stn_bilstm_att | [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_resnet_stn_bilstm_att.tar) |
-PaddleOCR文本识别算法的训练和使用请参考文档教程中[模型训练/评估中的文本识别部分](./recognition.md)。
+<a name="2"></a>
+## 2. 模型训练
+PaddleOCR文本检测算法的训练和使用请参考文档教程中[模型训练/评估中的文本检测部分](./detection.md)。文本识别算法的训练和使用请参考文档教程中[模型训练/评估中的文本识别部分](./recognition.md)。
+<a name="3"></a>
+## 3. 模型推理
+上述模型中除PP-OCR系列模型以外，其余模型仅支持基于Python引擎的推理，具体内容可参考[基于Python预测引擎推理](./inference.md)
--- a/doc/doc_ch/angle_class.md
+++ b/doc/doc_ch/angle_class.md
@@ -11,7 +11,7 @@
 ## 1. 方法介绍
 文本方向分类器主要用于图片非0度的场景下，在这种场景下需要对图片里检测到的文本行进行一个转正的操作。在PaddleOCR系统内，
 文字检测之后得到的文本行图片经过仿射变换之后送入识别模型，此时只需要对文字进行一个0和180度的角度分类，因此PaddleOCR内置的
-文字角度分类器**只支持了0和180度的分类**。如果想支持更多角度，可以自己修改算法进行支持。
+文本方向分类器**只支持了0和180度的分类**。如果想支持更多角度，可以自己修改算法进行支持。
 0和180度数据样本例子：
@@ -72,8 +72,6 @@ train/cls/train/word_002.jpg   180
 <a name="启动训练"></a>
 ## 3. 启动训练
-### 启动训练
 将准备好的txt文件和图片文件夹路径分别写入配置文件的 `Train/Eval.dataset.label_file_list` 和 `Train/Eval.dataset.data_dir` 字段下，`Train/Eval.dataset.data_dir`字段下的路径和文件里记载的图片名构成了图片的绝对路径。
 PaddleOCR提供了训练脚本、评估脚本和预测脚本。

--- a/doc/doc_ch/config.md
+++ b/doc/doc_ch/config.md
@@ -36,10 +36,10 @@
 |      pretrained_model    |    设置加载预训练模型路径      |  ./pretrain_models/CRNN/best_accuracy  |  \          |
 |      checkpoints         |    加载模型参数路径            |       None        |    用于中断后加载参数继续训练 |
 |      use_visualdl  |    设置是否启用visualdl进行可视化log展示 |          False        |    [教程地址](https://www.paddlepaddle.org.cn/paddle/visualdl) |
-|      infer_img            |    设置预测图像路径或文件夹路径     |       ./infer_img | \|
+|      infer_img            |    设置预测图像路径或文件夹路径     |       ./infer_img | \||
-|      character_dict_path |    设置字典路径            |  ./ppocr/utils/ppocr_keys_v1.txt  |    如果为空，则默认使用小写字母+数字作为字典                 |
+|      character_dict_path |    设置字典路径            |  ./ppocr/utils/ppocr_keys_v1.txt  | 如果为空，则默认使用小写字母+数字作为字典 |
 |      max_text_length     |    设置文本最大长度        |       25          |                \                 |
-|      use_space_char     |    设置是否识别空格             |        True      |                           |
+|      use_space_char     |    设置是否识别空格             |        True      |          \|               |
 |      label_list          |    设置方向分类器支持的角度       |    ['0','180']    |     仅在方向分类器中生效 |
 |      save_res_path          |    设置检测模型的结果保存地址       |    ./output/det_db/predicts_db.txt    |     仅在检测模型中生效 |
@@ -176,7 +176,7 @@ PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi
    --dict {path/of/dict} \             # 字典文件路径
    -o Global.use_gpu=False             # 是否使用gpu
    ...
    ```
 意大利文由拉丁字母组成，因此执行完命令后会得到名为 rec_latin_lite_train.yml 的配置文件。
@@ -191,21 +191,21 @@ PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi
      epoch_num: 500
      ...
      character_dict_path:  {path/of/dict} # 字典文件所在路径
   Train:
      dataset:
        name: SimpleDataSet
        data_dir: train_data/ # 数据存放根目录
        label_file_list: ["./train_data/train_list.txt"] # 训练集label路径
      ...
   Eval:
      dataset:
        name: SimpleDataSet
        data_dir: train_data/ # 数据存放根目录
        label_file_list: ["./train_data/val_list.txt"] # 验证集label路径
      ...
   ```
 目前PaddleOCR支持的多语言算法有：
@@ -214,12 +214,12 @@ PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi
 | :--------: |  :-------:   | :-------:  |   :-------:   |   :-----:   |  :-----:   | :-----:  |
 | rec_chinese_cht_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 中文繁体  |
 | rec_en_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 英语（区分大小写）   |
-| rec_french_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 法语 |  
+| rec_french_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 法语 |
 | rec_ger_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 德语   |
 | rec_japan_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 日语  |
 | rec_korean_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 韩语  |
 | rec_latin_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 拉丁字母  |
-| rec_arabic_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 阿拉伯字母 |  
+| rec_arabic_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 阿拉伯字母 |
 | rec_cyrillic_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 斯拉夫字母  |
 | rec_devanagari_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 梵文字母  |

--- a/doc/doc_ch/detection.md
+++ b/doc/doc_ch/detection.md
-# 目录
+# 文字检测
- [1. 文字检测](#1-----)
-  * [1.1 数据准备](#11-----)
-  * [1.2 下载预训练模型](#12--------)
-  * [1.3 启动训练](#13-----)
-  * [1.4 断点训练](#14-----)
-  * [1.5 更换Backbone 训练](#15---backbone---)
-  * [1.6 指标评估](#16-----)
-  * [1.7 测试检测效果](#17-------)
-  * [1.8 转inference模型测试](#18--inference----)
- [2. FAQ](#2-faq)
-<a name="1-----"></a>
-# 1. 文字检测
 本节以icdar2015数据集为例，介绍PaddleOCR中检测模型训练、评估、测试的使用方式。
+- [1. 准备数据和模型](#1--------)
+  * [1.1 数据准备](#11-----)
+  * [1.2 下载预训练模型](#12--------)
+- [2. 开始训练](#2-----)
+  * [2.1 启动训练](#21-----)
+  * [2.2 断点训练](#22-----)
+  * [2.3 更换Backbone 训练](#23---backbone---)
+- [3. 模型评估与预测](#3--------)
+  * [3.1 指标评估](#31-----)
+  * [3.2 测试检测效果](#32-------)
+- [4. 模型导出与预测](#4--------)
+- [5. FAQ](#5-faq)
+<a name="1--------"></a>
+# 1. 准备数据和模型
 <a name="11-----"></a>
 ## 1.1 数据准备
@@ -83,8 +85,11 @@ wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dyg
 wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_ssld_pretrained.pdparams
 ```
-<a name="13-----"></a>
+<a name="2-----"></a>
-## 1.3 启动训练
+# 2. 开始训练
+<a name="21-----"></a>
+## 2.1 启动训练
 *如果您安装的是cpu版本，请将配置文件中的 `use_gpu` 字段修改为false*
@@ -119,8 +124,8 @@ python3 tools/train.py -c configs/det/det_mv3_db.yml \
     Global.use_amp=True Global.scale_loss=1024.0 Global.use_dynamic_loss_scaling=True
 ```
-<a name="14-----"></a>
+<a name="22-----"></a>
-## 1.4 断点训练
+## 2.2 断点训练
 如果训练程序中断，如果希望加载训练中断的模型从而恢复训练，可以通过指定Global.checkpoints指定要加载的模型路径：
 ```shell
@@ -129,8 +134,8 @@ python3 tools/train.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=./you
 **注意**：`Global.checkpoints`的优先级高于`Global.pretrained_model`的优先级，即同时指定两个参数时，优先加载`Global.checkpoints`指定的模型，如果`Global.checkpoints`指定的模型路径有误，会加载`Global.pretrained_model`指定的模型。
-<a name="15---backbone---"></a>
+<a name="23---backbone---"></a>
-## 1.5 更换Backbone 训练
+## 2.3 更换Backbone 训练
 PaddleOCR将网络划分为四部分，分别在[ppocr/modeling](../../ppocr/modeling)下。 进入网络的数据将按照顺序(transforms->backbones->
 necks->heads)依次通过这四个部分。
@@ -177,8 +182,11 @@ args1: args1
 **注意**：如果要更换网络的其他模块，可以参考[文档](./add_new_algorithm.md)。
-<a name="16-----"></a>
+<a name="3--------"></a>
-## 1.6 指标评估
+# 3. 模型评估与预测
+<a name="31-----"></a>
+## 3.1 指标评估
 PaddleOCR计算三个OCR检测相关的指标，分别是：Precision、Recall、Hmean（F-Score）。
@@ -190,8 +198,8 @@ python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.checkpoints="{pat
 * 注：`box_thresh`、`unclip_ratio`是DB后处理所需要的参数，在评估EAST模型时不需要设置
-<a name="17-------"></a>
+<a name="32-------"></a>
-## 1.7 测试检测效果
+## 3.2 测试检测效果
 测试单张图像的检测效果
 ```shell
@@ -208,8 +216,8 @@ python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./
 python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy"
 ```
-<a name="18--inference----"></a>
+<a name="4--------"></a>
-## 1.8 转inference模型测试
+# 4. 模型导出与预测
 inference 模型（`paddle.jit.save`保存的模型）
 一般是模型训练，把模型结构和模型参数保存在文件中的固化模型，多用于预测部署场景。
@@ -231,10 +239,11 @@ python3 tools/infer/predict_det.py --det_algorithm="DB" --det_model_dir="./outpu
 python3 tools/infer/predict_det.py --det_algorithm="EAST" --det_model_dir="./output/det_db_inference/" --image_dir="./doc/imgs/" --use_gpu=True
 ```
-<a name="2"></a>
+<a name="5-faq"></a>
-# 2. FAQ
+# 5. FAQ
 Q1: 训练模型转inference 模型之后预测效果不一致？
 **A**：此类问题出现较多，问题多是trained model预测时候的预处理、后处理参数和inference model预测的时候的预处理、后处理参数不一致导致的。以det_mv3_db.yml配置文件训练的模型为例，训练模型、inference模型预测结果不一致问题解决方式如下：
 - 检查[trained model预处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L116)，和[inference model的预测预处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/predict_det.py#L42)函数是否一致。算法在评估的时候，输入图像大小会影响精度，为了和论文保持一致，训练icdar15配置文件中将图像resize到[736, 1280]，但是在inference model预测的时候只有一套默认参数，会考虑到预测速度问题，默认限制图像最长边为960做resize的。训练模型预处理和inference模型的预处理函数位于[ppocr/data/imaug/operators.py](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/ppocr/data/imaug/operators.py#L147)
 - 检查[trained model后处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L51)，和[inference 后处理参数](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/utility.py#L50)是否一致。