PaddleOCR/mkdocs.yml

site_name: PaddleOCR 文档
site_url: https://paddlepaddle.github.io/PaddleOCR/
site_author: PaddleOCR PMC
site_description:
  Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

repo_name: PaddlePaddle/PaddleOCR
repo_url: https://github.com/PaddlePaddle/PaddleOCR

copyright: Copyright © 2024 Maintained by PaddleOCR PMC.

edit_uri: edit/main/docs/

theme:
  name: material
  logo: ./static/images/logo.jpg
  favicon: ./static/images/logo.jpg
  custom_dir: overrides
  features:
    - announce.dismiss
    - content.tooltips
    - content.code.copy
    - content.tabs.link
    - content.footnote.tooltips
    - content.action.edit
    - content.action.view
    - navigation.expand  # 默认打开所有的字节
    - navigation.tabs # 顶级索引被作为tab
    - navigation.tabs.sticky # tab始终可见
    - navigation.top # 开启顶部导航栏
    - navigation.tracking # 导航栏跟踪
    - navigation.footer
    - navigation.indexes
    - search.highlight # 搜索高亮
    - search.share # 搜索分享
    - search.suggest # 搜索建议
    - toc.follow # 目录跟踪-页面右侧的小目录

  palette:
    - media: "(prefers-color-scheme: light)" # 浅色
      scheme: default
      primary: indigo
      accent: indigo
      toggle:
        icon: material/brightness-7
        name: Switch to dark mode
    - media: "(prefers-color-scheme: dark)" # 深色
      scheme: slate
      primary: black
      accent: indigo
      toggle:
        icon: material/brightness-4
        name: Switch to system preference

  icon:
    logo: logo
    previous: fontawesome/solid/angle-left
    next: fontawesome/solid/angle-right
    repo: fontawesome/brands/github
    edit: material/pencil
    view: material/eye
    tag:
      default-tag: fontawesome/solid/tag
      hardware-tag: fontawesome/solid/microchip
      software-tag: fontawesome/solid/laptop-code
    admonition:
      note: octicons/tag-16
      abstract: octicons/checklist-16
      info: octicons/info-16
      tip: octicons/squirrel-16
      success: octicons/check-16
      question: octicons/question-16
      warning: octicons/alert-16
      failure: octicons/x-circle-16
      danger: octicons/zap-16
      bug: octicons/bug-16
      example: octicons/beaker-16
      quote: octicons/quote-16

plugins:
  - tags
  - offline
  - search:
      separator: '[\s\u200b\-_,:!=\[\: )"`/]+|\.(?!\d)|&[lg]t;|(?!\b)(?=[A-Z][a-z])'
  - i18n:
      docs_structure: suffix
      fallback_to_default: true
      reconfigure_material: true
      reconfigure_search: true
      languages:
        - locale: zh
          name: 简体中文
          default: true
          build: true
        - locale: en
          name: English
          site_name: PaddleOCR Documentation
          link: /en/
          nav_translations:
            Home: Home
            快速开始: Quick Start
            近期更新: Recently Update
            低代码全流程开发: All-in-One Development
            概述: Overview
            模型: Model
            PP-OCR 文本检测识别: PP-OCR
            快速安装: Quick Installation
            效果展示: Visualization
            运行环境: Environment Preparation
            模型库: Model
            模型训练: Model Training
            基本概念: Basic concepts
            文本检测: Text Detection
            文本识别: Text Recognition
            文本方向分类器: Text Angle Classification
            关键信息提取: Key Information Extraction
            模型微调: Fine-tune
            训练tricks: Training Tricks
            模型压缩: Model Compression
            模型量化: Model Quantization
            模型裁剪: Model Prune
            知识蒸馏: Knowledge Distillation
            推理部署: Model Deploy
            基于Python预测引擎推理: Python Inference
            基于C++预测引擎推理: CPP Inference
            Visual Studio 2019 Community CMake 编译指南: Visual Studio 2019 Community CMake Compilation Guide
            服务化部署: Sever Deployment
            Jetson部署: Jetson Deployment
            端侧部署: Device-side Deployment
            网页前端部署: Paddle.js Web Deployment
            Paddle2ONNX模型转化与预测: Paddle2ONNX
            云上飞桨部署工具: Paddle Cloud
            Benchmark: Benchmark
            博客: Blog
            paddleocr package使用说明: Paddleocr Package Instructions
            多语言模型: Multi-language model
            动手学OCR: Dive into OCR
            切片操作: Slice
            PaddleOCR模型推理参数解释: PaddleOCR Model Inference Parameter Explanation
            分布式训练: Distributed training
            项目克隆: Project Clone
            配置文件内容与生成: Configuration
            如何生产自定义超轻量模型？: How To Make Your own lightweight OCR model?
            PP-Structure文档分析: PP-Structure
            版面分析: Layout Analysis
            版面恢复: Recovery To Doc
            表格识别: Table Recognition
            返回识别位置: Return Recognition Location
            怎样完成基于图像数据的信息抽取任务: Key Information Extraction Pipeline
            前沿算法与模型: Academic Algorithms
            文本检测算法: Text Detection Algorithms
            DB与DB++: DB and DB++
            文本识别算法: Text Recognition Algorithms
            文本超分辨率算法: Text Super-Resolution Algorithm
            公式识别算法: Formulat Recognition
            端到端OCR算法: End-to-End OCR Algorithms
            表格识别算法: Table Recognition Algorithms
            关键信息抽取算法: Key Information Extraction Algorithms
            使用PaddleOCR架构添加新算法: Add new algorithms
            场景应用: Applications
            数据标注与合成: Data Annotation and Synthesis
            其它数据标注工具: Other data annotation tools
            其它数据合成工具: Others data synthesis tools
            数据集: Datasets
            通用中英文OCR数据集: General Chinese and English OCR dataset
            手写中文OCR数据集: Handwritten Chinese OCR Dataset
            垂类多语言OCR数据集: Vertical multi-language OCR dataset
            版面分析数据集: Layout Analysis Dataset
            表格识别数据集: Table recognition dataset
            关键信息提取数据集: Key Information Extraction Dataset
            FAQ: FAQ
            社区: Community
            社区贡献: Community Contribution
            附录: Appendix
        - locale: ja
          name: 日本語
          site_name: PaddleOCR ドキュメント
          link: /ja/
          nav_translations:
            Home: トップページ
        - locale: ru
          name: Pу́сский язы́к
          site_name: Документация PaddleOCR
          link: /ru/
          nav_translations:
            Home: Главная страница
        - locale: hi
          name: हिन्दी
          site_name: पैडलओसीआर दस्तावेज़ीकरण
          link: /hi/
          nav_translations:
            Home: घर पृष्ठ
        - locale: ko
          name: 한국인
          site_name: PaddleOCR 문서
          link: /ko/
          nav_translations:
            Home: 첫 페이지
        - locale: "null"
          name: Help translating
          build: false
          fixed_link: "https://github.com/PaddlePaddle/PaddleOCR/discussions/13374"
  - git-committers:
      repository: PaddlePaddle/PaddleOCR
      branch: main
      token: !!python/object/apply:os.getenv ["MKDOCS_GIT_COMMITTERS_APIKEY"]
  - git-revision-date-localized:
      fallback_to_build_date: false
      enable_creation_date: true

markdown_extensions:
  - abbr
  - attr_list
  - pymdownx.snippets
  - pymdownx.critic
  - pymdownx.caret
  - pymdownx.keys
  - pymdownx.mark
  - pymdownx.tilde
  - footnotes
  - def_list
  - md_in_html
  - pymdownx.tasklist:
      custom_checkbox: true
  - toc:
      permalink: true
  - pymdownx.superfences:
      custom_fences:
        - name: mermaid
          class: mermaid
          format: !!python/name:pymdownx.superfences.fence_code_format
  - pymdownx.emoji:
      emoji_index: !!python/name:material.extensions.emoji.twemoji
      emoji_generator: !!python/name:material.extensions.emoji.to_svg
  - pymdownx.highlight:
        anchor_linenums: true
        line_spans: __span
        pygments_lang_class: true
  - pymdownx.inlinehilite
  - pymdownx.tabbed:
      alternate_style: true
  - admonition
  - pymdownx.details
  - pymdownx.superfences
  - pymdownx.arithmatex:
      generic: true

extra:
  social:
    - icon: fontawesome/brands/github
      link: https://github.com/PaddlePaddle/PaddleOCR
    - icon: fontawesome/brands/python
      link: https://pypi.org/project/paddleocr/
  version:
    provider: mike

extra_javascript:
  - javascripts/katex.min.js
  - https://unpkg.com/katex@0/dist/katex.min.js
  - https://unpkg.com/katex@0/dist/contrib/auto-render.min.js

extra_css:
  - https://unpkg.com/katex@0/dist/katex.min.css

nav:
  - Home: index.md
  - 快速开始: quick_start.md
  - 近期更新: update.md
  - 低代码全流程开发:
      - 概述: paddlex/overview.md
      - 快速开始: paddlex/quick_start.md
  - 模型:
    - 概览: model/index.md
    - 多硬件安装飞桨:
      - 多硬件安装飞桨: model/hardware/install_other_devices.md
      - 支持硬件列表: model/hardware/supported_models.md
  - 推理部署:
    - 概述: infer_deploy/index.md
    - 基于Python预测引擎推理: infer_deploy/python_infer.md
    - 基于C++预测引擎推理: infer_deploy/cpp_infer.md
    - Visual Studio 2019 Community CMake 编译指南: infer_deploy/windows_vs2019_build.md
    - 服务化部署: infer_deploy/paddle_server.md
    - Android部署: infer_deploy/android_demo.md
    - Jetson部署: infer_deploy/Jetson_infer.md
    - 端侧部署: infer_deploy/lite.md
    - 网页前端部署: infer_deploy/paddle_js.md
    - Paddle2ONNX模型转化与预测: infer_deploy/paddle2onnx.md
    - 云上飞桨部署工具: infer_deploy/paddle_cloud.md
    - Benchmark: infer_deploy/benchmark.md
  - PP-OCR 文本检测识别:
    - 概述: ppocr/overview.md
    - 快速开始: ppocr/quick_start.md
    - 快速安装: ppocr/installation.md
    - 效果展示: ppocr/visualization.md
    - 运行环境: ppocr/environment.md
    - 模型库: ppocr/model_list.md
    - 模型训练:
      - 基本概念: ppocr/model_train/training.md
      - 文本检测: ppocr/model_train/detection.md
      - 文本识别: ppocr/model_train/recognition.md
      - 文本方向分类器: ppocr/model_train/angle_class.md
      - 关键信息提取: ppocr/model_train/kie.md
      - 模型微调: ppocr/model_train/finetune.md
      - 训练tricks: ppocr/model_train/tricks.md
    - 模型压缩:
      - 模型量化: ppocr/model_compress/quantization.md
      - 模型裁剪: ppocr/model_compress/prune.md
      - 知识蒸馏: ppocr/model_compress/knowledge_distillation.md
    - 博客:
      - PP-OCRv3技术报告: ppocr/blog/PP-OCRv3_introduction.md
      - PP-OCRv4技术报告: ppocr/blog/PP-OCRv4_introduction.md
      - paddleocr package使用说明: ppocr/blog/whl.md
      - 多语言模型: ppocr/blog/multi_languages.md
      - 动手学OCR: ppocr/blog/ocr_book.md
      - Enhanced CTC Loss: ppocr/blog/enhanced_ctc_loss.md
      - 切片操作: ppocr/blog/slice.md
      - PaddleOCR模型推理参数解释: ppocr/blog/inference_args.md
      - 分布式训练: ppocr/blog/distributed_training.md
      - 项目克隆: ppocr/blog/clone.md
      - 配置文件内容与生成: ppocr/blog/config.md
      - 如何生产自定义超轻量模型？: ppocr/blog/customize.md
  - PP-Structure文档分析:
    - 概述: ppstructure/overview.md
    - 快速开始: ppstructure/quick_start.md
    - 模型库: ppstructure/models_list.md
    - 模型训练:
      - 基本概念: ppstructure/model_train/training.md
      - 版面分析: ppstructure/model_train/train_layout.md
      - 表格识别: ppstructure/model_train/train_table.md
      - 版面恢复: ppstructure/model_train/recovery_to_doc.md
      - 关键信息提取: ppstructure/model_train/train_kie.md
    - 推理部署:
      - 概述: ppstructure/infer_deploy/index.md
      - 基于Python预测引擎推理: ppstructure/infer_deploy/python_infer.md
      - 基于C++预测引擎推理: ppstructure/infer_deploy/cpp_infer.md
      - 服务化部署: ppstructure/infer_deploy/paddle_server.md
    - 博客:
      - 返回识别位置: ppstructure/blog/return_word_pos.md
      - 怎样完成基于图像数据的信息抽取任务: ppstructure/blog/how_to_do_kie.md
  - 前沿算法与模型:
    - 概述: algorithm/overview.md
    - 文本检测算法:
      - DB与DB++: algorithm/text_detection/algorithm_det_db.md
      - EAST: algorithm/text_detection/algorithm_det_east.md
      - SAST: algorithm/text_detection/algorithm_det_sast.md
      - PSENet: algorithm/text_detection/algorithm_det_psenet.md
      - FCENet: algorithm/text_detection/algorithm_det_fcenet.md
      - DRRG: algorithm/text_detection/algorithm_det_drrg.md
      - CT: algorithm/text_detection/algorithm_det_ct.md
    - 文本识别算法:
      - CRNN: algorithm/text_recognition/algorithm_rec_crnn.md
      - Rosetta: algorithm/text_recognition/algorithm_rec_rosetta.md
      - STAR-Net: algorithm/text_recognition/algorithm_rec_starnet.md
      - RARE: algorithm/text_recognition/algorithm_rec_rare.md
      - SRN: algorithm/text_recognition/algorithm_rec_srn.md
      - NRTR: algorithm/text_recognition/algorithm_rec_nrtr.md
      - SAR: algorithm/text_recognition/algorithm_rec_sar.md
      - SEED: algorithm/text_recognition/algorithm_rec_seed.md
      - SVTR: algorithm/text_recognition/algorithm_rec_svtr.md
      - SVTRv2: algorithm/text_recognition/algorithm_rec_svtrv2.md
      - ViTSTR: algorithm/text_recognition/algorithm_rec_vitstr.md
      - ABINet: algorithm/text_recognition/algorithm_rec_abinet.md
      - VisionLAN: algorithm/text_recognition/algorithm_rec_visionlan.md
      - SPIN: algorithm/text_recognition/algorithm_rec_spin.md
      - RobustScanner: algorithm/text_recognition/algorithm_rec_robustscanner.md
      - RFL: algorithm/text_recognition/algorithm_rec_rfl.md
      - ParseQ: algorithm/text_recognition/algorithm_rec_parseq.md
      - CPPD: algorithm/text_recognition/algorithm_rec_cppd.md
      - SATRN: algorithm/text_recognition/algorithm_rec_satrn.md
    - 文本超分辨率算法:
      - Text Gestalt: algorithm/super_resolution/algorithm_sr_gestalt.md
      - Text Telescope: algorithm/super_resolution/algorithm_sr_telescope.md
    - 公式识别算法:
      - CAN: algorithm/formula_recognition/algorithm_rec_can.md
      - LaTeX-OCR: algorithm/formula_recognition/algorithm_rec_latex_ocr.md
      - UniMERNet: algorithm/formula_recognition/algorithm_rec_unimernet.md
      - PP-FormulaNet: algorithm/formula_recognition/algorithm_rec_ppformulanet.md
    - 端到端OCR算法:
      - PGNet: algorithm/end_to_end/algorithm_e2e_pgnet.md
    - 表格识别算法:
      - TableMaster: algorithm/table_recognition/algorithm_table_master.md
      - TableSLANet: algorithm/table_recognition/algorithm_table_slanet.md
    - 关键信息抽取算法:
      - VI-LayoutXLM: algorithm/kie/algorithm_kie_vi_layoutxlm.md
      - LayoutLM: algorithm/kie/algorithm_kie_layoutxlm.md
      # - LayoutLMv2: algorithm/kie/algorithm_kie_layoutxlm.md
      # - LayoutXLM: algorithm/kie/algorithm_kie_layoutxlm.md
      - SDMGR: algorithm/kie/./algorithm_kie_sdmgr.md
    - 使用PaddleOCR架构添加新算法: algorithm/add_new_algorithm.md
  - 场景应用:
    - 概述: applications/overview.md
    - 通用:
      - 高精度中文场景文本识别模型SVTR: applications/高精度中文识别模型.md
      - 手写体识别: applications/手写文字识别.md
    - 制造:
      - 数码管识别: applications/光功率计数码管字符识别.md
      - 液晶屏读数识别: applications/液晶屏读数识别.md
      - 包装生产日期: applications/包装生产日期识别.md
      - PCB文字识别: applications/PCB字符识别.md
    - 金融:
      - 表单VQA: applications/多模态表单识别.md
      - 增值税发票: applications/发票关键信息抽取.md
      - 印章检测与识别: applications/印章弯曲文字识别.md
      - 通用卡证识别: applications/快速构建卡证类OCR.md
      - 合同比对: applications/扫描合同关键信息提取.md
    - 交通:
      - 车牌识别: applications/轻量级车牌识别.md
  - 数据标注与合成:
    - 概述: data_anno_synth/overview.md
    - 其它数据标注工具: data_anno_synth/data_annotation.md
    - 其它数据合成工具: data_anno_synth/data_synthesis.md
  - 数据集:
    - 通用中英文OCR数据集: datasets/datasets.md
    - 手写中文OCR数据集: datasets/handwritten_datasets.md
    - 垂类多语言OCR数据集: datasets/vertical_and_multilingual_datasets.md
    - 版面分析数据集: datasets/layout_datasets.md
    - 表格识别数据集: datasets/table_datasets.md
    - 关键信息提取数据集: datasets/kie_datasets.md
  - FAQ: FAQ.md
  - 社区:
    - 社区贡献: community/community_contribution.md
    - 附录: community/code_and_doc.md