Initial Release for Hugging Face

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,62 @@
+# PaddleOCR
+
+name: 🐛 Bug Report
+description: Problems with PaddleOCR
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for submitting a PaddleOCR 🐛 Bug Report!
+
+  - type: checkboxes
+    attributes:
+      label: 🔎 Search before asking
+      description: >
+        Please search the PaddleOCR [Docs](https://paddlepaddle.github.io/PaddleOCR/), [Issues](https://github.com/PaddlePaddle/PaddleOCR/issues) and [Discussions](https://github.com/PaddlePaddle/PaddleOCR/discussions) to see if a similar bug report already exists.
+      options:
+        - label: I have searched the PaddleOCR [Docs](https://paddlepaddle.github.io/PaddleOCR/) and found no similar bug report.
+          required: true
+        - label: I have searched the PaddleOCR [Issues](https://github.com/PaddlePaddle/PaddleOCR/issues) and found no similar bug report.
+          required: true
+        - label: I have searched the PaddleOCR [Discussions](https://github.com/PaddlePaddle/PaddleOCR/discussions) and found no similar bug report.
+          required: true
+
+  - type: textarea
+    attributes:
+      label: 🐛 Bug (问题描述)
+      description: Provide console output with error messages and/or screenshots of the bug. (请提供详细报错信息或者截图)
+      placeholder: |
+        💡 ProTip! Include as much information as possible (screenshots, logs, tracebacks etc.) to receive the most helpful response.
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: 🏃‍♂️ Environment (运行环境)
+      description: Please specify the software and hardware you used to produce the bug. (请给出详细依赖包信息，便于复现问题)
+      placeholder: |
+        ```bash
+        OS                  macOS-13.5.2
+        Environment         Jupyter
+        Python              3.11.2
+        PaddleOCR           2.8.1
+        Install             git
+        RAM                 16.00 GB
+        CPU                 Apple M2
+        CUDA                None
+        ```
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: 🌰 Minimal Reproducible Example (最小可复现问题的Demo)
+      description: >
+        When asking a question, people will be better able to provide help if you provide code that they can easily understand and use to **reproduce** the problem.
+        This is referred to by community members as creating a [minimal reproducible example](https://stackoverflow.com/help/minimal-reproducible-example). (请务必提供该Demo，这样节省大家时间)
+      placeholder: |
+        ```bash
+        # Code to reproduce your issue here
+        ```
+    validations:
+      required: true

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,11 @@
+blank_issues_enabled: false
+contact_links:
+  - name: 🙏 Q&A
+    url: https://github.com/PaddlePaddle/PaddleOCR/discussions/categories/q-a
+    about: Ask the community for help
+  - name: 💡 Feature requests and ideas
+    url: https://github.com/PaddlePaddle/PaddleOCR/discussions/categories/ideas
+    about: Share ideas for new features
+  - name: 🙌 Show and tell
+    url: https://github.com/PaddlePaddle/PaddleOCR/discussions/categories/show-and-tell
+    about: Show off something you've made

.github/dependabot.yml

@@ -0,0 +1,13 @@
+# Keep GitHub Actions up to date with GitHub's Dependabot...
+# https://docs.github.com/en/code-security/dependabot/working-with-dependabot/keeping-your-actions-up-to-date-with-dependabot
+# https://docs.github.com/en/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file#package-ecosystem
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    groups:
+      github-actions:
+        patterns:
+          - "*"  # Group all Actions updates into a single larger pull request
+    schedule:
+      interval: weekly

.github/workflows/build_publish_develop_docs.yml

@@ -0,0 +1,31 @@
+name: Build/Publish Develop Docs
+on:
+  push:
+    branches:
+      - master
+      - main
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Configure Git Credentials
+        run: |
+          git config user.name github-actions[bot]
+          git config user.email 41898282+github-actions[bot]@users.noreply.github.com
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
+      - uses: actions/cache@v4
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: .cache
+          restore-keys: |
+            mkdocs-material-
+      - run: pip install mike mkdocs-material jieba mkdocs-git-revision-date-localized-plugin mkdocs-git-committers-plugin-2 mkdocs-static-i18n markdown-callouts
+      - run: |
+          git fetch origin gh-pages --depth=1
+          mike deploy --push --update-aliases main latest

.github/workflows/build_publish_release_docs.yml

@@ -0,0 +1,31 @@
+name: Build/Publish Release Docs
+on:
+  push:
+    tags:
+      - v*
+
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Configure Git Credentials
+        run: |
+          git config user.name github-actions[bot]
+          git config user.email github-actions[bot]@users.noreply.github.com
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
+      - uses: actions/cache@v4
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: .cache
+          restore-keys: |
+            mkdocs-material-
+      - run: pip install mike mkdocs-material jieba mkdocs-git-revision-date-localized-plugin mkdocs-git-committers-plugin-2 mkdocs-static-i18n
+      - run: |
+          git fetch origin gh-pages --depth=1
+          mike deploy --push "${{ github.ref_name }}"

.github/workflows/close_inactive_issues.yaml

@@ -0,0 +1,23 @@
+name: Close inactive issues
+on:
+  schedule:
+    - cron: "30 1 * * *"
+
+jobs:
+  close-issues:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+      - uses: actions/stale@v9
+        with:
+          days-before-issue-stale: 90
+          days-before-issue-close: 14
+          stale-issue-label: "stale"
+          stale-issue-message: "This issue is stale because it has been open for 90 days with no activity."
+          close-issue-message: "This issue was closed because it has been inactive for 14 days since being marked as stale."
+          days-before-pr-stale: -1
+          days-before-pr-close: -1
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+    

.github/workflows/codestyle.yml

@@ -0,0 +1,36 @@
+name: PaddleOCR Code Style Check
+
+on:
+  pull_request:
+  push:
+    branches: ['main', 'release/*']
+
+jobs:
+  check-code-style:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        ref: ${{ github.ref }}
+
+    - uses: actions/setup-python@v5
+      with:
+        python-version: '3.10'
+
+    - name: Cache Python dependencies
+      uses: actions/cache@v4
+      with:
+        path: ~/.cache/pip
+        key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
+        restore-keys: |
+          ${{ runner.os }}-pip-
+
+    - name: Install Dependencies for Python
+      run: |
+        python -m pip install --upgrade pip
+        pip install "clang-format==13.0.0"
+
+    - uses: pre-commit/action@v3.0.1
+      with:
+        extra_args: '--all-files'

.github/workflows/link-check.yml

@@ -0,0 +1,35 @@
+name: Link Checker
+
+on:
+  repository_dispatch:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+  schedule:
+    - cron: "00 18 * * 6"
+
+jobs:
+  linkChecker:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Link Checker
+        id: lychee
+        uses: lycheeverse/lychee-action@v2
+        env:
+          GITHUB_TOKEN: ${{secrets.GITHUB_TOKEN}}
+        with:
+            args: --exclude 'docs/index/*.md' 'docs/update/*.md' --verbose --no-progress --max-redirects 8 'docs/**/*.md'
+            format: markdown
+            fail: false
+            output: lychee/results.md
+
+      - name: Create Issue From File
+        if: steps.lychee.outputs.exit_code != 0
+        uses: peter-evans/create-issue-from-file@v5
+        with:
+          title: Link Checker Report
+          content-filepath: ./lychee/results.md
+          labels: report, automated issue

.github/workflows/python-publish.yml

@@ -0,0 +1,39 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build==1.2.2
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@76f52bc884231f62b9a034ebfe128415bbaabdfc
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/test_gpu.yml

@@ -0,0 +1,73 @@
+name: PaddleOCR PR Tests GPU
+
+on:
+  push:
+    branches: ["main"]
+    paths-ignore:
+      - '**.md'
+      - '**.txt'
+      - '**.yml'
+      - '**.yaml'
+  pull_request:
+    branches: ["main"]
+    paths-ignore:
+      - '**.md'
+      - '**.txt'
+      - '**.yml'
+      - '**.yaml'
+  workflow_dispatch:
+env:
+  PR_ID: ${{ github.event.pull_request.number }}
+  COMMIT_ID: ${{ github.event.pull_request.head.sha }}
+  work_dir: /workspace/PaddleOCR
+  PADDLENLP_ROOT: /workspace/PaddleOCR
+  TASK: paddleocr-CI-${{ github.event.pull_request.number }}
+  BRANCH: ${{ github.event.pull_request.base.ref }}
+  AGILE_COMPILE_BRANCH: ${{ github.event.pull_request.base.ref }}
+  DIR_NAME: ${{ github.repository }}
+permissions:
+  contents: read
+
+jobs:
+  test-pr-gpu:
+    runs-on: [self-hosted, GPU-2Card-OCR]
+    steps:
+      - name: run test
+        env:
+          py_version: "3.10"
+          paddle_whl: https://paddle-qa.bj.bcebos.com/paddle-pipeline/Develop-GpuSome-LinuxCentos-Gcc82-Cuda118-Cudnn86-Trt85-Py310-CINN-Compile/latest/paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
+          docker_image: ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddle:latest-dev-cuda11.8-cudnn8.6-trt8.5-gcc82
+        run: |
+          work_dir=$RANDOM
+          mkdir $work_dir
+          cd $work_dir
+          git clone --depth=1 https://github.com/PaddlePaddle/PaddleOCR.git -b main
+          cd PaddleOCR
+          git fetch origin pull/${PR_ID}/head:ci_build
+          git checkout ci_build
+          docker run --gpus all --rm -i --name PaddleOCR_CI_$RANDOM \
+            --shm-size=128g --net=host \
+            -v $PWD:/workspace -w /workspace  \
+            -e "py_version=${py_version}" \
+            -e "paddle_whl=${paddle_whl}" \
+            ${docker_image} /bin/bash -c '
+            ldconfig;
+            nvidia-smi
+            df -hl
+
+            echo ${py_version}
+            rm -rf run_env
+            mkdir run_env
+            ln -s $(which python${py_version}) run_env/python
+            ln -s $(which python${py_version}) run_env/python3
+            ln -s $(which pip${py_version}) run_env/pip
+            export PATH=$PWD/run_env:${PATH}
+            
+            python -m pip install paddlepaddle-gpu==3.1.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
+            python -c "import paddle; paddle.version.show()"
+            python -m pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
+            python -m pip install pytest
+            if [ -f requirements.txt ]; then python -m pip install -r requirements.txt; fi
+            python -m pip install -e ".[all]"
+            python -m pytest --verbose tests/
+            '

.github/workflows/tests.yaml

@@ -0,0 +1,53 @@
+name: PaddleOCR PR Tests
+
+on:
+  push:
+    branches: ["main", "release/*"]
+    paths-ignore:
+      - '**.md'
+      - '**.txt'
+      - '**.yml'
+      - '**.yaml'
+  pull_request:
+    branches: ["main", "release/*"]
+    paths-ignore:
+      - '**.md'
+      - '**.txt'
+      - '**.yml'
+      - '**.yaml'
+
+permissions:
+  contents: read
+
+jobs:
+  test-pr:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.10"
+
+    - name: Cache dependencies
+      uses: actions/cache@v4
+      with:
+        path: |
+          ~/.cache/pip
+          ~/.local/lib/python3.10/site-packages
+          ~/.paddleocr/
+        key: ${{ runner.os }}-dependencies-${{ hashFiles('**/requirements.txt', 'pyproject.toml') }}
+        restore-keys: |
+          ${{ runner.os }}-dependencies-
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install pytest
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+        python -m pip install paddlepaddle==3.2.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
+        python -m pip install -e '.[all]' 'paddlex@git+https://github.com/PaddlePaddle/PaddleX.git@develop'
+    - name: Test with pytest
+      run: |
+        pytest --verbose tests/

.gitignore

@@ -0,0 +1,43 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+.ipynb_checkpoints/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+inference/
+inference_results/
+output/
+train_data/
+log/
+*.DS_Store
+*.vs
+*.user
+*~
+*.vscode
+*.idea
+
+*.log
+.clang-format
+.clang_format.hook
+
+build/
+dist/
+*.egg-info/
+/deploy/android_demo/app/OpenCV/
+/deploy/android_demo/app/PaddleLite/
+/deploy/android_demo/app/.cxx/
+/deploy/android_demo/app/cache/
+test_tipc/web/models/
+test_tipc/web/node_modules/
+deploy/
+ppocr/data/imaug/
+*.jpg
+*.png
+*.jpeg
+deploy/  
+ppocr/data/imaug/  
+deploy/
+ppocr/data/imaug/

.lycheeignore

@@ -0,0 +1,5 @@
+zhuanlan.zhihu.com/*
+https://demo.doctrp.top/
+http://127.0.0.1:8001/
+http://localhost:9003
+https://rrc.cvc.uab.es/

.pre-commit-config.yaml

@@ -0,0 +1,45 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+    -   id: check-added-large-files
+        args: ['--maxkb=512']
+    -   id: check-case-conflict
+    -   id: check-merge-conflict
+    -   id: check-symlinks
+    -   id: detect-private-key
+    -   id: end-of-file-fixer
+    -   id: trailing-whitespace
+        files: \.(c|cc|cxx|cpp|cu|h|hpp|hxx|py)$
+-   repo: https://github.com/Lucas-C/pre-commit-hooks
+    rev: v1.5.5
+    hooks:
+    -   id: remove-crlf
+    -   id: remove-tabs
+        files: \.(c|cc|cxx|cpp|cu|h|hpp|hxx|py)$
+-   repo: local
+    hooks:
+    -   id: clang-format
+        name: clang-format
+        description: Format files with ClangFormat
+        entry: bash .clang_format.hook -i
+        language: system
+        files: \.(c|cc|cxx|cpp|cu|h|hpp|hxx|cuh|proto)$
+# For Python files
+-   repo: https://github.com/psf/black.git
+    rev: 24.10.0
+    hooks:
+    -   id: black
+        files: (.*\.(py|pyi|bzl)|BUILD|.*\.BUILD|WORKSPACE)$
+
+# Flake8
+-   repo: https://github.com/pycqa/flake8
+    rev: 7.1.1
+    hooks:
+    -   id: flake8
+        args:
+            - --count
+            - --select=E9,F63,F7,F82,E721
+            - --show-source
+            - --statistics
+        exclude: ^benchmark/|^test_tipc/

.streamlit/config.toml

@@ -0,0 +1,2 @@
+[server]
+maxMessageSize = 500

.style.yapf

@@ -0,0 +1,3 @@
+[style]
+based_on_style = pep8
+column_limit = 80

CNAME

@@ -0,0 +1 @@
+www.paddleocr.ai

Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    software-properties-common \
+    git \
+    libgl1-mesa-glx \
+    libgomp1 \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY . .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+EXPOSE 8501
+
+HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+
+ENTRYPOINT ["streamlit", "run", "vizan_studio_v2/app.py", "--server.port=8501", "--server.address=0.0.0.0"]

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright (c) 2016 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.

MANIFEST.in

@@ -0,0 +1,22 @@
+prune .github
+prune applications
+prune benchmark
+prune configs
+prune deploy
+prune doc
+prune docs
+prune overrides
+prune ppocr/ext_op
+prune ppocr/losses
+prune ppocr/metrics
+prune ppocr/modeling
+prune ppocr/optimizer
+prune ppstructure/docs
+prune test_tipc
+prune tests
+exclude .clang_format.hook
+exclude .gitignore
+exclude .pre-commit-config.yaml
+exclude .style.yapf
+exclude mkdocs.yml
+exclude train.sh

README.md

@@ -0,0 +1,546 @@
+<div align="center">
+  <p>
+      <img width="100%" src="./docs/images/Banner.png" alt="PaddleOCR Banner">
+  </p>
+
+English | [简体中文](./readme/README_cn.md) | [繁體中文](./readme/README_tcn.md) | [日本語](./readme/README_ja.md) | [한국어](./readme/README_ko.md) | [Français](./readme/README_fr.md) | [Русский](./readme/README_ru.md) | [Español](./readme/README_es.md) | [العربية](./readme/README_ar.md)
+
+<!-- icon -->
+[![stars](https://img.shields.io/github/stars/PaddlePaddle/PaddleOCR?color=ccf)](https://github.com/PaddlePaddle/PaddleOCR)
+[![forks](https://img.shields.io/github/forks/PaddlePaddle/PaddleOCR.svg)](https://github.com/PaddlePaddle/PaddleOCR)
+[![arXiv](https://img.shields.io/badge/PaddleOCR_3.0-Technical%20Report-b31b1b.svg?logo=arXiv)](https://arxiv.org/pdf/2507.05595)
+[![arXiv](https://img.shields.io/badge/PaddleOCR--VL-Technical%20Report-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2510.14528)
+
+[![PyPI Downloads](https://static.pepy.tech/badge/paddleocr/month)](https://pepy.tech/projectsproject/paddleocr)
+[![PyPI Downloads](https://static.pepy.tech/badge/paddleocr)](https://pepy.tech/projects/paddleocr)
+[![Used by](https://img.shields.io/badge/Used%20by-6k%2B%20repositories-blue)](https://github.com/PaddlePaddle/PaddleOCR/network/dependents)
+[![PyPI version](https://img.shields.io/pypi/v/paddleocr)](https://pypi.org/project/paddleocr/)
+![python](https://img.shields.io/badge/python-3.8~3.12-aff.svg)
+
+![os](https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-pink.svg)
+![hardware](https://img.shields.io/badge/hardware-cpu%2C%20gpu%2C%20xpu%2C%20npu-yellow.svg)
+[![License](https://img.shields.io/badge/license-Apache_2.0-green)](../LICENSE)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/PaddlePaddle/PaddleOCR)
+[![AI Studio](https://img.shields.io/badge/PaddleOCR-_Offiical_Website-1927BA?logo=data:image/png;base64,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&labelColor=white)](https://www.paddleocr.com)
+
+
+
+**PaddleOCR is an industry-leading, production-ready OCR and document AI engine, offering end-to-end solutions from text extraction to intelligent document understanding**
+
+</div>
+
+# PaddleOCR
+[![Framework](https://img.shields.io/badge/PaddlePaddle-3.0-orange)](https://www.paddlepaddle.org.cn/en)
+[![Accuracy](https://img.shields.io/badge/Recognition%20Accuracy-🏆-green)](#)
+[![Multi-Language](https://img.shields.io/badge/Support_Languages-100+-brightgreen)](#)
+[![Handwriting](https://img.shields.io/badge/Handwriting-✓-success)](#)
+[![Hardware](https://img.shields.io/badge/Heterogeneous%20Hardware-Kunlunxin%20%7C%20Ascend_NPU-red)](#)
+
+> [!TIP]
+> PaddleOCR now provides an MCP server that supports integration with Agent applications like Claude Desktop. For details, please refer to [PaddleOCR MCP Server](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/mcp_server.html).
+>
+> The PaddleOCR 3.0 Technical Report is now available. See details at: [PaddleOCR 3.0 Technical Report](https://arxiv.org/abs/2507.05595).
+>
+> The PaddleOCR-VL Technical Report is now available. See details at [PaddleOCR-VL Technical Report](https://arxiv.org/abs/2510.14528).
+>
+> The Beta version of the PaddleOCR official website is now live, offering a more convenient online experience and large-scale PDF file parsing, as well as free API and MCP services. For more details, please visit the [PaddleOCR official website](https://www.paddleocr.com).
+
+
+**PaddleOCR** converts documents and images into **structured, AI-friendly data** (like JSON and Markdown) with **industry-leading accuracy**—powering AI applications for everyone from indie developers and startups to large enterprises worldwide. With over **60,000 stars** and deep integration into leading projects like **MinerU, RAGFlow, pathway and cherry-studio**, PaddleOCR has become the **premier solution** for developers building intelligent document applications in the **AI era**.
+
+### PaddleOCR 3.0 Core Features
+
+[![HuggingFace](https://img.shields.io/badge/PaddleOCR--VL-_Demo_on_HuggingFace-yellow?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/PaddlePaddle/PaddleOCR-VL_Online_Demo)
+[![AI Studio](https://img.shields.io/badge/PaddleOCR--VL-_Demo_on_AI_Studio-1927BA?logo=data:image/png;base64,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&labelColor=white)](https://aistudio.baidu.com/application/detail/98365)
+[![ModelScope](https://img.shields.io/badge/PaddleOCR--VL-_Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/PaddlePaddle/PaddleOCR-VL_Online_Demo)
+
+[![AI Studio](https://img.shields.io/badge/PP--OCRv5-Demo_on_AI_Studio-1927BA?logo=data:image/png;base64,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&labelColor=white)](https://aistudio.baidu.com/community/app/91660/webUI)
+[![AI Studio](https://img.shields.io/badge/PP--StructureV3-Demo_on_AI_Studio-1927BA?logo=data:image/png;base64,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&labelColor=white)](https://aistudio.baidu.com/community/app/518494/webUI)
+[![AI Studio](https://img.shields.io/badge/PP--ChatOCRv4-Demo_on_AI_Studio-1927BA?logo=data:image/png;base64,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&labelColor=white)](https://aistudio.baidu.com/community/app/518493/webUI)
+
+
+- **PaddleOCR-VL - Multilingual Document Parsing via a 0.9B VLM**  
+  **The SOTA and resource-efficient model tailored for document parsing**, that supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption.
+
+- **PP-OCRv5 — Universal Scene Text Recognition**  
+  **Single model supports five text types** (Simplified Chinese, Traditional Chinese, English, Japanese, and Pinyin) with **13% accuracy improvement**. Solves multilingual mixed document recognition challenges.
+
+- **PP-StructureV3 — Complex Document Parsing**  
+  Intelligently converts complex PDFs and document images into **Markdown and JSON files that preserve original structure**. **Outperforms** numerous commercial solutions in public benchmarks. **Perfectly maintains document layout and hierarchical structure**.
+
+- **PP-ChatOCRv4 — Intelligent Information Extraction**  
+  Natively integrates ERNIE 4.5 to **precisely extract key information** from massive documents, with 15% accuracy improvement over previous generation. Makes documents "**understand**" your questions and provide accurate answers.
+
+In addition to providing an outstanding model library, PaddleOCR 3.0 also offers user-friendly tools covering model training, inference, and service deployment, so developers can rapidly bring AI applications to production.
+<div align="center">
+  <p>
+      <img width="100%" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/Arch.jpg" alt="PaddleOCR Architecture">
+  </p>
+</div>
+
+**Special Note**: PaddleOCR 3.x introduces several significant interface changes. **Old code written based on PaddleOCR 2.x is likely incompatible with PaddleOCR 3.x**. Please ensure that the documentation you are reading matches the version of PaddleOCR you are using. [This document](https://paddlepaddle.github.io/PaddleOCR/latest/en/update/upgrade_notes.html) explains the reasons for the upgrade and the major changes from PaddleOCR 2.x to 3.x.
+
+## 📣 Recent updates
+
+### 🔥🔥 2025.10.16: PaddleOCR 3.3.0 released, includes:
+
+- Released PaddleOCR-VL:
+    - **Model Introduction**:
+        - **PaddleOCR-VL** is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. **This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption**. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios. The model has been released on [HuggingFace](https://huggingface.co/PaddlePaddle/PaddleOCR-VL). Everyone is welcome to download and use it! More introduction infomation can be found in [PaddleOCR-VL](https://www.paddleocr.ai/latest/version3.x/algorithm/PaddleOCR-VL/PaddleOCR-VL.html).
+
+    - **Core Features**:
+        - **Compact yet Powerful VLM Architecture**: We present a novel vision-language model that is specifically designed for resource-efficient inference, achieving outstanding performance in element recognition. By integrating a NaViT-style dynamic high-resolution visual encoder with the lightweight ERNIE-4.5-0.3B language model, we significantly enhance the model’s recognition capabilities and decoding efficiency. This integration maintains high accuracy while reducing computational demands, making it well-suited for efficient and practical document processing applications.
+        - **SOTA Performance on Document Parsing**: PaddleOCR-VL achieves state-of-the-art performance in both page-level document parsing and element-level recognition. It significantly outperforms existing pipeline-based solutions and exhibiting strong competitiveness against leading vision-language models (VLMs) in document parsing. Moreover, it excels in recognizing complex document elements, such as text, tables, formulas, and charts, making it suitable for a wide range of challenging content types, including handwritten text and historical documents. This makes it highly versatile and suitable for a wide range of document types and scenarios.
+        - **Multilingual Support**: PaddleOCR-VL Supports 109 languages, covering major global languages, including but not limited to Chinese, English, Japanese, Latin, and Korean, as well as languages with different scripts and structures, such as Russian (Cyrillic script), Arabic, Hindi (Devanagari script), and Thai. This broad language coverage substantially enhances the applicability of our system to multilingual and globalized document processing scenarios.
+
+- Released PP-OCRv5 Multilingual Recognition Model:
+    - Improved the accuracy and coverage of Latin script recognition; added support for Cyrillic, Arabic, Devanagari, Telugu, Tamil, and other language systems, covering recognition of 109 languages. The model has only 2M parameters, and the accuracy of some models has increased by over 40% compared to the previous generation.
+
+
+<details>
+<summary><strong>2025.08.21: Release of PaddleOCR 3.2.0</strong></summary>
+
+- **Significant Model Additions:**
+    - Introduced training, inference, and deployment for PP-OCRv5 recognition models in English, Thai, and Greek. **The PP-OCRv5 English model delivers an 11% improvement in English scenarios compared to the main PP-OCRv5 model, with the Thai and Greek recognition models achieving accuracies of 82.68% and 89.28%, respectively.**
+
+- **Deployment Capability Upgrades:**
+    - **Full support for PaddlePaddle framework versions 3.1.0 and 3.1.1.**
+    - **Comprehensive upgrade of the PP-OCRv5 C++ local deployment solution, now supporting both Linux and Windows, with feature parity and identical accuracy to the Python implementation.**
+    - **High-performance inference now supports CUDA 12, and inference can be performed using either the Paddle Inference or ONNX Runtime backends.**
+    - **The high-stability service-oriented deployment solution is now fully open-sourced, allowing users to customize Docker images and SDKs as required.**
+    - The high-stability service-oriented deployment solution also supports invocation via manually constructed HTTP requests, enabling client-side code development in any programming language.
+
+- **Benchmark Support:**
+    - **All production lines now support fine-grained benchmarking, enabling measurement of end-to-end inference time as well as per-layer and per-module latency data to assist with performance analysis. [Here's](docs/version3.x/pipeline_usage/instructions/benchmark.en.md) how to set up and use the benchmark feature.**
+    - **Documentation has been updated to include key metrics for commonly used configurations on mainstream hardware, such as inference latency and memory usage, providing deployment references for users.**
+
+- **Bug Fixes:**
+    - Resolved the issue of failed log saving during model training.
+    - Upgraded the data augmentation component for formula models for compatibility with newer versions of the albumentations dependency, and fixed deadlock warnings when using the tokenizers package in multi-process scenarios.
+    - Fixed inconsistencies in switch behaviors (e.g., `use_chart_parsing`) in the PP-StructureV3 configuration files compared to other pipelines.
+
+- **Other Enhancements:**
+    - **Separated core and optional dependencies. Only minimal core dependencies are required for basic text recognition; additional dependencies for document parsing and information extraction can be installed as needed.**
+    - **Enabled support for NVIDIA RTX 50 series graphics cards on Windows; users can refer to the [installation guide](docs/version3.x/installation.en.md) for the corresponding PaddlePaddle framework versions.**
+    - **PP-OCR series models now support returning single-character coordinates.**
+    - Added AIStudio, ModelScope, and other model download sources, allowing users to specify the source for model downloads.
+    - Added support for chart-to-table conversion via the PP-Chart2Table module.
+    - Optimized documentation descriptions to improve usability.
+</details>
+
+<details>
+<summary><strong>2025.08.15: PaddleOCR 3.1.1 Released</strong></summary>
+
+- **Bug Fixes:**
+  - Added the missing methods `save_vector`, `save_visual_info_list`, `load_vector`, and `load_visual_info_list` in the `PP-ChatOCRv4` class.
+  - Added the missing parameters `glossary` and `llm_request_interval` to the `translate` method in the `PPDocTranslation` class.
+
+- **Documentation Improvements:**
+  - Added a demo to the MCP documentation.
+  - Added information about the PaddlePaddle and PaddleOCR version used for performance metrics testing in the documentation.
+  - Fixed errors and omissions in the production line document translation.
+
+- **Others:**
+  - Changed the MCP server dependency to use the pure Python library `puremagic` instead of `python-magic` to reduce installation issues.
+  - Retested PP-OCRv5 performance metrics with PaddleOCR version 3.1.0 and updated the documentation.
+
+</details>
+
+<details>
+<summary><strong>2025.06.29: PaddleOCR 3.1.0 Released</strong></summary>
+
+- **Key Models and Pipelines:**
+  - **Added PP-OCRv5 Multilingual Text Recognition Model**, which supports the training and inference process for text recognition models in 37 languages, including French, Spanish, Portuguese, Russian, Korean, etc. **Average accuracy improved by over 30%.** [Details](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/algorithm/PP-OCRv5/PP-OCRv5_multi_languages.html)
+  - Upgraded the **PP-Chart2Table model** in PP-StructureV3, further enhancing the capability of converting charts to tables. On internal custom evaluation sets, the metric (RMS-F1) **increased by 9.36 percentage points (71.24% -> 80.60%).**
+  - Newly launched **document translation pipeline, PP-DocTranslation, based on PP-StructureV3 and ERNIE 4.5**, which supports the translation of Markdown format documents, various complex-layout PDF documents, and document images, with the results saved as Markdown format documents. [Details](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/pipeline_usage/PP-DocTranslation.html)
+
+
+- **New MCP server:** [Details](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/mcp_server.html)
+  - **Supports both OCR and PP-StructureV3 pipelines.**
+  - Supports three working modes: local Python library, AIStudio Community Cloud Service, and self-hosted service.
+  - Supports invoking local services via stdio and remote services via Streamable HTTP.
+
+- **Documentation Optimization:** Improved the descriptions in some user guides for a smoother reading experience.
+
+</details>
+
+<details>
+    <summary><strong>2025.06.26: PaddleOCR 3.0.3 Released</strong></summary>
+- Bug Fix: Resolved the issue where the `enable_mkldnn` parameter was not effective, restoring the default behavior of using MKL-DNN for CPU inference.
+</details>
+
+<details>
+    <summary><strong>2025.06.19: PaddleOCR 3.0.2 Released</strong></summary>
+- **New Features:**
+
+  - The default download source has been changed from `BOS` to `HuggingFace`. Users can also change the environment variable `PADDLE_PDX_MODEL_SOURCE` to `BOS` to set the model download source back to Baidu Object Storage (BOS).
+  - Added service invocation examples for six languages—C++, Java, Go, C#, Node.js, and PHP—for pipelines like PP-OCRv5, PP-StructureV3, and PP-ChatOCRv4.
+  - Improved the layout partition sorting algorithm in the PP-StructureV3 pipeline, enhancing the sorting logic for complex vertical layouts to deliver better results.
+  - Enhanced model selection logic: when a language is specified but a model version is not, the system will automatically select the latest model version supporting that language. 
+  - Set a default upper limit for MKL-DNN cache size to prevent unlimited growth, while also allowing users to configure cache capacity.
+  - Updated default configurations for high-performance inference to support Paddle MKL-DNN acceleration and optimized the logic for automatic configuration selection for smarter choices.
+  - Adjusted the logic for obtaining the default device to consider the actual support for computing devices by the installed Paddle framework, making program behavior more intuitive.
+  - Added Android example for PP-OCRv5. [Details](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/on_device_deployment.html).
+
+- **Bug Fixes:**
+  - Fixed an issue with some CLI parameters in PP-StructureV3 not taking effect.
+  - Resolved an issue where `export_paddlex_config_to_yaml` would not function correctly in certain cases.
+  - Corrected the discrepancy between the actual behavior of `save_path` and its documentation description.
+  - Fixed potential multithreading errors when using MKL-DNN in basic service deployment.
+  - Corrected channel order errors in image preprocessing for the Latex-OCR model.
+  - Fixed channel order errors in saving visualized images within the text recognition module.
+  - Resolved channel order errors in visualized table results within PP-StructureV3 pipeline.
+  - Fixed an overflow issue in the calculation of `overlap_ratio` under extremely special circumstances in the PP-StructureV3 pipeline.
+
+- **Documentation Improvements:**
+  - Updated the description of the `enable_mkldnn` parameter in the documentation to accurately reflect the program's actual behavior.
+  - Fixed errors in the documentation regarding the `lang` and `ocr_version` parameters.
+  - Added instructions for exporting pipeline configuration files via CLI.
+  - Fixed missing columns in the performance data table for PP-OCRv5.
+  - Refined benchmark metrics for PP-StructureV3 across different configurations.
+
+- **Others:**
+
+  - Relaxed version restrictions on dependencies like numpy and pandas, restoring support for Python 3.12.
+</details>
+
+<details>
+    <summary><strong>History Log</strong></summary>
+
+2025.06.05: **PaddleOCR 3.0.1 Released**, includes:
+
+- **Optimisation of certain models and model configurations:**
+  - Updated the default model configuration for PP-OCRv5, changing both detection and recognition from mobile to server models. To improve default performance in most scenarios, the parameter `limit_side_len` in the configuration has been changed from 736 to 64.
+  - Added a new text line orientation classification model `PP-LCNet_x1_0_textline_ori` with an accuracy of 99.42%. The default text line orientation classifier for OCR, PP-StructureV3, and PP-ChatOCRv4 pipelines has been updated to this model.
+  - Optimized the text line orientation classification model `PP-LCNet_x0_25_textline_ori`, improving accuracy by 3.3 percentage points to a current accuracy of 98.85%.
+- **Optimizations and fixes for some issues in version 3.0.0, [details](https://paddlepaddle.github.io/PaddleOCR/latest/en/update/update.html)**
+
+🔥🔥2025.05.20: Official Release of **PaddleOCR v3.0**, including:
+- **PP-OCRv5**: High-Accuracy Text Recognition Model for All Scenarios - Instant Text from Images/PDFs.
+   1. 🌐 Single-model support for **five** text types - Seamlessly process **Simplified Chinese, Traditional Chinese, Simplified Chinese Pinyin, English** and **Japanese** within a single model.
+   2. ✍️ Improved **handwriting recognition**: Significantly better at complex cursive scripts and non-standard handwriting.
+   3. 🎯 **13-point accuracy gain** over PP-OCRv4, achieving state-of-the-art performance across a variety of real-world scenarios.
+
+- **PP-StructureV3**: General-Purpose Document Parsing – Unleash SOTA Images/PDFs Parsing for Real-World Scenarios! 
+   1. 🧮 **High-Accuracy multi-scene PDF parsing**, leading both open- and closed-source solutions on the OmniDocBench benchmark.
+   2. 🧠 Specialized capabilities include **seal recognition**, **chart-to-table conversion**, **table recognition with nested formulas/images**, **vertical text document parsing**, and **complex table structure analysis**.
+
+- **PP-ChatOCRv4**: Intelligent Document Understanding – Extract Key Information, not just text from Images/PDFs.
+   1. 🔥 **15-point accuracy gain** in key-information extraction on PDF/PNG/JPG files over the previous generation.
+   2. 💻 Native support for **ERNIE 4.5**, with compatibility for large-model deployments via PaddleNLP, Ollama, vLLM, and more.
+   3. 🤝 Integrated [PP-DocBee2](https://github.com/PaddlePaddle/PaddleMIX/tree/develop/paddlemix/examples/ppdocbee2), enabling extraction and understanding of printed text, handwriting, seals, tables, charts, and other common elements in complex documents.
+
+[History Log](https://paddlepaddle.github.io/PaddleOCR/latest/en/update/update.html)
+
+</details>
+
+## ⚡ Quick Start
+### 1. Run online demo 
+[![AI Studio](https://img.shields.io/badge/PP_OCRv5-AI_Studio-green)](https://aistudio.baidu.com/community/app/91660/webUI)
+[![AI Studio](https://img.shields.io/badge/PP_StructureV3-AI_Studio-green)](https://aistudio.baidu.com/community/app/518494/webUI)
+[![AI Studio](https://img.shields.io/badge/PP_ChatOCRv4-AI_Studio-green)](https://aistudio.baidu.com/community/app/518493/webUI)
+
+### 2. Installation
+
+Install PaddlePaddle refer to [Installation Guide](https://www.paddlepaddle.org.cn/en/install/quick?docurl=/documentation/docs/en/develop/install/pip/linux-pip_en.html), after then, install the PaddleOCR toolkit.
+
+```bash
+# If you only want to use the basic text recognition feature (returns text position coordinates and content), including the PP-OCR series
+python -m pip install paddleocr
+# If you want to use all features such as document parsing, document understanding, document translation, key information extraction, etc.
+# python -m pip install "paddleocr[all]"
+```
+
+Starting from version 3.2.0, in addition to the `all` dependency group demonstrated above, PaddleOCR also supports installing partial optional features by specifying other dependency groups. All dependency groups provided by PaddleOCR are as follows:
+
+| Dependency Group Name | Corresponding Functionality |
+| - | - |
+| `doc-parser` | Document parsing: can be used to extract layout elements such as tables, formulas, stamps, images, etc. from documents; includes models like PP-StructureV3, PaddleOCR-VL |
+| `ie` | Information extraction: can be used to extract key information from documents, such as names, dates, addresses, amounts, etc.; includes models like PP-ChatOCRv4 |
+| `trans` | Document translation: can be used to translate documents from one language to another; includes models like PP-DocTranslation |
+| `all` | Complete functionality |
+
+### 3. Run inference by CLI
+```bash
+# Run PP-OCRv5 inference
+paddleocr ocr -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png --use_doc_orientation_classify False --use_doc_unwarping False --use_textline_orientation False  
+
+# Run PP-StructureV3 inference
+paddleocr pp_structurev3 -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/pp_structure_v3_demo.png --use_doc_orientation_classify False --use_doc_unwarping False
+
+# Get the Qianfan API Key at first, and then run PP-ChatOCRv4 inference
+paddleocr pp_chatocrv4_doc -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/vehicle_certificate-1.png -k 驾驶室准乘人数 --qianfan_api_key your_api_key --use_doc_orientation_classify False --use_doc_unwarping False 
+
+# Run PaddleOCR-VL inference
+paddleocr doc_parser -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/paddleocr_vl_demo.png
+
+# Get more information about "paddleocr ocr"
+paddleocr ocr --help
+```
+
+### 4. Run inference by API
+**4.1 PP-OCRv5 Example**
+```python
+# Initialize PaddleOCR instance
+from paddleocr import PaddleOCR
+ocr = PaddleOCR(
+    use_doc_orientation_classify=False,
+    use_doc_unwarping=False,
+    use_textline_orientation=False)
+
+# Run OCR inference on a sample image 
+result = ocr.predict(
+    input="https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png")
+
+# Visualize the results and save the JSON results
+for res in result:
+    res.print()
+    res.save_to_img("output")
+    res.save_to_json("output")
+```
+
+<details>
+    <summary><strong>4.2 PP-StructureV3 Example</strong></summary>
+
+```python
+from pathlib import Path
+from paddleocr import PPStructureV3
+
+pipeline = PPStructureV3(
+    use_doc_orientation_classify=False,
+    use_doc_unwarping=False
+)
+
+# For Image
+output = pipeline.predict(
+    input="https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/pp_structure_v3_demo.png",
+)
+
+# Visualize the results and save the JSON results
+for res in output:
+    res.print() 
+    res.save_to_json(save_path="output") 
+    res.save_to_markdown(save_path="output")           
+```
+
+</details>
+
+<details>
+   <summary><strong>4.3 PP-ChatOCRv4 Example</strong></summary>
+
+```python
+from paddleocr import PPChatOCRv4Doc
+
+chat_bot_config = {
+    "module_name": "chat_bot",
+    "model_name": "ernie-3.5-8k",
+    "base_url": "https://qianfan.baidubce.com/v2",
+    "api_type": "openai",
+    "api_key": "api_key",  # your api_key
+}
+
+retriever_config = {
+    "module_name": "retriever",
+    "model_name": "embedding-v1",
+    "base_url": "https://qianfan.baidubce.com/v2",
+    "api_type": "qianfan",
+    "api_key": "api_key",  # your api_key
+}
+
+pipeline = PPChatOCRv4Doc(
+    use_doc_orientation_classify=False,
+    use_doc_unwarping=False
+)
+
+visual_predict_res = pipeline.visual_predict(
+    input="https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/vehicle_certificate-1.png",
+    use_common_ocr=True,
+    use_seal_recognition=True,
+    use_table_recognition=True,
+)
+
+mllm_predict_info = None
+use_mllm = False
+# If a multimodal large model is used, the local mllm service needs to be started. You can refer to the documentation: https://github.com/PaddlePaddle/PaddleX/blob/release/3.0/docs/pipeline_usage/tutorials/vlm_pipelines/doc_understanding.en.md performs deployment and updates the mllm_chat_bot_config configuration.
+if use_mllm:
+    mllm_chat_bot_config = {
+        "module_name": "chat_bot",
+        "model_name": "PP-DocBee",
+        "base_url": "http://127.0.0.1:8080/",  # your local mllm service url
+        "api_type": "openai",
+        "api_key": "api_key",  # your api_key
+    }
+
+    mllm_predict_res = pipeline.mllm_pred(
+        input="https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/vehicle_certificate-1.png",
+        key_list=["驾驶室准乘人数"],
+        mllm_chat_bot_config=mllm_chat_bot_config,
+    )
+    mllm_predict_info = mllm_predict_res["mllm_res"]
+
+visual_info_list = []
+for res in visual_predict_res:
+    visual_info_list.append(res["visual_info"])
+    layout_parsing_result = res["layout_parsing_result"]
+
+vector_info = pipeline.build_vector(
+    visual_info_list, flag_save_bytes_vector=True, retriever_config=retriever_config
+)
+chat_result = pipeline.chat(
+    key_list=["驾驶室准乘人数"],
+    visual_info=visual_info_list,
+    vector_info=vector_info,
+    mllm_predict_info=mllm_predict_info,
+    chat_bot_config=chat_bot_config,
+    retriever_config=retriever_config,
+)
+print(chat_result)
+```
+
+</details>
+
+<details>
+   <summary><strong>4.4 PaddleOCR-VL Example</strong></summary>
+
+```python
+from paddleocr import PaddleOCRVL
+
+pipeline = PaddleOCRVL()
+output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/paddleocr_vl_demo.png")
+for res in output:
+    res.print()
+    res.save_to_json(save_path="output")
+    res.save_to_markdown(save_path="output")
+```
+
+</details>
+
+### 5. Chinese Heterogeneous AI Accelerators
+- [Huawei Ascend](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/other_devices_support/paddlepaddle_install_NPU.html)
+- [KUNLUNXIN](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/other_devices_support/paddlepaddle_install_XPU.html)
+
+## 🧩 More Features
+
+- Convert models to ONNX format: [Obtaining ONNX Models](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/obtaining_onnx_models.html).
+- Accelerate inference using engines like OpenVINO, ONNX Runtime, TensorRT, or perform inference using ONNX format models: [High-Performance Inference](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/high_performance_inference.html).
+- Accelerate inference using multi-GPU and multi-process: [Parallel Inference for Pipelines](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/pipeline_usage/instructions/parallel_inference.html).
+- Integrate PaddleOCR into applications written in C++, C#, Java, etc.: [Serving](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/serving.html).
+
+## ⛰️ Advanced Tutorials
+
+- [PP-OCRv5 Tutorial](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/pipeline_usage/OCR.html)
+- [PP-StructureV3 Tutorial](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/pipeline_usage/PP-StructureV3.html)
+- [PP-ChatOCRv4 Tutorial](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/pipeline_usage/PP-ChatOCRv4.html)
+- [PaddleOCR-VL Tutorial](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/pipeline_usage/PaddleOCR-VL.html)
+
+## 🔄 Quick Overview of Execution Results
+
+### PP-OCRv5
+
+<div align="center">
+  <p>
+       <img width="100%" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/PP-OCRv5_demo.gif" alt="PP-OCRv5 Demo">
+  </p>
+</div>
+
+
+
+### PP-StructureV3
+
+<div align="center">
+  <p>
+      <img width="100%" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/PP-StructureV3_demo.gif" alt="PP-StructureV3 Demo">
+  </p>
+</div>
+
+### PaddleOCR-VL
+
+<div align="center">
+  <p>
+      <img width="100%" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/PaddleOCR-VL_demo.gif" alt="PP-StructureV3 Demo">
+  </p>
+</div>
+
+
+## ✨ Stay Tuned
+
+⭐ **Star this repository to keep up with exciting updates and new releases, including powerful OCR and document parsing capabilities!** ⭐
+
+<div align="center">
+  <p>
+       <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr.en.gif" alt="Star-Project">
+  </p>
+</div>
+
+## 👩‍👩‍👧‍👦 Community
+
+<div align="center">
+
+| PaddlePaddle WeChat official account |  Join the tech discussion group |
+| :---: | :---: |
+| <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr/README/qrcode_for_paddlepaddle_official_account.jpg" width="150"> | <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr/README/qr_code_for_the_questionnaire.jpg" width="150"> |
+</div>
+
+
+## 😃 Awesome Projects Leveraging PaddleOCR
+PaddleOCR wouldn't be where it is today without its incredible community! 💗 A massive thank you to all our longtime partners, new collaborators, and everyone who's poured their passion into PaddleOCR — whether we've named you or not. Your support fuels our fire!
+
+<div align="center">
+
+| Project Name | Description |
+| ------------ | ----------- |
+| [RAGFlow](https://github.com/infiniflow/ragflow) <a href="https://github.com/infiniflow/ragflow"><img src="https://img.shields.io/github/stars/infiniflow/ragflow"></a>|RAG engine based on deep document understanding.|
+| [pathway](https://github.com/pathwaycom/pathway) <a href="https://github.com/pathwaycom/pathway"><img src="https://img.shields.io/github/stars/pathwaycom/pathway"></a>|Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.|
+| [MinerU](https://github.com/opendatalab/MinerU) <a href="https://github.com/opendatalab/MinerU"><img src="https://img.shields.io/github/stars/opendatalab/MinerU"></a>|Multi-type Document to Markdown Conversion Tool|
+| [Umi-OCR](https://github.com/hiroi-sora/Umi-OCR) <a href="https://github.com/hiroi-sora/Umi-OCR"><img src="https://img.shields.io/github/stars/hiroi-sora/Umi-OCR"></a>|Free, Open-source, Batch Offline OCR Software.|
+| [cherry-studio](https://github.com/CherryHQ/cherry-studio) <a href="https://github.com/CherryHQ/cherry-studio"><img src="https://img.shields.io/github/stars/CherryHQ/cherry-studio"></a>|A desktop client that supports for multiple LLM providers.|
+| [OmniParser](https://github.com/microsoft/OmniParser)<a href="https://github.com/microsoft/OmniParser"><img src="https://img.shields.io/github/stars/microsoft/OmniParser"></a> |OmniParser: Screen Parsing tool for Pure Vision Based GUI Agent.|
+| [QAnything](https://github.com/netease-youdao/QAnything)<a href="https://github.com/netease-youdao/QAnything"><img src="https://img.shields.io/github/stars/netease-youdao/QAnything"></a> |Question and Answer based on Anything.|
+| [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit) <a href="https://github.com/opendatalab/PDF-Extract-Kit"><img src="https://img.shields.io/github/stars/opendatalab/PDF-Extract-Kit"></a>|A powerful open-source toolkit designed to efficiently extract high-quality content from complex and diverse PDF documents.|
+| [Dango-Translator](https://github.com/PantsuDango/Dango-Translator)<a href="https://github.com/PantsuDango/Dango-Translator"><img src="https://img.shields.io/github/stars/PantsuDango/Dango-Translator"></a> |Recognize text on the screen, translate it and show the translation results in real time.|
+| [Learn more projects](./awesome_projects.md) | [More projects based on PaddleOCR](./awesome_projects.md)|
+</div>
+
+## 👩‍👩‍👧‍👦 Contributors
+
+<div align="center">
+<a href="https://github.com/PaddlePaddle/PaddleOCR/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=PaddlePaddle/PaddleOCR&max=400&columns=20"  width="800"/>
+</a>
+</div>
+
+## 🌟 Star
+
+<div align="center">
+  <p>
+      <img width="800" src="https://api.star-history.com/svg?repos=PaddlePaddle/PaddleOCR&type=Date" alt="Star-history">
+  </p>
+</div>
+
+
+## 📄 License
+This project is released under the [Apache 2.0 license](LICENSE).
+
+## 🎓 Citation
+
+```bibtex
+@misc{cui2025paddleocr30technicalreport,
+      title={PaddleOCR 3.0 Technical Report}, 
+      author={Cheng Cui and Ting Sun and Manhui Lin and Tingquan Gao and Yubo Zhang and Jiaxuan Liu and Xueqing Wang and Zelun Zhang and Changda Zhou and Hongen Liu and Yue Zhang and Wenyu Lv and Kui Huang and Yichao Zhang and Jing Zhang and Jun Zhang and Yi Liu and Dianhai Yu and Yanjun Ma},
+      year={2025},
+      eprint={2507.05595},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2507.05595}, 
+}
+
+@misc{cui2025paddleocrvlboostingmultilingualdocument,
+      title={PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model}, 
+      author={Cheng Cui and Ting Sun and Suyin Liang and Tingquan Gao and Zelun Zhang and Jiaxuan Liu and Xueqing Wang and Changda Zhou and Hongen Liu and Manhui Lin and Yue Zhang and Yubo Zhang and Handong Zheng and Jing Zhang and Jun Zhang and Yi Liu and Dianhai Yu and Yanjun Ma},
+      year={2025},
+      eprint={2510.14528},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2510.14528}, 
+}
+```

applications/README.md

@@ -0,0 +1 @@
+移步[docs](https://www.paddleocr.ai/v2.10.0/applications/overview.html)

awesome_projects.md

@@ -0,0 +1,30 @@
+## 😃 Awesome projects based on PaddleOCR
+💗 PaddleOCR wouldn’t be where it is today without its incredible community! A massive 🙌 thank you 🙌 to all our longtime partners, new collaborators, and everyone who’s poured their passion into PaddleOCR — whether we’ve named you or not. Your support fuels our fire! 🔥
+| Project Name | Description |
+| ------------ | ----------- |
+| [Umi-OCR](https://github.com/hiroi-sora/Umi-OCR) <a href="https://github.com/hiroi-sora/Umi-OCR"><img src="https://img.shields.io/github/stars/hiroi-sora/Umi-OCR"></a>|Free, Open-source, Batch Offline OCR Software.|
+| [LearnOpenCV](http://github.com/spmallick/learnopencv) <a href="http://github.com/spmallick/learnopencv"><img src="https://img.shields.io/github/stars/spmallick/learnopencv"></a> | code for Computer Vision, Deep learning, and AI research articles.|
+| [OmniParser](https://github.com/microsoft/OmniParser)<a href="https://github.com/microsoft/OmniParser"><img src="https://img.shields.io/github/stars/microsoft/OmniParser"></a> |OmniParser: Screen Parsing tool for Pure Vision Based GUI Agent.|
+| [QAnything](https://github.com/netease-youdao/QAnything)<a href="https://github.com/netease-youdao/QAnything"><img src="https://img.shields.io/github/stars/netease-youdao/QAnything"></a> |Question and Answer based on Anything.|
+| [PaddleHub](https://github.com/PaddlePaddle/PaddleHub)<a href="https://github.com/PaddlePaddle/PaddleHub"><img src="https://img.shields.io/github/stars/PaddlePaddle/PaddleHub"></a> |400+ AI Models: Rich, high-quality AI models, including CV, NLP, Speech, Video and Cross-Modal.|
+| [PaddleNLP](https://github.com/PaddlePaddle/PaddleNLP)<a href="https://github.com/PaddlePaddle/PaddleNLP"><img src="https://img.shields.io/github/stars/PaddlePaddle/PaddleNLP"></a> |A Large Language Model (LLM) development suite based on the PaddlePaddle.|
+| [Rerun](https://github.com/rerun-io/rerun) <a href="https://github.com/rerun-io/rerun"><img src="https://img.shields.io/github/stars/rerun-io/rerun"></a> | Rerun is building the multimodal data stack to model, ingest, store, query and view robotics-style data |
+| [Dango-Translator](https://github.com/PantsuDango/Dango-Translator) <a href="https://github.com/PantsuDango/Dango-Translator"><img src="https://img.shields.io/github/stars/PantsuDango/Dango-Translator"></a> | Recognize text on the screen, translate it and show the translation results in real time.|
+| [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit) <a href="https://github.com/opendatalab/PDF-Extract-Kit"><img src="https://img.shields.io/github/stars/opendatalab/PDF-Extract-Kit"></a> | PDF-Extract-Kit is a powerful open-source toolkit designed to efficiently extract high-quality content from complex and diverse PDF documents.  |
+| [manga-image-translator](https://github.com/zyddnys/manga-image-translator) <a href="https://github.com/zyddnys/manga-image-translator"><img src="https://img.shields.io/github/stars/zyddnys/manga-image-translator"></a> | Translate texts in manga/images.|
+| [March7thAssistant](https://github.com/moesnow/March7thAssistant) <a href="https://github.com/moesnow/March7thAssistant"><img src="https://img.shields.io/github/stars/moesnow/March7thAssistant"></a> | Daily Tasks: Stamina recovery, daily training, claiming rewards, commissions, and farming. |
+| [PaddlePaddle/models](https://github.com/PaddlePaddle/models) <a href="https://github.com/PaddlePaddle/models"><img src="https://img.shields.io/github/stars/PaddlePaddle/models"></a> |PaddlePaddle's industrial-grade model zoo.|
+| [katanaml/sparrow](https://github.com/katanaml/sparrow) <a href="https://github.com/katanaml/sparrow"><img src="https://img.shields.io/github/stars/katanaml/sparrow"></a> | Sparrow is an innovative open-source solution for efficient data extraction and processing from various documents and images. |
+| [RapidOCR](https://github.com/RapidAI/RapidOCR) <a href="https://github.com/RapidAI/RapidOCR"><img src="https://img.shields.io/github/stars/RapidAI/RapidOCR"></a> | Awesome OCR multiple programming languages toolkits based on ONNXRuntime, OpenVINO, PaddlePaddle and PyTorch |
+| [autoMate](https://github.com/yuruotong1/autoMate) <a href="https://github.com/yuruotong1/autoMate"><img src="https://img.shields.io/github/stars/yuruotong1/autoMate"></a> | AI-Powered Local Automation Tool & Let Your Computer Work for You. |
+| [Agent-S](https://github.com/simular-ai/Agent-S) <a href="https://github.com/simular-ai/Agent-S"><img src="https://img.shields.io/github/stars/simular-ai/Agent-S"></a> | A Compositional Generalist-Specialist Framework for Computer Use Agents.  |
+| [pdf-craft](https://github.com/oomol-lab/pdf-craft) <a href="https://github.com/oomol-lab/pdf-craft"><img src="https://img.shields.io/github/stars/oomol-lab/pdf-craft"></a> | PDF Craft can convert PDF files into various other formats. |
+| [VV](https://github.com/Cicada000/VV) <a href="https://github.com/Cicada000/VV"><img src="https://img.shields.io/github/stars/Cicada000/VV"></a> | Zhang Weiwei Quotations Search Project. |
+| [docetl](https://github.com/ucbepic/docetl) <a href="https://github.com/ucbepic/docetl"><img src="https://img.shields.io/github/stars/ucbepic/docetl"></a> | DocETL is a tool for creating and executing data processing pipelines, especially suited for complex document processing tasks. |
+| [ZenlessZoneZero-Auto](https://github.com/sMythicalBird/ZenlessZoneZero-Auto) <a href="https://github.com/sMythicalBird/ZenlessZoneZero-Auto"><img src="https://img.shields.io/github/stars/sMythicalBird/ZenlessZoneZero-Auto"></a> | Zenless Zone Zero Automation Framework. |
+| [Yuxi-Know](https://github.com/xerrors/Yuxi-Know) <a href="https://github.com/xerrors/Yuxi-Know"><img src="https://img.shields.io/github/stars/xerrors/Yuxi-Know"></a> | Knowledge graph question answering system based on LLMs. |
+| [PaddleSharp](https://github.com/sdcb/PaddleSharp) <a href="https://github.com/sdcb/PaddleSharp"><img src="https://img.shields.io/github/stars/sdcb/PaddleSharp"></a>|.NET/C# binding for Baidu paddle inference library and PaddleOCR |
+| [python-office](https://github.com/CoderWanFeng/python-office) <a href="https://github.com/CoderWanFeng/python-office"><img src="https://img.shields.io/github/stars/CoderWanFeng/python-office"></a> | Python tool for office works. |
+| [OnnxOCR](https://github.com/jingsongliujing/OnnxOCR) <a href="https://github.com/jingsongliujing/OnnxOCR"><img src="https://img.shields.io/github/stars/jingsongliujing/OnnxOCR"></a>|A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed |
+| [Frigate](https://github.com/blakeblackshear/frigate) <a href="https://github.com/blakeblackshear/frigate"><img src="https://img.shields.io/github/stars/blakeblackshear/frigate"></a> | Real-time NVR system with AI-powered object detection and License Plate Recognition (LPR) using PaddleOCR. |
+| ... |... |

configs/cls/ch_PP-OCRv3/ch_PP-OCRv3_rotnet.yml

@@ -0,0 +1,98 @@
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 100
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v3_rotnet
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model: null
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+  save_res_path: ./output/rec/predicts_chinese_lite_v2.0.txt
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: L2
+    factor: 1.0e-05
+Architecture:
+  model_type: cls
+  algorithm: CLS
+  Transform: null
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Neck:
+  Head:
+    name: ClsHead
+    class_dim: 4
+
+Loss:
+  name: ClsLoss
+  main_indicator: acc
+
+PostProcess:
+  name: ClsPostProcess
+
+Metric:
+  name: ClsMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - BaseDataAugmentation:
+    - RandAugment:
+    - SSLRotateResize:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys: ["image", "label"]
+  loader:
+    collate_fn: "SSLRotateCollate"
+    shuffle: true
+    batch_size_per_card: 32
+    drop_last: true
+    num_workers: 8
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - SSLRotateResize:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys: ["image", "label"]
+  loader:
+    collate_fn: "SSLRotateCollate"
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 64
+    num_workers: 8
+profiler_options: null

configs/cls/cls_mv3.yml

@@ -0,0 +1,94 @@
+Global:
+  use_gpu: true
+  epoch_num: 100
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/cls/mv3/
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 1000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  label_list: ['0','180']
+
+Architecture:
+  model_type: cls
+  algorithm: CLS
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.35
+    model_name: small
+  Neck:
+  Head:
+    name: ClsHead
+    class_dim: 2
+
+Loss:
+  name: ClsLoss
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: ClsPostProcess
+
+Metric:
+  name: ClsMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/cls
+    label_file_list:
+      - ./train_data/cls/train.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - ClsLabelEncode: # Class handling label
+      - BaseDataAugmentation:
+      - RandAugment:
+      - ClsResizeImg:
+          image_shape: [3, 48, 192]
+      - KeepKeys:
+          keep_keys: ['image', 'label'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 512
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/cls
+    label_file_list:
+      - ./train_data/cls/test.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - ClsLabelEncode: # Class handling label
+      - ClsResizeImg:
+          image_shape: [3, 48, 192]
+      - KeepKeys:
+          keep_keys: ['image', 'label'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 512
+    num_workers: 4

configs/det/PP-OCRv3/PP-OCRv3_det_cml.yml

@@ -0,0 +1,226 @@
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_PP-OCR_v3_det/
+  save_epoch_step: 100
+  eval_batch_step:
+  - 0
+  - 400
+  cal_metric_during_train: false
+  pretrained_model: null
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  distributed: true
+  d2s_train_image_shape: [3, -1, -1]
+  amp_dtype: bfloat16
+
+Architecture:
+  name: DistillationModel
+  algorithm: Distillation
+  model_type: det
+  Models:
+    Student:
+      pretrained:
+      model_type: det
+      algorithm: DB
+      Transform: null
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: true
+      Neck:
+        name: RSEFPN
+        out_channels: 96
+        shortcut: True
+      Head:
+        name: DBHead
+        k: 50
+    Student2:
+      pretrained:
+      model_type: det
+      algorithm: DB
+      Transform: null
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: true
+      Neck:
+        name: RSEFPN
+        out_channels: 96
+        shortcut: True
+      Head:
+        name: DBHead
+        k: 50
+    Teacher:
+      freeze_params: true
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: ResNet_vd
+        in_channels: 3
+        layers: 50
+      Neck:
+        name: LKPAN
+        out_channels: 256
+      Head:
+        name: DBHead
+        kernel_list: [7,2,2]
+        k: 50
+
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDilaDBLoss:
+      weight: 1.0
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      - ["Student2", "Teacher"]
+      key: maps
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+  - DistillationDMLLoss:
+      model_name_pairs:
+      - ["Student", "Student2"]
+      maps_name: "thrink_maps"
+      weight: 1.0
+      model_name_pairs: ["Student", "Student2"]
+      key: maps
+  - DistillationDBLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Student2"]
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 5.0e-05
+
+PostProcess:
+  name: DistillationDBPostProcess
+  model_name: ["Student"]
+  key: head_out
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DistillationMetric
+  base_metric_name: DetMetric
+  main_indicator: hmean
+  key: "Student"
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - CopyPaste:
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 960
+        - 960
+        max_tries: 50
+        keep_ratio: true
+    - MakeBorderMap:
+        shrink_ratio: 0.4
+        thresh_min: 0.3
+        thresh_max: 0.7
+    - MakeShrinkMap:
+        shrink_ratio: 0.4
+        min_text_size: 8
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/det/PP-OCRv3/PP-OCRv3_det_dml.yml

@@ -0,0 +1,174 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/ch_db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [3000, 2000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+  d2s_train_image_shape: [3, -1, -1]
+
+Architecture:
+  name: DistillationModel
+  algorithm: Distillation
+  model_type: det
+  Models:
+    Student:
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: ResNet_vd
+        in_channels: 3
+        layers: 50
+      Neck:
+        name: LKPAN
+        out_channels: 256
+      Head:
+        name: DBHead
+        kernel_list: [7,2,2]
+        k: 50
+    Student2:
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: ResNet_vd
+        in_channels: 3
+        layers: 50
+      Neck:
+        name: LKPAN
+        out_channels: 256
+      Head:
+        name: DBHead
+        kernel_list: [7,2,2]
+        k: 50
+
+
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDMLLoss:
+      model_name_pairs:
+      - ["Student", "Student2"]
+      maps_name: "thrink_maps"
+      weight: 1.0
+      # act: None
+      model_name_pairs: ["Student", "Student2"]
+      key: maps
+  - DistillationDBLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Student2"]
+      # key: maps
+      name: DBLoss
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DistillationDBPostProcess
+  model_name: ["Student", "Student2"]
+  key: head_out
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DistillationMetric
+  base_metric_name: DetMetric
+  main_indicator: hmean
+  key: "Student"
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - CopyPaste:
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [960, 960]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+#           image_shape: [736, 1280]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/det/PP-OCRv3/PP-OCRv3_mobile_det.yml

@@ -0,0 +1,165 @@
+Global:
+  model_name: PP-OCRv3_mobile_det # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/PP-OCRv3_mobile_det/
+  save_epoch_step: 100
+  eval_batch_step:
+  - 0
+  - 400
+  cal_metric_during_train: false
+  pretrained_model: https://paddleocr.bj.bcebos.com/pretrained/MobileNetV3_large_x0_5_pretrained.pdparams
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  distributed: true
+  d2s_train_image_shape: [3, -1, -1]
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 5.0e-05
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 960
+        - 960
+        max_tries: 50
+        keep_ratio: true
+    - MakeBorderMap:
+        shrink_ratio: 0.4
+        thresh_min: 0.3
+        thresh_max: 0.7
+    - MakeShrinkMap:
+        shrink_ratio: 0.4
+        min_text_size: 8
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 8
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest: null
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 2

configs/det/PP-OCRv3/PP-OCRv3_server_det.yml

@@ -0,0 +1,160 @@
+Global:
+  model_name: PP-OCRv3_server_det # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/PP-OCRv3_server_det/
+  save_epoch_step: 100
+  eval_batch_step:
+  - 0
+  - 400
+  cal_metric_during_train: false
+  pretrained_model: https://paddleocr.bj.bcebos.com/pretrained/ResNet50_vd_ssld_pretrained.pdparams
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  distributed: true
+  d2s_train_image_shape: [3, -1, -1]
+  amp_dtype: bfloat16
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Backbone:
+    name: ResNet_vd
+    in_channels: 3
+    layers: 50
+  Neck:
+    name: LKPAN
+    out_channels: 256
+  Head:
+    name: DBHead
+    kernel_list: [7,2,2]
+    k: 50
+
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 5.0e-05
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - CopyPaste:
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 960
+        - 960
+        max_tries: 50
+        keep_ratio: true
+    - MakeBorderMap:
+        shrink_ratio: 0.4
+        thresh_min: 0.3
+        thresh_max: 0.7
+    - MakeShrinkMap:
+        shrink_ratio: 0.4
+        min_text_size: 8
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2
+profiler_options: null

configs/det/PP-OCRv4/PP-OCRv4_det_cml.yml

@@ -0,0 +1,240 @@
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 20
+  save_model_dir: ./output/ch_PP-OCRv4
+  save_epoch_step: 50
+  eval_batch_step:
+  - 0
+  - 1000
+  cal_metric_during_train: false
+  checkpoints: null
+  pretrained_model: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  d2s_train_image_shape: [3, 640, 640]
+  distributed: true
+Architecture:
+  name: DistillationModel
+  algorithm: Distillation
+  model_type: det
+  Models:
+    Student:
+      model_type: det
+      algorithm: DB
+      Transform: null
+      Backbone:
+        name: PPLCNetV3
+        scale: 0.75
+        pretrained: false
+        det: true
+      Neck:
+        name: RSEFPN
+        out_channels: 96
+        shortcut: true
+      Head:
+        name: DBHead
+        k: 50
+    Student2:
+      pretrained: null
+      model_type: det
+      algorithm: DB
+      Transform: null
+      Backbone:
+        name: PPLCNetV3
+        scale: 0.75
+        pretrained: true
+        det: true
+      Neck:
+        name: RSEFPN
+        out_channels: 96
+        shortcut: true
+      Head:
+        name: DBHead
+        k: 50
+    Teacher:
+      pretrained: https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_det_cml_teacher_pretrained/teacher.pdparams
+      freeze_params: true
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: ResNet_vd
+        in_channels: 3
+        layers: 50
+      Neck:
+        name: LKPAN
+        out_channels: 256
+      Head:
+        name: DBHead
+        kernel_list:
+        - 7
+        - 2
+        - 2
+        k: 50
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDilaDBLoss:
+      weight: 1.0
+      model_name_pairs:
+      - - Student
+        - Teacher
+      - - Student2
+        - Teacher
+      key: maps
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+  - DistillationDMLLoss:
+      model_name_pairs:
+      - Student
+      - Student2
+      maps_name: thrink_maps
+      weight: 1.0
+      key: maps
+  - DistillationDBLoss:
+      weight: 1.0
+      model_name_list:
+      - Student
+      - Student2
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 5.0e-05
+PostProcess:
+  name: DistillationDBPostProcess
+  model_name:
+  - Student
+  key: head_out
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+Metric:
+  name: DistillationMetric
+  base_metric_name: DetMetric
+  main_indicator: hmean
+  key: Student
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 640
+        - 640
+        max_tries: 50
+        keep_ratio: true
+    - MakeBorderMap:
+        shrink_ratio: 0.4
+        thresh_min: 0.3
+        thresh_max: 0.7
+        total_epoch: 500
+    - MakeShrinkMap:
+        shrink_ratio: 0.4
+        min_text_size: 8
+        total_epoch: 500
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 16
+    num_workers: 8
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest: 
+        limit_side_len: 960
+        limit_type: max
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 2
+profiler_options: null

configs/det/PP-OCRv4/PP-OCRv4_mobile_det.yml

@@ -0,0 +1,174 @@
+Global:
+  model_name: PP-OCRv4_mobile_det # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: &epoch_num 500
+  log_smooth_window: 20
+  print_batch_step: 100
+  save_model_dir: ./output/PP-OCRv4_mobile_det
+  save_epoch_step: 10
+  eval_batch_step:
+  - 0
+  - 1500
+  cal_metric_during_train: false
+  checkpoints:
+  pretrained_model: https://paddleocr.bj.bcebos.com/pretrained/PPLCNetV3_x0_75_ocr_det.pdparams
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  d2s_train_image_shape: [3, 640, 640]
+  distributed: true
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform: null
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.75
+    det: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+    fix_nan: True
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001 #(8*8c)
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 5.0e-05
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - CopyPaste: null
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 640
+        - 640
+        max_tries: 50
+        keep_ratio: true
+    - MakeBorderMap:
+        shrink_ratio: 0.4
+        thresh_min: 0.3
+        thresh_max: 0.7
+        total_epoch: *epoch_num
+    - MakeShrinkMap:
+        shrink_ratio: 0.4
+        min_text_size: 8
+        total_epoch: *epoch_num
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 8
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest:
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 2
+profiler_options: null

configs/det/PP-OCRv4/PP-OCRv4_mobile_seal_det.yml

@@ -0,0 +1,171 @@
+Global:
+  model_name: PP-OCRv4_mobile_seal_det # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 100
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: output
+  save_epoch_step: 1
+  eval_batch_step:
+  - 0
+  - 100
+  cal_metric_during_train: false
+  checkpoints:
+  pretrained_model: https://paddleocr.bj.bcebos.com/pretrained/PPLCNetV3_x0_75_ocr_det.pdparams
+  save_inference_dir: null
+  use_visualdl: false
+  distributed: true
+  d2s_train_image_shape: [3, 640, 640]
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform: null
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.75
+    det: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 1e-6
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.2
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 0.5
+  box_type: "poly"
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: TextDetDataset
+    data_dir: datasets/ICDAR2015
+    label_file_list:
+      - datasets/ICDAR2015/train.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 640
+        - 640
+        max_tries: 50
+        keep_ratio: true
+    - MakeBorderMap:
+        shrink_ratio: 0.8
+        thresh_min: 0.3
+        thresh_max: 0.7
+        total_epoch: 500
+    - MakeShrinkMap:
+        shrink_ratio: 0.8
+        min_text_size: 8
+        total_epoch: 500
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 8
+    num_workers: 3
+
+Eval:
+  dataset:
+    name: TextDetDataset
+    data_dir: datasets/ICDAR2015
+    label_file_list:
+      - datasets/ICDAR2015/val.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest:
+        resize_long: 736
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 0
+profiler_options: null

configs/det/PP-OCRv4/PP-OCRv4_server_det.yml

@@ -0,0 +1,175 @@
+Global:
+  model_name: PP-OCRv4_server_det # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: &epoch_num 500
+  log_smooth_window: 20
+  print_batch_step: 100
+  save_model_dir: ./output/PP-OCRv4_server_det
+  save_epoch_step: 10
+  eval_batch_step:
+  - 0
+  - 1500
+  cal_metric_during_train: false
+  checkpoints:
+  pretrained_model: https://paddleocr.bj.bcebos.com/pretrained/PPHGNet_small_ocr_det.pdparams
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  d2s_train_image_shape: [3, 640, 640]
+  distributed: true
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform: null
+  Backbone:
+    name: PPHGNet_small
+    det: True
+  Neck:
+    name: LKPAN
+    out_channels: 256
+    intracl: true
+  Head:
+    name: PFHeadLocal
+    k: 50
+    mode: "large"
+    fix_nan: True
+    
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001 #(8*8c)
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 1e-6
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - CopyPaste: null
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 640
+        - 640
+        max_tries: 50
+        keep_ratio: true
+    - MakeBorderMap:
+        shrink_ratio: 0.4
+        thresh_min: 0.3
+        thresh_max: 0.7
+        total_epoch: *epoch_num
+    - MakeShrinkMap:
+        shrink_ratio: 0.4
+        min_text_size: 8
+        total_epoch: *epoch_num
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 8
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest:
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 2
+profiler_options: null

configs/det/PP-OCRv4/PP-OCRv4_server_seal_det.yml

@@ -0,0 +1,171 @@
+Global:
+  model_name: PP-OCRv4_server_seal_det # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 100
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: output
+  save_epoch_step: 1
+  eval_batch_step:
+  - 0
+  - 100
+  cal_metric_during_train: false
+  checkpoints:
+  pretrained_model: https://paddleocr.bj.bcebos.com/pretrained/PPHGNet_small_ocr_det.pdparams
+  save_inference_dir: null
+  use_visualdl: false
+  distributed: true
+  d2s_train_image_shape: [3, 640, 640]
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform: null
+  Backbone:
+    name: PPHGNet_small
+    det: True
+  Neck:
+    name: LKPAN
+    out_channels: 256
+    intracl: true
+  Head:
+    name: PFHeadLocal
+    k: 50
+    mode: "large"
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 1e-6
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.2
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 0.5
+  box_type: "poly"
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: TextDetDataset
+    data_dir: datasets/ICDAR2015
+    label_file_list:
+      - datasets/ICDAR2015/train.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 640
+        - 640
+        max_tries: 50
+        keep_ratio: true
+    - MakeBorderMap:
+        shrink_ratio: 0.8
+        thresh_min: 0.3
+        thresh_max: 0.7
+        total_epoch: 500
+    - MakeShrinkMap:
+        shrink_ratio: 0.8
+        min_text_size: 8
+        total_epoch: 500
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 4
+    num_workers: 3
+
+Eval:
+  dataset:
+    name: TextDetDataset
+    data_dir: datasets/ICDAR2015
+    label_file_list:
+      - datasets/ICDAR2015/val.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest:
+        resize_long: 736
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 0
+profiler_options: null

configs/det/PP-OCRv5/PP-OCRv5_mobile_det.yml

@@ -0,0 +1,174 @@
+Global:
+  model_name: PP-OCRv5_mobile_det # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: &epoch_num 500
+  log_smooth_window: 20
+  print_batch_step: 100
+  save_model_dir: ./output/PP-OCRv5_mobile_det
+  save_epoch_step: 10
+  eval_batch_step:
+  - 0
+  - 1500
+  cal_metric_during_train: false
+  checkpoints:
+  pretrained_model: https://paddleocr.bj.bcebos.com/pretrained/PPLCNetV3_x0_75_ocr_det.pdparams
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  d2s_train_image_shape: [3, 640, 640]
+  distributed: true
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform: null
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.75
+    det: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+    fix_nan: True
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001 #(8*8c)
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 5.0e-05
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - CopyPaste: null
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 640
+        - 640
+        max_tries: 50
+        keep_ratio: true
+    - MakeBorderMap:
+        shrink_ratio: 0.4
+        thresh_min: 0.3
+        thresh_max: 0.7
+        total_epoch: *epoch_num
+    - MakeShrinkMap:
+        shrink_ratio: 0.4
+        min_text_size: 8
+        total_epoch: *epoch_num
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 8
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest:
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 2
+profiler_options: null

configs/det/PP-OCRv5/PP-OCRv5_server_det.yml

@@ -0,0 +1,173 @@
+Global:
+  model_name: PP-OCRv5_server_det # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: &epoch_num 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/PP-OCRv5_server_det
+  save_epoch_step: 10
+  eval_batch_step:
+  - 0
+  - 1500
+  cal_metric_during_train: false
+  checkpoints:
+  pretrained_model: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PPHGNetV2_B4_ocr_det.pdparams
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  distributed: true
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform: null
+  Backbone:
+    name: PPHGNetV2_B4
+    det: True
+  Neck:
+    name: LKPAN
+    out_channels: 256
+    intracl: true
+  Head:
+    name: PFHeadLocal
+    k: 50
+    mode: "large"
+    
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001 #(8*8c)
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 1e-6
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - CopyPaste: null
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 640
+        - 640
+        max_tries: 50
+        keep_ratio: true
+    - MakeBorderMap:
+        shrink_ratio: 0.4
+        thresh_min: 0.3
+        thresh_max: 0.7
+        total_epoch: *epoch_num
+    - MakeShrinkMap:
+        shrink_ratio: 0.4
+        min_text_size: 8
+        total_epoch: *epoch_num
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 8
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest:
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 2
+profiler_options: null

configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml

@@ -0,0 +1,206 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/ch_db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [3000, 2000]
+  cal_metric_during_train: False
+  pretrained_model: 
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+  use_amp: False
+  amp_level: O2
+  amp_dtype: bfloat16
+
+Architecture:
+  name: DistillationModel
+  algorithm: Distillation
+  model_type: det
+  Models:
+    Teacher:
+      pretrained: ./pretrain_models/ch_ppocr_server_v2.0_det_train/best_accuracy
+      freeze_params: true
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Transform:
+      Backbone:
+        name: ResNet_vd
+        layers: 18
+      Neck:
+        name: DBFPN
+        out_channels: 256
+      Head:
+        name: DBHead
+        k: 50
+    Student:
+      pretrained:
+      freeze_params: false
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: True
+      Neck:
+        name: DBFPN
+        out_channels: 96
+      Head:
+        name: DBHead
+        k: 50
+    Student2:
+      pretrained:
+      freeze_params: false
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Transform:
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: True
+      Neck:
+        name: DBFPN
+        out_channels: 96
+      Head:
+        name: DBHead
+        k: 50
+    
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDilaDBLoss:
+      weight: 1.0
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      - ["Student2", "Teacher"]
+      key: maps
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+  - DistillationDMLLoss:
+      model_name_pairs:
+      - ["Student", "Student2"]
+      maps_name: "thrink_maps"
+      weight: 1.0
+      # act: None
+      model_name_pairs: ["Student", "Student2"]
+      key: maps
+  - DistillationDBLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Student2"]
+      # key: maps
+      # name: DBLoss
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DistillationDBPostProcess
+  model_name: ["Student", "Student2", "Teacher"]
+  # key: maps
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DistillationMetric
+  base_metric_name: DetMetric
+  main_indicator: hmean
+  key: "Student"
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - CopyPaste:
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [960, 960]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_distill.yml

@@ -0,0 +1,175 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/ch_db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [3000, 2000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  name: DistillationModel
+  algorithm: Distillation
+  model_type: det
+  Models:
+    Student:
+      pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+      freeze_params: false
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: True
+      Neck:
+        name: DBFPN
+        out_channels: 96
+      Head:
+        name: DBHead
+        k: 50
+    Teacher:
+      pretrained: ./pretrain_models/ch_ppocr_server_v2.0_det_train/best_accuracy
+      freeze_params: true
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Transform:
+      Backbone:
+        name: ResNet_vd
+        layers: 18
+      Neck:
+        name: DBFPN
+        out_channels: 256
+      Head:
+        name: DBHead
+        k: 50
+
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDilaDBLoss:
+      weight: 1.0
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      key: maps
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+  - DistillationDBLoss:
+      weight: 1.0
+      model_name_list: ["Student"]
+      name: DBLoss
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DistillationDBPostProcess
+  model_name: ["Student"]
+  key: head_out
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DistillationMetric
+  base_metric_name: DetMetric
+  main_indicator: hmean
+  key: "Student"
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - CopyPaste:
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [960, 960]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+#           image_shape: [736, 1280]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_dml.yml

@@ -0,0 +1,178 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/ch_db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [3000, 2000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  name: DistillationModel
+  algorithm: Distillation
+  model_type: det
+  Models:
+    Student:
+      pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+      freeze_params: false
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: True
+      Neck:
+        name: DBFPN
+        out_channels: 96
+      Head:
+        name: DBHead
+        k: 50
+    Teacher:
+      pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+      freeze_params: false
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Transform:
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: True
+      Neck:
+        name: DBFPN
+        out_channels: 96
+      Head:
+        name: DBHead
+        k: 50
+
+
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDMLLoss:
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      maps_name: "thrink_maps"
+      weight: 1.0
+      # act: None
+      model_name_pairs: ["Student", "Teacher"]
+      key: maps
+  - DistillationDBLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Teacher"]
+      # key: maps
+      name: DBLoss
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DistillationDBPostProcess
+  model_name: ["Student", "Teacher"]
+  key: head_out
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DistillationMetric
+  base_metric_name: DetMetric
+  main_indicator: hmean
+  key: "Student"
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - CopyPaste:
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [960, 960]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+#           image_shape: [736, 1280]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_student.yml

@@ -0,0 +1,132 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 400]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/student.pdparams
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: DBFPN
+    out_channels: 96
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [960, 960]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+#           image_shape: [736, 1280]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml

@@ -0,0 +1,132 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/ch_db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [3000, 2000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: DBFPN
+    out_channels: 96
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [960, 960]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+#           image_shape: [736, 1280]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml

@@ -0,0 +1,131 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/ch_db_res18/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [3000, 2000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet18_vd_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: ResNet_vd
+    layers: 18
+    disable_se: True
+  Neck:
+    name: DBFPN
+    out_channels: 256
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [960, 960]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+#           image_shape: [736, 1280]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/det/det_mv3_db.yml

@@ -0,0 +1,133 @@
+Global:
+  use_gpu: true
+  use_xpu: false
+  use_mlu: false
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: DBFPN
+    out_channels: 256
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [640, 640]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 16
+    num_workers: 8
+    use_shared_memory: True
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          image_shape: [736, 1280]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 8
+    use_shared_memory: True

configs/det/det_mv3_east.yml

@@ -0,0 +1,109 @@
+Global:
+  use_gpu: true
+  epoch_num: 10000
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/east_mv3/
+  save_epoch_step: 1000
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [4000, 5000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: 
+  save_res_path: ./output/det_east/predicts_east.txt
+
+Architecture:
+  model_type: det
+  algorithm: EAST
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: EASTFPN
+    model_name: small
+  Head:
+    name: EASTHead
+    model_name: small
+
+Loss:
+  name: EASTLoss
+  
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+  #  name: Cosine
+    learning_rate: 0.001
+  #  warmup_epoch: 0
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: EASTPostProcess
+  score_thresh: 0.8
+  cover_thresh: 0.1
+  nms_thresh: 0.2
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - EASTProcessTrain:
+          image_shape: [512, 512]
+          background_ratio: 0.125
+          min_crop_side_ratio: 0.1
+          min_text_size: 10
+      - KeepKeys:
+          keep_keys: ['image', 'score_map', 'geo_map', 'training_mask'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 16
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          limit_side_len: 2400
+          limit_type: max
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/det/det_mv3_pse.yml

@@ -0,0 +1,135 @@
+Global:
+  use_gpu: true
+  epoch_num: 600
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/det_mv3_pse/
+  save_epoch_step: 600
+  # evaluation is run every 63 iterations
+  eval_batch_step: [ 0,63 ]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints: #./output/det_r50_vd_pse_batch8_ColorJitter/best_accuracy
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_pse/predicts_pse.txt
+
+Architecture:
+  model_type: det
+  algorithm: PSE
+  Transform: null
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: FPN
+    out_channels: 96
+  Head:
+    name: PSEHead
+    hidden_dim: 96
+    out_channels: 7
+
+Loss:
+  name: PSELoss
+  alpha: 0.7
+  ohem_ratio: 3
+  kernel_sample_mask: pred
+  reduction: none
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Step
+    learning_rate: 0.001
+    step_size: 200
+    gamma: 0.1
+  regularizer:
+    name: 'L2'
+    factor: 0.0005
+
+PostProcess:
+  name: PSEPostProcess
+  thresh: 0
+  box_thresh: 0.85
+  min_area: 16
+  box_type: quad # 'quad' or 'poly'
+  scale: 1
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [ 1.0 ]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - ColorJitter:
+          brightness: 0.12549019607843137
+          saturation: 0.5
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Resize, 'args': { 'size': [ 0.5, 3 ] } }
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [ -10, 10 ] } }
+      - MakePseGt:
+          kernel_num: 7
+          min_shrink_ratio: 0.4
+          size: 640
+      - RandomCropImgMask:
+          size: [ 640,640 ]
+          main_key: gt_text
+          crop_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [ 0.485, 0.456, 0.406 ]
+          std: [ 0.229, 0.224, 0.225 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 16
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    ratio_list: [ 1.0 ]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          limit_side_len: 736
+          limit_type: min
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [ 0.485, 0.456, 0.406 ]
+          std: [ 0.229, 0.224, 0.225 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'image', 'shape', 'polys', 'ignore_tags' ]
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 8

configs/det/det_r18_vd_ct.yml

@@ -0,0 +1,107 @@
+Global:
+  use_gpu: true
+  epoch_num: 600
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/det_ct/
+  save_epoch_step: 10
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0,1000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet18_vd_pretrained.pdparams
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img623.jpg
+  save_res_path: ./output/det_ct/predicts_ct.txt
+
+Architecture:
+  model_type: det
+  algorithm: CT
+  Transform:
+  Backbone:
+    name: ResNet_vd
+    layers: 18
+  Neck:
+    name: CTFPN
+  Head:
+    name: CT_Head
+    in_channels: 512
+    hidden_dim: 128
+    num_classes: 3
+
+Loss:
+  name: CTLoss
+
+Optimizer:
+  name: Adam
+  lr:  #PolynomialDecay
+    name: Linear 
+    learning_rate: 0.001
+    end_lr: 0.
+    epochs: 600
+    step_each_epoch: 1254
+    power: 0.9
+
+PostProcess:
+  name: CTPostProcess
+  box_type: poly
+
+Metric:
+  name: CTMetric
+  main_indicator: f_score
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/total_text/train
+    label_file_list:
+      - ./train_data/total_text/train/train.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage:
+          img_mode: RGB
+          channel_first: False
+      - CTLabelEncode: # Class handling label
+      - RandomScale:
+      - MakeShrink:
+      - GroupRandomHorizontalFlip:
+      - GroupRandomRotate:
+      - GroupRandomCropPadding:
+      - MakeCentripetalShift:
+      - ColorJitter:
+          brightness: 0.125
+          saturation: 0.5 
+      - ToCHWImage: 
+      - NormalizeImage:
+      - KeepKeys:
+          keep_keys: ['image', 'gt_kernel', 'training_mask', 'gt_instance', 'gt_kernel_instance', 'training_mask_distance', 'gt_distance'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: True
+    batch_size_per_card: 4
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/total_text/test
+    label_file_list:
+      - ./train_data/total_text/test/test.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage:
+          img_mode: RGB
+          channel_first: False
+      - CTLabelEncode: # Class handling label
+      - ScaleAlignedShort:
+      - NormalizeImage:
+          order: 'hwc'
+      - ToCHWImage: 
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'texts'] # the order of the dataloader list          
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1
+    num_workers: 2

configs/det/det_r50_db++_icdar15.yml

@@ -0,0 +1,164 @@
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 1000
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/det_r50_icdar15/
+  save_epoch_step: 200
+  eval_batch_step:
+  - 0
+  - 2000
+  cal_metric_during_train: false
+  pretrained_model: ./pretrain_models/ResNet50_dcn_asf_synthtext_pretrained
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+Architecture:
+  model_type: det
+  algorithm: DB++
+  Transform: null
+  Backbone:
+    name: ResNet
+    layers: 50
+    dcn_stage: [False, True, True, True]
+  Neck:
+    name: DBFPN
+    out_channels: 256
+    use_asf: True
+  Head:
+    name: DBHead
+    k: 50
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: BCELoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: DecayLearningRate
+    learning_rate: 0.007
+    epochs: 1000
+    factor: 0.9
+    end_lr: 0
+  weight_decay: 0.0001
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+  det_box_type: 'quad' # 'quad' or 'poly'
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/                                                                        
+    label_file_list:                                                                                            
+    - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt                                                     
+    ratio_list:                                                                                                 
+    - 1.0 
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 640
+        - 640
+        max_tries: 10
+        keep_ratio: true
+    - MakeShrinkMap:
+        shrink_ratio: 0.4
+        min_text_size: 8
+    - MakeBorderMap:
+        shrink_ratio: 0.4
+        thresh_min: 0.3
+        thresh_max: 0.7
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.48109378172549
+        - 0.45752457890196
+        - 0.40787054090196
+        std:
+        - 1.0
+        - 1.0
+        - 1.0
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 4
+    num_workers: 8
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization                                                                          
+    label_file_list:                                                                                            
+    - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest:
+        image_shape:
+        - 1152
+        - 2048
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.48109378172549
+        - 0.45752457890196
+        - 0.40787054090196
+        std:
+        - 1.0
+        - 1.0
+        - 1.0
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 2
+profiler_options: null

configs/det/det_r50_db++_td_tr.yml

@@ -0,0 +1,167 @@
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 1000
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/det_r50_td_tr/
+  save_epoch_step: 200
+  eval_batch_step:
+  - 0
+  - 2000
+  cal_metric_during_train: false
+  pretrained_model: ./pretrain_models/ResNet50_dcn_asf_synthtext_pretrained
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+Architecture:
+  model_type: det
+  algorithm: DB++
+  Transform: null
+  Backbone:
+    name: ResNet
+    layers: 50
+    dcn_stage: [False, True, True, True]
+  Neck:
+    name: DBFPN
+    out_channels: 256
+    use_asf: True
+  Head:
+    name: DBHead
+    k: 50
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: BCELoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: DecayLearningRate
+    learning_rate: 0.007
+    epochs: 1000
+    factor: 0.9
+    end_lr: 0
+  weight_decay: 0.0001
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.5
+  max_candidates: 1000
+  unclip_ratio: 1.5
+  det_box_type: 'quad' # 'quad' or 'poly'
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/                                                                                 
+    label_file_list:                                                                                            
+    - ./train_data/TD_TR/TD500/train_gt_labels.txt                                                           
+    - ./train_data/TD_TR/TR400/gt_labels.txt                                                                 
+    ratio_list:                                                                                                 
+    - 1.0                                                                                                       
+    - 1.0 
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - IaaAugment:
+        augmenter_args:
+        - type: Fliplr
+          args:
+            p: 0.5
+        - type: Affine
+          args:
+            rotate:
+            - -10
+            - 10
+        - type: Resize
+          args:
+            size:
+            - 0.5
+            - 3
+    - EastRandomCropData:
+        size:
+        - 640
+        - 640
+        max_tries: 10
+        keep_ratio: true
+    - MakeShrinkMap:
+        shrink_ratio: 0.4
+        min_text_size: 8
+    - MakeBorderMap:
+        shrink_ratio: 0.4
+        thresh_min: 0.3
+        thresh_max: 0.7
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.48109378172549
+        - 0.45752457890196
+        - 0.40787054090196
+        std:
+        - 1.0
+        - 1.0
+        - 1.0
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  loader:
+    shuffle: true
+    drop_last: false
+    batch_size_per_card: 4
+    num_workers: 8
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/                                                                          
+    label_file_list:                                                                                            
+    - ./train_data/TD_TR/TD500/test_gt_labels.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest:
+        image_shape:
+        - 736
+        - 736
+        keep_ratio: True
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.48109378172549
+        - 0.45752457890196
+        - 0.40787054090196
+        std:
+        - 1.0
+        - 1.0
+        - 1.0
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 2
+profiler_options: null

configs/det/det_r50_drrg_ctw.yml

@@ -0,0 +1,133 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 5
+  save_model_dir: ./output/det_r50_drrg_ctw/
+  save_epoch_step: 100
+  # evaluation is run every 1260 iterations
+  eval_batch_step: [37800, 1260]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained.pdparams 
+  checkpoints: 
+  save_inference_dir: 
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_drrg/predicts_drrg.txt
+
+
+Architecture:
+  model_type: det
+  algorithm: DRRG
+  Transform:
+  Backbone:
+    name: ResNet_vd
+    layers: 50
+  Neck:
+    name: FPN_UNet
+    in_channels: [256, 512, 1024, 2048]
+    out_channels: 32
+  Head:
+    name: DRRGHead
+    in_channels: 32
+    text_region_thr: 0.3
+    center_region_thr: 0.4
+Loss:
+  name: DRRGLoss
+  
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: DecayLearningRate
+    learning_rate: 0.028
+    epochs: 1200
+    factor: 0.9
+    end_lr: 0.0000001
+  weight_decay: 0.0001
+
+PostProcess:
+  name: DRRGPostprocess
+  link_thr: 0.8
+
+Metric:
+  name: DetFCEMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ctw1500/imgs/
+    label_file_list: 
+      - ./train_data/ctw1500/imgs/training.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+          ignore_orientation: True
+      - DetLabelEncode: # Class handling label
+      - ColorJitter: 
+          brightness: 0.12549019607843137
+          saturation: 0.5
+      - RandomScaling: 
+      - RandomCropFlip:
+          crop_ratio: 0.5
+      - RandomCropPolyInstances:
+          crop_ratio: 0.8
+          min_side_ratio: 0.3
+      - RandomRotatePolyInstances:
+          rotate_ratio: 0.5
+          max_angle: 60
+          pad_with_fixed_color: False
+      - SquareResizePad:
+          target_size: 800
+          pad_ratio: 0.6
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+      - DRRGTargets:
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
+            'gt_top_height_map', 'gt_bot_height_map', 'gt_sin_map',
+            'gt_cos_map', 'gt_comp_attribs'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 4
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ctw1500/imgs/
+    label_file_list:
+      - ./train_data/ctw1500/imgs/test.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+          ignore_orientation: True
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          limit_type: 'min'
+          limit_side_len: 640
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - Pad: 
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/det/det_r50_vd_db.yml

@@ -0,0 +1,128 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/det_r50_vd/
+  save_epoch_step: 1200
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0,2000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: ResNet_vd
+    layers: 50
+  Neck:
+    name: DBFPN
+    out_channels: 256
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  name: DBLoss
+  balance_loss: true
+  main_loss_type: DiceLoss
+  alpha: 5
+  beta: 10
+  ohem_ratio: 3
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.7
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [640, 640]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 16
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          image_shape: [736, 1280]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 8