[Update] Inital Update

app.py

@@ -0,0 +1,139 @@
+import cv2
+import argparse
+import gradio as gr
+import numpy as np
+
+# MMOCR
+from mmocr.apis.inferencers import MMOCRInferencer
+
+# BUILD MMOCR
+
+
+def arg_parse():
+    parser = argparse.ArgumentParser(description='MMOCR demo for gradio app')
+    parser.add_argument(
+        '--rec_config',
+        type=str,
+        default='mmocr-dev-1.x/configs/textrecog/maerec/maerec_b_union14m.py',
+        help='The recognition config file.')
+    parser.add_argument(
+        '--rec_weight',
+        type=str,
+        default=
+        'mmocr-dev-1.x/work_dirs/maerec_b_union14m/maerec_b_union14m.pth',
+        help='The recognition weight file.')
+    parser.add_argument(
+        '--det_config',
+        type=str,
+        default=
+        'mmocr-dev-1.x/configs/textdet/dbnetpp/dbnetpp_resnet50-oclip_fpnc_1200e_icdar2015.py',  # noqa,
+        help='The detection config file.')
+    parser.add_argument(
+        '--det_weight',
+        type=str,
+        default='mmocr-dev-1.x/dbnetpp.pth',
+        help='The detection weight file.')
+    parser.add_argument(
+        '--device',
+        type=str,
+        default='cuda:0',
+        help='The device used for inference.')
+    args = parser.parse_args()
+    return args
+
+
+def run_mmocr(img: np.ndarray, use_detector: bool = True):
+    """Run MMOCR and SAM
+
+    Args:
+        img (np.ndarray): Input image
+        use_detector (bool, optional): Whether to use detector. Defaults to
+            True.
+    """
+    if use_detector:
+        mode = 'det_rec'
+    else:
+        mode = 'rec'
+    # Build MMOCR
+    mmocr_inferencer.mode = mode
+    result = mmocr_inferencer(img, return_vis=True)
+    visualization = result['visualization'][0]
+    result = result['predictions'][0]
+
+    if mode == 'det_rec':
+        rec_texts = result['rec_texts']
+        det_polygons = result['det_polygons']
+        det_results = []
+        for rec_text, det_polygon in zip(rec_texts, det_polygons):
+            det_polygon = np.array(det_polygon).astype(np.int32).tolist()
+            det_results.append(f'{rec_text}: {det_polygon}')
+        out_results = '\n'.join(det_results)
+        visualization = cv2.cvtColor(
+            np.array(visualization), cv2.COLOR_RGB2BGR)
+    else:
+        rec_text = result['rec_texts'][0]
+        rec_score = result['rec_scores'][0]
+        out_results = f'pred: {rec_text} \n score: {rec_score:.2f}'
+        visualization = None
+    return visualization, out_results
+
+
+if __name__ == '__main__':
+    args = arg_parse()
+    mmocr_inferencer = MMOCRInferencer(
+        args.det_config,
+        args.det_weight,
+        args.rec_config,
+        args.rec_weight,
+        device=args.device)
+
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column(scale=1):
+                gr.HTML("""
+                    <div style="text-align: center; max-width: 1200px; margin: 20px auto;">
+                    <h1 style="font-weight: 900; font-size: 3rem; margin: 0rem">
+                        MAERec: A MAE-pretrained Scene Text Recognizer
+                    </h1>
+                    <h3 style="font-weight: 450; font-size: 1rem; margin: 0rem"> 
+                    [<a href="https://arxiv.org/abs/2305.10855" style="color:blue;">arXiv</a>] 
+                    [<a href="https://github.com/Mountchicken/Union14M" style="color:green;">Code</a>]
+                    </h3>
+                    <h2 style="text-align: left; font-weight: 600; font-size: 1rem; margin-top: 0.5rem; margin-bottom: 0.5rem">
+                    MAERec is a scene text recognition model composed of a ViT backbone and a Transformer decoder in auto-regressive
+                    style. It shows an outstanding performance in scene text recognition, especially when pre-trained on the
+                    Union14M-U through MAE.
+                    </h2>
+                    <h2 style="text-align: left; font-weight: 600; font-size: 1rem; margin-top: 0.5rem; margin-bottom: 0.5rem">
+                    In this demo, we combine MAERec with DBNet++ to build an
+                    end-to-end scene text recognition model.
+                    </h2>
+                    </div>
+                    """)
+                gr.Image('github/maerec.png')
+            with gr.Column(scale=1):
+                input_image = gr.Image(label='Input Image')
+                output_image = gr.Image(label='Output Image')
+                use_detector = gr.Checkbox(
+                    label=
+                    'Use Scene Text Detector or Not (Disabled for Recognition Only)',
+                    default=True)
+                det_results = gr.Textbox(label='Detection Results')
+                mmocr = gr.Button('Run MMOCR')
+                gr.Markdown("## Image Examples")
+        with gr.Row():
+            gr.Examples(
+                examples=[
+                    'github/author.jpg', 'github/gradio1.jpeg',
+                    'github/Art_Curve_178.jpg', 'github/cute_3.jpg',
+                    'github/cute_168.jpg', 'github/hiercurve_2229.jpg',
+                    'github/ic15_52.jpg', 'github/ic15_698.jpg',
+                    'github/Art_Curve_352.jpg'
+                ],
+                inputs=input_image,
+            )
+        mmocr.click(
+            fn=run_mmocr,
+            inputs=[input_image, use_detector],
+            outputs=[output_image, det_results])
+    demo.launch(debug=True)

mmocr-dev-1.x/.circleci/config.yml

@@ -0,0 +1,34 @@
+version: 2.1
+
+# this allows you to use CircleCI's dynamic configuration feature
+setup: true
+
+# the path-filtering orb is required to continue a pipeline based on
+# the path of an updated fileset
+orbs:
+  path-filtering: circleci/[email protected]
+
+workflows:
+  # the always-run workflow is always triggered, regardless of the pipeline parameters.
+  always-run:
+    jobs:
+      # the path-filtering/filter job determines which pipeline
+      # parameters to update.
+      - path-filtering/filter:
+          name: check-updated-files
+          # 3-column, whitespace-delimited mapping. One mapping per
+          # line:
+          # <regex path-to-test> <parameter-to-set> <value-of-pipeline-parameter>
+          mapping: |
+            mmocr/.* lint_only false
+            requirements/.* lint_only false
+            tests/.* lint_only false
+            tools/.* lint_only false
+            configs/.* lint_only false
+            .circleci/.* lint_only false
+          base-revision: dev-1.x
+          # this is the path of the configuration we should trigger once
+          # path filtering and pipeline parameter value updates are
+          # complete. In this case, we are using the parent dynamic
+          # configuration itself.
+          config-path: .circleci/test.yml

mmocr-dev-1.x/.circleci/docker/Dockerfile

@@ -0,0 +1,11 @@
+ARG PYTORCH="1.8.1"
+ARG CUDA="10.2"
+ARG CUDNN="7"
+
+FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
+
+# To fix GPG key error when running apt-get update
+RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub
+RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub
+
+RUN apt-get update && apt-get install -y ninja-build libglib2.0-0 libsm6 libxrender-dev libxext6 libgl1-mesa-glx

mmocr-dev-1.x/.circleci/test.yml

@@ -0,0 +1,196 @@
+version: 2.1
+
+# the default pipeline parameters, which will be updated according to
+# the results of the path-filtering orb
+parameters:
+  lint_only:
+    type: boolean
+    default: true
+
+jobs:
+  lint:
+    docker:
+      - image: cimg/python:3.7.4
+    steps:
+      - checkout
+      - run:
+          name: Install pre-commit hook
+          command: |
+            pip install pre-commit
+            pre-commit install
+      - run:
+          name: Linting
+          command: pre-commit run --all-files
+      - run:
+          name: Check docstring coverage
+          command: |
+            pip install interrogate
+            interrogate -v --ignore-init-method --ignore-module --ignore-nested-functions --ignore-magic --ignore-regex "__repr__" --fail-under 90 mmocr
+  build_cpu:
+    parameters:
+      # The python version must match available image tags in
+      # https://circleci.com/developer/images/image/cimg/python
+      python:
+        type: string
+      torch:
+        type: string
+      torchvision:
+        type: string
+    docker:
+      - image: cimg/python:<< parameters.python >>
+    resource_class: large
+    steps:
+      - checkout
+      - run:
+          name: Install Libraries
+          command: |
+            sudo apt-get update
+            sudo apt-get install -y ninja-build libglib2.0-0 libsm6 libxrender-dev libxext6 libgl1-mesa-glx libjpeg-dev zlib1g-dev libtinfo-dev libncurses5 libgeos-dev
+      - run:
+          name: Configure Python & pip
+          command: |
+            pip install --upgrade pip
+            pip install wheel
+      - run:
+          name: Install PyTorch
+          command: |
+            python -V
+            pip install torch==<< parameters.torch >>+cpu torchvision==<< parameters.torchvision >>+cpu -f https://download.pytorch.org/whl/torch_stable.html
+      - run:
+          name: Install mmocr dependencies
+          command: |
+            pip install git+https://github.com/open-mmlab/mmengine.git@main
+            pip install -U openmim
+            mim install 'mmcv >= 2.0.0rc1'
+            pip install git+https://github.com/open-mmlab/[email protected]
+            pip install -r requirements/tests.txt
+      - run:
+          name: Build and install
+          command: |
+            pip install -e .
+      - run:
+          name: Run unittests
+          command: |
+            coverage run --branch --source mmocr -m pytest tests/
+            coverage xml
+            coverage report -m
+  build_cuda:
+    parameters:
+      torch:
+        type: string
+      cuda:
+        type: enum
+        enum: ["10.1", "10.2", "11.1", "11.7"]
+      cudnn:
+        type: integer
+        default: 7
+    machine:
+      image: ubuntu-2004-cuda-11.4:202110-01
+      # docker_layer_caching: true
+    resource_class: gpu.nvidia.small
+    steps:
+      - checkout
+      - run:
+          # Cloning repos in VM since Docker doesn't have access to the private key
+          name: Clone Repos
+          command: |
+            git clone -b main --depth 1 https://github.com/open-mmlab/mmengine.git /home/circleci/mmengine
+            git clone -b dev-3.x --depth 1 https://github.com/open-mmlab/mmdetection.git /home/circleci/mmdetection
+      - run:
+          name: Build Docker image
+          command: |
+            docker build .circleci/docker -t mmocr:gpu --build-arg PYTORCH=<< parameters.torch >> --build-arg CUDA=<< parameters.cuda >> --build-arg CUDNN=<< parameters.cudnn >>
+            docker run --gpus all -t -d -v /home/circleci/project:/mmocr -v /home/circleci/mmengine:/mmengine -v /home/circleci/mmdetection:/mmdetection -w /mmocr --name mmocr mmocr:gpu
+      - run:
+          name: Install mmocr dependencies
+          command: |
+            docker exec mmocr pip install -e /mmengine
+            docker exec mmocr pip install -U openmim
+            docker exec mmocr mim install 'mmcv >= 2.0.0rc1'
+            docker exec mmocr pip install -e /mmdetection
+            docker exec mmocr pip install -r requirements/tests.txt
+      - run:
+          name: Build and install
+          command: |
+            docker exec mmocr pip install -e .
+      - run:
+          name: Run unittests
+          command: |
+            docker exec mmocr pytest tests/
+
+workflows:
+  pr_stage_lint:
+    when: << pipeline.parameters.lint_only >>
+    jobs:
+      - lint:
+          name: lint
+          filters:
+            branches:
+              ignore:
+                - dev-1.x
+                - 1.x
+                - main
+  pr_stage_test:
+    when:
+      not:
+        << pipeline.parameters.lint_only >>
+    jobs:
+      - lint:
+          name: lint
+          filters:
+            branches:
+              ignore:
+                - dev-1.x
+                - test-1.x
+                - main
+      - build_cpu:
+          name: minimum_version_cpu
+          torch: 1.6.0
+          torchvision: 0.7.0
+          python: "3.7"
+          requires:
+            - lint
+      - build_cpu:
+          name: maximum_version_cpu
+          torch: 2.0.0
+          torchvision: 0.15.1
+          python: 3.9.0
+          requires:
+            - minimum_version_cpu
+      - hold:
+          type: approval
+          requires:
+            - maximum_version_cpu
+      - build_cuda:
+          name: mainstream_version_gpu
+          torch: 1.8.1
+          # Use double quotation mark to explicitly specify its type
+          # as string instead of number
+          cuda: "10.2"
+          requires:
+            - hold
+      - build_cuda:
+          name: mainstream_version_gpu
+          torch: 2.0.0
+          # Use double quotation mark to explicitly specify its type
+          # as string instead of number
+          cuda: "11.7"
+          cudnn: 8
+          requires:
+            - hold
+  merge_stage_test:
+    when:
+      not:
+        << pipeline.parameters.lint_only >>
+    jobs:
+      - build_cuda:
+          name: minimum_version_gpu
+          torch: 1.6.0
+          # Use double quotation mark to explicitly specify its type
+          # as string instead of number
+          cuda: "10.1"
+          filters:
+            branches:
+              only:
+                - dev-1.x
+                - main

mmocr-dev-1.x/.codespellrc

@@ -0,0 +1,5 @@
+[codespell]
+skip = *.ipynb
+count =
+quiet-level = 3
+ignore-words-list = convertor,convertors,formating,nin,wan,datas,hist,ned

mmocr-dev-1.x/.coveragerc

@@ -0,0 +1,3 @@
+[run]
+omit =
+    */__init__.py

mmocr-dev-1.x/.dev_scripts/benchmark_full_models.txt

@@ -0,0 +1,18 @@
+textdet/dbnet/dbnet_resnet18_fpnc_1200e_icdar2015.py
+textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015.py
+textdet/drrg/drrg_resnet50_fpn-unet_1200e_ctw1500.py
+textdet/fcenet/fcenet_resnet50_fpn_1500e_icdar2015.py
+textdet/maskrcnn/mask-rcnn_resnet50_fpn_160e_icdar2015.py
+textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py
+textdet/psenet/psenet_resnet50_fpnf_600e_icdar2015.py
+textdet/textsnake/textsnake_resnet50_fpn-unet_1200e_ctw1500.py
+textrecog/abinet/abinet-vision_20e_st-an_mj.py
+textrecog/crnn/crnn_mini-vgg_5e_mj.py
+textrecog/master/master_resnet31_12e_st_mj_sa.py
+textrecog/nrtr/nrtr_resnet31-1by16-1by8_6e_st_mj.py
+textrecog/robust_scanner/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real.py
+textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real.py
+textrecog/satrn/satrn_shallow-small_5e_st_mj.py
+textrecog/satrn/satrn_shallow-small_5e_st_mj.py
+textrecog/aster/aster_resnet45_6e_st_mj.py
+textrecog/svtr/svtr-small_20e_st_mj.py

mmocr-dev-1.x/.dev_scripts/benchmark_options.py

@@ -0,0 +1,7 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+
+third_part_libs = [
+    'pip install -r ../requirements/albu.txt',
+]
+
+default_floating_range = 0.5

mmocr-dev-1.x/.dev_scripts/benchmark_train_models.txt

@@ -0,0 +1,9 @@
+textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015.py
+textdet/fcenet/fcenet_resnet50_fpn_1500e_icdar2015.py
+textdet/maskrcnn/mask-rcnn_resnet50_fpn_160e_icdar2015.py
+textrecog/abinet/abinet-vision_20e_st-an_mj.py
+textrecog/crnn/crnn_mini-vgg_5e_mj.py
+textrecog/aster/aster_resnet45_6e_st_mj.py
+textrecog/nrtr/nrtr_resnet31-1by16-1by8_6e_st_mj.py
+textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real.py
+textrecog/svtr/svtr-small_20e_st_mj.py

mmocr-dev-1.x/.dev_scripts/covignore.cfg

@@ -0,0 +1,18 @@
+# Each line should be the relative path to the root directory
+# of this repo. Support regular expression as well.
+# For example:
+# mmocr/models/textdet/postprocess/utils.py
+# .*/utils.py
+.*/__init__.py
+
+# It will be removed after all models have been refactored
+mmocr/utils/bbox_utils.py
+
+# Major part is covered, however, it's hard to cover model's output.
+mmocr/models/textdet/detectors/mmdet_wrapper.py
+
+# It will be removed after KieVisualizer and TextSpotterVisualizer
+mmocr/visualization/visualize.py
+
+# Add tests for data preparers later
+mmocr/datasets/preparers

mmocr-dev-1.x/.dev_scripts/diff_coverage_test.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+
+set -e
+
+readarray -t IGNORED_FILES < $( dirname "$0" )/covignore.cfg
+
+REUSE_COVERAGE_REPORT=${REUSE_COVERAGE_REPORT:-0}
+REPO=${1:-"origin"}
+BRANCH=${2:-"refactor_dev"}
+
+git fetch $REPO $BRANCH
+
+PY_FILES=""
+for FILE_NAME in $(git diff --name-only ${REPO}/${BRANCH}); do
+    # Only test python files in mmocr/ existing in current branch, and not ignored in covignore.cfg
+    if [ ${FILE_NAME: -3} == ".py" ] && [ ${FILE_NAME:0:6} == "mmocr/" ] && [ -f "$FILE_NAME" ]; then
+        IGNORED=false
+        for IGNORED_FILE_NAME in "${IGNORED_FILES[@]}"; do
+            # Skip blank lines
+            if [ -z "$IGNORED_FILE_NAME" ]; then
+                continue
+            fi
+            if [ "${IGNORED_FILE_NAME::1}" != "#" ] && [[ "$FILE_NAME" =~ $IGNORED_FILE_NAME ]]; then
+                echo "Ignoring $FILE_NAME"
+                IGNORED=true
+                break
+            fi
+        done
+        if [ "$IGNORED" = false ]; then
+            PY_FILES="$PY_FILES $FILE_NAME"
+        fi
+    fi
+done
+
+# Only test the coverage when PY_FILES are not empty, otherwise they will test the entire project
+if [ ! -z "${PY_FILES}" ]
+then
+    if [ "$REUSE_COVERAGE_REPORT" == "0" ]; then
+        coverage run --branch --source mmocr -m pytest tests/
+    fi
+    coverage report --fail-under 90 -m $PY_FILES
+    interrogate -v --ignore-init-method --ignore-module --ignore-nested-functions --ignore-magic --ignore-regex "__repr__" --fail-under 95 $PY_FILES
+fi

mmocr-dev-1.x/.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,76 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, sex characteristics, gender identity and expression,
+level of experience, education, socio-economic status, nationality, personal
+appearance, race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+- Using welcoming and inclusive language
+- Being respectful of differing viewpoints and experiences
+- Gracefully accepting constructive criticism
+- Focusing on what is best for the community
+- Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+- The use of sexualized language or imagery and unwelcome sexual attention or
+  advances
+- Trolling, insulting/derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at [email protected]. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+
+For answers to common questions about this code of conduct, see
+https://www.contributor-covenant.org/faq
+
+[homepage]: https://www.contributor-covenant.org

mmocr-dev-1.x/.github/CONTRIBUTING.md

@@ -0,0 +1 @@
+We appreciate all contributions to improve MMOCR. Please read [Contribution Guide](/docs/en/notes/contribution_guide.md) for step-by-step instructions to make a contribution to MMOCR, and [CONTRIBUTING.md](https://github.com/open-mmlab/mmcv/blob/master/CONTRIBUTING.md) in MMCV for more details about the contributing guideline.

mmocr-dev-1.x/.github/ISSUE_TEMPLATE/1-bug-report.yml

@@ -0,0 +1,121 @@
+name: "🐞 Bug report"
+description: "Create a report to help us reproduce and fix the bug"
+labels: kind/bug
+title: "[Bug] "
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Note
+        For general usage questions or idea discussions, please post it to our [**Forum**](https://github.com/open-mmlab/mmocr/discussions)
+        If this issue is about installing MMCV, please file an issue at [MMCV](https://github.com/open-mmlab/mmcv/issues/new/choose).
+        If it's anything about model deployment, please raise it to [MMDeploy](https://github.com/open-mmlab/mmdeploy)
+
+        Please fill in as **much** of the following form as you're able to. **The clearer the description, the shorter it will take to solve it.**
+
+  - type: checkboxes
+    attributes:
+      label: Prerequisite
+      description: Please check the following items before creating a new issue.
+      options:
+      - label: I have searched [Issues](https://github.com/open-mmlab/mmocr/issues) and [Discussions](https://github.com/open-mmlab/mmocr/discussions) but cannot get the expected help.
+        required: true
+      # - label: I have read the [FAQ documentation](https://mmocr.readthedocs.io/en/1.x/notes/4_faq.html) but cannot get the expected help.
+      #   required: true
+      - label: The bug has not been fixed in the [latest version (0.x)](https://github.com/open-mmlab/mmocr) or [latest version (1.x)](https://github.com/open-mmlab/mmocr/tree/dev-1.x).
+        required: true
+
+  - type: dropdown
+    id: task
+    attributes:
+      label: Task
+      description: The problem arises when
+      options:
+        - I'm using the official example scripts/configs for the officially supported tasks/models/datasets.
+        - I have modified the scripts/configs, or I'm working on my own tasks/models/datasets.
+    validations:
+      required: true
+
+  - type: dropdown
+    id: branch
+    attributes:
+      label: Branch
+      description: The problem arises when I'm working on
+      options:
+        - main branch https://github.com/open-mmlab/mmocr
+        - 1.x branch https://github.com/open-mmlab/mmocr/tree/dev-1.x
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Environment
+      description: |
+        Please run `python mmocr/utils/collect_env.py` to collect necessary environment information and copy-paste it here.
+        You may add additional information that may be helpful for locating the problem, such as
+          - How you installed PyTorch \[e.g., pip, conda, source\]
+          - Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.)
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Reproduces the problem - code sample
+      description: |
+        Please provide a code sample that reproduces the problem you ran into. It can be a Colab link or just a code snippet.
+      placeholder: |
+        ```python
+        # Sample code to reproduce the problem
+        ```
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Reproduces the problem - command or script
+      description: |
+        What command or script did you run?
+      placeholder: |
+        ```shell
+        The command or script you run.
+        ```
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Reproduces the problem - error message
+      description: |
+        Please provide the error message or logs you got, with the full traceback.
+
+        Tip: You can attach images or log files by dragging them into the text area..
+      placeholder: |
+        ```
+        The error message or logs you got, with the full traceback.
+        ```
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Additional information
+      description: |
+        Tell us anything else you think we should know.
+
+        Tip: You can attach images or log files by dragging them into the text area.
+      placeholder: |
+        1. What's your expected result?
+        2. What dataset did you use?
+        3. What do you think might be the reason?
+
+  - type: markdown
+    attributes:
+      value: |
+        ## Acknowledgement
+        Thanks for taking the time to fill out this report.
+
+        If you have already identified the reason, we strongly appreciate you creating a new PR to fix it [**Here**](https://github.com/open-mmlab/mmocr/pulls)!
+        Please refer to [**Contribution Guide**](https://mmocr.readthedocs.io/en/dev-1.x/notes/contribution_guide.html) for contributing.
+
+        Welcome to join our [**Community**](https://mmocr.readthedocs.io/en/latest/contact.html) to discuss together. 👬

mmocr-dev-1.x/.github/ISSUE_TEMPLATE/2-feature_request.yml

@@ -0,0 +1,39 @@
+name: 🚀 Feature request
+description: Suggest an idea for this project
+labels: [feature-request]
+title: "[Feature] "
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Note
+        For general usage questions or idea discussions, please post it to our [**Forum**](https://github.com/open-mmlab/mmocr/discussions)
+
+        Please fill in as **much** of the following form as you're able to. **The clearer the description, the shorter it will take to solve it.**
+
+  - type: textarea
+    attributes:
+      label: What is the feature?
+      description: Tell us more about the feature and how this feature can help.
+      placeholder: |
+        E.g., It is inconvenient when \[....\].
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Any other context?
+      description: |
+        Have you considered any alternative solutions or features? If so, what are they? Also, feel free to add any other context or screenshots about the feature request here.
+
+  - type: markdown
+    attributes:
+      value: |
+        ## Acknowledgement
+        Thanks for taking the time to fill out this report.
+
+        We strongly appreciate you creating a new PR to implement it [**Here**](https://github.com/open-mmlab/mmocr/pulls)!
+        Please refer to [**Contribution Guide**](https://mmocr.readthedocs.io/en/dev-1.x/notes/contribution_guide.html) for contributing.
+
+        Welcome to join our [**Community**](https://mmocr.readthedocs.io/en/latest/contact.html) to discuss together. 👬

mmocr-dev-1.x/.github/ISSUE_TEMPLATE/3-new-model.yml

@@ -0,0 +1,51 @@
+name: "\U0001F31F New model/dataset/scheduler addition"
+description: Submit a proposal/request to implement a new model / dataset / scheduler
+labels: [ "feature-request" ]
+title: "[New Models] "
+
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Note
+        For general usage questions or idea discussions, please post it to our [**Forum**](https://github.com/open-mmlab/mmocr/discussions)
+
+        Please fill in as **much** of the following form as you're able to. **The clearer the description, the shorter it will take to solve it.**
+
+  - type: textarea
+    id: description-request
+    validations:
+      required: true
+    attributes:
+      label: Model/Dataset/Scheduler description
+      description: |
+        Put any and all important information relative to the model/dataset/scheduler
+
+  - type: checkboxes
+    attributes:
+      label: Open source status
+      description: |
+          Please provide the open-source status, which would be very helpful
+      options:
+        - label: "The model implementation is available"
+        - label: "The model weights are available."
+
+  - type: textarea
+    id: additional-info
+    attributes:
+      label: Provide useful links for the implementation
+      description: |
+        Please provide information regarding the implementation, the weights, and the authors.
+        Please mention the authors by @gh-username if you're aware of their usernames.
+
+  - type: markdown
+    attributes:
+      value: |
+        ## Acknowledgement
+        Thanks for taking the time to fill out this report.
+
+        We strongly appreciate you creating a new PR to implement it [**Here**](https://github.com/open-mmlab/mmocr/pulls)!
+        Please refer to [**Contribution Guide**](https://mmocr.readthedocs.io/en/dev-1.x/notes/contribution_guide.html) for contributing.
+
+        Welcome to join our [**Community**](https://mmocr.readthedocs.io/en/latest/contact.html) to discuss together. 👬

mmocr-dev-1.x/.github/ISSUE_TEMPLATE/4-documentation.yml

@@ -0,0 +1,48 @@
+name: 📚 Documentation
+description: Report an issue related to the documentation.
+labels: "docs"
+title: "[Docs] "
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Note
+        For general usage questions or idea discussions, please post it to our [**Forum**](https://github.com/open-mmlab/mmocr/discussions)
+        Please fill in as **much** of the following form as you're able to. **The clearer the description, the shorter it will take to solve it.**
+
+  - type: dropdown
+    id: branch
+    attributes:
+      label: Branch
+      description: This issue is related to the
+      options:
+        - master branch  https://mmocr.readthedocs.io/en/latest/
+        - 1.x branch https://mmocr.readthedocs.io/en/dev-1.x/
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: 📚 The doc issue
+      description: >
+        A clear and concise description the issue.
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Suggest a potential alternative/fix
+      description: >
+        Tell us how we could improve the documentation in this regard.
+
+  - type: markdown
+    attributes:
+      value: |
+        ## Acknowledgement
+        Thanks for taking the time to fill out this report.
+
+        If you have already identified the reason, we strongly appreciate you creating a new PR to fix it [**here**](https://github.com/open-mmlab/mmocr/pulls)!
+        Please refer to [**Contribution Guide**](https://mmocr.readthedocs.io/en/dev-1.x/notes/contribution_guide.html) for contributing.
+
+        Welcome to join our [**Community**](https://mmocr.readthedocs.io/en/latest/contact.html) to discuss together. 👬

mmocr-dev-1.x/.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,12 @@
+blank_issues_enabled: false
+
+contact_links:
+  - name: ❔ FAQ
+    url: https://mmocr.readthedocs.io/en/dev-1.x/get_started/faq.html
+    about: Is your question frequently asked?
+  - name: 💬 Forum
+    url: https://github.com/open-mmlab/mmocr/discussions
+    about: Ask general usage questions and discuss with other MMOCR community members
+  - name: 🌐 Explore OpenMMLab
+    url: https://openmmlab.com/
+    about: Get know more about OpenMMLab

mmocr-dev-1.x/.github/pull_request_template.md

@@ -0,0 +1,33 @@
+Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
+
+## Motivation
+
+Please describe the motivation of this PR and the goal you want to achieve through this PR.
+
+## Modification
+
+Please briefly describe what modification is made in this PR.
+
+## BC-breaking (Optional)
+
+Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
+If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
+
+## Use cases (Optional)
+
+If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.
+
+## Checklist
+
+**Before PR**:
+
+- [ ] I have read and followed the workflow indicated in the [CONTRIBUTING.md](https://github.com/open-mmlab/mmocr/blob/main/.github/CONTRIBUTING.md) to create this PR.
+- [ ] Pre-commit or linting tools indicated in [CONTRIBUTING.md](https://github.com/open-mmlab/mmocr/blob/main/.github/CONTRIBUTING.md) are used to fix the potential lint issues.
+- [ ] Bug fixes are covered by unit tests, the case that causes the bug should be added in the unit tests.
+- [ ] New functionalities are covered by complete unit tests. If not, please add more unit test to ensure the correctness.
+- [ ] The documentation has been modified accordingly, including docstring or example tutorials.
+
+**After PR**:
+
+- [ ] If the modification has potential influence on downstream or other related projects, this PR should be tested with some of those projects.
+- [ ] CLA has been signed and all committers have signed the CLA in this PR.

mmocr-dev-1.x/.github/workflows/lint.yml

@@ -0,0 +1,27 @@
+name: lint
+
+on: [push, pull_request]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python 3.7
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.7
+      - name: Install pre-commit hook
+        run: |
+          pip install pre-commit
+          pre-commit install
+      - name: Linting
+        run: pre-commit run --all-files
+      - name: Check docstring coverage
+        run: |
+          pip install interrogate
+          interrogate -v --ignore-init-method --ignore-module --ignore-nested-functions --ignore-regex "__repr__" --fail-under 90 mmocr

mmocr-dev-1.x/.github/workflows/merge_stage_test.yml

@@ -0,0 +1,160 @@
+name: merge_stage_test
+
+on:
+  push:
+    paths-ignore:
+      - 'README.md'
+      - 'README_zh-CN.md'
+      - 'docs/**'
+      - 'demo/**'
+      - '.dev_scripts/**'
+      - '.circleci/**'
+      - 'projects/**'
+    branches:
+      - dev-1.x
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build_cpu_py:
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        python-version: [3.8, 3.9]
+        torch: [1.8.1]
+        include:
+          - torch: 1.8.1
+            torchvision: 0.9.1
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Upgrade pip
+        run: pip install pip --upgrade
+      - name: Install PyTorch
+        run: pip install torch==${{matrix.torch}}+cpu torchvision==${{matrix.torchvision}}+cpu -f https://download.pytorch.org/whl/cpu/torch_stable.html
+      - name: Install MMEngine
+        run: pip install git+https://github.com/open-mmlab/mmengine.git@main
+      - name: Install MMCV
+        run: |
+          pip install -U openmim
+          mim install 'mmcv >= 2.0.0rc1'
+      - name: Install MMDet
+        run: pip install git+https://github.com/open-mmlab/[email protected]
+      - name: Install other dependencies
+        run: pip install -r requirements/tests.txt
+      - name: Build and install
+        run: rm -rf .eggs && pip install -e .
+      - name: Run unittests and generate coverage report
+        run: |
+          coverage run --branch --source mmocr -m pytest tests/
+          coverage xml
+          coverage report -m
+
+  build_cpu_pt:
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        python-version: [3.7]
+        torch: [1.6.0, 1.7.1, 1.8.1, 1.9.1, 1.10.1, 1.11.0, 1.12.1, 1.13.0]
+        include:
+          - torch: 1.6.0
+            torchvision: 0.7.0
+          - torch: 1.7.1
+            torchvision: 0.8.2
+          - torch: 1.8.1
+            torchvision: 0.9.1
+          - torch: 1.9.1
+            torchvision: 0.10.1
+          - torch: 1.10.1
+            torchvision: 0.11.2
+          - torch: 1.11.0
+            torchvision: 0.12.0
+          - torch: 1.12.1
+            torchvision: 0.13.1
+          - torch: 1.13.0
+            torchvision: 0.14.0
+          - torch: 2.0.0
+            torchvision: 0.15.1
+            python-version: 3.8
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Upgrade pip
+        run: pip install pip --upgrade
+      - name: Install PyTorch
+        run: pip install torch==${{matrix.torch}}+cpu torchvision==${{matrix.torchvision}}+cpu -f https://download.pytorch.org/whl/cpu/torch_stable.html
+      - name: Install MMEngine
+        run: pip install git+https://github.com/open-mmlab/mmengine.git@main
+      - name: Install MMCV
+        run: |
+          pip install -U openmim
+          mim install 'mmcv >= 2.0.0rc1'
+      - name: Install MMDet
+        run: pip install git+https://github.com/open-mmlab/[email protected]
+      - name: Install other dependencies
+        run: pip install -r requirements/tests.txt
+      - name: Build and install
+        run: rm -rf .eggs && pip install -e .
+      - name: Run unittests and generate coverage report
+        run: |
+          coverage run --branch --source mmocr -m pytest tests/
+          coverage xml
+          coverage report -m
+      # Only upload coverage report for python3.7 && pytorch1.8.1 cpu
+      - name: Upload coverage to Codecov
+        if: ${{matrix.torch == '1.8.1' && matrix.python-version == '3.7'}}
+        uses: codecov/[email protected]
+        with:
+          file: ./coverage.xml
+          flags: unittests
+          env_vars: OS,PYTHON
+          name: codecov-umbrella
+          fail_ci_if_error: false
+
+
+  build_windows:
+    runs-on: windows-2022
+    strategy:
+      matrix:
+        python: [3.7]
+        platform: [cpu, cu111]
+        torch: [1.8.1]
+        torchvision: [0.9.1]
+        include:
+          - python-version: 3.8
+            platform: cu117
+            torch: 2.0.0
+            torchvision: 0.15.1
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python }}
+      - name: Upgrade pip
+        run: python -m pip install --upgrade pip
+      - name: Install lmdb
+        run: pip install lmdb
+      - name: Install PyTorch
+        run: pip install torch==${{matrix.torch}}+${{matrix.platform}} torchvision==${{matrix.torchvision}}+${{matrix.platform}} -f https://download.pytorch.org/whl/${{matrix.platform}}/torch_stable.html
+      - name: Install mmocr dependencies
+        run: |
+          pip install git+https://github.com/open-mmlab/mmengine.git@main
+          pip install -U openmim
+          mim install 'mmcv >= 2.0.0rc1'
+          pip install git+https://github.com/open-mmlab/[email protected]
+          pip install -r requirements/tests.txt
+      - name: Build and install
+        run: |
+          pip install -e .
+      - name: Run unittests and generate coverage report
+        run: |
+          pytest tests/

mmocr-dev-1.x/.github/workflows/pr_stage_test.yml

@@ -0,0 +1,102 @@
+name: pr_stage_test
+
+on:
+  pull_request:
+    paths-ignore:
+      - 'README.md'
+      - 'README_zh-CN.md'
+      - 'docs/**'
+      - 'demo/**'
+      - '.dev_scripts/**'
+      - '.circleci/**'
+      - 'projects/**'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build_cpu:
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        python-version: [3.7]
+        include:
+          - torch: 1.8.1
+            torchvision: 0.9.1
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Upgrade pip
+        run: pip install pip --upgrade
+      - name: Install PyTorch
+        run: pip install torch==${{matrix.torch}}+cpu torchvision==${{matrix.torchvision}}+cpu -f https://download.pytorch.org/whl/cpu/torch_stable.html
+      - name: Install MMEngine
+        run: pip install git+https://github.com/open-mmlab/mmengine.git@main
+      - name: Install MMCV
+        run: |
+          pip install -U openmim
+          mim install 'mmcv >= 2.0.0rc1'
+      - name: Install MMDet
+        run: pip install git+https://github.com/open-mmlab/[email protected]
+      - name: Install other dependencies
+        run: pip install -r requirements/tests.txt
+      - name: Build and install
+        run: rm -rf .eggs && pip install -e .
+      - name: Run unittests and generate coverage report
+        run: |
+          coverage run --branch --source mmocr -m pytest tests/
+          coverage xml
+          coverage report -m
+      # Upload coverage report for python3.7 && pytorch1.8.1 cpu
+      - name: Upload coverage to Codecov
+        uses: codecov/[email protected]
+        with:
+          file: ./coverage.xml
+          flags: unittests
+          env_vars: OS,PYTHON
+          name: codecov-umbrella
+          fail_ci_if_error: false
+
+
+  build_windows:
+    runs-on: windows-2022
+    strategy:
+      matrix:
+        python: [3.7]
+        platform: [cpu, cu111]
+        torch: [1.8.1]
+        torchvision: [0.9.1]
+        include:
+          - python-version: 3.8
+            platform: cu117
+            torch: 2.0.0
+            torchvision: 0.15.1
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python }}
+      - name: Upgrade pip
+        run: python -m pip install --upgrade pip
+      - name: Install lmdb
+        run: pip install lmdb
+      - name: Install PyTorch
+        run: pip install torch==${{matrix.torch}}+${{matrix.platform}} torchvision==${{matrix.torchvision}}+${{matrix.platform}} -f https://download.pytorch.org/whl/${{matrix.platform}}/torch_stable.html
+      - name: Install mmocr dependencies
+        run: |
+          pip install git+https://github.com/open-mmlab/mmengine.git@main
+          pip install -U openmim
+          mim install 'mmcv >= 2.0.0rc1'
+          pip install git+https://github.com/open-mmlab/[email protected]
+          pip install -r requirements/tests.txt
+      - name: Build and install
+        run: |
+          pip install -e .
+      - name: Run unittests and generate coverage report
+        run: |
+          pytest tests/

mmocr-dev-1.x/.github/workflows/publish-to-pypi.yml

@@ -0,0 +1,26 @@
+name: deploy
+
+on: push
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build-n-publish:
+    runs-on: ubuntu-latest
+    if: startsWith(github.event.ref, 'refs/tags')
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python 3.7
+        uses: actions/setup-python@v1
+        with:
+          python-version: 3.7
+      - name: Build MMOCR
+        run: |
+          pip install wheel
+          python setup.py sdist bdist_wheel
+      - name: Publish distribution to PyPI
+        run: |
+          pip install twine
+          twine upload dist/* -u __token__ -p ${{ secrets.pypi_password }}

mmocr-dev-1.x/.github/workflows/test_mim.yml

@@ -0,0 +1,44 @@
+name: test-mim
+
+on:
+  push:
+    paths:
+      - 'model-index.yml'
+      - 'configs/**'
+
+  pull_request:
+    paths:
+      - 'model-index.yml'
+      - 'configs/**'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build_cpu:
+    runs-on: ubuntu-18.04
+    strategy:
+      matrix:
+        python-version: [3.7]
+        torch: [1.8.0]
+        include:
+          - torch: 1.8.0
+            torch_version: torch1.8
+            torchvision: 0.9.0
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Upgrade pip
+        run: pip install pip --upgrade
+      - name: Install PyTorch
+        run: pip install torch==${{matrix.torch}}+cpu torchvision==${{matrix.torchvision}}+cpu -f https://download.pytorch.org/whl/torch_stable.html
+      - name: Install openmim
+        run: pip install openmim
+      - name: Build and install
+        run: rm -rf .eggs && mim install -e .
+      - name: test commands of mim
+        run: mim search mmocr

mmocr-dev-1.x/.gitignore

@@ -0,0 +1,146 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+*.ipynb
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/en/_build/
+docs/zh_cn/_build/
+docs/*/api/generated/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# cython generated cpp
+!data/dict
+/data
+.vscode
+.idea
+
+# custom
+*.pkl
+*.pkl.json
+*.log.json
+work_dirs/
+exps/
+*~
+show_dir/
+
+# Pytorch
+*.pth
+
+# demo
+!tests/data
+tests/results
+
+#temp files
+.DS_Store
+
+checkpoints
+
+htmlcov
+*.swp
+log.txt
+workspace.code-workspace
+results
+mmocr/core/font.TTF
+mmocr/.mim
+workdirs/
+.history/
+.dev/
+data/

mmocr-dev-1.x/.owners.yml

@@ -0,0 +1,9 @@
+assign:
+  strategy:
+    random
+    # daily-shift-based
+  scedule:
+    '*/1 * * * *'
+  assignees:
+    - gaotongxiao
+    - Harold-lkk

mmocr-dev-1.x/.pre-commit-config.yaml

@@ -0,0 +1,63 @@
+exclude: ^tests/data/
+repos:
+  - repo: https://github.com/PyCQA/flake8
+    rev: 5.0.4
+    hooks:
+      - id: flake8
+  - repo: https://github.com/zhouzaida/isort
+    rev: 5.12.1
+    hooks:
+      - id: isort
+  - repo: https://github.com/pre-commit/mirrors-yapf
+    rev: v0.32.0
+    hooks:
+      - id: yapf
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.1
+    hooks:
+      - id: codespell
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: trailing-whitespace
+        exclude: |
+            (?x)^(
+              dicts/|
+              projects/.*?/dicts/
+            )
+      - id: check-yaml
+      - id: end-of-file-fixer
+        exclude: |
+            (?x)^(
+              dicts/|
+              projects/.*?/dicts/
+            )
+      - id: requirements-txt-fixer
+      - id: double-quote-string-fixer
+      - id: check-merge-conflict
+      - id: fix-encoding-pragma
+        args: ["--remove"]
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.9
+    hooks:
+      - id: mdformat
+        args: ["--number", "--table-width", "200"]
+        additional_dependencies:
+          - mdformat-openmmlab
+          - mdformat_frontmatter
+          - linkify-it-py
+  - repo: https://github.com/myint/docformatter
+    rev: v1.3.1
+    hooks:
+      - id: docformatter
+        args: ["--in-place", "--wrap-descriptions", "79"]
+  - repo: https://github.com/open-mmlab/pre-commit-hooks
+    rev: v0.2.0  # Use the ref you want to point at
+    hooks:
+      - id: check-algo-readme
+      - id: check-copyright
+        args: ["mmocr", "tests", "tools"]  # these directories will be checked

mmocr-dev-1.x/.pylintrc

@@ -0,0 +1,621 @@
+[MASTER]
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code.
+extension-pkg-whitelist=
+
+# Specify a score threshold to be exceeded before program exits with error.
+fail-under=10.0
+
+# Add files or directories to the blacklist. They should be base names, not
+# paths.
+ignore=CVS,configs
+
+# Add files or directories matching the regex patterns to the blacklist. The
+# regex matches against base names, not paths.
+ignore-patterns=
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+#init-hook=
+
+# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
+# number of processors available to use.
+jobs=1
+
+# Control the amount of potential inferred values when inferring a single
+# object. This can help the performance when dealing with large functions or
+# complex, nested conditions.
+limit-inference-results=100
+
+# List of plugins (as comma separated values of python module names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+# Pickle collected data for later comparisons.
+persistent=yes
+
+# When enabled, pylint would attempt to guess common misconfiguration and emit
+# user-friendly hints instead of false-positive error messages.
+suggestion-mode=yes
+
+# Allow loading of arbitrary C extensions. Extensions are imported into the
+# active Python interpreter and may run arbitrary code.
+unsafe-load-any-extension=no
+
+
+[MESSAGES CONTROL]
+
+# Only show warnings with the listed confidence levels. Leave empty to show
+# all. Valid levels: HIGH, INFERENCE, INFERENCE_FAILURE, UNDEFINED.
+confidence=
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once). You can also use "--disable=all" to
+# disable everything first and then reenable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use "--disable=all --enable=classes
+# --disable=W".
+disable=print-statement,
+        parameter-unpacking,
+        unpacking-in-except,
+        old-raise-syntax,
+        backtick,
+        long-suffix,
+        old-ne-operator,
+        old-octal-literal,
+        import-star-module-level,
+        non-ascii-bytes-literal,
+        raw-checker-failed,
+        bad-inline-option,
+        locally-disabled,
+        file-ignored,
+        suppressed-message,
+        useless-suppression,
+        deprecated-pragma,
+        use-symbolic-message-instead,
+        apply-builtin,
+        basestring-builtin,
+        buffer-builtin,
+        cmp-builtin,
+        coerce-builtin,
+        execfile-builtin,
+        file-builtin,
+        long-builtin,
+        raw_input-builtin,
+        reduce-builtin,
+        standarderror-builtin,
+        unicode-builtin,
+        xrange-builtin,
+        coerce-method,
+        delslice-method,
+        getslice-method,
+        setslice-method,
+        no-absolute-import,
+        old-division,
+        dict-iter-method,
+        dict-view-method,
+        next-method-called,
+        metaclass-assignment,
+        indexing-exception,
+        raising-string,
+        reload-builtin,
+        oct-method,
+        hex-method,
+        nonzero-method,
+        cmp-method,
+        input-builtin,
+        round-builtin,
+        intern-builtin,
+        unichr-builtin,
+        map-builtin-not-iterating,
+        zip-builtin-not-iterating,
+        range-builtin-not-iterating,
+        filter-builtin-not-iterating,
+        using-cmp-argument,
+        eq-without-hash,
+        div-method,
+        idiv-method,
+        rdiv-method,
+        exception-message-attribute,
+        invalid-str-codec,
+        sys-max-int,
+        bad-python3-import,
+        deprecated-string-function,
+        deprecated-str-translate-call,
+        deprecated-itertools-function,
+        deprecated-types-field,
+        next-method-defined,
+        dict-items-not-iterating,
+        dict-keys-not-iterating,
+        dict-values-not-iterating,
+        deprecated-operator-function,
+        deprecated-urllib-function,
+        xreadlines-attribute,
+        deprecated-sys-function,
+        exception-escape,
+        comprehension-escape,
+        no-member,
+        invalid-name,
+        too-many-branches,
+        wrong-import-order,
+        too-many-arguments,
+        missing-function-docstring,
+        missing-module-docstring,
+        too-many-locals,
+        too-few-public-methods,
+        abstract-method,
+        broad-except,
+        too-many-nested-blocks,
+        too-many-instance-attributes,
+        missing-class-docstring,
+        duplicate-code,
+        not-callable,
+        protected-access,
+        dangerous-default-value,
+        no-name-in-module,
+        logging-fstring-interpolation,
+        super-init-not-called,
+        redefined-builtin,
+        attribute-defined-outside-init,
+        arguments-differ,
+        cyclic-import,
+        bad-super-call,
+        too-many-statements
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time (only on the command line, not in the configuration file where
+# it should appear only once). See also the "--disable" option for examples.
+enable=c-extension-no-member
+
+
+[REPORTS]
+
+# Python expression which should return a score less than or equal to 10. You
+# have access to the variables 'error', 'warning', 'refactor', and 'convention'
+# which contain the number of messages in each category, as well as 'statement'
+# which is the total number of statements analyzed. This score is used by the
+# global evaluation report (RP0004).
+evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details.
+#msg-template=
+
+# Set the output format. Available formats are text, parseable, colorized, json
+# and msvs (visual studio). You can also give a reporter class, e.g.
+# mypackage.mymodule.MyReporterClass.
+output-format=text
+
+# Tells whether to display a full report or only the messages.
+reports=no
+
+# Activate the evaluation score.
+score=yes
+
+
+[REFACTORING]
+
+# Maximum number of nested blocks for function / method body
+max-nested-blocks=5
+
+# Complete name of functions that never returns. When checking for
+# inconsistent-return-statements if a never returning function is called then
+# it will be considered as an explicit return statement and no message will be
+# printed.
+never-returning-functions=sys.exit
+
+
+[TYPECHECK]
+
+# List of decorators that produce context managers, such as
+# contextlib.contextmanager. Add to this list to register other decorators that
+# produce valid context managers.
+contextmanager-decorators=contextlib.contextmanager
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E1101 when accessed. Python regular
+# expressions are accepted.
+generated-members=
+
+# Tells whether missing members accessed in mixin class should be ignored. A
+# mixin class is detected if its name ends with "mixin" (case insensitive).
+ignore-mixin-members=yes
+
+# Tells whether to warn about missing members when the owner of the attribute
+# is inferred to be None.
+ignore-none=yes
+
+# This flag controls whether pylint should warn about no-member and similar
+# checks whenever an opaque object is returned when inferring. The inference
+# can return multiple potential results while evaluating a Python object, but
+# some branches might not be evaluated, which results in partial inference. In
+# that case, it might be useful to still emit no-member and other checks for
+# the rest of the inferred objects.
+ignore-on-opaque-inference=yes
+
+# List of class names for which member attributes should not be checked (useful
+# for classes with dynamically set attributes). This supports the use of
+# qualified names.
+ignored-classes=optparse.Values,thread._local,_thread._local
+
+# List of module names for which member attributes should not be checked
+# (useful for modules/projects where namespaces are manipulated during runtime
+# and thus existing member attributes cannot be deduced by static analysis). It
+# supports qualified module names, as well as Unix pattern matching.
+ignored-modules=
+
+# Show a hint with possible names when a member name was not found. The aspect
+# of finding the hint is based on edit distance.
+missing-member-hint=yes
+
+# The minimum edit distance a name should have in order to be considered a
+# similar match for a missing member name.
+missing-member-hint-distance=1
+
+# The total number of similar names that should be taken in consideration when
+# showing a hint for a missing member.
+missing-member-max-choices=1
+
+# List of decorators that change the signature of a decorated function.
+signature-mutators=
+
+
+[SPELLING]
+
+# Limits count of emitted suggestions for spelling mistakes.
+max-spelling-suggestions=4
+
+# Spelling dictionary name. Available dictionaries: none. To make it work,
+# install the python-enchant package.
+spelling-dict=
+
+# List of comma separated words that should not be checked.
+spelling-ignore-words=
+
+# A path to a file that contains the private dictionary; one word per line.
+spelling-private-dict-file=
+
+# Tells whether to store unknown words to the private dictionary (see the
+# --spelling-private-dict-file option) instead of raising a message.
+spelling-store-unknown-words=no
+
+
+[LOGGING]
+
+# The type of string formatting that logging methods do. `old` means using %
+# formatting, `new` is for `{}` formatting.
+logging-format-style=old
+
+# Logging modules to check that the string format arguments are in logging
+# function parameter format.
+logging-modules=logging
+
+
+[VARIABLES]
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid defining new builtins when possible.
+additional-builtins=
+
+# Tells whether unused global variables should be treated as a violation.
+allow-global-unused-variables=yes
+
+# List of strings which can identify a callback function by name. A callback
+# name must start or end with one of those strings.
+callbacks=cb_,
+          _cb
+
+# A regular expression matching the name of dummy variables (i.e. expected to
+# not be used).
+dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_
+
+# Argument names that match this expression will be ignored. Default to name
+# with leading underscore.
+ignored-argument-names=_.*|^ignored_|^unused_
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# List of qualified module names which can have objects that can redefine
+# builtins.
+redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io
+
+
+[FORMAT]
+
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+expected-line-ending-format=
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines=^\s*(# )?<?https?://\S+>?$
+
+# Number of spaces of indent required inside a hanging or continued line.
+indent-after-paren=4
+
+# String used as indentation unit. This is usually "    " (4 spaces) or "\t" (1
+# tab).
+indent-string='    '
+
+# Maximum number of characters on a single line.
+max-line-length=100
+
+# Maximum number of lines in a module.
+max-module-lines=1000
+
+# Allow the body of a class to be on the same line as the declaration if body
+# contains single statement.
+single-line-class-stmt=no
+
+# Allow the body of an if to be on the same line as the test if there is no
+# else.
+single-line-if-stmt=no
+
+
+[STRING]
+
+# This flag controls whether inconsistent-quotes generates a warning when the
+# character used as a quote delimiter is used inconsistently within a module.
+check-quote-consistency=no
+
+# This flag controls whether the implicit-str-concat should generate a warning
+# on implicit string concatenation in sequences defined over several lines.
+check-str-concat-over-line-jumps=no
+
+
+[SIMILARITIES]
+
+# Ignore comments when computing similarities.
+ignore-comments=yes
+
+# Ignore docstrings when computing similarities.
+ignore-docstrings=yes
+
+# Ignore imports when computing similarities.
+ignore-imports=no
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=FIXME,
+      XXX,
+      TODO
+
+# Regular expression of note tags to take in consideration.
+#notes-rgx=
+
+
+[BASIC]
+
+# Naming style matching correct argument names.
+argument-naming-style=snake_case
+
+# Regular expression matching correct argument names. Overrides argument-
+# naming-style.
+#argument-rgx=
+
+# Naming style matching correct attribute names.
+attr-naming-style=snake_case
+
+# Regular expression matching correct attribute names. Overrides attr-naming-
+# style.
+#attr-rgx=
+
+# Bad variable names which should always be refused, separated by a comma.
+bad-names=foo,
+          bar,
+          baz,
+          toto,
+          tutu,
+          tata
+
+# Bad variable names regexes, separated by a comma. If names match any regex,
+# they will always be refused
+bad-names-rgxs=
+
+# Naming style matching correct class attribute names.
+class-attribute-naming-style=any
+
+# Regular expression matching correct class attribute names. Overrides class-
+# attribute-naming-style.
+#class-attribute-rgx=
+
+# Naming style matching correct class names.
+class-naming-style=PascalCase
+
+# Regular expression matching correct class names. Overrides class-naming-
+# style.
+#class-rgx=
+
+# Naming style matching correct constant names.
+const-naming-style=UPPER_CASE
+
+# Regular expression matching correct constant names. Overrides const-naming-
+# style.
+#const-rgx=
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=-1
+
+# Naming style matching correct function names.
+function-naming-style=snake_case
+
+# Regular expression matching correct function names. Overrides function-
+# naming-style.
+#function-rgx=
+
+# Good variable names which should always be accepted, separated by a comma.
+good-names=i,
+           j,
+           k,
+           ex,
+           Run,
+           _,
+           x,
+           y,
+           w,
+           h,
+           a,
+           b
+
+# Good variable names regexes, separated by a comma. If names match any regex,
+# they will always be accepted
+good-names-rgxs=
+
+# Include a hint for the correct naming format with invalid-name.
+include-naming-hint=no
+
+# Naming style matching correct inline iteration names.
+inlinevar-naming-style=any
+
+# Regular expression matching correct inline iteration names. Overrides
+# inlinevar-naming-style.
+#inlinevar-rgx=
+
+# Naming style matching correct method names.
+method-naming-style=snake_case
+
+# Regular expression matching correct method names. Overrides method-naming-
+# style.
+#method-rgx=
+
+# Naming style matching correct module names.
+module-naming-style=snake_case
+
+# Regular expression matching correct module names. Overrides module-naming-
+# style.
+#module-rgx=
+
+# Colon-delimited sets of names that determine each other's naming style when
+# the name regexes allow several styles.
+name-group=
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=^_
+
+# List of decorators that produce properties, such as abc.abstractproperty. Add
+# to this list to register other decorators that produce valid properties.
+# These decorators are taken in consideration only for invalid-name.
+property-classes=abc.abstractproperty
+
+# Naming style matching correct variable names.
+variable-naming-style=snake_case
+
+# Regular expression matching correct variable names. Overrides variable-
+# naming-style.
+#variable-rgx=
+
+
+[DESIGN]
+
+# Maximum number of arguments for function / method.
+max-args=5
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=7
+
+# Maximum number of boolean expressions in an if statement (see R0916).
+max-bool-expr=5
+
+# Maximum number of branch for function / method body.
+max-branches=12
+
+# Maximum number of locals for function / method body.
+max-locals=15
+
+# Maximum number of parents for a class (see R0901).
+max-parents=7
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods=20
+
+# Maximum number of return / yield for function / method body.
+max-returns=6
+
+# Maximum number of statements in function / method body.
+max-statements=50
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods=2
+
+
+[IMPORTS]
+
+# List of modules that can be imported at any level, not just the top level
+# one.
+allow-any-import-level=
+
+# Allow wildcard imports from modules that define __all__.
+allow-wildcard-with-all=no
+
+# Analyse import fallback blocks. This can be used to support both Python 2 and
+# 3 compatible code, which means that the block might have code that exists
+# only in one or another interpreter, leading to false positives when analysed.
+analyse-fallback-blocks=no
+
+# Deprecated modules which should not be used, separated by a comma.
+deprecated-modules=optparse,tkinter.tix
+
+# Create a graph of external dependencies in the given file (report RP0402 must
+# not be disabled).
+ext-import-graph=
+
+# Create a graph of every (i.e. internal and external) dependencies in the
+# given file (report RP0402 must not be disabled).
+import-graph=
+
+# Create a graph of internal dependencies in the given file (report RP0402 must
+# not be disabled).
+int-import-graph=
+
+# Force import order to recognize a module as part of the standard
+# compatibility libraries.
+known-standard-library=
+
+# Force import order to recognize a module as part of a third party library.
+known-third-party=enchant
+
+# Couples of modules and preferred modules, separated by a comma.
+preferred-modules=
+
+
+[CLASSES]
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,
+                      __new__,
+                      setUp,
+                      __post_init__
+
+# List of member names, which should be excluded from the protected access
+# warning.
+exclude-protected=_asdict,
+                  _fields,
+                  _replace,
+                  _source,
+                  _make
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=cls
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when being caught. Defaults to
+# "BaseException, Exception".
+overgeneral-exceptions=BaseException,
+                       Exception

mmocr-dev-1.x/.readthedocs.yml

@@ -0,0 +1,9 @@
+version: 2
+
+formats: all
+
+python:
+    version: 3.7
+    install:
+      - requirements: requirements/docs.txt
+      - requirements: requirements/readthedocs.txt

mmocr-dev-1.x/CITATION.cff

@@ -0,0 +1,9 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+title: "OpenMMLab Text Detection, Recognition and Understanding Toolbox"
+authors:
+  - name: "MMOCR Contributors"
+version: 0.3.0
+date-released: 2020-08-15
+repository-code: "https://github.com/open-mmlab/mmocr"
+license: Apache-2.0

mmocr-dev-1.x/LICENSE

@@ -0,0 +1,203 @@
+Copyright (c) MMOCR Authors. All rights reserved.
+
+                                 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 2021 MMOCR 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.

mmocr-dev-1.x/MANIFEST.in

@@ -0,0 +1,5 @@
+include requirements/*.txt
+include mmocr/.mim/model-index.yml
+include mmocr/.mim/dicts/*.txt
+recursive-include mmocr/.mim/configs *.py *.yml
+recursive-include mmocr/.mim/tools *.sh *.py

mmocr-dev-1.x/README.md

@@ -0,0 +1,251 @@
+<div align="center">
+  <img src="resources/mmocr-logo.png" width="500px"/>
+  <div>&nbsp;</div>
+  <div align="center">
+    <b><font size="5">OpenMMLab website</font></b>
+    <sup>
+      <a href="https://openmmlab.com">
+        <i><font size="4">HOT</font></i>
+      </a>
+    </sup>
+    &nbsp;&nbsp;&nbsp;&nbsp;
+    <b><font size="5">OpenMMLab platform</font></b>
+    <sup>
+      <a href="https://platform.openmmlab.com">
+        <i><font size="4">TRY IT OUT</font></i>
+      </a>
+    </sup>
+  </div>
+  <div>&nbsp;</div>
+
+[![build](https://github.com/open-mmlab/mmocr/workflows/build/badge.svg)](https://github.com/open-mmlab/mmocr/actions)
+[![docs](https://readthedocs.org/projects/mmocr/badge/?version=dev-1.x)](https://mmocr.readthedocs.io/en/dev-1.x/?badge=dev-1.x)
+[![codecov](https://codecov.io/gh/open-mmlab/mmocr/branch/main/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmocr)
+[![license](https://img.shields.io/github/license/open-mmlab/mmocr.svg)](https://github.com/open-mmlab/mmocr/blob/main/LICENSE)
+[![PyPI](https://badge.fury.io/py/mmocr.svg)](https://pypi.org/project/mmocr/)
+[![Average time to resolve an issue](https://isitmaintained.com/badge/resolution/open-mmlab/mmocr.svg)](https://github.com/open-mmlab/mmocr/issues)
+[![Percentage of issues still open](https://isitmaintained.com/badge/open/open-mmlab/mmocr.svg)](https://github.com/open-mmlab/mmocr/issues)
+<a href="https://console.tiyaro.ai/explore?q=mmocr&pub=mmocr"> <img src="https://tiyaro-public-docs.s3.us-west-2.amazonaws.com/assets/try_on_tiyaro_badge.svg"></a>
+
+[📘Documentation](https://mmocr.readthedocs.io/en/dev-1.x/) |
+[🛠️Installation](https://mmocr.readthedocs.io/en/dev-1.x/get_started/install.html) |
+[👀Model Zoo](https://mmocr.readthedocs.io/en/dev-1.x/modelzoo.html) |
+[🆕Update News](https://mmocr.readthedocs.io/en/dev-1.x/notes/changelog.html) |
+[🤔Reporting Issues](https://github.com/open-mmlab/mmocr/issues/new/choose)
+
+</div>
+
+<div align="center">
+
+English | [简体中文](README_zh-CN.md)
+
+</div>
+<div align="center">
+  <a href="https://openmmlab.medium.com/" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219255827-67c1a27f-f8c5-46a9-811d-5e57448c61d1.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://discord.gg/raweFPmdzG" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218347213-c080267f-cbb6-443e-8532-8e1ed9a58ea9.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://twitter.com/OpenMMLab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218346637-d30c8a0f-3eba-4699-8131-512fb06d46db.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://www.youtube.com/openmmlab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218346691-ceb2116a-465a-40af-8424-9f30d2348ca9.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://space.bilibili.com/1293512903" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219026751-d7d14cce-a7c9-4e82-9942-8375fca65b99.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://www.zhihu.com/people/openmmlab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219026120-ba71e48b-6e94-4bd4-b4e9-b7d175b5e362.png" width="3%" alt="" /></a>
+</div>
+
+## Latest Updates
+
+**The default branch is now `main` and the code on the branch has been upgraded to v1.0.0. The old `main` branch (v0.6.3) code now exists on the `0.x` branch.** If you have been using the `main` branch and encounter upgrade issues, please read the [Migration Guide](https://mmocr.readthedocs.io/en/dev-1.x/migration/overview.html) and notes on [Branches](https://mmocr.readthedocs.io/en/dev-1.x/migration/branches.html) .
+
+v1.0.0 was released in 2023-04-06. Major updates from 1.0.0rc6 include:
+
+1. Support for SCUT-CTW1500, SynthText, and MJSynth datasets in Dataset Preparer
+2. Updated FAQ and documentation
+3. Deprecation of file_client_args in favor of backend_args
+4. Added a new MMOCR tutorial notebook
+
+To know more about the updates in MMOCR 1.0, please refer to [What's New in MMOCR 1.x](https://mmocr.readthedocs.io/en/dev-1.x/migration/news.html), or
+Read [Changelog](https://mmocr.readthedocs.io/en/dev-1.x/notes/changelog.html) for more details!
+
+## Introduction
+
+MMOCR is an open-source toolbox based on PyTorch and mmdetection for text detection, text recognition, and the corresponding downstream tasks including key information extraction. It is part of the [OpenMMLab](https://openmmlab.com/) project.
+
+The main branch works with **PyTorch 1.6+**.
+
+<div align="center">
+  <img src="https://user-images.githubusercontent.com/24622904/187838618-1fdc61c0-2d46-49f9-8502-976ffdf01f28.png"/>
+</div>
+
+### Major Features
+
+- **Comprehensive Pipeline**
+
+  The toolbox supports not only text detection and text recognition, but also their downstream tasks such as key information extraction.
+
+- **Multiple Models**
+
+  The toolbox supports a wide variety of state-of-the-art models for text detection, text recognition and key information extraction.
+
+- **Modular Design**
+
+  The modular design of MMOCR enables users to define their own optimizers, data preprocessors, and model components such as backbones, necks and heads as well as losses. Please refer to [Overview](https://mmocr.readthedocs.io/en/dev-1.x/get_started/overview.html) for how to construct a customized model.
+
+- **Numerous Utilities**
+
+  The toolbox provides a comprehensive set of utilities which can help users assess the performance of models. It includes visualizers which allow visualization of images, ground truths as well as predicted bounding boxes, and a validation tool for evaluating checkpoints during training.  It also includes data converters to demonstrate how to convert your own data to the annotation files which the toolbox supports.
+
+## Installation
+
+MMOCR depends on [PyTorch](https://pytorch.org/), [MMEngine](https://github.com/open-mmlab/mmengine), [MMCV](https://github.com/open-mmlab/mmcv) and [MMDetection](https://github.com/open-mmlab/mmdetection).
+Below are quick steps for installation.
+Please refer to [Install Guide](https://mmocr.readthedocs.io/en/dev-1.x/get_started/install.html) for more detailed instruction.
+
+```shell
+conda create -n open-mmlab python=3.8 pytorch=1.10 cudatoolkit=11.3 torchvision -c pytorch -y
+conda activate open-mmlab
+pip3 install openmim
+git clone https://github.com/open-mmlab/mmocr.git
+cd mmocr
+mim install -e .
+```
+
+## Get Started
+
+Please see [Quick Run](https://mmocr.readthedocs.io/en/dev-1.x/get_started/quick_run.html) for the basic usage of MMOCR.
+
+## [Model Zoo](https://mmocr.readthedocs.io/en/dev-1.x/modelzoo.html)
+
+Supported algorithms:
+
+<details open>
+<summary>BackBone</summary>
+
+- [x] [oCLIP](configs/backbone/oclip/README.md) (ECCV'2022)
+
+</details>
+
+<details open>
+<summary>Text Detection</summary>
+
+- [x] [DBNet](configs/textdet/dbnet/README.md) (AAAI'2020) / [DBNet++](configs/textdet/dbnetpp/README.md) (TPAMI'2022)
+- [x] [Mask R-CNN](configs/textdet/maskrcnn/README.md) (ICCV'2017)
+- [x] [PANet](configs/textdet/panet/README.md) (ICCV'2019)
+- [x] [PSENet](configs/textdet/psenet/README.md) (CVPR'2019)
+- [x] [TextSnake](configs/textdet/textsnake/README.md) (ECCV'2018)
+- [x] [DRRG](configs/textdet/drrg/README.md) (CVPR'2020)
+- [x] [FCENet](configs/textdet/fcenet/README.md) (CVPR'2021)
+
+</details>
+
+<details open>
+<summary>Text Recognition</summary>
+
+- [x] [ABINet](configs/textrecog/abinet/README.md) (CVPR'2021)
+- [x] [ASTER](configs/textrecog/aster/README.md) (TPAMI'2018)
+- [x] [CRNN](configs/textrecog/crnn/README.md) (TPAMI'2016)
+- [x] [MASTER](configs/textrecog/master/README.md) (PR'2021)
+- [x] [NRTR](configs/textrecog/nrtr/README.md) (ICDAR'2019)
+- [x] [RobustScanner](configs/textrecog/robust_scanner/README.md) (ECCV'2020)
+- [x] [SAR](configs/textrecog/sar/README.md) (AAAI'2019)
+- [x] [SATRN](configs/textrecog/satrn/README.md) (CVPR'2020 Workshop on Text and Documents in the Deep Learning Era)
+- [x] [SVTR](configs/textrecog/svtr/README.md) (IJCAI'2022)
+
+</details>
+
+<details open>
+<summary>Key Information Extraction</summary>
+
+- [x] [SDMG-R](configs/kie/sdmgr/README.md) (ArXiv'2021)
+
+</details>
+
+<details open>
+<summary>Text Spotting</summary>
+
+- [x] [ABCNet](projects/ABCNet/README.md) (CVPR'2020)
+- [x] [ABCNetV2](projects/ABCNet/README_V2.md) (TPAMI'2021)
+- [x] [SPTS](projects/SPTS/README.md) (ACM MM'2022)
+
+</details>
+
+Please refer to [model_zoo](https://mmocr.readthedocs.io/en/dev-1.x/modelzoo.html) for more details.
+
+## Projects
+
+[Here](projects/README.md) are some implementations of SOTA models and solutions built on MMOCR, which are supported and maintained by community users. These projects demonstrate the best practices based on MMOCR for research and product development. We welcome and appreciate all the contributions to OpenMMLab ecosystem.
+
+## Contributing
+
+We appreciate all contributions to improve MMOCR. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guidelines.
+
+## Acknowledgement
+
+MMOCR is an open-source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks.
+We hope the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new OCR methods.
+
+## Citation
+
+If you find this project useful in your research, please consider cite:
+
+```bibtex
+@article{mmocr2021,
+    title={MMOCR:  A Comprehensive Toolbox for Text Detection, Recognition and Understanding},
+    author={Kuang, Zhanghui and Sun, Hongbin and Li, Zhizhong and Yue, Xiaoyu and Lin, Tsui Hin and Chen, Jianyong and Wei, Huaqiang and Zhu, Yiqin and Gao, Tong and Zhang, Wenwei and Chen, Kai and Zhang, Wayne and Lin, Dahua},
+    journal= {arXiv preprint arXiv:2108.06543},
+    year={2021}
+}
+```
+
+## License
+
+This project is released under the [Apache 2.0 license](LICENSE).
+
+## OpenMMLab Family
+
+- [MMEngine](https://github.com/open-mmlab/mmengine): OpenMMLab foundational library for training deep learning models
+- [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab foundational library for computer vision.
+- [MIM](https://github.com/open-mmlab/mim): MIM installs OpenMMLab packages.
+- [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab image classification toolbox and benchmark.
+- [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab detection toolbox and benchmark.
+- [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab's next-generation platform for general 3D object detection.
+- [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab rotated object detection toolbox and benchmark.
+- [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab semantic segmentation toolbox and benchmark.
+- [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab text detection, recognition, and understanding toolbox.
+- [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab pose estimation toolbox and benchmark.
+- [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 3D human parametric model toolbox and benchmark.
+- [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab self-supervised learning toolbox and benchmark.
+- [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab model compression toolbox and benchmark.
+- [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab fewshot learning toolbox and benchmark.
+- [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab's next-generation action understanding toolbox and benchmark.
+- [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab video perception toolbox and benchmark.
+- [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab optical flow toolbox and benchmark.
+- [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab image and video editing toolbox.
+- [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab image and video generative models toolbox.
+- [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab model deployment framework.
+
+## Welcome to the OpenMMLab community
+
+Scan the QR code below to follow the OpenMMLab team's [**Zhihu Official Account**](https://www.zhihu.com/people/openmmlab) and join the OpenMMLab team's [**QQ Group**](https://jq.qq.com/?_wv=1027&k=aCvMxdr3), or join the official communication WeChat group by adding the WeChat, or join our [**Slack**](https://join.slack.com/t/mmocrworkspace/shared_invite/zt-1ifqhfla8-yKnLO_aKhVA2h71OrK8GZw)
+
+<div align="center">
+<img src="https://raw.githubusercontent.com/open-mmlab/mmcv/master/docs/en/_static/zhihu_qrcode.jpg" height="400" />  <img src="https://raw.githubusercontent.com/open-mmlab/mmcv/master/docs/en/_static/qq_group_qrcode.jpg" height="400" />  <img src="https://raw.githubusercontent.com/open-mmlab/mmcv/master/docs/en/_static/wechat_qrcode.jpg" height="400" />
+</div>
+
+We will provide you with the OpenMMLab community
+
+- 📢 share the latest core technologies of AI frameworks
+- 💻 Explaining PyTorch common module source Code
+- 📰 News related to the release of OpenMMLab
+- 🚀 Introduction of cutting-edge algorithms developed by OpenMMLab
+  🏃 Get the more efficient answer and feedback
+- 🔥 Provide a platform for communication with developers from all walks of life
+
+The OpenMMLab community looks forward to your participation! 👬

mmocr-dev-1.x/README_zh-CN.md

@@ -0,0 +1,250 @@
+<div align="center">
+  <img src="resources/mmocr-logo.png" width="500px"/>
+  <div>&nbsp;</div>
+  <div align="center">
+    <b><font size="5">OpenMMLab 官网</font></b>
+    <sup>
+      <a href="https://openmmlab.com">
+        <i><font size="4">HOT</font></i>
+      </a>
+    </sup>
+    &nbsp;&nbsp;&nbsp;&nbsp;
+    <b><font size="5">OpenMMLab 开放平台</font></b>
+    <sup>
+      <a href="https://platform.openmmlab.com">
+        <i><font size="4">TRY IT OUT</font></i>
+      </a>
+    </sup>
+  </div>
+  <div>&nbsp;</div>
+
+[![build](https://github.com/open-mmlab/mmocr/workflows/build/badge.svg)](https://github.com/open-mmlab/mmocr/actions)
+[![docs](https://readthedocs.org/projects/mmocr/badge/?version=dev-1.x)](https://mmocr.readthedocs.io/en/dev-1.x/?badge=dev-1.x)
+[![codecov](https://codecov.io/gh/open-mmlab/mmocr/branch/main/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmocr)
+[![license](https://img.shields.io/github/license/open-mmlab/mmocr.svg)](https://github.com/open-mmlab/mmocr/blob/main/LICENSE)
+[![PyPI](https://badge.fury.io/py/mmocr.svg)](https://pypi.org/project/mmocr/)
+[![Average time to resolve an issue](https://isitmaintained.com/badge/resolution/open-mmlab/mmocr.svg)](https://github.com/open-mmlab/mmocr/issues)
+[![Percentage of issues still open](https://isitmaintained.com/badge/open/open-mmlab/mmocr.svg)](https://github.com/open-mmlab/mmocr/issues)
+<a href="https://console.tiyaro.ai/explore?q=mmocr&pub=mmocr"> <img src="https://tiyaro-public-docs.s3.us-west-2.amazonaws.com/assets/try_on_tiyaro_badge.svg"></a>
+
+[📘文档](https://mmocr.readthedocs.io/zh_CN/dev-1.x/) |
+[🛠️安装](https://mmocr.readthedocs.io/zh_CN/dev-1.x/get_started/install.html) |
+[👀模型库](https://mmocr.readthedocs.io/zh_CN/dev-1.x/modelzoo.html) |
+[🆕更新日志](https://mmocr.readthedocs.io/en/dev-1.x/notes/changelog.html) |
+[🤔报告问题](https://github.com/open-mmlab/mmocr/issues/new/choose)
+
+</div>
+
+<div align="center">
+
+[English](/README.md) | 简体中文
+
+</div>
+
+<div align="center">
+  <a href="https://openmmlab.medium.com/" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219255827-67c1a27f-f8c5-46a9-811d-5e57448c61d1.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://discord.gg/raweFPmdzG" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218347213-c080267f-cbb6-443e-8532-8e1ed9a58ea9.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://twitter.com/OpenMMLab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218346637-d30c8a0f-3eba-4699-8131-512fb06d46db.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://www.youtube.com/openmmlab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218346691-ceb2116a-465a-40af-8424-9f30d2348ca9.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://space.bilibili.com/1293512903" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219026751-d7d14cce-a7c9-4e82-9942-8375fca65b99.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://www.zhihu.com/people/openmmlab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/219026120-ba71e48b-6e94-4bd4-b4e9-b7d175b5e362.png" width="3%" alt="" /></a>
+</div>
+
+## 近期更新
+
+**默认分支目前为 `main`，且分支上的代码已经切换到 v1.0.0 版本。旧版 `main` 分支（v0.6.3）的代码现存在 `0.x` 分支上。** 如果您一直在使用 `main` 分支，并遇到升级问题，请阅读 [迁移指南](https://mmocr.readthedocs.io/zh_CN/dev-1.x/migration/overview.html) 和 [分支说明](https://mmocr.readthedocs.io/zh_CN/dev-1.x/migration/branches.html) 。
+
+最新的版本 v1.0.0 于 2023-04-06 发布。其相对于 1.0.0rc6 的主要更新如下：
+
+1. Dataset Preparer 中支持了 SCUT-CTW1500, SynthText 和 MJSynth 数据集；
+2. 更新了文档和 FAQ；
+3. 升级文件后端；使用了 `backend_args` 替换 `file_client_args`;
+4. 增加了 MMOCR 教程 notebook。
+
+如果需要了解 MMOCR 1.0 相对于 0.x 的升级内容，请阅读 [MMOCR 1.x 更新汇总](https://mmocr.readthedocs.io/zh_CN/dev-1.x/migration/news.html)；或者阅读[更新日志](https://mmocr.readthedocs.io/zh_CN/dev-1.x/notes/changelog.html)以获取更多信息。
+
+## 简介
+
+MMOCR 是基于 PyTorch 和 mmdetection 的开源工具箱，专注于文本检测，文本识别以及相应的下游任务，如关键信息提取。 它是 OpenMMLab 项目的一部分。
+
+主分支目前支持 **PyTorch 1.6 以上**的版本。
+
+<div align="center">
+  <img src="https://user-images.githubusercontent.com/24622904/187838618-1fdc61c0-2d46-49f9-8502-976ffdf01f28.png"/>
+</div>
+
+### 主要特性
+
+-**全流程**
+
+该工具箱不仅支持文本检测和文本识别，还支持其下游任务，例如关键信息提取。
+
+-**多种模型**
+
+该工具箱支持用于文本检测，文本识别和关键信息提取的各种最新模型。
+
+-**模块化设计**
+
+MMOCR 的模块化设计使用户可以定义自己的优化器，数据预处理器，模型组件如主干模块，颈部模块和头部模块，以及损失函数。有关如何构建自定义模型的信息，请参考[概览](https://mmocr.readthedocs.io/zh_CN/dev-1.x/get_started/overview.html)。
+
+-**众多实用工具**
+
+该工具箱提供了一套全面的实用程序，可以帮助用户评估模型的性能。它包括可对图像，标注的真值以及预测结果进行可视化的可视化工具，以及用于在训练过程中评估模型的验证工具。它还包括数据转换器，演示了如何将用户自建的标注数据转换为 MMOCR 支持的标注文件。
+
+## 安装
+
+MMOCR 依赖 [PyTorch](https://pytorch.org/), [MMEngine](https://github.com/open-mmlab/mmengine), [MMCV](https://github.com/open-mmlab/mmcv) 和 [MMDetection](https://github.com/open-mmlab/mmdetection)，以下是安装的简要步骤。
+更详细的安装指南请参考 [安装文档](https://mmocr.readthedocs.io/zh_CN/dev-1.x/get_started/install.html)。
+
+```shell
+conda create -n open-mmlab python=3.8 pytorch=1.10 cudatoolkit=11.3 torchvision -c pytorch -y
+conda activate open-mmlab
+pip3 install openmim
+git clone https://github.com/open-mmlab/mmocr.git
+cd mmocr
+mim install -e .
+```
+
+## 快速入门
+
+请参考[快速入门](https://mmocr.readthedocs.io/zh_CN/dev-1.x/get_started/quick_run.html)文档学习 MMOCR 的基本使用。
+
+## [模型库](https://mmocr.readthedocs.io/zh_CN/dev-1.x/modelzoo.html)
+
+支持的算法：
+
+<details open>
+<summary>骨干网络</summary>
+
+- [x] [oCLIP](configs/backbone/oclip/README.md) (ECCV'2022)
+
+</details>
+
+<details open>
+<summary>文字检测</summary>
+
+- [x] [DBNet](configs/textdet/dbnet/README.md) (AAAI'2020) / [DBNet++](configs/textdet/dbnetpp/README.md) (TPAMI'2022)
+- [x] [Mask R-CNN](configs/textdet/maskrcnn/README.md) (ICCV'2017)
+- [x] [PANet](configs/textdet/panet/README.md) (ICCV'2019)
+- [x] [PSENet](configs/textdet/psenet/README.md) (CVPR'2019)
+- [x] [TextSnake](configs/textdet/textsnake/README.md) (ECCV'2018)
+- [x] [DRRG](configs/textdet/drrg/README.md) (CVPR'2020)
+- [x] [FCENet](configs/textdet/fcenet/README.md) (CVPR'2021)
+
+</details>
+
+<details open>
+<summary>文字识别</summary>
+
+- [x] [ABINet](configs/textrecog/abinet/README.md) (CVPR'2021)
+- [x] [ASTER](configs/textrecog/aster/README.md) (TPAMI'2018)
+- [x] [CRNN](configs/textrecog/crnn/README.md) (TPAMI'2016)
+- [x] [MASTER](configs/textrecog/master/README.md) (PR'2021)
+- [x] [NRTR](configs/textrecog/nrtr/README.md) (ICDAR'2019)
+- [x] [RobustScanner](configs/textrecog/robust_scanner/README.md) (ECCV'2020)
+- [x] [SAR](configs/textrecog/sar/README.md) (AAAI'2019)
+- [x] [SATRN](configs/textrecog/satrn/README.md) (CVPR'2020 Workshop on Text and Documents in the Deep Learning Era)
+- [x] [SVTR](configs/textrecog/svtr/README.md) (IJCAI'2022)
+
+</details>
+
+<details open>
+<summary>关键信息提取</summary>
+
+- [x] [SDMG-R](configs/kie/sdmgr/README.md) (ArXiv'2021)
+
+</details>
+
+<details open>
+<summary>端对端 OCR</summary>
+
+- [x] [ABCNet](projects/ABCNet/README.md) (CVPR'2020)
+- [x] [ABCNetV2](projects/ABCNet/README_V2.md) (TPAMI'2021)
+- [x] [SPTS](projects/SPTS/README.md) (ACM MM'2022)
+
+</details>
+
+请点击[模型库](https://mmocr.readthedocs.io/zh_CN/dev-1.x/modelzoo.html)查看更多关于上述算法的详细信息。
+
+## 社区项目
+
+[这里](projects/README.md)有一些由社区用户支持和维护的基于 MMOCR 的 SOTA 模型和解决方案的实现。这些项目展示了基于 MMOCR 的研究和产品开发的最佳实践。
+我们欢迎并感谢对 OpenMMLab 生态系统的所有贡献。
+
+## 贡献指南
+
+我们感谢所有的贡献者为改进和提升 MMOCR 所作出的努力。请参考[贡献指南](.github/CONTRIBUTING.md)来了解参与项目贡献的相关指引。
+
+## 致谢
+
+MMOCR 是一款由来自不同高校和企业的研发人员共同参与贡献的开源项目。我们感谢所有为项目提供算法复现和新功能支持的贡献者，以及提供宝贵反馈的用户。 我们希望此工具箱可以帮助大家来复现已有的方法和开发新的方法，从而为研究社区贡献力量。
+
+## 引用
+
+如果您发现此项目对您的研究有用，请考虑引用：
+
+```bibtex
+@article{mmocr2021,
+    title={MMOCR:  A Comprehensive Toolbox for Text Detection, Recognition and Understanding},
+    author={Kuang, Zhanghui and Sun, Hongbin and Li, Zhizhong and Yue, Xiaoyu and Lin, Tsui Hin and Chen, Jianyong and Wei, Huaqiang and Zhu, Yiqin and Gao, Tong and Zhang, Wenwei and Chen, Kai and Zhang, Wayne and Lin, Dahua},
+    journal= {arXiv preprint arXiv:2108.06543},
+    year={2021}
+}
+```
+
+## 开源许可证
+
+该项目采用 [Apache 2.0 license](LICENSE) 开源许可证。
+
+## OpenMMLab 的其他项目
+
+- [MMEngine](https://github.com/open-mmlab/mmengine): OpenMMLab 深度学习模型训练基础库
+- [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab 计算机视觉基础库
+- [MIM](https://github.com/open-mmlab/mim): MIM 是 OpenMMlab 项目、算法、模型的统一入口
+- [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab 图像分类工具箱
+- [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab 目标检测工具箱
+- [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab 新一代通用 3D 目标检测平台
+- [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab 旋转框检测工具箱与测试基准
+- [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab 语义分割工具箱
+- [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab 全流程文字检测识别理解工具箱
+- [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab 姿态估计工具箱
+- [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 人体参数化模型工具箱与测试基准
+- [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab 自监督学习工具箱与测试基准
+- [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab 模型压缩工具箱与测试基准
+- [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab 少样本学习工具箱与测试基准
+- [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab 新一代视频理解工具箱
+- [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab 一体化视频目标感知平台
+- [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab 光流估计工具箱与测试基准
+- [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab 图像视频编辑工具箱
+- [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab 图片视频生成模型工具箱
+- [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab 模型部署框架
+
+## 欢迎加入 OpenMMLab 社区
+
+扫描下方的二维码可关注 OpenMMLab 团队的 [知乎官方账号](https://www.zhihu.com/people/openmmlab)，加入 OpenMMLab 团队的 [官方交流 QQ 群](https://r.vansin.top/?r=join-qq)，或通过添加微信“Open小喵Lab”加入官方交流微信群。
+
+<div align="center">
+<img src="https://raw.githubusercontent.com/open-mmlab/mmcv/master/docs/en/_static/zhihu_qrcode.jpg" height="400" />  <img src="https://cdn.vansin.top/OpenMMLab/q3.png" height="400" />  <img src="https://raw.githubusercontent.com/open-mmlab/mmcv/master/docs/en/_static/wechat_qrcode.jpg" height="400" />
+</div>
+
+我们会在 OpenMMLab 社区为大家
+
+- 📢 分享 AI 框架的前沿核心技术
+- 💻 解读 PyTorch 常用模块源码
+- 📰 发布 OpenMMLab 的相关新闻
+- 🚀 介绍 OpenMMLab 开发的前沿算法
+- 🏃 获取更高效的问题答疑和意见反馈
+- 🔥 提供与各行各业开发者充分交流的平台
+
+干货满满 📘，等你来撩 💗，OpenMMLab 社区期待您的加入 👬

mmocr-dev-1.x/configs/backbone/oclip/README.md

@@ -0,0 +1,41 @@
+# oCLIP
+
+> [Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136880282.pdf)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Recently, Vision-Language Pre-training (VLP) techniques have greatly benefited various vision-language tasks by jointly learning visual and textual representations, which intuitively helps in Optical Character Recognition (OCR) tasks due to the rich visual and textual information in scene text images. However, these methods cannot well cope with OCR tasks because of the difficulty in both instance-level text encoding and image-text pair acquisition (i.e. images and captured texts in them). This paper presents a weakly supervised pre-training method, oCLIP, which can acquire effective scene text representations by jointly learning and aligning visual and textual information. Our network consists of an image encoder and a character-aware text encoder that extract visual and textual features, respectively, as well as a visual-textual decoder that models the interaction among textual and visual features for learning effective scene text representations. With the learning of textual features, the pre-trained model can attend texts in images well with character awareness. Besides, these designs enable the learning from weakly annotated texts (i.e. partial texts in images without text bounding boxes) which mitigates the data annotation constraint greatly. Experiments over the weakly annotated images in ICDAR2019-LSVT show that our pre-trained model improves F-score by +2.5% and +4.8% while transferring its weights to other text detection and spotting networks, respectively. In addition, the proposed method outperforms existing pre-training techniques consistently across multiple public datasets (e.g., +3.2% and +1.3% for Total-Text and CTW1500).
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/24622904/199475057-aa688422-518d-4d7a-86fc-1be0cc1b5dc6.png"/>
+</div>
+
+## Models
+
+| Backbone  | Pre-train Data |                                       Model                                       |
+| :-------: | :------------: | :-------------------------------------------------------------------------------: |
+| ResNet-50 |   SynthText    | [Link](https://download.openmmlab.com/mmocr/backbone/resnet50-oclip-7ba0c533.pth) |
+
+```{note}
+The model is converted from the official [oCLIP](https://github.com/bytedance/oclip.git).
+```
+
+## Supported Text Detection Models
+
+|           | [DBNet](https://mmocr.readthedocs.io/en/dev-1.x/textdet_models.html#dbnet) | [DBNet++](https://mmocr.readthedocs.io/en/dev-1.x/textdet_models.html#dbnetpp) | [FCENet](https://mmocr.readthedocs.io/en/dev-1.x/textdet_models.html#fcenet) | [TextSnake](https://mmocr.readthedocs.io/en/dev-1.x/textdet_models.html#fcenet) | [PSENet](https://mmocr.readthedocs.io/en/dev-1.x/textdet_models.html#psenet) | [DRRG](https://mmocr.readthedocs.io/en/dev-1.x/textdet_models.html#drrg) | [Mask R-CNN](https://mmocr.readthedocs.io/en/dev-1.x/textdet_models.html#mask-r-cnn) |
+| :-------: | :------------------------------------------------------------------------: | :----------------------------------------------------------------------------: | :--------------------------------------------------------------------------: | :-----------------------------------------------------------------------------: | :--------------------------------------------------------------------------: | :----------------------------------------------------------------------: | :----------------------------------------------------------------------------------: |
+| ICDAR2015 |                                     ✓                                      |                                       ✓                                        |                                      ✓                                       |                                                                                 |                                      ✓                                       |                                                                          |                                          ✓                                           |
+|  CTW1500  |                                                                            |                                                                                |                                      ✓                                       |                                        ✓                                        |                                      ✓                                       |                                    ✓                                     |                                          ✓                                           |
+
+## Citation
+
+```bibtex
+@article{xue2022language,
+  title={Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting},
+  author={Xue, Chuhui and Zhang, Wenqing and Hao, Yu and Lu, Shijian and Torr, Philip and Bai, Song},
+  journal={Proceedings of the European Conference on Computer Vision (ECCV)},
+  year={2022}
+}
+```

mmocr-dev-1.x/configs/backbone/oclip/metafile.yml

@@ -0,0 +1,13 @@
+Collections:
+- Name: oCLIP
+  Metadata:
+    Training Data: SynthText
+    Architecture:
+      - CLIPResNet
+  Paper:
+    URL: https://arxiv.org/abs/2203.03911
+    Title: 'Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting'
+  README: configs/backbone/oclip/README.md
+
+Models:
+  Weights: https://download.openmmlab.com/mmocr/backbone/resnet50-oclip-7ba0c533.pth

mmocr-dev-1.x/configs/kie/_base_/datasets/wildreceipt-openset.py

@@ -0,0 +1,26 @@
+wildreceipt_openset_data_root = 'data/wildreceipt/'
+
+wildreceipt_openset_train = dict(
+    type='WildReceiptDataset',
+    data_root=wildreceipt_openset_data_root,
+    metainfo=dict(category=[
+        dict(id=0, name='bg'),
+        dict(id=1, name='key'),
+        dict(id=2, name='value'),
+        dict(id=3, name='other')
+    ]),
+    ann_file='openset_train.txt',
+    pipeline=None)
+
+wildreceipt_openset_test = dict(
+    type='WildReceiptDataset',
+    data_root=wildreceipt_openset_data_root,
+    metainfo=dict(category=[
+        dict(id=0, name='bg'),
+        dict(id=1, name='key'),
+        dict(id=2, name='value'),
+        dict(id=3, name='other')
+    ]),
+    ann_file='openset_test.txt',
+    test_mode=True,
+    pipeline=None)

mmocr-dev-1.x/configs/kie/_base_/datasets/wildreceipt.py

@@ -0,0 +1,16 @@
+wildreceipt_data_root = 'data/wildreceipt/'
+
+wildreceipt_train = dict(
+    type='WildReceiptDataset',
+    data_root=wildreceipt_data_root,
+    metainfo=wildreceipt_data_root + 'class_list.txt',
+    ann_file='train.txt',
+    pipeline=None)
+
+wildreceipt_test = dict(
+    type='WildReceiptDataset',
+    data_root=wildreceipt_data_root,
+    metainfo=wildreceipt_data_root + 'class_list.txt',
+    ann_file='test.txt',
+    test_mode=True,
+    pipeline=None)

mmocr-dev-1.x/configs/kie/_base_/default_runtime.py

@@ -0,0 +1,33 @@
+default_scope = 'mmocr'
+env_cfg = dict(
+    cudnn_benchmark=False,
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+    dist_cfg=dict(backend='nccl'),
+)
+randomness = dict(seed=None)
+
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=100),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(type='CheckpointHook', interval=1),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    sync_buffer=dict(type='SyncBuffersHook'),
+    visualization=dict(
+        type='VisualizationHook',
+        interval=1,
+        enable=False,
+        show=False,
+        draw_gt=False,
+        draw_pred=False),
+)
+
+# Logging
+log_level = 'INFO'
+log_processor = dict(type='LogProcessor', window_size=10, by_epoch=True)
+
+load_from = None
+resume = False
+
+visualizer = dict(
+    type='KIELocalVisualizer', name='visualizer', is_openset=False)

mmocr-dev-1.x/configs/kie/_base_/schedules/schedule_adam_60e.py

@@ -0,0 +1,10 @@
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper', optimizer=dict(type='Adam', weight_decay=0.0001))
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=60, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+# learning rate
+param_scheduler = [
+    dict(type='MultiStepLR', milestones=[40, 50], end=60),
+]

mmocr-dev-1.x/configs/kie/sdmgr/README.md

@@ -0,0 +1,41 @@
+# SDMGR
+
+> [Spatial Dual-Modality Graph Reasoning for Key Information Extraction](https://arxiv.org/abs/2103.14470)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Key information extraction from document images is of paramount importance in office automation. Conventional template matching based approaches fail to generalize well to document images of unseen templates, and are not robust against text recognition errors. In this paper, we propose an end-to-end Spatial Dual-Modality Graph Reasoning method (SDMG-R) to extract key information from unstructured document images. We model document images as dual-modality graphs, nodes of which encode both the visual and textual features of detected text regions, and edges of which represent the spatial relations between neighboring text regions. The key information extraction is solved by iteratively propagating messages along graph edges and reasoning the categories of graph nodes. In order to roundly evaluate our proposed method as well as boost the future research, we release a new dataset named WildReceipt, which is collected and annotated tailored for the evaluation of key information extraction from document images of unseen templates in the wild. It contains 25 key information categories, a total of about 69000 text boxes, and is about 2 times larger than the existing public datasets. Extensive experiments validate that all information including visual features, textual features and spatial relations can benefit key information extraction. It has been shown that SDMG-R can effectively extract key information from document images of unseen templates, and obtain new state-of-the-art results on the recent popular benchmark SROIE and our WildReceipt. Our code and dataset will be publicly released.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/22607038/142580689-18edb4d7-f716-475c-b1c1-e2b934658cee.png"/>
+</div>
+
+## Results and models
+
+### WildReceipt
+
+|                                 Method                                 |     Modality     | Macro F1-Score |                                               Download                                               |
+| :--------------------------------------------------------------------: | :--------------: | :------------: | :--------------------------------------------------------------------------------------------------: |
+|   [sdmgr_unet16](/configs/kie/sdmgr/sdmgr_unet16_60e_wildreceipt.py)   | Visual + Textual |     0.890      | [model](https://download.openmmlab.com/mmocr/kie/sdmgr/sdmgr_unet16_60e_wildreceipt/sdmgr_unet16_60e_wildreceipt_20220825_151648-22419f37.pth) \| [log](https://download.openmmlab.com/mmocr/kie/sdmgr/sdmgr_unet16_60e_wildreceipt/20220825_151648.log) |
+| [sdmgr_novisual](/configs/kie/sdmgr/sdmgr_novisual_60e_wildreceipt.py) |     Textual      |     0.873      | [model](https://download.openmmlab.com/mmocr/kie/sdmgr/sdmgr_novisual_60e_wildreceipt/sdmgr_novisual_60e_wildreceipt_20220831_193317-827649d8.pth) \| [log](https://download.openmmlab.com/mmocr/kie/sdmgr/sdmgr_novisual_60e_wildreceipt/20220831_193317.log) |
+
+### WildReceiptOpenset
+
+|                                Method                                 | Modality | Edge F1-Score | Node Macro F1-Score | Node Micro F1-Score |                                 Download                                 |
+| :-------------------------------------------------------------------: | :------: | :-----------: | :-----------------: | :-----------------: | :----------------------------------------------------------------------: |
+| [sdmgr_novisual_openset](/configs/kie/sdmgr/sdmgr_novisual_60e_wildreceipt-openset.py) | Textual  |     0.792     |        0.931        |        0.940        | [model](https://download.openmmlab.com/mmocr/kie/sdmgr/sdmgr_novisual_60e_wildreceipt-openset/sdmgr_novisual_60e_wildreceipt-openset_20220831_200807-dedf15ec.pth) \| [log](https://download.openmmlab.com/mmocr/kie/sdmgr/sdmgr_novisual_60e_wildreceipt-openset/20220831_200807.log) |
+
+## Citation
+
+```bibtex
+@misc{sun2021spatial,
+      title={Spatial Dual-Modality Graph Reasoning for Key Information Extraction},
+      author={Hongbin Sun and Zhanghui Kuang and Xiaoyu Yue and Chenhao Lin and Wayne Zhang},
+      year={2021},
+      eprint={2103.14470},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```

mmocr-dev-1.x/configs/kie/sdmgr/_base_sdmgr_novisual.py

@@ -0,0 +1,35 @@
+num_classes = 26
+
+model = dict(
+    type='SDMGR',
+    kie_head=dict(
+        type='SDMGRHead',
+        visual_dim=16,
+        num_classes=num_classes,
+        module_loss=dict(type='SDMGRModuleLoss'),
+        postprocessor=dict(type='SDMGRPostProcessor')),
+    dictionary=dict(
+        type='Dictionary',
+        dict_file='{{ fileDirname }}/../../../dicts/sdmgr_dict.txt',
+        with_padding=True,
+        with_unknown=True,
+        unknown_token=None),
+)
+
+train_pipeline = [
+    dict(type='LoadKIEAnnotations'),
+    dict(type='Resize', scale=(1024, 512), keep_ratio=True),
+    dict(type='PackKIEInputs')
+]
+test_pipeline = [
+    dict(type='LoadKIEAnnotations'),
+    dict(type='Resize', scale=(1024, 512), keep_ratio=True),
+    dict(type='PackKIEInputs'),
+]
+
+val_evaluator = dict(
+    type='F1Metric',
+    mode='macro',
+    num_classes=num_classes,
+    ignored_classes=[0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 25])
+test_evaluator = val_evaluator

mmocr-dev-1.x/configs/kie/sdmgr/_base_sdmgr_unet16.py

@@ -0,0 +1,28 @@
+_base_ = '_base_sdmgr_novisual.py'
+
+model = dict(
+    backbone=dict(type='UNet', base_channels=16),
+    roi_extractor=dict(
+        type='mmdet.SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', output_size=7),
+        featmap_strides=[1]),
+    data_preprocessor=dict(
+        type='ImgDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_size_divisor=32),
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadKIEAnnotations'),
+    dict(type='Resize', scale=(1024, 512), keep_ratio=True),
+    dict(type='PackKIEInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadKIEAnnotations'),
+    dict(type='Resize', scale=(1024, 512), keep_ratio=True),
+    dict(type='PackKIEInputs', meta_keys=('img_path', )),
+]

mmocr-dev-1.x/configs/kie/sdmgr/metafile.yml

@@ -0,0 +1,52 @@
+Collections:
+- Name: SDMGR
+  Metadata:
+    Training Data: KIEDataset
+    Training Techniques:
+      - Adam
+    Training Resources: 1x NVIDIA A100-SXM4-80GB
+    Architecture:
+      - UNet
+      - SDMGRHead
+  Paper:
+    URL: https://arxiv.org/abs/2103.14470.pdf
+    Title: 'Spatial Dual-Modality Graph Reasoning for Key Information Extraction'
+  README: configs/kie/sdmgr/README.md
+
+Models:
+  - Name: sdmgr_unet16_60e_wildreceipt
+    Alias: SDMGR
+    In Collection: SDMGR
+    Config: configs/kie/sdmgr/sdmgr_unet16_60e_wildreceipt.py
+    Metadata:
+      Training Data: wildreceipt
+    Results:
+      - Task: Key Information Extraction
+        Dataset: wildreceipt
+        Metrics:
+          macro_f1: 0.890
+    Weights: https://download.openmmlab.com/mmocr/kie/sdmgr/sdmgr_unet16_60e_wildreceipt/sdmgr_unet16_60e_wildreceipt_20220825_151648-22419f37.pth
+  - Name: sdmgr_novisual_60e_wildreceipt
+    In Collection: SDMGR
+    Config: configs/kie/sdmgr/sdmgr_novisual_60e_wildreceipt.py
+    Metadata:
+      Training Data: wildreceipt
+    Results:
+      - Task: Key Information Extraction
+        Dataset: wildreceipt
+        Metrics:
+          macro_f1: 0.873
+    Weights: https://download.openmmlab.com/mmocr/kie/sdmgr/sdmgr_novisual_60e_wildreceipt/sdmgr_novisual_60e_wildreceipt_20220831_193317-827649d8.pth
+  - Name: sdmgr_novisual_60e_wildreceipt_openset
+    In Collection: SDMGR
+    Config: configs/kie/sdmgr/sdmgr_novisual_60e_wildreceipt-openset.py
+    Metadata:
+      Training Data: wildreceipt-openset
+    Results:
+      - Task: Key Information Extraction
+        Dataset: wildreceipt
+        Metrics:
+          macro_f1: 0.931
+          micro_f1: 0.940
+          edge_micro_f1: 0.792
+    Weights: https://download.openmmlab.com/mmocr/kie/sdmgr/sdmgr_novisual_60e_wildreceipt-openset/sdmgr_novisual_60e_wildreceipt-openset_20220831_200807-dedf15ec.pth

mmocr-dev-1.x/configs/kie/sdmgr/sdmgr_novisual_60e_wildreceipt-openset.py

@@ -0,0 +1,71 @@
+_base_ = [
+    '../_base_/default_runtime.py',
+    '../_base_/datasets/wildreceipt-openset.py',
+    '../_base_/schedules/schedule_adam_60e.py',
+    '_base_sdmgr_novisual.py',
+]
+
+node_num_classes = 4  # 4 classes: bg, key, value and other
+edge_num_classes = 2  # edge connectivity
+key_node_idx = 1
+value_node_idx = 2
+
+model = dict(
+    type='SDMGR',
+    kie_head=dict(
+        num_classes=node_num_classes,
+        postprocessor=dict(
+            link_type='one-to-many',
+            key_node_idx=key_node_idx,
+            value_node_idx=value_node_idx)),
+)
+
+test_pipeline = [
+    dict(
+        type='LoadKIEAnnotations',
+        key_node_idx=key_node_idx,
+        value_node_idx=value_node_idx),  # Keep key->value edges for evaluation
+    dict(type='Resize', scale=(1024, 512), keep_ratio=True),
+    dict(type='PackKIEInputs'),
+]
+
+wildreceipt_openset_train = _base_.wildreceipt_openset_train
+wildreceipt_openset_train.pipeline = _base_.train_pipeline
+wildreceipt_openset_test = _base_.wildreceipt_openset_test
+wildreceipt_openset_test.pipeline = test_pipeline
+
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=1,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=wildreceipt_openset_train)
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=wildreceipt_openset_test)
+test_dataloader = val_dataloader
+
+val_evaluator = [
+    dict(
+        type='F1Metric',
+        prefix='node',
+        key='labels',
+        mode=['micro', 'macro'],
+        num_classes=node_num_classes,
+        cared_classes=[key_node_idx, value_node_idx]),
+    dict(
+        type='F1Metric',
+        prefix='edge',
+        mode='micro',
+        key='edge_labels',
+        cared_classes=[1],  # Collapse to binary F1 score
+        num_classes=edge_num_classes)
+]
+test_evaluator = val_evaluator
+
+visualizer = dict(
+    type='KIELocalVisualizer', name='visualizer', is_openset=True)
+auto_scale_lr = dict(base_batch_size=4)

mmocr-dev-1.x/configs/kie/sdmgr/sdmgr_novisual_60e_wildreceipt.py

@@ -0,0 +1,28 @@
+_base_ = [
+    '../_base_/default_runtime.py',
+    '../_base_/datasets/wildreceipt.py',
+    '../_base_/schedules/schedule_adam_60e.py',
+    '_base_sdmgr_novisual.py',
+]
+
+wildreceipt_train = _base_.wildreceipt_train
+wildreceipt_train.pipeline = _base_.train_pipeline
+wildreceipt_test = _base_.wildreceipt_test
+wildreceipt_test.pipeline = _base_.test_pipeline
+
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=1,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=wildreceipt_train)
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=wildreceipt_test)
+test_dataloader = val_dataloader
+
+auto_scale_lr = dict(base_batch_size=4)

mmocr-dev-1.x/configs/kie/sdmgr/sdmgr_unet16_60e_wildreceipt.py

@@ -0,0 +1,29 @@
+_base_ = [
+    '../_base_/default_runtime.py',
+    '../_base_/datasets/wildreceipt.py',
+    '../_base_/schedules/schedule_adam_60e.py',
+    '_base_sdmgr_unet16.py',
+]
+
+wildreceipt_train = _base_.wildreceipt_train
+wildreceipt_train.pipeline = _base_.train_pipeline
+wildreceipt_test = _base_.wildreceipt_test
+wildreceipt_test.pipeline = _base_.test_pipeline
+
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=wildreceipt_train)
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=wildreceipt_test)
+
+test_dataloader = val_dataloader
+
+auto_scale_lr = dict(base_batch_size=4)

mmocr-dev-1.x/configs/textdet/_base_/datasets/ctw1500.py

@@ -0,0 +1,15 @@
+ctw1500_textdet_data_root = 'data/ctw1500'
+
+ctw1500_textdet_train = dict(
+    type='OCRDataset',
+    data_root=ctw1500_textdet_data_root,
+    ann_file='textdet_train.json',
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=None)
+
+ctw1500_textdet_test = dict(
+    type='OCRDataset',
+    data_root=ctw1500_textdet_data_root,
+    ann_file='textdet_test.json',
+    test_mode=True,
+    pipeline=None)

mmocr-dev-1.x/configs/textdet/_base_/datasets/icdar2015.py

@@ -0,0 +1,15 @@
+icdar2015_textdet_data_root = 'data/icdar2015'
+
+icdar2015_textdet_train = dict(
+    type='OCRDataset',
+    data_root=icdar2015_textdet_data_root,
+    ann_file='textdet_train.json',
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=None)
+
+icdar2015_textdet_test = dict(
+    type='OCRDataset',
+    data_root=icdar2015_textdet_data_root,
+    ann_file='textdet_test.json',
+    test_mode=True,
+    pipeline=None)

mmocr-dev-1.x/configs/textdet/_base_/datasets/icdar2017.py

@@ -0,0 +1,17 @@
+icdar2017_textdet_data_root = 'data/det/icdar_2017'
+
+icdar2017_textdet_train = dict(
+    type='OCRDataset',
+    data_root=icdar2017_textdet_data_root,
+    ann_file='instances_training.json',
+    data_prefix=dict(img_path='imgs/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=None)
+
+icdar2017_textdet_test = dict(
+    type='OCRDataset',
+    data_root=icdar2017_textdet_data_root,
+    ann_file='instances_test.json',
+    data_prefix=dict(img_path='imgs/'),
+    test_mode=True,
+    pipeline=None)