Add application file

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

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

MANIFEST.in

@@ -0,0 +1,4 @@
+include requirements/*.txt
+include mmocr/.mim/model-index.yml
+recursive-include mmocr/.mim/configs *.py *.yml
+recursive-include mmocr/.mim/tools *.sh *.py

README_zh-CN.md

@@ -0,0 +1,183 @@
+<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>
+</div>
+
+## 简介
+
+[English](/README.md) | 简体中文
+
+[![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=latest)](https://mmocr.readthedocs.io/en/latest/?badge=latest)
+[![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)
+
+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。
+
+文档：https://mmocr.readthedocs.io/zh_CN/latest/
+
+<div align="left">
+  <img src="resources/illustration.jpg"/>
+</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[快速入门](https://mmocr.readthedocs.io/zh_CN/latest/getting_started.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。
+## [模型库](https://mmocr.readthedocs.io/en/latest/modelzoo.html)
+
+支持的算法：
+
+<details open>
+<summary>文字检测</summary>
+
+- [x] [DBNet](configs/textdet/dbnet/README.md) (AAAI'2020)
+- [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] [CRNN](configs/textrecog/crnn/README.md) (TPAMI'2016)
+- [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] [SegOCR](configs/textrecog/seg/README.md) (Manuscript'2021)
+
+</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>命名实体识别</summary>
+
+- [x] [Bert-Softmax](configs/ner/bert_softmax/README.md) (NAACL'2019)
+
+</details>
+
+请点击[模型库](https://mmocr.readthedocs.io/en/latest/modelzoo.html)查看更多关于上述算法的详细信息。
+
+## 开源许可证
+
+该项目采用 [Apache 2.0 license](LICENSE) 开源许可证。
+
+## 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}
+}
+```
+
+## 更新日志
+
+最新的月度版本 v0.4.1 在 2022.01.27 发布。
+
+## 安装
+
+请参考[安装文档](https://mmocr.readthedocs.io/zh_CN/latest/install.html)进行安装。
+
+## 快速入门
+
+请参考[快速入门](https://mmocr.readthedocs.io/zh_CN/latest/getting_started.html)文档学习 MMOCR 的基本使用。
+
+## 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。
+
+## OpenMMLab 的其他项目
+
+
+- [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://jq.qq.com/?_wv=1027&k=aCvMxdr3)
+
+<div align="center">
+<img src="resources/zhihu_qrcode.jpg" height="400" />  <img src="resources/qq_group_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 👬

app.py

@@ -0,0 +1,33 @@
+import os
+import torch
+
+print(torch.__version__)
+torch_ver, cuda_ver = torch.__version__.split('+')
+os.system(f'pip install mmdet mmcv-full -f https://download.openmmlab.com/mmcv/dist/{cuda_ver}/torch{torch_ver}/index.html --no-cache-dir')
+os.system('wget -c https://download.openmmlab.com/mmocr/data/wildreceipt.tar; mkdir -p data; tar -xf wildreceipt.tar --directory data; rm -f wildreceipt.tar')
+
+import datetime
+import gradio as gr
+import pandas as pd
+from mmocr.utils.ocr import MMOCR
+
+def inference(img):
+    print(datetime.datetime.now(), 'start')
+    ocr = MMOCR(det='PS_CTW', recog='SAR', kie='SDMGR')
+    print(datetime.datetime.now(), 'start read')
+    results = ocr.readtext(img.name, details=True, output='result.png')
+    print(datetime.datetime.now(), results)
+    return ['result.png', pd.DataFrame(results[0]['result']).iloc[: , 2:]]
+
+description = 'Gradio demo for MMOCR. 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. To use it, simply upload your image or click one of the examples to load them. Read more at the links below.'
+article = "<p style='text-align: center'><a href='https://mmocr.readthedocs.io/en/latest/'>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.</a> | <a href='https://github.com/open-mmlab/mmocr'>Github Repo</a></p>"
+gr.Interface(inference,
+    gr.inputs.Image(type='file', label='Input'),
+    [gr.outputs.Image(type='file', label='Output'), gr.outputs.Dataframe(headers=['text', 'text_score', 'label', 'label_score'])],
+    title='MMOCR',
+    description=description,
+    article=article,
+    examples=['demo/demo_kie.jpeg', 'demo/demo_text_ocr.jpg', 'demo/demo_text_det.jpg', 'demo/demo_densetext_det.jpg'],
+    css=".output_image, .input_image {height: 40rem !important; width: 100% !important;}",
+    enable_queue=True
+    ).launch(debug=True)

configs/_base_/default_runtime.py

@@ -0,0 +1,19 @@
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=5,
+    hooks=[
+        dict(type='TextLoggerHook')
+
+    ])
+# yapf:enable
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+
+# disable opencv multithreading to avoid system being overloaded
+opencv_num_threads = 0
+# set multi-process start method as `fork` to speed up the training
+mp_start_method = 'fork'

configs/_base_/det_datasets/ctw1500.py

@@ -0,0 +1,18 @@
+dataset_type = 'IcdarDataset'
+data_root = 'data/ctw1500'
+
+train = dict(
+    type=dataset_type,
+    ann_file=f'{data_root}/instances_training.json',
+    img_prefix=f'{data_root}/imgs',
+    pipeline=None)
+
+test = dict(
+    type=dataset_type,
+    ann_file=f'{data_root}/instances_test.json',
+    img_prefix=f'{data_root}/imgs',
+    pipeline=None)
+
+train_list = [train]
+
+test_list = [test]

configs/_base_/det_datasets/icdar2015.py

@@ -0,0 +1,18 @@
+dataset_type = 'IcdarDataset'
+data_root = 'data/icdar2015'
+
+train = dict(
+    type=dataset_type,
+    ann_file=f'{data_root}/instances_training.json',
+    img_prefix=f'{data_root}/imgs',
+    pipeline=None)
+
+test = dict(
+    type=dataset_type,
+    ann_file=f'{data_root}/instances_test.json',
+    img_prefix=f'{data_root}/imgs',
+    pipeline=None)
+
+train_list = [train]
+
+test_list = [test]

configs/_base_/det_datasets/icdar2017.py

@@ -0,0 +1,18 @@
+dataset_type = 'IcdarDataset'
+data_root = 'data/icdar2017'
+
+train = dict(
+    type=dataset_type,
+    ann_file=f'{data_root}/instances_training.json',
+    img_prefix=f'{data_root}/imgs',
+    pipeline=None)
+
+test = dict(
+    type=dataset_type,
+    ann_file=f'{data_root}/instances_val.json',
+    img_prefix=f'{data_root}/imgs',
+    pipeline=None)
+
+train_list = [train]
+
+test_list = [test]

configs/_base_/det_datasets/toy_data.py

@@ -0,0 +1,39 @@
+root = 'tests/data/toy_dataset'
+
+# dataset with type='TextDetDataset'
+train1 = dict(
+    type='TextDetDataset',
+    img_prefix=f'{root}/imgs',
+    ann_file=f'{root}/instances_test.txt',
+    loader=dict(
+        type='HardDiskLoader',
+        repeat=4,
+        parser=dict(
+            type='LineJsonParser',
+            keys=['file_name', 'height', 'width', 'annotations'])),
+    pipeline=None,
+    test_mode=False)
+
+# dataset with type='IcdarDataset'
+train2 = dict(
+    type='IcdarDataset',
+    ann_file=f'{root}/instances_test.json',
+    img_prefix=f'{root}/imgs',
+    pipeline=None)
+
+test = dict(
+    type='TextDetDataset',
+    img_prefix=f'{root}/imgs',
+    ann_file=f'{root}/instances_test.txt',
+    loader=dict(
+        type='HardDiskLoader',
+        repeat=1,
+        parser=dict(
+            type='LineJsonParser',
+            keys=['file_name', 'height', 'width', 'annotations'])),
+    pipeline=None,
+    test_mode=True)
+
+train_list = [train1, train2]
+
+test_list = [test]

configs/_base_/det_models/dbnet_r18_fpnc.py

@@ -0,0 +1,21 @@
+model = dict(
+    type='DBNet',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=18,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=-1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet18'),
+        norm_eval=False,
+        style='caffe'),
+    neck=dict(
+        type='FPNC', in_channels=[64, 128, 256, 512], lateral_channels=256),
+    bbox_head=dict(
+        type='DBHead',
+        in_channels=256,
+        loss=dict(type='DBLoss', alpha=5.0, beta=10.0, bbce_loss=True),
+        postprocessor=dict(type='DBPostprocessor', text_repr_type='quad')),
+    train_cfg=None,
+    test_cfg=None)

configs/_base_/det_models/dbnet_r50dcnv2_fpnc.py

@@ -0,0 +1,23 @@
+model = dict(
+    type='DBNet',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=-1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=False,
+        style='pytorch',
+        dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='FPNC', in_channels=[256, 512, 1024, 2048], lateral_channels=256),
+    bbox_head=dict(
+        type='DBHead',
+        in_channels=256,
+        loss=dict(type='DBLoss', alpha=5.0, beta=10.0, bbce_loss=True),
+        postprocessor=dict(type='DBPostprocessor', text_repr_type='quad')),
+    train_cfg=None,
+    test_cfg=None)

configs/_base_/det_models/drrg_r50_fpn_unet.py

@@ -0,0 +1,21 @@
+model = dict(
+    type='DRRG',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=-1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
+        norm_eval=True,
+        style='caffe'),
+    neck=dict(
+        type='FPN_UNet', in_channels=[256, 512, 1024, 2048], out_channels=32),
+    bbox_head=dict(
+        type='DRRGHead',
+        in_channels=32,
+        text_region_thr=0.3,
+        center_region_thr=0.4,
+        loss=dict(type='DRRGLoss'),
+        postprocessor=dict(type='DRRGPostprocessor', link_thr=0.80)))

configs/_base_/det_models/fcenet_r50_fpn.py

@@ -0,0 +1,33 @@
+model = dict(
+    type='FCENet',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(1, 2, 3),
+        frozen_stages=-1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
+        norm_eval=False,
+        style='pytorch'),
+    neck=dict(
+        type='mmdet.FPN',
+        in_channels=[512, 1024, 2048],
+        out_channels=256,
+        add_extra_convs='on_output',
+        num_outs=3,
+        relu_before_extra_convs=True,
+        act_cfg=None),
+    bbox_head=dict(
+        type='FCEHead',
+        in_channels=256,
+        scales=(8, 16, 32),
+        fourier_degree=5,
+        loss=dict(type='FCELoss', num_sample=50),
+        postprocessor=dict(
+            type='FCEPostprocessor',
+            text_repr_type='quad',
+            num_reconstr_points=50,
+            alpha=1.2,
+            beta=1.0,
+            score_thr=0.3)))

configs/_base_/det_models/fcenet_r50dcnv2_fpn.py

@@ -0,0 +1,35 @@
+model = dict(
+    type='FCENet',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(1, 2, 3),
+        frozen_stages=-1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        dcn=dict(type='DCNv2', deform_groups=2, fallback_on_stride=False),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='mmdet.FPN',
+        in_channels=[512, 1024, 2048],
+        out_channels=256,
+        add_extra_convs='on_output',
+        num_outs=3,
+        relu_before_extra_convs=True,
+        act_cfg=None),
+    bbox_head=dict(
+        type='FCEHead',
+        in_channels=256,
+        scales=(8, 16, 32),
+        fourier_degree=5,
+        loss=dict(type='FCELoss', num_sample=50),
+        postprocessor=dict(
+            type='FCEPostprocessor',
+            text_repr_type='poly',
+            num_reconstr_points=50,
+            alpha=1.0,
+            beta=2.0,
+            score_thr=0.3)))

configs/_base_/det_models/ocr_mask_rcnn_r50_fpn_ohem.py

@@ -0,0 +1,126 @@
+# model settings
+model = dict(
+    type='OCRMaskRCNN',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
+        norm_eval=True,
+        style='pytorch'),
+    neck=dict(
+        type='mmdet.FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[4],
+            ratios=[0.17, 0.44, 1.13, 2.90, 7.46],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=1,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=4,
+            in_channels=256,
+            conv_out_channels=256,
+            num_classes=1,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1,
+                gpu_assign_thr=50),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_across_levels=False,
+            nms_pre=2000,
+            nms_post=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='OHEMSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=28,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_across_levels=False,
+            nms_pre=1000,
+            nms_post=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/det_models/ocr_mask_rcnn_r50_fpn_ohem_poly.py

@@ -0,0 +1,126 @@
+# model settings
+model = dict(
+    type='OCRMaskRCNN',
+    text_repr_type='poly',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
+        style='pytorch'),
+    neck=dict(
+        type='mmdet.FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[4],
+            ratios=[0.17, 0.44, 1.13, 2.90, 7.46],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sample_num=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sample_num=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=4,
+            in_channels=256,
+            conv_out_channels=256,
+            num_classes=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_across_levels=False,
+            nms_pre=2000,
+            nms_post=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=True,
+                ignore_iof_thr=-1,
+                gpu_assign_thr=50),
+            sampler=dict(
+                type='OHEMSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=28,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_across_levels=False,
+            nms_pre=1000,
+            nms_post=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/det_models/panet_r18_fpem_ffm.py

@@ -0,0 +1,43 @@
+model_poly = dict(
+    type='PANet',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=18,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=-1,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet18'),
+        norm_eval=True,
+        style='caffe'),
+    neck=dict(type='FPEM_FFM', in_channels=[64, 128, 256, 512]),
+    bbox_head=dict(
+        type='PANHead',
+        in_channels=[128, 128, 128, 128],
+        out_channels=6,
+        loss=dict(type='PANLoss'),
+        postprocessor=dict(type='PANPostprocessor', text_repr_type='poly')),
+    train_cfg=None,
+    test_cfg=None)
+
+model_quad = dict(
+    type='PANet',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=18,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=-1,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet18'),
+        norm_eval=True,
+        style='caffe'),
+    neck=dict(type='FPEM_FFM', in_channels=[64, 128, 256, 512]),
+    bbox_head=dict(
+        type='PANHead',
+        in_channels=[128, 128, 128, 128],
+        out_channels=6,
+        loss=dict(type='PANLoss'),
+        postprocessor=dict(type='PANPostprocessor', text_repr_type='quad')),
+    train_cfg=None,
+    test_cfg=None)

configs/_base_/det_models/panet_r50_fpem_ffm.py

@@ -0,0 +1,21 @@
+model = dict(
+    type='PANet',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='caffe'),
+    neck=dict(type='FPEM_FFM', in_channels=[256, 512, 1024, 2048]),
+    bbox_head=dict(
+        type='PANHead',
+        in_channels=[128, 128, 128, 128],
+        out_channels=6,
+        loss=dict(type='PANLoss', speedup_bbox_thr=32),
+        postprocessor=dict(type='PANPostprocessor', text_repr_type='poly')),
+    train_cfg=None,
+    test_cfg=None)

configs/_base_/det_models/psenet_r50_fpnf.py

@@ -0,0 +1,51 @@
+model_poly = dict(
+    type='PSENet',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=-1,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
+        norm_eval=True,
+        style='caffe'),
+    neck=dict(
+        type='FPNF',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        fusion_type='concat'),
+    bbox_head=dict(
+        type='PSEHead',
+        in_channels=[256],
+        out_channels=7,
+        loss=dict(type='PSELoss'),
+        postprocessor=dict(type='PSEPostprocessor', text_repr_type='poly')),
+    train_cfg=None,
+    test_cfg=None)
+
+model_quad = dict(
+    type='PSENet',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=-1,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
+        norm_eval=True,
+        style='caffe'),
+    neck=dict(
+        type='FPNF',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        fusion_type='concat'),
+    bbox_head=dict(
+        type='PSEHead',
+        in_channels=[256],
+        out_channels=7,
+        loss=dict(type='PSELoss'),
+        postprocessor=dict(type='PSEPostprocessor', text_repr_type='quad')),
+    train_cfg=None,
+    test_cfg=None)

configs/_base_/det_models/textsnake_r50_fpn_unet.py

@@ -0,0 +1,22 @@
+model = dict(
+    type='TextSnake',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=-1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
+        norm_eval=True,
+        style='caffe'),
+    neck=dict(
+        type='FPN_UNet', in_channels=[256, 512, 1024, 2048], out_channels=32),
+    bbox_head=dict(
+        type='TextSnakeHead',
+        in_channels=32,
+        loss=dict(type='TextSnakeLoss'),
+        postprocessor=dict(
+            type='TextSnakePostprocessor', text_repr_type='poly')),
+    train_cfg=None,
+    test_cfg=None)

configs/_base_/det_pipelines/dbnet_pipeline.py

@@ -0,0 +1,88 @@
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+train_pipeline_r18 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='LoadTextAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(
+        type='ImgAug',
+        args=[['Fliplr', 0.5],
+              dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
+    dict(type='EastRandomCrop', target_size=(640, 640)),
+    dict(type='DBNetTargets', shrink_ratio=0.4),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='CustomFormatBundle',
+        keys=['gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'],
+        visualize=dict(flag=False, boundary_key='gt_shrink')),
+    dict(
+        type='Collect',
+        keys=['img', 'gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'])
+]
+
+test_pipeline_1333_736 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 736),
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(2944, 736), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+
+# for dbnet_r50dcnv2_fpnc
+img_norm_cfg_r50dcnv2 = dict(
+    mean=[122.67891434, 116.66876762, 104.00698793],
+    std=[58.395, 57.12, 57.375],
+    to_rgb=True)
+
+train_pipeline_r50dcnv2 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='LoadTextAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
+    dict(type='Normalize', **img_norm_cfg_r50dcnv2),
+    dict(
+        type='ImgAug',
+        args=[['Fliplr', 0.5],
+              dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
+    dict(type='EastRandomCrop', target_size=(640, 640)),
+    dict(type='DBNetTargets', shrink_ratio=0.4),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='CustomFormatBundle',
+        keys=['gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'],
+        visualize=dict(flag=False, boundary_key='gt_shrink')),
+    dict(
+        type='Collect',
+        keys=['img', 'gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'])
+]
+
+test_pipeline_4068_1024 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(4068, 1024),
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(2944, 736), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg_r50dcnv2),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]

configs/_base_/det_pipelines/drrg_pipeline.py

@@ -0,0 +1,60 @@
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='LoadTextAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='RandomScaling', size=800, scale=(0.75, 2.5)),
+    dict(
+        type='RandomCropFlip', crop_ratio=0.5, iter_num=1, min_area_ratio=0.2),
+    dict(
+        type='RandomCropPolyInstances',
+        instance_key='gt_masks',
+        crop_ratio=0.8,
+        min_side_ratio=0.3),
+    dict(
+        type='RandomRotatePolyInstances',
+        rotate_ratio=0.5,
+        max_angle=60,
+        pad_with_fixed_color=False),
+    dict(type='SquareResizePad', target_size=800, pad_ratio=0.6),
+    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
+    dict(type='DRRGTargets'),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='CustomFormatBundle',
+        keys=[
+            'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
+            'gt_top_height_map', 'gt_bot_height_map', 'gt_sin_map',
+            'gt_cos_map', 'gt_comp_attribs'
+        ],
+        visualize=dict(flag=False, boundary_key='gt_text_mask')),
+    dict(
+        type='Collect',
+        keys=[
+            'img', 'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
+            'gt_top_height_map', 'gt_bot_height_map', 'gt_sin_map',
+            'gt_cos_map', 'gt_comp_attribs'
+        ])
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1024, 640),
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(1024, 640), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]

configs/_base_/det_pipelines/fcenet_pipeline.py

@@ -0,0 +1,118 @@
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+# for icdar2015
+leval_prop_range_icdar2015 = ((0, 0.4), (0.3, 0.7), (0.6, 1.0))
+train_pipeline_icdar2015 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='LoadTextAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(
+        type='ColorJitter',
+        brightness=32.0 / 255,
+        saturation=0.5,
+        contrast=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='RandomScaling', size=800, scale=(3. / 4, 5. / 2)),
+    dict(
+        type='RandomCropFlip', crop_ratio=0.5, iter_num=1, min_area_ratio=0.2),
+    dict(
+        type='RandomCropPolyInstances',
+        instance_key='gt_masks',
+        crop_ratio=0.8,
+        min_side_ratio=0.3),
+    dict(
+        type='RandomRotatePolyInstances',
+        rotate_ratio=0.5,
+        max_angle=30,
+        pad_with_fixed_color=False),
+    dict(type='SquareResizePad', target_size=800, pad_ratio=0.6),
+    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='FCENetTargets',
+        fourier_degree=5,
+        level_proportion_range=leval_prop_range_icdar2015),
+    dict(
+        type='CustomFormatBundle',
+        keys=['p3_maps', 'p4_maps', 'p5_maps'],
+        visualize=dict(flag=False, boundary_key=None)),
+    dict(type='Collect', keys=['img', 'p3_maps', 'p4_maps', 'p5_maps'])
+]
+
+img_scale_icdar2015 = (2260, 2260)
+test_pipeline_icdar2015 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale_icdar2015,
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(1280, 800), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+
+# for ctw1500
+leval_prop_range_ctw1500 = ((0, 0.25), (0.2, 0.65), (0.55, 1.0))
+train_pipeline_ctw1500 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='LoadTextAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(
+        type='ColorJitter',
+        brightness=32.0 / 255,
+        saturation=0.5,
+        contrast=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='RandomScaling', size=800, scale=(3. / 4, 5. / 2)),
+    dict(
+        type='RandomCropFlip', crop_ratio=0.5, iter_num=1, min_area_ratio=0.2),
+    dict(
+        type='RandomCropPolyInstances',
+        instance_key='gt_masks',
+        crop_ratio=0.8,
+        min_side_ratio=0.3),
+    dict(
+        type='RandomRotatePolyInstances',
+        rotate_ratio=0.5,
+        max_angle=30,
+        pad_with_fixed_color=False),
+    dict(type='SquareResizePad', target_size=800, pad_ratio=0.6),
+    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='FCENetTargets',
+        fourier_degree=5,
+        level_proportion_range=leval_prop_range_ctw1500),
+    dict(
+        type='CustomFormatBundle',
+        keys=['p3_maps', 'p4_maps', 'p5_maps'],
+        visualize=dict(flag=False, boundary_key=None)),
+    dict(type='Collect', keys=['img', 'p3_maps', 'p4_maps', 'p5_maps'])
+]
+
+img_scale_ctw1500 = (1080, 736)
+test_pipeline_ctw1500 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale_ctw1500,
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(1280, 800), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]

configs/_base_/det_pipelines/maskrcnn_pipeline.py

@@ -0,0 +1,57 @@
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='ScaleAspectJitter',
+        img_scale=None,
+        keep_ratio=False,
+        resize_type='indep_sample_in_range',
+        scale_range=(640, 2560)),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(
+        type='RandomCropInstances',
+        target_size=(640, 640),
+        mask_type='union_all',
+        instance_key='gt_masks'),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+
+# for ctw1500
+img_scale_ctw1500 = (1600, 1600)
+test_pipeline_ctw1500 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale_ctw1500,
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+
+# for icdar2015
+img_scale_icdar2015 = (1920, 1920)
+test_pipeline_icdar2015 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale_icdar2015,
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]

configs/_base_/det_pipelines/panet_pipeline.py

@@ -0,0 +1,156 @@
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+# for ctw1500
+img_scale_train_ctw1500 = [(3000, 640)]
+shrink_ratio_train_ctw1500 = (1.0, 0.7)
+target_size_train_ctw1500 = (640, 640)
+train_pipeline_ctw1500 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='LoadTextAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(
+        type='ScaleAspectJitter',
+        img_scale=img_scale_train_ctw1500,
+        ratio_range=(0.7, 1.3),
+        aspect_ratio_range=(0.9, 1.1),
+        multiscale_mode='value',
+        keep_ratio=False),
+    # shrink_ratio is from big to small. The 1st must be 1.0
+    dict(type='PANetTargets', shrink_ratio=shrink_ratio_train_ctw1500),
+    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
+    dict(type='RandomRotateTextDet'),
+    dict(
+        type='RandomCropInstances',
+        target_size=target_size_train_ctw1500,
+        instance_key='gt_kernels'),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='CustomFormatBundle',
+        keys=['gt_kernels', 'gt_mask'],
+        visualize=dict(flag=False, boundary_key='gt_kernels')),
+    dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
+]
+
+img_scale_test_ctw1500 = (3000, 640)
+test_pipeline_ctw1500 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale_test_ctw1500,
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(3000, 640), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+
+# for icdar2015
+img_scale_train_icdar2015 = [(3000, 736)]
+shrink_ratio_train_icdar2015 = (1.0, 0.5)
+target_size_train_icdar2015 = (736, 736)
+train_pipeline_icdar2015 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='LoadTextAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(
+        type='ScaleAspectJitter',
+        img_scale=img_scale_train_icdar2015,
+        ratio_range=(0.7, 1.3),
+        aspect_ratio_range=(0.9, 1.1),
+        multiscale_mode='value',
+        keep_ratio=False),
+    dict(type='PANetTargets', shrink_ratio=shrink_ratio_train_icdar2015),
+    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
+    dict(type='RandomRotateTextDet'),
+    dict(
+        type='RandomCropInstances',
+        target_size=target_size_train_icdar2015,
+        instance_key='gt_kernels'),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='CustomFormatBundle',
+        keys=['gt_kernels', 'gt_mask'],
+        visualize=dict(flag=False, boundary_key='gt_kernels')),
+    dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
+]
+
+img_scale_test_icdar2015 = (1333, 736)
+test_pipeline_icdar2015 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale_test_icdar2015,
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(3000, 640), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+
+# for icdar2017
+img_scale_train_icdar2017 = [(3000, 800)]
+shrink_ratio_train_icdar2017 = (1.0, 0.5)
+target_size_train_icdar2017 = (800, 800)
+train_pipeline_icdar2017 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='LoadTextAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(
+        type='ScaleAspectJitter',
+        img_scale=img_scale_train_icdar2017,
+        ratio_range=(0.7, 1.3),
+        aspect_ratio_range=(0.9, 1.1),
+        multiscale_mode='value',
+        keep_ratio=False),
+    dict(type='PANetTargets', shrink_ratio=shrink_ratio_train_icdar2017),
+    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
+    dict(type='RandomRotateTextDet'),
+    dict(
+        type='RandomCropInstances',
+        target_size=target_size_train_icdar2017,
+        instance_key='gt_kernels'),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='CustomFormatBundle',
+        keys=['gt_kernels', 'gt_mask'],
+        visualize=dict(flag=False, boundary_key='gt_kernels')),
+    dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
+]
+
+img_scale_test_icdar2017 = (1333, 800)
+test_pipeline_icdar2017 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale_test_icdar2017,
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(3000, 640), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]

configs/_base_/det_pipelines/psenet_pipeline.py

@@ -0,0 +1,70 @@
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='LoadTextAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(
+        type='ScaleAspectJitter',
+        img_scale=[(3000, 736)],
+        ratio_range=(0.5, 3),
+        aspect_ratio_range=(1, 1),
+        multiscale_mode='value',
+        long_size_bound=1280,
+        short_size_bound=640,
+        resize_type='long_short_bound',
+        keep_ratio=False),
+    dict(type='PSENetTargets'),
+    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
+    dict(type='RandomRotateTextDet'),
+    dict(
+        type='RandomCropInstances',
+        target_size=(640, 640),
+        instance_key='gt_kernels'),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='CustomFormatBundle',
+        keys=['gt_kernels', 'gt_mask'],
+        visualize=dict(flag=False, boundary_key='gt_kernels')),
+    dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
+]
+
+# for ctw1500
+img_scale_test_ctw1500 = (1280, 1280)
+test_pipeline_ctw1500 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale_test_ctw1500,
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(1280, 1280), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+
+# for icdar2015
+img_scale_test_icdar2015 = (2240, 2240)
+test_pipeline_icdar2015 = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale_test_icdar2015,
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(1280, 1280), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]

configs/_base_/det_pipelines/textsnake_pipeline.py

@@ -0,0 +1,65 @@
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='LoadTextAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(
+        type='RandomCropPolyInstances',
+        instance_key='gt_masks',
+        crop_ratio=0.65,
+        min_side_ratio=0.3),
+    dict(
+        type='RandomRotatePolyInstances',
+        rotate_ratio=0.5,
+        max_angle=20,
+        pad_with_fixed_color=False),
+    dict(
+        type='ScaleAspectJitter',
+        img_scale=[(3000, 736)],  # unused
+        ratio_range=(0.7, 1.3),
+        aspect_ratio_range=(0.9, 1.1),
+        multiscale_mode='value',
+        long_size_bound=800,
+        short_size_bound=480,
+        resize_type='long_short_bound',
+        keep_ratio=False),
+    dict(type='SquareResizePad', target_size=800, pad_ratio=0.6),
+    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
+    dict(type='TextSnakeTargets'),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='CustomFormatBundle',
+        keys=[
+            'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
+            'gt_radius_map', 'gt_sin_map', 'gt_cos_map'
+        ],
+        visualize=dict(flag=False, boundary_key='gt_text_mask')),
+    dict(
+        type='Collect',
+        keys=[
+            'img', 'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
+            'gt_radius_map', 'gt_sin_map', 'gt_cos_map'
+        ])
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 736),
+        flip=False,
+        transforms=[
+            dict(type='Resize', img_scale=(1333, 736), keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]

configs/_base_/recog_datasets/MJ_train.py

@@ -0,0 +1,24 @@
+# Text Recognition Training set, including:
+# Synthetic Datasets: Syn90k
+
+train_root = 'data/mixture/Syn90k'
+
+train_img_prefix = f'{train_root}/mnt/ramdisk/max/90kDICT32px'
+train_ann_file = f'{train_root}/label.lmdb'
+
+train = dict(
+    type='OCRDataset',
+    img_prefix=train_img_prefix,
+    ann_file=train_ann_file,
+    loader=dict(
+        type='LmdbLoader',
+        repeat=1,
+        parser=dict(
+            type='LineStrParser',
+            keys=['filename', 'text'],
+            keys_idx=[0, 1],
+            separator=' ')),
+    pipeline=None,
+    test_mode=False)
+
+train_list = [train]

configs/_base_/recog_datasets/ST_MJ_alphanumeric_train.py

@@ -0,0 +1,34 @@
+# Text Recognition Training set, including:
+# Synthetic Datasets: SynthText, Syn90k
+# Both annotations are filtered so that
+# only alphanumeric terms are left
+
+train_root = 'data/mixture'
+
+train_img_prefix1 = f'{train_root}/Syn90k/mnt/ramdisk/max/90kDICT32px'
+train_ann_file1 = f'{train_root}/Syn90k/label.lmdb'
+
+train1 = dict(
+    type='OCRDataset',
+    img_prefix=train_img_prefix1,
+    ann_file=train_ann_file1,
+    loader=dict(
+        type='LmdbLoader',
+        repeat=1,
+        parser=dict(
+            type='LineStrParser',
+            keys=['filename', 'text'],
+            keys_idx=[0, 1],
+            separator=' ')),
+    pipeline=None,
+    test_mode=False)
+
+train_img_prefix2 = f'{train_root}/SynthText/' + \
+    'synthtext/SynthText_patch_horizontal'
+train_ann_file2 = f'{train_root}/SynthText/alphanumeric_label.lmdb'
+
+train2 = {key: value for key, value in train1.items()}
+train2['img_prefix'] = train_img_prefix2
+train2['ann_file'] = train_ann_file2
+
+train_list = [train1, train2]

configs/_base_/recog_datasets/ST_MJ_train.py

@@ -0,0 +1,32 @@
+# Text Recognition Training set, including:
+# Synthetic Datasets: SynthText, Syn90k
+
+train_root = 'data/mixture'
+
+train_img_prefix1 = f'{train_root}/Syn90k/mnt/ramdisk/max/90kDICT32px'
+train_ann_file1 = f'{train_root}/Syn90k/label.lmdb'
+
+train1 = dict(
+    type='OCRDataset',
+    img_prefix=train_img_prefix1,
+    ann_file=train_ann_file1,
+    loader=dict(
+        type='LmdbLoader',
+        repeat=1,
+        parser=dict(
+            type='LineStrParser',
+            keys=['filename', 'text'],
+            keys_idx=[0, 1],
+            separator=' ')),
+    pipeline=None,
+    test_mode=False)
+
+train_img_prefix2 = f'{train_root}/SynthText/' + \
+    'synthtext/SynthText_patch_horizontal'
+train_ann_file2 = f'{train_root}/SynthText/label.lmdb'
+
+train2 = {key: value for key, value in train1.items()}
+train2['img_prefix'] = train_img_prefix2
+train2['ann_file'] = train_ann_file2
+
+train_list = [train1, train2]

configs/_base_/recog_datasets/ST_SA_MJ_real_train.py

@@ -0,0 +1,79 @@
+# Text Recognition Training set, including:
+# Synthetic Datasets: SynthText, SynthAdd, Syn90k
+# Real Dataset: IC11, IC13, IC15, COCO-Test, IIIT5k
+
+train_prefix = 'data/mixture'
+
+train_img_prefix1 = f'{train_prefix}/icdar_2011'
+train_img_prefix2 = f'{train_prefix}/icdar_2013'
+train_img_prefix3 = f'{train_prefix}/icdar_2015'
+train_img_prefix4 = f'{train_prefix}/coco_text'
+train_img_prefix5 = f'{train_prefix}/IIIT5K'
+train_img_prefix6 = f'{train_prefix}/SynthText_Add'
+train_img_prefix7 = f'{train_prefix}/SynthText'
+train_img_prefix8 = f'{train_prefix}/Syn90k'
+
+train_ann_file1 = f'{train_prefix}/icdar_2011/train_label.txt',
+train_ann_file2 = f'{train_prefix}/icdar_2013/train_label.txt',
+train_ann_file3 = f'{train_prefix}/icdar_2015/train_label.txt',
+train_ann_file4 = f'{train_prefix}/coco_text/train_label.txt',
+train_ann_file5 = f'{train_prefix}/IIIT5K/train_label.txt',
+train_ann_file6 = f'{train_prefix}/SynthText_Add/label.txt',
+train_ann_file7 = f'{train_prefix}/SynthText/shuffle_labels.txt',
+train_ann_file8 = f'{train_prefix}/Syn90k/shuffle_labels.txt'
+
+train1 = dict(
+    type='OCRDataset',
+    img_prefix=train_img_prefix1,
+    ann_file=train_ann_file1,
+    loader=dict(
+        type='HardDiskLoader',
+        repeat=20,
+        parser=dict(
+            type='LineStrParser',
+            keys=['filename', 'text'],
+            keys_idx=[0, 1],
+            separator=' ')),
+    pipeline=None,
+    test_mode=False)
+
+train2 = {key: value for key, value in train1.items()}
+train2['img_prefix'] = train_img_prefix2
+train2['ann_file'] = train_ann_file2
+
+train3 = {key: value for key, value in train1.items()}
+train3['img_prefix'] = train_img_prefix3
+train3['ann_file'] = train_ann_file3
+
+train4 = {key: value for key, value in train1.items()}
+train4['img_prefix'] = train_img_prefix4
+train4['ann_file'] = train_ann_file4
+
+train5 = {key: value for key, value in train1.items()}
+train5['img_prefix'] = train_img_prefix5
+train5['ann_file'] = train_ann_file5
+
+train6 = dict(
+    type='OCRDataset',
+    img_prefix=train_img_prefix6,
+    ann_file=train_ann_file6,
+    loader=dict(
+        type='HardDiskLoader',
+        repeat=1,
+        parser=dict(
+            type='LineStrParser',
+            keys=['filename', 'text'],
+            keys_idx=[0, 1],
+            separator=' ')),
+    pipeline=None,
+    test_mode=False)
+
+train7 = {key: value for key, value in train6.items()}
+train7['img_prefix'] = train_img_prefix7
+train7['ann_file'] = train_ann_file7
+
+train8 = {key: value for key, value in train6.items()}
+train8['img_prefix'] = train_img_prefix8
+train8['ann_file'] = train_ann_file8
+
+train_list = [train1, train2, train3, train4, train5, train6, train7, train8]

configs/_base_/recog_datasets/ST_charbox_train.py

@@ -0,0 +1,22 @@
+# Text Recognition Training set, including:
+# Synthetic Datasets: SynthText (with character level boxes)
+
+train_img_root = 'data/mixture'
+
+train_img_prefix = f'{train_img_root}/SynthText'
+
+train_ann_file = f'{train_img_root}/SynthText/instances_train.txt'
+
+train = dict(
+    type='OCRSegDataset',
+    img_prefix=train_img_prefix,
+    ann_file=train_ann_file,
+    loader=dict(
+        type='HardDiskLoader',
+        repeat=1,
+        parser=dict(
+            type='LineJsonParser', keys=['file_name', 'annotations', 'text'])),
+    pipeline=None,
+    test_mode=False)
+
+train_list = [train]

configs/_base_/recog_datasets/academic_test.py

@@ -0,0 +1,56 @@
+# Text Recognition Testing set, including:
+# Regular Datasets: IIIT5K, SVT, IC13
+# Irregular Datasets: IC15, SVTP, CT80
+
+test_root = 'data/mixture'
+
+test_img_prefix1 = f'{test_root}/IIIT5K/'
+test_img_prefix2 = f'{test_root}/svt/'
+test_img_prefix3 = f'{test_root}/icdar_2013/'
+test_img_prefix4 = f'{test_root}/icdar_2015/'
+test_img_prefix5 = f'{test_root}/svtp/'
+test_img_prefix6 = f'{test_root}/ct80/'
+
+test_ann_file1 = f'{test_root}/IIIT5K/test_label.txt'
+test_ann_file2 = f'{test_root}/svt/test_label.txt'
+test_ann_file3 = f'{test_root}/icdar_2013/test_label_1015.txt'
+test_ann_file4 = f'{test_root}/icdar_2015/test_label.txt'
+test_ann_file5 = f'{test_root}/svtp/test_label.txt'
+test_ann_file6 = f'{test_root}/ct80/test_label.txt'
+
+test1 = dict(
+    type='OCRDataset',
+    img_prefix=test_img_prefix1,
+    ann_file=test_ann_file1,
+    loader=dict(
+        type='HardDiskLoader',
+        repeat=1,
+        parser=dict(
+            type='LineStrParser',
+            keys=['filename', 'text'],
+            keys_idx=[0, 1],
+            separator=' ')),
+    pipeline=None,
+    test_mode=True)
+
+test2 = {key: value for key, value in test1.items()}
+test2['img_prefix'] = test_img_prefix2
+test2['ann_file'] = test_ann_file2
+
+test3 = {key: value for key, value in test1.items()}
+test3['img_prefix'] = test_img_prefix3
+test3['ann_file'] = test_ann_file3
+
+test4 = {key: value for key, value in test1.items()}
+test4['img_prefix'] = test_img_prefix4
+test4['ann_file'] = test_ann_file4
+
+test5 = {key: value for key, value in test1.items()}
+test5['img_prefix'] = test_img_prefix5
+test5['ann_file'] = test_ann_file5
+
+test6 = {key: value for key, value in test1.items()}
+test6['img_prefix'] = test_img_prefix6
+test6['ann_file'] = test_ann_file6
+
+test_list = [test1, test2, test3, test4, test5, test6]

configs/_base_/recog_datasets/seg_toy_data.py

@@ -0,0 +1,32 @@
+prefix = 'tests/data/ocr_char_ann_toy_dataset/'
+
+train = dict(
+    type='OCRSegDataset',
+    img_prefix=f'{prefix}/imgs',
+    ann_file=f'{prefix}/instances_train.txt',
+    loader=dict(
+        type='HardDiskLoader',
+        repeat=100,
+        parser=dict(
+            type='LineJsonParser', keys=['file_name', 'annotations', 'text'])),
+    pipeline=None,
+    test_mode=True)
+
+test = dict(
+    type='OCRDataset',
+    img_prefix=f'{prefix}/imgs',
+    ann_file=f'{prefix}/instances_test.txt',
+    loader=dict(
+        type='HardDiskLoader',
+        repeat=1,
+        parser=dict(
+            type='LineStrParser',
+            keys=['filename', 'text'],
+            keys_idx=[0, 1],
+            separator=' ')),
+    pipeline=None,
+    test_mode=True)
+
+train_list = [train]
+
+test_list = [test]

configs/_base_/recog_datasets/toy_data.py

@@ -0,0 +1,56 @@
+dataset_type = 'OCRDataset'
+
+root = 'tests/data/ocr_toy_dataset'
+img_prefix = f'{root}/imgs'
+train_anno_file1 = f'{root}/label.txt'
+
+train1 = dict(
+    type=dataset_type,
+    img_prefix=img_prefix,
+    ann_file=train_anno_file1,
+    loader=dict(
+        type='HardDiskLoader',
+        repeat=100,
+        parser=dict(
+            type='LineStrParser',
+            keys=['filename', 'text'],
+            keys_idx=[0, 1],
+            separator=' ')),
+    pipeline=None,
+    test_mode=False)
+
+train_anno_file2 = f'{root}/label.lmdb'
+train2 = dict(
+    type=dataset_type,
+    img_prefix=img_prefix,
+    ann_file=train_anno_file2,
+    loader=dict(
+        type='LmdbLoader',
+        repeat=100,
+        parser=dict(
+            type='LineStrParser',
+            keys=['filename', 'text'],
+            keys_idx=[0, 1],
+            separator=' ')),
+    pipeline=None,
+    test_mode=False)
+
+test_anno_file1 = f'{root}/label.lmdb'
+test = dict(
+    type=dataset_type,
+    img_prefix=img_prefix,
+    ann_file=test_anno_file1,
+    loader=dict(
+        type='LmdbLoader',
+        repeat=1,
+        parser=dict(
+            type='LineStrParser',
+            keys=['filename', 'text'],
+            keys_idx=[0, 1],
+            separator=' ')),
+    pipeline=None,
+    test_mode=True)
+
+train_list = [train1, train2]
+
+test_list = [test]

configs/_base_/recog_models/abinet.py

@@ -0,0 +1,70 @@
+# num_chars depends on the configuration of label_convertor. The actual
+# dictionary size is 36 + 1 (<BOS/EOS>).
+# TODO: Automatically update num_chars based on the configuration of
+# label_convertor
+num_chars = 37
+max_seq_len = 26
+
+label_convertor = dict(
+    type='ABIConvertor',
+    dict_type='DICT36',
+    with_unknown=False,
+    with_padding=False,
+    lower=True,
+)
+
+model = dict(
+    type='ABINet',
+    backbone=dict(type='ResNetABI'),
+    encoder=dict(
+        type='ABIVisionModel',
+        encoder=dict(
+            type='TransformerEncoder',
+            n_layers=3,
+            n_head=8,
+            d_model=512,
+            d_inner=2048,
+            dropout=0.1,
+            max_len=8 * 32,
+        ),
+        decoder=dict(
+            type='ABIVisionDecoder',
+            in_channels=512,
+            num_channels=64,
+            attn_height=8,
+            attn_width=32,
+            attn_mode='nearest',
+            use_result='feature',
+            num_chars=num_chars,
+            max_seq_len=max_seq_len,
+            init_cfg=dict(type='Xavier', layer='Conv2d')),
+    ),
+    decoder=dict(
+        type='ABILanguageDecoder',
+        d_model=512,
+        n_head=8,
+        d_inner=2048,
+        n_layers=4,
+        dropout=0.1,
+        detach_tokens=True,
+        use_self_attn=False,
+        pad_idx=num_chars - 1,
+        num_chars=num_chars,
+        max_seq_len=max_seq_len,
+        init_cfg=None),
+    fuser=dict(
+        type='ABIFuser',
+        d_model=512,
+        num_chars=num_chars,
+        init_cfg=None,
+        max_seq_len=max_seq_len,
+    ),
+    loss=dict(
+        type='ABILoss',
+        enc_weight=1.0,
+        dec_weight=1.0,
+        fusion_weight=1.0,
+        num_classes=num_chars),
+    label_convertor=label_convertor,
+    max_seq_len=max_seq_len,
+    iter_size=3)

configs/_base_/recog_models/crnn.py

@@ -0,0 +1,12 @@
+label_convertor = dict(
+    type='CTCConvertor', dict_type='DICT36', with_unknown=False, lower=True)
+
+model = dict(
+    type='CRNNNet',
+    preprocessor=None,
+    backbone=dict(type='VeryDeepVgg', leaky_relu=False, input_channels=1),
+    encoder=None,
+    decoder=dict(type='CRNNDecoder', in_channels=512, rnn_flag=True),
+    loss=dict(type='CTCLoss'),
+    label_convertor=label_convertor,
+    pretrained=None)

configs/_base_/recog_models/crnn_tps.py

@@ -0,0 +1,18 @@
+# model
+label_convertor = dict(
+    type='CTCConvertor', dict_type='DICT36', with_unknown=False, lower=True)
+
+model = dict(
+    type='CRNNNet',
+    preprocessor=dict(
+        type='TPSPreprocessor',
+        num_fiducial=20,
+        img_size=(32, 100),
+        rectified_img_size=(32, 100),
+        num_img_channel=1),
+    backbone=dict(type='VeryDeepVgg', leaky_relu=False, input_channels=1),
+    encoder=None,
+    decoder=dict(type='CRNNDecoder', in_channels=512, rnn_flag=True),
+    loss=dict(type='CTCLoss'),
+    label_convertor=label_convertor,
+    pretrained=None)

configs/_base_/recog_models/nrtr_modality_transform.py

@@ -0,0 +1,11 @@
+label_convertor = dict(
+    type='AttnConvertor', dict_type='DICT36', with_unknown=True, lower=True)
+
+model = dict(
+    type='NRTR',
+    backbone=dict(type='NRTRModalityTransform'),
+    encoder=dict(type='NRTREncoder', n_layers=12),
+    decoder=dict(type='NRTRDecoder'),
+    loss=dict(type='TFLoss'),
+    label_convertor=label_convertor,
+    max_seq_len=40)

configs/_base_/recog_models/robust_scanner.py

@@ -0,0 +1,24 @@
+label_convertor = dict(
+    type='AttnConvertor', dict_type='DICT90', with_unknown=True)
+
+hybrid_decoder = dict(type='SequenceAttentionDecoder')
+
+position_decoder = dict(type='PositionAttentionDecoder')
+
+model = dict(
+    type='RobustScanner',
+    backbone=dict(type='ResNet31OCR'),
+    encoder=dict(
+        type='ChannelReductionEncoder',
+        in_channels=512,
+        out_channels=128,
+    ),
+    decoder=dict(
+        type='RobustScannerDecoder',
+        dim_input=512,
+        dim_model=128,
+        hybrid_decoder=hybrid_decoder,
+        position_decoder=position_decoder),
+    loss=dict(type='SARLoss'),
+    label_convertor=label_convertor,
+    max_seq_len=30)

configs/_base_/recog_models/sar.py

@@ -0,0 +1,24 @@
+label_convertor = dict(
+    type='AttnConvertor', dict_type='DICT90', with_unknown=True)
+
+model = dict(
+    type='SARNet',
+    backbone=dict(type='ResNet31OCR'),
+    encoder=dict(
+        type='SAREncoder',
+        enc_bi_rnn=False,
+        enc_do_rnn=0.1,
+        enc_gru=False,
+    ),
+    decoder=dict(
+        type='ParallelSARDecoder',
+        enc_bi_rnn=False,
+        dec_bi_rnn=False,
+        dec_do_rnn=0,
+        dec_gru=False,
+        pred_dropout=0.1,
+        d_k=512,
+        pred_concat=True),
+    loss=dict(type='SARLoss'),
+    label_convertor=label_convertor,
+    max_seq_len=30)

configs/_base_/recog_models/satrn.py

@@ -0,0 +1,11 @@
+label_convertor = dict(
+    type='AttnConvertor', dict_type='DICT36', with_unknown=True, lower=True)
+
+model = dict(
+    type='SATRN',
+    backbone=dict(type='ShallowCNN'),
+    encoder=dict(type='SatrnEncoder'),
+    decoder=dict(type='TFDecoder'),
+    loss=dict(type='TFLoss'),
+    label_convertor=label_convertor,
+    max_seq_len=40)

configs/_base_/recog_models/seg.py

@@ -0,0 +1,21 @@
+label_convertor = dict(
+    type='SegConvertor', dict_type='DICT36', with_unknown=True, lower=True)
+
+model = dict(
+    type='SegRecognizer',
+    backbone=dict(
+        type='ResNet31OCR',
+        layers=[1, 2, 5, 3],
+        channels=[32, 64, 128, 256, 512, 512],
+        out_indices=[0, 1, 2, 3],
+        stage4_pool_cfg=dict(kernel_size=2, stride=2),
+        last_stage_pool=True),
+    neck=dict(
+        type='FPNOCR', in_channels=[128, 256, 512, 512], out_channels=256),
+    head=dict(
+        type='SegHead',
+        in_channels=256,
+        upsample_param=dict(scale_factor=2.0, mode='nearest')),
+    loss=dict(
+        type='SegLoss', seg_downsample_ratio=1.0, seg_with_loss_weight=True),
+    label_convertor=label_convertor)

configs/_base_/recog_pipelines/abinet_pipeline.py

@@ -0,0 +1,96 @@
+img_norm_cfg = dict(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeOCR',
+        height=32,
+        min_width=128,
+        max_width=128,
+        keep_aspect_ratio=False,
+        width_downsample_ratio=0.25),
+    dict(
+        type='RandomWrapper',
+        p=0.5,
+        transforms=[
+            dict(
+                type='OneOfWrapper',
+                transforms=[
+                    dict(
+                        type='RandomRotateTextDet',
+                        max_angle=15,
+                    ),
+                    dict(
+                        type='TorchVisionWrapper',
+                        op='RandomAffine',
+                        degrees=15,
+                        translate=(0.3, 0.3),
+                        scale=(0.5, 2.),
+                        shear=(-45, 45),
+                    ),
+                    dict(
+                        type='TorchVisionWrapper',
+                        op='RandomPerspective',
+                        distortion_scale=0.5,
+                        p=1,
+                    ),
+                ])
+        ],
+    ),
+    dict(
+        type='RandomWrapper',
+        p=0.25,
+        transforms=[
+            dict(type='PyramidRescale'),
+            dict(
+                type='Albu',
+                transforms=[
+                    dict(type='GaussNoise', var_limit=(20, 20), p=0.5),
+                    dict(type='MotionBlur', blur_limit=6, p=0.5),
+                ]),
+        ]),
+    dict(
+        type='RandomWrapper',
+        p=0.25,
+        transforms=[
+            dict(
+                type='TorchVisionWrapper',
+                op='ColorJitter',
+                brightness=0.5,
+                saturation=0.5,
+                contrast=0.5,
+                hue=0.1),
+        ]),
+    dict(type='ToTensorOCR'),
+    dict(type='NormalizeOCR', **img_norm_cfg),
+    dict(
+        type='Collect',
+        keys=['img'],
+        meta_keys=[
+            'filename', 'ori_shape', 'img_shape', 'text', 'valid_ratio',
+            'resize_shape'
+        ]),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiRotateAugOCR',
+        rotate_degrees=[0, 90, 270],
+        transforms=[
+            dict(
+                type='ResizeOCR',
+                height=32,
+                min_width=128,
+                max_width=128,
+                keep_aspect_ratio=False,
+                width_downsample_ratio=0.25),
+            dict(type='ToTensorOCR'),
+            dict(type='NormalizeOCR', **img_norm_cfg),
+            dict(
+                type='Collect',
+                keys=['img'],
+                meta_keys=[
+                    'filename', 'ori_shape', 'img_shape', 'valid_ratio',
+                    'resize_shape', 'img_norm_cfg', 'ori_filename'
+                ]),
+        ])
+]

configs/_base_/recog_pipelines/crnn_pipeline.py

@@ -0,0 +1,35 @@
+img_norm_cfg = dict(mean=[127], std=[127])
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', color_type='grayscale'),
+    dict(
+        type='ResizeOCR',
+        height=32,
+        min_width=100,
+        max_width=100,
+        keep_aspect_ratio=False),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='DefaultFormatBundle'),
+    dict(
+        type='Collect',
+        keys=['img'],
+        meta_keys=['filename', 'resize_shape', 'text', 'valid_ratio']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', color_type='grayscale'),
+    dict(
+        type='ResizeOCR',
+        height=32,
+        min_width=32,
+        max_width=None,
+        keep_aspect_ratio=True),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='DefaultFormatBundle'),
+    dict(
+        type='Collect',
+        keys=['img'],
+        meta_keys=[
+            'filename', 'resize_shape', 'valid_ratio', 'img_norm_cfg',
+            'ori_filename', 'img_shape', 'ori_shape'
+        ]),
+]

configs/_base_/recog_pipelines/crnn_tps_pipeline.py

@@ -0,0 +1,37 @@
+img_norm_cfg = dict(mean=[0.5], std=[0.5])
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', color_type='grayscale'),
+    dict(
+        type='ResizeOCR',
+        height=32,
+        min_width=100,
+        max_width=100,
+        keep_aspect_ratio=False),
+    dict(type='ToTensorOCR'),
+    dict(type='NormalizeOCR', **img_norm_cfg),
+    dict(
+        type='Collect',
+        keys=['img'],
+        meta_keys=[
+            'filename', 'ori_shape', 'resize_shape', 'text', 'valid_ratio'
+        ]),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', color_type='grayscale'),
+    dict(
+        type='ResizeOCR',
+        height=32,
+        min_width=32,
+        max_width=100,
+        keep_aspect_ratio=False),
+    dict(type='ToTensorOCR'),
+    dict(type='NormalizeOCR', **img_norm_cfg),
+    dict(
+        type='Collect',
+        keys=['img'],
+        meta_keys=[
+            'filename', 'ori_shape', 'resize_shape', 'valid_ratio',
+            'img_norm_cfg', 'ori_filename', 'img_shape'
+        ]),
+]

configs/_base_/recog_pipelines/nrtr_pipeline.py

@@ -0,0 +1,38 @@
+img_norm_cfg = dict(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeOCR',
+        height=32,
+        min_width=32,
+        max_width=160,
+        keep_aspect_ratio=True,
+        width_downsample_ratio=0.25),
+    dict(type='ToTensorOCR'),
+    dict(type='NormalizeOCR', **img_norm_cfg),
+    dict(
+        type='Collect',
+        keys=['img'],
+        meta_keys=[
+            'filename', 'ori_shape', 'resize_shape', 'text', 'valid_ratio'
+        ]),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeOCR',
+        height=32,
+        min_width=32,
+        max_width=160,
+        keep_aspect_ratio=True),
+    dict(type='ToTensorOCR'),
+    dict(type='NormalizeOCR', **img_norm_cfg),
+    dict(
+        type='Collect',
+        keys=['img'],
+        meta_keys=[
+            'filename', 'ori_shape', 'resize_shape', 'valid_ratio',
+            'img_norm_cfg', 'ori_filename', 'img_shape'
+        ])
+]

configs/_base_/recog_pipelines/sar_pipeline.py

@@ -0,0 +1,43 @@
+img_norm_cfg = dict(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeOCR',
+        height=48,
+        min_width=48,
+        max_width=160,
+        keep_aspect_ratio=True,
+        width_downsample_ratio=0.25),
+    dict(type='ToTensorOCR'),
+    dict(type='NormalizeOCR', **img_norm_cfg),
+    dict(
+        type='Collect',
+        keys=['img'],
+        meta_keys=[
+            'filename', 'ori_shape', 'resize_shape', 'text', 'valid_ratio'
+        ]),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiRotateAugOCR',
+        rotate_degrees=[0, 90, 270],
+        transforms=[
+            dict(
+                type='ResizeOCR',
+                height=48,
+                min_width=48,
+                max_width=160,
+                keep_aspect_ratio=True,
+                width_downsample_ratio=0.25),
+            dict(type='ToTensorOCR'),
+            dict(type='NormalizeOCR', **img_norm_cfg),
+            dict(
+                type='Collect',
+                keys=['img'],
+                meta_keys=[
+                    'filename', 'ori_shape', 'resize_shape', 'valid_ratio',
+                    'img_norm_cfg', 'ori_filename', 'img_shape'
+                ]),
+        ])
+]

configs/_base_/recog_pipelines/satrn_pipeline.py

@@ -0,0 +1,44 @@
+img_norm_cfg = dict(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeOCR',
+        height=32,
+        min_width=100,
+        max_width=100,
+        keep_aspect_ratio=False,
+        width_downsample_ratio=0.25),
+    dict(type='ToTensorOCR'),
+    dict(type='NormalizeOCR', **img_norm_cfg),
+    dict(
+        type='Collect',
+        keys=['img'],
+        meta_keys=[
+            'filename', 'ori_shape', 'img_shape', 'text', 'valid_ratio',
+            'resize_shape'
+        ]),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiRotateAugOCR',
+        rotate_degrees=[0, 90, 270],
+        transforms=[
+            dict(
+                type='ResizeOCR',
+                height=32,
+                min_width=100,
+                max_width=100,
+                keep_aspect_ratio=False,
+                width_downsample_ratio=0.25),
+            dict(type='ToTensorOCR'),
+            dict(type='NormalizeOCR', **img_norm_cfg),
+            dict(
+                type='Collect',
+                keys=['img'],
+                meta_keys=[
+                    'filename', 'ori_shape', 'img_shape', 'valid_ratio',
+                    'resize_shape', 'img_norm_cfg', 'ori_filename'
+                ]),
+        ])
+]