From 1a379f2f1b9c89b4c927b70081a170579df47559 Mon Sep 17 00:00:00 2001
From: Tong Gao <gaotongxiao@gmail.com>
Date: Wed, 22 Mar 2023 14:00:55 +0800
Subject: [PATCH] [Fix] Clear up some unused scripts (#1798)
---
docs/en/user_guides/data_prepare/det.md | 59 ---
docs/en/user_guides/data_prepare/recog.md | 39 --
docs/zh_cn/user_guides/data_prepare/det.md | 147 -------
docs/zh_cn/user_guides/data_prepare/recog.md | 314 --------------
.../textdet/ctw1500_converter.py | 233 ----------
.../textdet/ic13_converter.py | 167 -------
.../textdet/icdar_converter.py | 185 --------
.../textdet/synthtext_converter.py | 181 --------
.../textdet/textocr_converter.py | 76 ----
.../textdet/totaltext_converter.py | 410 ------------------
.../textrecog/ic13_converter.py | 67 ---
.../textrecog/svt_converter.py | 88 ----
.../textrecog/synthtext_converter.py | 146 -------
.../textrecog/textocr_converter.py | 113 -----
.../textrecog/totaltext_converter.py | 388 -----------------
15 files changed, 2613 deletions(-)
delete mode 100644 docs/zh_cn/user_guides/data_prepare/det.md
delete mode 100644 docs/zh_cn/user_guides/data_prepare/recog.md
delete mode 100644 tools/dataset_converters/textdet/ctw1500_converter.py
delete mode 100644 tools/dataset_converters/textdet/ic13_converter.py
delete mode 100644 tools/dataset_converters/textdet/icdar_converter.py
delete mode 100644 tools/dataset_converters/textdet/synthtext_converter.py
delete mode 100644 tools/dataset_converters/textdet/textocr_converter.py
delete mode 100644 tools/dataset_converters/textdet/totaltext_converter.py
delete mode 100644 tools/dataset_converters/textrecog/ic13_converter.py
delete mode 100644 tools/dataset_converters/textrecog/svt_converter.py
delete mode 100644 tools/dataset_converters/textrecog/synthtext_converter.py
delete mode 100644 tools/dataset_converters/textrecog/textocr_converter.py
delete mode 100644 tools/dataset_converters/textrecog/totaltext_converter.py
diff --git a/docs/en/user_guides/data_prepare/det.md b/docs/en/user_guides/data_prepare/det.md
index fcf87073..82212150 100644
--- a/docs/en/user_guides/data_prepare/det.md
+++ b/docs/en/user_guides/data_prepare/det.md
@@ -9,10 +9,8 @@ This page is a manual preparation guide for datasets not yet supported by [Datas
| Dataset | Images | | Annotation Files | | |
| :---------------: | :------------------------------------------------------: | :------------------------------------------------: | :-----------------------------------------------------------------: | :-----: | :-: |
| | | training | validation | testing | |
-| CTW1500 | [homepage](https://github.com/Yuliang-Liu/Curve-Text-Detector) | - | - | - | |
| ICDAR2011 | [homepage](https://rrc.cvc.uab.es/?ch=1) | - | - | | |
| ICDAR2017 | [homepage](https://rrc.cvc.uab.es/?ch=8&com=downloads) | [instances_training.json](https://download.openmmlab.com/mmocr/data/icdar2017/instances_training.json) | [instances_val.json](https://download.openmmlab.com/mmocr/data/icdar2017/instances_val.json) | - | |
-| Synthtext | [homepage](https://www.robots.ox.ac.uk/~vgg/data/scenetext/) | instances_training.lmdb ([data.mdb](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.lmdb/data.mdb), [lock.mdb](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.lmdb/lock.mdb)) | - | - | |
| CurvedSynText150k | [homepage](https://github.com/aim-uofa/AdelaiDet/blob/master/datasets/README.md) \| [Part1](https://drive.google.com/file/d/1OSJ-zId2h3t_-I7g_wUkrK-VqQy153Kj/view?usp=sharing) \| [Part2](https://drive.google.com/file/d/1EzkcOlIgEp5wmEubvHb7-J5EImHExYgY/view?usp=sharing) | [instances_training.json](https://download.openmmlab.com/mmocr/data/curvedsyntext/instances_training.json) | - | - | |
| DeText | [homepage](https://rrc.cvc.uab.es/?ch=9) | - | - | - | |
| Lecture Video DB | [homepage](https://cvit.iiit.ac.in/research/projects/cvit-projects/lecturevideodb) | - | - | - | |
@@ -62,47 +60,6 @@ backend used in MMCV would read them and apply the rotation on the images. Howe
inconsistency results in false examples in the training set. Therefore, users should use `dict(type='LoadImageFromFile', color_type='color_ignore_orientation')` in pipelines to change MMCV's default loading behaviour. (see [DBNet's pipeline config](https://github.com/open-mmlab/mmocr/blob/main/configs/_base_/det_pipelines/dbnet_pipeline.py) for example)
```
-## CTW1500
-
-- Step0: Read [Important Note](#important-note)
-
-- Step1: Download `train_images.zip`, `test_images.zip`, `train_labels.zip`, `test_labels.zip` from [github](https://github.com/Yuliang-Liu/Curve-Text-Detector)
-
- ```bash
- mkdir ctw1500 && cd ctw1500
- mkdir imgs && mkdir annotations
-
- # For annotations
- cd annotations
- wget -O train_labels.zip https://universityofadelaide.box.com/shared/static/jikuazluzyj4lq6umzei7m2ppmt3afyw.zip
- wget -O test_labels.zip https://cloudstor.aarnet.edu.au/plus/s/uoeFl0pCN9BOCN5/download
- unzip train_labels.zip && mv ctw1500_train_labels training
- unzip test_labels.zip -d test
- cd ..
- # For images
- cd imgs
- wget -O train_images.zip https://universityofadelaide.box.com/shared/static/py5uwlfyyytbb2pxzq9czvu6fuqbjdh8.zip
- wget -O test_images.zip https://universityofadelaide.box.com/shared/static/t4w48ofnqkdw7jyc4t11nsukoeqk9c3d.zip
- unzip train_images.zip && mv train_images training
- unzip test_images.zip && mv test_images test
- ```
-
-- Step2: Generate `instances_training.json` and `instances_test.json` with following command:
-
- ```bash
- python tools/dataset_converters/textdet/ctw1500_converter.py /path/to/ctw1500 -o /path/to/ctw1500 --split-list training test
- ```
-
-- The resulting directory structure looks like the following:
-
- ```text
- ├── ctw1500
- │ ├── imgs
- │ ├── annotations
- │ ├── instances_training.json
- │ └── instances_val.json
- ```
-
## ICDAR 2011 (Born-Digital Images)
- Step1: Download `Challenge1_Training_Task12_Images.zip`, `Challenge1_Training_Task1_GT.zip`, `Challenge1_Test_Task12_Images.zip`, and `Challenge1_Test_Task1_GT.zip` from [homepage](https://rrc.cvc.uab.es/?ch=1&com=downloads) `Task 1.1: Text Localization (2013 edition)`.
@@ -156,22 +113,6 @@ inconsistency results in false examples in the training set. Therefore, users sh
│ └── instances_val.json
```
-## SynthText
-
-- Step1: Download SynthText.zip from \[homepage\](<https://www.robots.ox.ac.uk/~vgg/data/scenetext/> and extract its content to `synthtext/img`.
-
-- Step2: Download [data.mdb](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.lmdb/data.mdb) and [lock.mdb](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.lmdb/lock.mdb) to `synthtext/instances_training.lmdb/`.
-
-- The resulting directory structure looks like the following:
-
- ```text
- ├── synthtext
- │ ├── imgs
- │ └── instances_training.lmdb
- │ ├── data.mdb
- │ └── lock.mdb
- ```
-
## CurvedSynText150k
- Step1: Download [syntext1.zip](https://drive.google.com/file/d/1OSJ-zId2h3t_-I7g_wUkrK-VqQy153Kj/view?usp=sharing) and [syntext2.zip](https://drive.google.com/file/d/1EzkcOlIgEp5wmEubvHb7-J5EImHExYgY/view?usp=sharing) to `CurvedSynText150k/`.
diff --git a/docs/en/user_guides/data_prepare/recog.md b/docs/en/user_guides/data_prepare/recog.md
index 47a3dd04..e4a02158 100644
--- a/docs/en/user_guides/data_prepare/recog.md
+++ b/docs/en/user_guides/data_prepare/recog.md
@@ -11,7 +11,6 @@ This page is a manual preparation guide for datasets not yet supported by [Datas
| | | training | test |
| coco_text | [homepage](https://rrc.cvc.uab.es/?ch=5&com=downloads) | [train_labels.json](#TODO) | - |
| ICDAR2011 | [homepage](https://rrc.cvc.uab.es/?ch=1) | - | - |
-| MJSynth (Syn90k) | [homepage](https://www.robots.ox.ac.uk/~vgg/data/text/) | [subset_train_labels.json](https://download.openmmlab.com/mmocr/data/1.x/recog/Syn90k/subset_train_labels.json) \| [train_labels.json](https://download.openmmlab.com/mmocr/data/1.x/recog/Syn90k/train_labels.json) | - |
| SynthAdd | [SynthText_Add.zip](https://pan.baidu.com/s/1uV0LtoNmcxbO-0YA7Ch4dg) (code:627x) | [train_labels.json](https://download.openmmlab.com/mmocr/data/1.x/recog/synthtext_add/train_labels.json) | - |
| OpenVINO | [Open Images](https://github.com/cvdfoundation/open-images-dataset) | [annotations](https://storage.openvinotoolkit.org/repositories/openvino_training_extensions/datasets/open_images_v5_text) | [annotations](https://storage.openvinotoolkit.org/repositories/openvino_training_extensions/datasets/open_images_v5_text) |
| DeText | [homepage](https://rrc.cvc.uab.es/?ch=9) | - | - |
@@ -110,44 +109,6 @@ For users in China, these datasets can also be downloaded from [OpenDataLab](htt
│ └── train_words
```
-## MJSynth (Syn90k)
-
-- Step1: Download `mjsynth.tar.gz` from [homepage](https://www.robots.ox.ac.uk/~vgg/data/text/)
-- Step2: Download [train_labels.json](https://download.openmmlab.com/mmocr/data/1.x/recog/Syn90k/train_labels.json) (8,919,273 annotations) and [subset_train_labels.json](https://download.openmmlab.com/mmocr/data/1.x/recog/Syn90k/subset_train_labels.json) (2,400,000 randomly sampled annotations).
-
-```{note}
-Please make sure you're using the right annotation to train the model by checking its dataset specs in Model Zoo.
-```
-
-- Step3:
-
- ```bash
- mkdir Syn90k && cd Syn90k
-
- mv /path/to/mjsynth.tar.gz .
-
- tar -xzf mjsynth.tar.gz
-
- mv /path/to/subset_train_labels.json .
- mv /path/to/train_labels.json .
-
- # create soft link
- cd /path/to/mmocr/data/recog/
-
- ln -s /path/to/Syn90k Syn90k
-
- ```
-
-- After running the above codes, the directory structure
- should be as follows:
-
- ```text
- ├── Syn90k
- │ ├── subset_train_labels.json
- │ ├── train_labels.json
- │ └── mnt
- ```
-
## SynthAdd
- Step1: Download `SynthText_Add.zip` from [SynthAdd](https://pan.baidu.com/s/1uV0LtoNmcxbO-0YA7Ch4dg) (code:627x))
diff --git a/docs/zh_cn/user_guides/data_prepare/det.md b/docs/zh_cn/user_guides/data_prepare/det.md
deleted file mode 100644
index 14f0b9ed..00000000
--- a/docs/zh_cn/user_guides/data_prepare/det.md
+++ /dev/null
@@ -1,147 +0,0 @@
-# 文字检测
-
-```{warning}
-该页面版本落后于英文版文档，请切换至英文阅读最新文档。
-```
-
-```{note}
-我们正努力往 [Dataset Preparer](./dataset_preparer.md) 中增加更多数据集。对于 [Dataset Preparer](./dataset_preparer.md) 暂未能完整支持的数据集，本页提供了一系列手动下载的步骤，供有需要的用户使用。
-```
-
-## 概览
-
-| 数据集名称 | 数据图片 | | 标注文件 | |
-| :--------: | :-----------------------------------------------: | :-------------------------------------------: | :------------------------------------------------: | :--------------------------------------------: |
-| | | 训练集 (training) | 验证集 (validation) | 测试集 (testing) |
-| CTW1500 | [下载地址](https://github.com/Yuliang-Liu/Curve-Text-Detector) | - | - | - |
-| ICDAR2015 | [下载地址](https://rrc.cvc.uab.es/?ch=4&com=downloads) | [instances_training.json](https://download.openmmlab.com/mmocr/data/icdar2015/instances_training.json) | - | [instances_test.json](https://download.openmmlab.com/mmocr/data/icdar2015/instances_test.json) |
-| ICDAR2017 | [下载地址](https://rrc.cvc.uab.es/?ch=8&com=downloads) | [instances_training.json](https://download.openmmlab.com/mmocr/data/icdar2017/instances_training.json) | [instances_val.json](https://download.openmmlab.com/mmocr/data/icdar2017/instances_val.json) | - |
-| Synthtext | [下载地址](https://www.robots.ox.ac.uk/~vgg/data/scenetext/) | instances_training.lmdb ([data.mdb](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.lmdb/data.mdb), [lock.mdb](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.lmdb/lock.mdb)) | - | - |
-| TextOCR | [下载地址](https://textvqa.org/textocr/dataset) | - | - | - |
-| Totaltext | [下载地址](https://github.com/cs-chan/Total-Text-Dataset) | - | - | - |
-
-对于中国境内的用户，我们也推荐使用开源数据平台[OpenDataLab](https://opendatalab.com/)来获取这些数据集，以获得更好的下载体验:
-
-- [CTW1500](https://opendatalab.com/SCUT-CTW1500?source=OpenMMLab%20GitHub)
-- [ICDAR2013](https://opendatalab.com/ICDAR_2013?source=OpenMMLab%20GitHub)
-- [ICDAR2015](https://opendatalab.com/ICDAR2015?source=OpenMMLab%20GitHub)
-- [Totaltext](https://opendatalab.com/TotalText?source=OpenMMLab%20GitHub)
-- [MSRA-TD500](https://opendatalab.com/MSRA-TD500?source=OpenMMLab%20GitHub)
-
-## 重要提醒
-
-```{note}
-**若用户需要在 CTW1500, ICDAR 2015/2017 或 Totaltext 数据集上训练模型**, 请注意这些数据集中有部分图片的 EXIF 信息里保存着方向信息。MMCV 采用的 OpenCV 后端会默认根据方向信息对图片进行旋转；而由于数据集的标注是在原图片上进行的，这种冲突会使得部分训练样本失效。因此，用户应该在配置 pipeline 时使用 `dict(type='LoadImageFromFile', color_type='color_ignore_orientation')` 以避免 MMCV 的这一行为。（配置文件可参考 [DBNet 的 pipeline 配置](https://github.com/open-mmlab/mmocr/blob/main/configs/_base_/det_pipelines/dbnet_pipeline.py)）
-```
-
-## 准备步骤
-
-### ICDAR 2015
-
-- 第一步：从[下载地址](https://rrc.cvc.uab.es/?ch=4&com=downloads)下载 `ch4_training_images.zip`、`ch4_test_images.zip`、`ch4_training_localization_transcription_gt.zip`、`Challenge4_Test_Task1_GT.zip` 四个文件，分别对应训练集数据、测试集数据、训练集标注、测试集标注。
-- 第二步：运行以下命令，移动数据集到对应文件夹
-
-```bash
-mkdir icdar2015 && cd icdar2015
-mkdir imgs && mkdir annotations
-# 移动数据到目录：
-mv ch4_training_images imgs/training
-mv ch4_test_images imgs/test
-# 移动标注到目录：
-mv ch4_training_localization_transcription_gt annotations/training
-mv Challenge4_Test_Task1_GT annotations/test
-```
-
-- 第三步：下载 [instances_training.json](https://download.openmmlab.com/mmocr/data/icdar2015/instances_training.json) 和 [instances_test.json](https://download.openmmlab.com/mmocr/data/icdar2015/instances_test.json)，并放入 `icdar2015` 文件夹里。或者也可以用以下命令直接生成 `instances_training.json` 和 `instances_test.json`:
-
-```bash
-python tools/data/textdet/icdar_converter.py /path/to/icdar2015 -o /path/to/icdar2015 -d icdar2015 --split-list training test
-```
-
-### ICDAR 2017
-
-- 与上述步骤类似。
-
-### CTW1500
-
-- 第一步：执行以下命令，从 [下载地址](https://github.com/Yuliang-Liu/Curve-Text-Detector) 下载 `train_images.zip`，`test_images.zip`，`train_labels.zip`，`test_labels.zip` 四个文件并配置到对应目录：
-
-```bash
-mkdir ctw1500 && cd ctw1500
-mkdir imgs && mkdir annotations
-
-# 下载并配置标注
-cd annotations
-wget -O train_labels.zip https://universityofadelaide.box.com/shared/static/jikuazluzyj4lq6umzei7m2ppmt3afyw.zip
-wget -O test_labels.zip https://cloudstor.aarnet.edu.au/plus/s/uoeFl0pCN9BOCN5/download
-unzip train_labels.zip && mv ctw1500_train_labels training
-unzip test_labels.zip -d test
-cd ..
-# 下载并配置数据
-cd imgs
-wget -O train_images.zip https://universityofadelaide.box.com/shared/static/py5uwlfyyytbb2pxzq9czvu6fuqbjdh8.zip
-wget -O test_images.zip https://universityofadelaide.box.com/shared/static/t4w48ofnqkdw7jyc4t11nsukoeqk9c3d.zip
-unzip train_images.zip && mv train_images training
-unzip test_images.zip && mv test_images test
-```
-
-- 第二步：执行以下命令，生成 `instances_training.json` 和 `instances_test.json`。
-
-```bash
-python tools/data/textdet/ctw1500_converter.py /path/to/ctw1500 -o /path/to/ctw1500 --split-list training test
-```
-
-### SynthText
-
-- 下载 [data.mdb](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.lmdb/data.mdb) 和 [lock.mdb](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.lmdb/lock.mdb) 并放置到 `synthtext/instances_training.lmdb/` 中.
-
-### TextOCR
-
-- 第一步：下载 [train_val_images.zip](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip)，[TextOCR_0.1_train.json](https://dl.fbaipublicfiles.com/textvqa/data/textocr/TextOCR_0.1_train.json) 和 [TextOCR_0.1_val.json](https://dl.fbaipublicfiles.com/textvqa/data/textocr/TextOCR_0.1_val.json) 到 `textocr` 文件夹里。
-
-```bash
-mkdir textocr && cd textocr
-
-# 下载 TextOCR 数据集
-wget https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip
-wget https://dl.fbaipublicfiles.com/textvqa/data/textocr/TextOCR_0.1_train.json
-wget https://dl.fbaipublicfiles.com/textvqa/data/textocr/TextOCR_0.1_val.json
-
-# 把图片移到对应目录
-unzip -q train_val_images.zip
-mv train_images train
-```
-
-- 第二步：生成 `instances_training.json` 和 `instances_val.json`:
-
-```bash
-python tools/data/textdet/textocr_converter.py /path/to/textocr
-```
-
-### Totaltext
-
-- 第一步：从 [github dataset](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Dataset) 下载 `totaltext.zip`，从 [github Groundtruth](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Groundtruth/Text) 下载 `groundtruth_text.zip` 。（建议下载 `.mat` 格式的标注文件，因为我们提供的标注格式转换脚本 `totaltext_converter.py` 仅支持 `.mat` 格式。）
-
-```bash
-mkdir totaltext && cd totaltext
-mkdir imgs && mkdir annotations
-
-# 图像
-# 在 ./totaltext 中执行
-unzip totaltext.zip
-mv Images/Train imgs/training
-mv Images/Test imgs/test
-
-# 标注文件
-unzip groundtruth_text.zip
-cd Groundtruth
-mv Polygon/Train ../annotations/training
-mv Polygon/Test ../annotations/test
-
-```
-
-- 第二步：用以下命令生成 `instances_training.json` 和 `instances_test.json` ：
-
-```bash
-python tools/data/textdet/totaltext_converter.py /path/to/totaltext -o /path/to/totaltext --split-list training test
-```
diff --git a/docs/zh_cn/user_guides/data_prepare/recog.md b/docs/zh_cn/user_guides/data_prepare/recog.md
deleted file mode 100644
index 90f89172..00000000
--- a/docs/zh_cn/user_guides/data_prepare/recog.md
+++ /dev/null
@@ -1,314 +0,0 @@
-# 文字识别
-
-```{warning}
-该页面版本落后于英文版文档，请切换至英文阅读最新文档。
-```
-
-```{note}
-我们正努力往 [Dataset Preparer](./dataset_preparer.md) 中增加更多数据集。对于 [Dataset Preparer](./dataset_preparer.md) 暂未能完整支持的数据集，本页提供了一系列手动下载的步骤，供有需要的用户使用。
-```
-
-## 概览
-
-**文字识别任务的数据集应按如下目录配置：**
-
-```text
-├── mixture
-│ ├── coco_text
-│ │ ├── train_label.txt
-│ │ ├── train_words
-│ ├── icdar_2011
-│ │ ├── training_label.txt
-│ │ ├── Challenge1_Training_Task3_Images_GT
-│ ├── icdar_2013
-│ │ ├── train_label.txt
-│ │ ├── test_label_1015.txt
-│ │ ├── test_label_1095.txt
-│ │ ├── Challenge2_Training_Task3_Images_GT
-│ │ ├── Challenge2_Test_Task3_Images
-│ ├── icdar_2015
-│ │ ├── train_label.txt
-│ │ ├── test_label.txt
-│ │ ├── ch4_training_word_images_gt
-│ │ ├── ch4_test_word_images_gt
-│ ├── III5K
-│ │ ├── train_label.txt
-│ │ ├── test_label.txt
-│ │ ├── train
-│ │ ├── test
-│ ├── ct80
-│ │ ├── test_label.txt
-│ │ ├── image
-│ ├── svt
-│ │ ├── test_label.txt
-│ │ ├── image
-│ ├── svtp
-│ │ ├── test_label.txt
-│ │ ├── image
-│ ├── Syn90k
-│ │ ├── shuffle_labels.txt
-│ │ ├── label.txt
-│ │ ├── label.lmdb
-│ │ ├── mnt
-│ ├── SynthText
-│ │ ├── alphanumeric_labels.txt
-│ │ ├── shuffle_labels.txt
-│ │ ├── instances_train.txt
-│ │ ├── label.txt
-│ │ ├── label.lmdb
-│ │ ├── synthtext
-│ ├── SynthAdd
-│ │ ├── label.txt
-│ │ ├── label.lmdb
-│ │ ├── SynthText_Add
-│ ├── TextOCR
-│ │ ├── image
-│ │ ├── train_label.txt
-│ │ ├── val_label.txt
-│ ├── Totaltext
-│ │ ├── imgs
-│ │ ├── annotations
-│ │ ├── train_label.txt
-│ │ ├── test_label.txt
-│ ├── OpenVINO
-│ │ ├── image_1
-│ │ ├── image_2
-│ │ ├── image_5
-│ │ ├── image_f
-│ │ ├── image_val
-│ │ ├── train_1_label.txt
-│ │ ├── train_2_label.txt
-│ │ ├── train_5_label.txt
-│ │ ├── train_f_label.txt
-│ │ ├── val_label.txt
-```
-
-| 数据集名称 | 数据图片 | 标注文件 | 标注文件 |
-| :-------------------: | :---------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
-| | | 训练集(training) | 测试集(test) |
-| coco_text | [下载地址](https://rrc.cvc.uab.es/?ch=5&com=downloads) | [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/coco_text/train_label.txt) | - |
-| icdar_2011 | [下载地址](http://www.cvc.uab.es/icdar2011competition/?com=downloads) | [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2015/train_label.txt) | - |
-| icdar_2013 | [下载地址](https://rrc.cvc.uab.es/?ch=2&com=downloads) | [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2013/train_label.txt) | [test_label_1015.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2013/test_label_1015.txt) |
-| icdar_2015 | [下载地址](https://rrc.cvc.uab.es/?ch=4&com=downloads) | [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2015/train_label.txt) | [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2015/test_label.txt) |
-| IIIT5K | [下载地址](http://cvit.iiit.ac.in/projects/SceneTextUnderstanding/IIIT5K.html) | [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/IIIT5K/train_label.txt) | [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/IIIT5K/test_label.txt) |
-| ct80 | [下载地址](http://cs-chan.com/downloads_CUTE80_dataset.html) | - | [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/ct80/test_label.txt) |
-| svt | [下载地址](http://www.iapr-tc11.org/mediawiki/index.php/The_Street_View_Text_Dataset) | - | [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/svt/test_label.txt) |
-| svtp | [非官方下载地址\*](https://github.com/Jyouhou/Case-Sensitive-Scene-Text-Recognition-Datasets) | - | [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/svtp/test_label.txt) |
-| MJSynth (Syn90k) | [下载地址](https://www.robots.ox.ac.uk/~vgg/data/text/) | [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/Syn90k/shuffle_labels.txt) \| [label.txt](https://download.openmmlab.com/mmocr/data/mixture/Syn90k/label.txt) | - |
-| SynthText (Synth800k) | [下载地址](https://www.robots.ox.ac.uk/~vgg/data/scenetext/) | [alphanumeric_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/alphanumeric_labels.txt) \| [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/shuffle_labels.txt) \| [instances_train.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/instances_train.txt) \| [label.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/label.txt) | - |
-| SynthAdd | [SynthText_Add.zip](https://pan.baidu.com/s/1uV0LtoNmcxbO-0YA7Ch4dg) (code:627x) | [label.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthAdd/label.txt) | - |
-| TextOCR | [下载地址](https://textvqa.org/textocr/dataset) | - | - |
-| Totaltext | [下载地址](https://github.com/cs-chan/Total-Text-Dataset) | - | - |
-| OpenVINO | [下载地址](https://github.com/cvdfoundation/open-images-dataset) | [下载地址](https://storage.openvinotoolkit.org/repositories/openvino_training_extensions/datasets/open_images_v5_text) | [下载地址](https://storage.openvinotoolkit.org/repositories/openvino_training_extensions/datasets/open_images_v5_text) |
-
-(\*) 注：由于官方的下载地址已经无法访问，我们提供了一个非官方的地址以供参考，但我们无法保证数据的准确性。
-
-对于中国境内的用户，我们也推荐使用开源数据平台[OpenDataLab](https://opendatalab.com/)来获取这些数据集，以获得更好的下载体验:
-
-- [icdar_2013](https://opendatalab.com/ICDAR_2013?source=OpenMMLab%20GitHub)
-- [icdar_2015](https://opendatalab.com/ICDAR2015?source=OpenMMLab%20GitHub)
-- [IIIT5K](https://opendatalab.com/IIIT_5K?source=OpenMMLab%20GitHub)
-- [ct80](https://opendatalab.com/CUTE_80?source=OpenMMLab%20GitHub)
-- [svt](https://opendatalab.com/SVT?source=OpenMMLab%20GitHub)
-- [Totaltext](https://opendatalab.com/TotalText?source=OpenMMLab%20GitHub)
-- [IAM](https://opendatalab.com/IAM_Handwriting?source=OpenMMLab%20GitHub)
-
-## 准备步骤
-
-### ICDAR 2013
-
-- 第一步：从 [下载地址](https://rrc.cvc.uab.es/?ch=2&com=downloads) 下载 `Challenge2_Test_Task3_Images.zip` 和 `Challenge2_Training_Task3_Images_GT.zip`
-- 第二步：下载 [test_label_1015.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2013/test_label_1015.txt) 和 [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2013/train_label.txt)
-
-### ICDAR 2015
-
-- 第一步：从 [下载地址](https://rrc.cvc.uab.es/?ch=4&com=downloads) 下载 `ch4_training_word_images_gt.zip` 和 `ch4_test_word_images_gt.zip`
-- 第二步：下载 [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2015/train_label.txt) and [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2015/test_label.txt)
-
-### IIIT5K
-
-- 第一步：从 [下载地址](http://cvit.iiit.ac.in/projects/SceneTextUnderstanding/IIIT5K.html) 下载 `IIIT5K-Word_V3.0.tar.gz`
-- 第二步：下载 [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/IIIT5K/train_label.txt) 和 [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/IIIT5K/test_label.txt)
-
-### svt
-
-- 第一步：从 [下载地址](http://www.iapr-tc11.org/mediawiki/index.php/The_Street_View_Text_Dataset) 下载 `svt.zip`
-- 第二步：下载 [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/svt/test_label.txt)
-- 第三步：
-
-```bash
-python tools/data/textrecog/svt_converter.py <download_svt_dir_path>
-```
-
-### ct80
-
-- 第一步：下载 [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/ct80/test_label.txt)
-
-### svtp
-
-- 第一步：下载 [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/svtp/test_label.txt)
-
-### coco_text
-
-- 第一步：从 [下载地址](https://rrc.cvc.uab.es/?ch=5&com=downloads) 下载文件
-- 第二步：下载 [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/coco_text/train_label.txt)
-
-### MJSynth (Syn90k)
-
-- 第一步：从 [下载地址](https://www.robots.ox.ac.uk/~vgg/data/text/) 下载 `mjsynth.tar.gz`
-- 第二步：下载 [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/Syn90k/shuffle_labels.txt)
-- 第三步：
-
-```bash
-mkdir Syn90k && cd Syn90k
-
-mv /path/to/mjsynth.tar.gz .
-
-tar -xzf mjsynth.tar.gz
-
-mv /path/to/shuffle_labels.txt .
-mv /path/to/label.txt .
-
-# 创建软链接
-cd /path/to/mmocr/data/mixture
-
-ln -s /path/to/Syn90k Syn90k
-```
-
-### SynthText (Synth800k)
-
-- 第一步：下载 `SynthText.zip`: [下载地址](https://www.robots.ox.ac.uk/~vgg/data/scenetext/)
-
-- 第二步：请根据你的实际需要，从下列标注中选择最适合的下载：[label.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/label.txt) （7,266,686个标注）； [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/shuffle_labels.txt) （2,400,000个随机采样的标注）；[alphanumeric_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/alphanumeric_labels.txt) （7,239,272个仅包含数字和字母的标注）；[instances_train.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/instances_train.txt) （7,266,686个字符级别的标注）。
-
-- 第三步：
-
-```bash
-mkdir SynthText && cd SynthText
-mv /path/to/SynthText.zip .
-unzip SynthText.zip
-mv SynthText synthtext
-
-mv /path/to/shuffle_labels.txt .
-mv /path/to/label.txt .
-mv /path/to/alphanumeric_labels.txt .
-mv /path/to/instances_train.txt .
-
-# 创建软链接
-cd /path/to/mmocr/data/mixture
-ln -s /path/to/SynthText SynthText
-```
-
-- 第四步：生成裁剪后的图像和标注：
-
-```bash
-cd /path/to/mmocr
-
-python tools/data/textrecog/synthtext_converter.py data/mixture/SynthText/gt.mat data/mixture/SynthText/ data/mixture/SynthText/synthtext/SynthText_patch_horizontal --n_proc 8
-```
-
-### SynthAdd
-
-- 第一步：从 [SynthAdd](https://pan.baidu.com/s/1uV0LtoNmcxbO-0YA7Ch4dg) (code:627x) 下载 `SynthText_Add.zip`
-- 第二步：下载 [label.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthAdd/label.txt)
-- 第三步：
-
-`````bash
-mkdir SynthAdd && cd SynthAdd
-
-mv /path/to/SynthText_Add.zip .
-
-unzip SynthText_Add.zip
-
-mv /path/to/label.txt .
-
-# 创建软链接
-cd /path/to/mmocr/data/mixture
-
-````{tip}
-运行以下命令，可以把 `.txt` 格式的标注文件转换成 `.lmdb` 格式：
-```bash
-python tools/data/utils/txt2lmdb.py -i <txt_label_path> -o <lmdb_label_path>
-`````
-
-例如：
-
-```bash
-python tools/data/utils/txt2lmdb.py -i data/mixture/Syn90k/label.txt -o data/mixture/Syn90k/label.lmdb
-```
-
-````
-
-### TextOCR
- - 第一步：下载 [train_val_images.zip](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip)，[TextOCR_0.1_train.json](https://dl.fbaipublicfiles.com/textvqa/data/textocr/TextOCR_0.1_train.json) 和 [TextOCR_0.1_val.json](https://dl.fbaipublicfiles.com/textvqa/data/textocr/TextOCR_0.1_val.json) 到 `textocr/` 目录.
- ```bash
- mkdir textocr && cd textocr
-
- # 下载 TextOCR 数据集
- wget https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip
- wget https://dl.fbaipublicfiles.com/textvqa/data/textocr/TextOCR_0.1_train.json
- wget https://dl.fbaipublicfiles.com/textvqa/data/textocr/TextOCR_0.1_val.json
-
- # 对于数据图像
- unzip -q train_val_images.zip
- mv train_images train
- ```
- - 第二步：用四个并行进程剪裁图像然后生成 `train_label.txt`，`val_label.txt` ，可以使用以下命令：
- ```bash
- python tools/data/textrecog/textocr_converter.py /path/to/textocr 4
- ```
-
-
-### Totaltext
- - 第一步：从 [github dataset](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Dataset) 下载 `totaltext.zip`，然后从 [github Groundtruth](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Groundtruth/Text) 下载 `groundtruth_text.zip` （我们建议下载 `.mat` 格式的标注文件，因为我们提供的 `totaltext_converter.py` 标注格式转换工具只支持 `.mat` 文件）
- ```bash
- mkdir totaltext && cd totaltext
- mkdir imgs && mkdir annotations
-
- # 对于图像数据
- # 在 ./totaltext 目录下运行
- unzip totaltext.zip
- mv Images/Train imgs/training
- mv Images/Test imgs/test
-
- # 对于标注文件
- unzip groundtruth_text.zip
- cd Groundtruth
- mv Polygon/Train ../annotations/training
- mv Polygon/Test ../annotations/test
- ```
- - 第二步：用以下命令生成经剪裁后的标注文件 `train_label.txt` 和 `test_label.txt` （剪裁后的图像会被保存在目录 `data/totaltext/dst_imgs/`）：
- ```bash
- python tools/data/textrecog/totaltext_converter.py /path/to/totaltext -o /path/to/totaltext --split-list training test
- ```
-
-### OpenVINO
- - 第零步：安装 [awscli](https://aws.amazon.com/cli/)。
- - 第一步：下载 [Open Images](https://github.com/cvdfoundation/open-images-dataset#download-images-with-bounding-boxes-annotations) 的子数据集 `train_1`、 `train_2`、 `train_5`、 `train_f` 及 `validation` 至 `openvino/`。
- ```bash
- mkdir openvino && cd openvino
-
- # 下载 Open Images 的子数据集
- for s in 1 2 5 f; do
- aws s3 --no-sign-request cp s3://open-images-dataset/tar/train_${s}.tar.gz .
- done
- aws s3 --no-sign-request cp s3://open-images-dataset/tar/validation.tar.gz .
-
- # 下载标注文件
- for s in 1 2 5 f; do
- wget https://storage.openvinotoolkit.org/repositories/openvino_training_extensions/datasets/open_images_v5_text/text_spotting_openimages_v5_train_${s}.json
- done
- wget https://storage.openvinotoolkit.org/repositories/openvino_training_extensions/datasets/open_images_v5_text/text_spotting_openimages_v5_validation.json
-
- # 解压数据集
- mkdir -p openimages_v5/val
- for s in 1 2 5 f; do
- tar zxf train_${s}.tar.gz -C openimages_v5
- done
- tar zxf validation.tar.gz -C openimages_v5/val
- ```
- - 第二步： 运行以下的命令，以用4个进程生成标注 `train_{1,2,5,f}_label.txt` 和 `val_label.txt` 并裁剪原图：
- ```bash
- python tools/data/textrecog/openvino_converter.py /path/to/openvino 4
- ```
-````
diff --git a/tools/dataset_converters/textdet/ctw1500_converter.py b/tools/dataset_converters/textdet/ctw1500_converter.py
deleted file mode 100644
index 8a40ada0..00000000
--- a/tools/dataset_converters/textdet/ctw1500_converter.py
+++ /dev/null
@@ -1,233 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import glob
-import os.path as osp
-import xml.etree.ElementTree as ET
-from functools import partial
-
-import mmcv
-import mmengine
-import numpy as np
-from shapely.geometry import Polygon
-
-from mmocr.utils import dump_ocr_data, list_from_file
-
-
-def collect_files(img_dir, gt_dir, split):
- """Collect all images and their corresponding groundtruth files.
-
- Args:
- img_dir(str): The image directory
- gt_dir(str): The groundtruth directory
- split(str): The split of dataset. Namely: training or test
-
- Returns:
- files(list): The list of tuples (img_file, groundtruth_file)
- """
- assert isinstance(img_dir, str)
- assert img_dir
- assert isinstance(gt_dir, str)
- assert gt_dir
-
- # note that we handle png and jpg only. Pls convert others such as gif to
- # jpg or png offline
- suffixes = ['.png', '.PNG', '.jpg', '.JPG', '.jpeg', '.JPEG']
-
- imgs_list = []
- for suffix in suffixes:
- imgs_list.extend(glob.glob(osp.join(img_dir, '*' + suffix)))
-
- files = []
- if split == 'training':
- for img_file in imgs_list:
- gt_file = gt_dir + '/' + osp.splitext(
- osp.basename(img_file))[0] + '.xml'
- files.append((img_file, gt_file))
- assert len(files), f'No images found in {img_dir}'
- print(f'Loaded {len(files)} images from {img_dir}')
- elif split == 'test':
- for img_file in imgs_list:
- gt_file = gt_dir + '/000' + osp.splitext(
- osp.basename(img_file))[0] + '.txt'
- files.append((img_file, gt_file))
- assert len(files), f'No images found in {img_dir}'
- print(f'Loaded {len(files)} images from {img_dir}')
-
- return files
-
-
-def collect_annotations(files, split, nproc=1):
- """Collect the annotation information.
-
- Args:
- files(list): The list of tuples (image_file, groundtruth_file)
- split(str): The split of dataset. Namely: training or test
- nproc(int): The number of process to collect annotations
-
- Returns:
- images(list): The list of image information dicts
- """
- assert isinstance(files, list)
- assert isinstance(split, str)
- assert isinstance(nproc, int)
-
- load_img_info_with_split = partial(load_img_info, split=split)
- if nproc > 1:
- images = mmengine.track_parallel_progress(
- load_img_info_with_split, files, nproc=nproc)
- else:
- images = mmengine.track_progress(load_img_info_with_split, files)
-
- return images
-
-
-def load_txt_info(gt_file, img_info):
- anno_info = []
- for line in list_from_file(gt_file):
- # each line has one ploygen (n vetices), and one text.
- # e.g., 695,885,866,888,867,1146,696,1143,####Latin 9
- line = line.strip()
- strs = line.split(',')
- category_id = 1
- assert strs[28][0] == '#'
- xy = [int(x) for x in strs[0:28]]
- assert len(xy) == 28
- coordinates = np.array(xy).reshape(-1, 2)
- polygon = Polygon(coordinates)
- iscrowd = 0
- area = polygon.area
- # convert to COCO style XYWH format
- min_x, min_y, max_x, max_y = polygon.bounds
- bbox = [min_x, min_y, max_x - min_x, max_y - min_y]
- text = strs[28][4:]
-
- anno = dict(
- iscrowd=iscrowd,
- category_id=category_id,
- bbox=bbox,
- area=area,
- text=text,
- segmentation=[xy])
- anno_info.append(anno)
- img_info.update(anno_info=anno_info)
- return img_info
-
-
-def load_xml_info(gt_file, img_info):
-
- obj = ET.parse(gt_file)
- anno_info = []
- for image in obj.getroot(): # image
- for box in image: # image
- h = box.attrib['height']
- w = box.attrib['width']
- x = box.attrib['left']
- y = box.attrib['top']
- text = box[0].text
- segs = box[1].text
- pts = segs.strip().split(',')
- pts = [int(x) for x in pts]
- assert len(pts) == 28
- # pts = []
- # for iter in range(2,len(box)):
- # pts.extend([int(box[iter].attrib['x']),
- # int(box[iter].attrib['y'])])
- iscrowd = 0
- category_id = 1
- bbox = [int(x), int(y), int(w), int(h)]
-
- coordinates = np.array(pts).reshape(-1, 2)
- polygon = Polygon(coordinates)
- area = polygon.area
- anno = dict(
- iscrowd=iscrowd,
- category_id=category_id,
- bbox=bbox,
- area=area,
- text=text,
- segmentation=[pts])
- anno_info.append(anno)
-
- img_info.update(anno_info=anno_info)
-
- return img_info
-
-
-def load_img_info(files, split):
- """Load the information of one image.
-
- Args:
- files(tuple): The tuple of (img_file, groundtruth_file)
- split(str): The split of dataset: training or test
-
- Returns:
- img_info(dict): The dict of the img and annotation information
- """
- assert isinstance(files, tuple)
- assert isinstance(split, str)
-
- img_file, gt_file = files
- # read imgs with ignoring orientations
- img = mmcv.imread(img_file, 'unchanged')
-
- split_name = osp.basename(osp.dirname(img_file))
- img_info = dict(
- # remove img_prefix for filename
- file_name=osp.join(split_name, osp.basename(img_file)),
- height=img.shape[0],
- width=img.shape[1],
- # anno_info=anno_info,
- segm_file=osp.join(split_name, osp.basename(gt_file)))
-
- if split == 'training':
- img_info = load_xml_info(gt_file, img_info)
- elif split == 'test':
- img_info = load_txt_info(gt_file, img_info)
- else:
- raise NotImplementedError
-
- return img_info
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Convert ctw1500 annotations to COCO format')
- parser.add_argument('root_path', help='ctw1500 root path')
- parser.add_argument('-o', '--out-dir', help='output path')
- parser.add_argument(
- '--split-list',
- nargs='+',
- help='a list of splits. e.g., "--split-list training test"')
-
- parser.add_argument(
- '--nproc', default=1, type=int, help='number of process')
- args = parser.parse_args()
- return args
-
-
-def main():
- args = parse_args()
- root_path = args.root_path
- out_dir = args.out_dir if args.out_dir else root_path
- mmengine.mkdir_or_exist(out_dir)
-
- img_dir = osp.join(root_path, 'imgs')
- gt_dir = osp.join(root_path, 'annotations')
-
- set_name = {}
- for split in args.split_list:
- set_name.update({split: 'instances_' + split + '.json'})
- assert osp.exists(osp.join(img_dir, split))
-
- for split, json_name in set_name.items():
- print(f'Converting {split} into {json_name}')
- with mmengine.Timer(
- print_tmpl='It takes {}s to convert icdar annotation'):
- files = collect_files(
- osp.join(img_dir, split), osp.join(gt_dir, split), split)
- image_infos = collect_annotations(files, split, nproc=args.nproc)
- dump_ocr_data(image_infos, osp.join(out_dir, json_name), 'textdet')
-
-
-if __name__ == '__main__':
- main()
diff --git a/tools/dataset_converters/textdet/ic13_converter.py b/tools/dataset_converters/textdet/ic13_converter.py
deleted file mode 100644
index bdf891c7..00000000
--- a/tools/dataset_converters/textdet/ic13_converter.py
+++ /dev/null
@@ -1,167 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import os
-import os.path as osp
-
-import mmcv
-import mmengine
-
-from mmocr.utils import dump_ocr_data
-
-
-def collect_files(img_dir, gt_dir, split):
- """Collect all images and their corresponding groundtruth files.
-
- Args:
- img_dir (str): The image directory
- gt_dir (str): The groundtruth directory
-
- Returns:
- files (list): The list of tuples (img_file, groundtruth_file)
- """
- assert isinstance(img_dir, str)
- assert img_dir
- assert isinstance(gt_dir, str)
- assert gt_dir
-
- ann_list, imgs_list, splits = [], [], []
- for img in os.listdir(img_dir):
- img_path = osp.join(img_dir, img)
- imgs_list.append(img_path)
- ann_list.append(osp.join(gt_dir, 'gt_' + img.split('.')[0] + '.txt'))
- splits.append(split)
-
- files = list(zip(sorted(imgs_list), sorted(ann_list), splits))
- assert len(files), f'No images found in {img_dir}'
- print(f'Loaded {len(files)} images from {img_dir}')
-
- return files
-
-
-def collect_annotations(files, nproc=1):
- """Collect the annotation information.
-
- Args:
- files (list): The list of tuples (image_file, groundtruth_file)
- nproc (int): The number of process to collect annotations
-
- Returns:
- images (list): The list of image information dicts
- """
- assert isinstance(files, list)
- assert isinstance(nproc, int)
-
- if nproc > 1:
- images = mmengine.track_parallel_progress(
- load_img_info, files, nproc=nproc)
- else:
- images = mmengine.track_progress(load_img_info, files)
-
- return images
-
-
-def load_img_info(files):
- """Load the information of one image.
-
- Args:
- files (tuple): The tuple of (img_file, groundtruth_file, split)
-
- Returns:
- img_info (dict): The dict of the img and annotation information
- """
- assert isinstance(files, tuple)
-
- img_file, gt_file, split = files
- # read imgs while ignoring orientations
- img = mmcv.imread(img_file, 'unchanged')
-
- img_info = dict(
- file_name=osp.join(osp.basename(img_file)),
- height=img.shape[0],
- width=img.shape[1],
- segm_file=osp.join(osp.basename(gt_file)))
-
- # IC13 uses different separator in gt files
- if split == 'training':
- separator = ' '
- elif split == 'test':
- separator = ','
- else:
- raise NotImplementedError
- if osp.splitext(gt_file)[1] == '.txt':
- img_info = load_txt_info(gt_file, img_info, separator)
- else:
- raise NotImplementedError
-
- return img_info
-
-
-def load_txt_info(gt_file, img_info, separator):
- """Collect the annotation information.
-
- The annotation format is as the following:
- [train]
- left top right bottom "transcription"
- [test]
- left, top, right, bottom, "transcription"
-
- Args:
- gt_file (str): The path to ground-truth
- img_info (dict): The dict of the img and annotation information
-
- Returns:
- img_info (dict): The dict of the img and annotation information
- """
- anno_info = []
- with open(gt_file) as f:
- lines = f.readlines()
- for line in lines:
- xmin, ymin, xmax, ymax = line.split(separator)[0:4]
- x = max(0, int(xmin))
- y = max(0, int(ymin))
- w = int(xmax) - x
- h = int(ymax) - y
- bbox = [x, y, w, h]
- segmentation = [x, y, x + w, y, x + w, y + h, x, y + h]
-
- anno = dict(
- iscrowd=0,
- category_id=1,
- bbox=bbox,
- area=w * h,
- segmentation=[segmentation])
- anno_info.append(anno)
- img_info.update(anno_info=anno_info)
-
- return img_info
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Generate training and test set of IC13')
- parser.add_argument('root_path', help='Root dir path of IC13')
- parser.add_argument(
- '--nproc', default=1, type=int, help='Number of process')
- args = parser.parse_args()
- return args
-
-
-def main():
- args = parse_args()
- root_path = args.root_path
-
- for split in ['training', 'test']:
- print(f'Processing {split} set...')
- with mmengine.Timer(
- print_tmpl='It takes {}s to convert IC13 annotation'):
- files = collect_files(
- osp.join(root_path, 'imgs', split),
- osp.join(root_path, 'annotations', split), split)
- image_infos = collect_annotations(files, nproc=args.nproc)
- dump_ocr_data(image_infos,
- osp.join(root_path, 'instances_' + split + '.json'),
- 'textdet')
-
-
-if __name__ == '__main__':
- main()
diff --git a/tools/dataset_converters/textdet/icdar_converter.py b/tools/dataset_converters/textdet/icdar_converter.py
deleted file mode 100644
index 453aae7d..00000000
--- a/tools/dataset_converters/textdet/icdar_converter.py
+++ /dev/null
@@ -1,185 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import glob
-import os.path as osp
-from functools import partial
-
-import mmcv
-import mmengine
-import numpy as np
-from shapely.geometry import Polygon
-
-from mmocr.utils import dump_ocr_data, list_from_file
-
-
-def collect_files(img_dir, gt_dir):
- """Collect all images and their corresponding groundtruth files.
-
- Args:
- img_dir(str): The image directory
- gt_dir(str): The groundtruth directory
-
- Returns:
- files(list): The list of tuples (img_file, groundtruth_file)
- """
- assert isinstance(img_dir, str)
- assert img_dir
- assert isinstance(gt_dir, str)
- assert gt_dir
-
- # note that we handle png and jpg only. Pls convert others such as gif to
- # jpg or png offline
- suffixes = ['.png', '.PNG', '.jpg', '.JPG', '.jpeg', '.JPEG']
- imgs_list = []
- for suffix in suffixes:
- imgs_list.extend(glob.glob(osp.join(img_dir, '*' + suffix)))
-
- files = []
- for img_file in imgs_list:
- gt_file = gt_dir + '/gt_' + osp.splitext(
- osp.basename(img_file))[0] + '.txt'
- files.append((img_file, gt_file))
- assert len(files), f'No images found in {img_dir}'
- print(f'Loaded {len(files)} images from {img_dir}')
-
- return files
-
-
-def collect_annotations(files, dataset, nproc=1):
- """Collect the annotation information.
-
- Args:
- files(list): The list of tuples (image_file, groundtruth_file)
- dataset(str): The dataset name, icdar2015 or icdar2017
- nproc(int): The number of process to collect annotations
-
- Returns:
- images(list): The list of image information dicts
- """
- assert isinstance(files, list)
- assert isinstance(dataset, str)
- assert dataset
- assert isinstance(nproc, int)
-
- load_img_info_with_dataset = partial(load_img_info, dataset=dataset)
- if nproc > 1:
- images = mmengine.track_parallel_progress(
- load_img_info_with_dataset, files, nproc=nproc)
- else:
- images = mmengine.track_progress(load_img_info_with_dataset, files)
-
- return images
-
-
-def load_img_info(files, dataset):
- """Load the information of one image.
-
- Args:
- files(tuple): The tuple of (img_file, groundtruth_file)
- dataset(str): Dataset name, icdar2015 or icdar2017
-
- Returns:
- img_info(dict): The dict of the img and annotation information
- """
- assert isinstance(files, tuple)
- assert isinstance(dataset, str)
- assert dataset
-
- img_file, gt_file = files
- # read imgs with ignoring orientations
- img = mmcv.imread(img_file, 'unchanged')
-
- if dataset == 'icdar2017':
- gt_list = list_from_file(gt_file)
- elif dataset == 'icdar2015':
- gt_list = list_from_file(gt_file, encoding='utf-8-sig')
- else:
- raise NotImplementedError(f'Not support {dataset}')
-
- anno_info = []
- for line in gt_list:
- # each line has one ploygen (4 vetices), and others.
- # e.g., 695,885,866,888,867,1146,696,1143,Latin,9
- line = line.strip()
- strs = line.split(',')
- category_id = 1
- xy = [int(x) for x in strs[0:8]]
- coordinates = np.array(xy).reshape(-1, 2)
- polygon = Polygon(coordinates)
- iscrowd = 0
- # set iscrowd to 1 to ignore 1.
- if (dataset == 'icdar2015'
- and strs[8] == '###') or (dataset == 'icdar2017'
- and strs[9] == '###'):
- iscrowd = 1
- print('ignore text')
-
- area = polygon.area
- # convert to COCO style XYWH format
- min_x, min_y, max_x, max_y = polygon.bounds
- bbox = [min_x, min_y, max_x - min_x, max_y - min_y]
-
- anno = dict(
- iscrowd=iscrowd,
- category_id=category_id,
- bbox=bbox,
- area=area,
- segmentation=[xy])
- anno_info.append(anno)
- split_name = osp.basename(osp.dirname(img_file))
- img_info = dict(
- # remove img_prefix for filename
- file_name=osp.join(split_name, osp.basename(img_file)),
- height=img.shape[0],
- width=img.shape[1],
- anno_info=anno_info,
- segm_file=osp.join(split_name, osp.basename(gt_file)))
- return img_info
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Convert Icdar2015 or Icdar2017 annotations to COCO format'
- )
- parser.add_argument('icdar_path', help='icdar root path')
- parser.add_argument('-o', '--out-dir', help='output path')
- parser.add_argument(
- '-d', '--dataset', required=True, help='icdar2017 or icdar2015')
- parser.add_argument(
- '--split-list',
- nargs='+',
- help='a list of splits. e.g., "--split-list training test"')
-
- parser.add_argument(
- '--nproc', default=1, type=int, help='number of process')
- args = parser.parse_args()
- return args
-
-
-def main():
- args = parse_args()
- icdar_path = args.icdar_path
- out_dir = args.out_dir if args.out_dir else icdar_path
- mmengine.mkdir_or_exist(out_dir)
-
- img_dir = osp.join(icdar_path, 'imgs')
- gt_dir = osp.join(icdar_path, 'annotations')
-
- set_name = {}
- for split in args.split_list:
- set_name.update({split: 'instances_' + split + '.json'})
- assert osp.exists(osp.join(img_dir, split))
-
- for split, json_name in set_name.items():
- print(f'Converting {split} into {json_name}')
- with mmengine.Timer(
- print_tmpl='It takes {}s to convert icdar annotation'):
- files = collect_files(
- osp.join(img_dir, split), osp.join(gt_dir, split))
- image_infos = collect_annotations(
- files, args.dataset, nproc=args.nproc)
- dump_ocr_data(image_infos, osp.join(out_dir, json_name), 'textdet')
-
-
-if __name__ == '__main__':
- main()
diff --git a/tools/dataset_converters/textdet/synthtext_converter.py b/tools/dataset_converters/textdet/synthtext_converter.py
deleted file mode 100644
index 811b1cc0..00000000
--- a/tools/dataset_converters/textdet/synthtext_converter.py
+++ /dev/null
@@ -1,181 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import json
-import os.path as osp
-import time
-
-import lmdb
-import mmcv
-import mmengine
-import numpy as np
-from scipy.io import loadmat
-from shapely.geometry import Polygon
-
-from mmocr.utils import check_argument
-
-
-def trace_boundary(char_boxes):
- """Trace the boundary point of text.
-
- Args:
- char_boxes (list[ndarray]): The char boxes for one text. Each element
- is 4x2 ndarray.
-
- Returns:
- boundary (ndarray): The boundary point sets with size nx2.
- """
- assert check_argument.is_type_list(char_boxes, np.ndarray)
-
- # from top left to to right
- p_top = [box[0:2] for box in char_boxes]
- # from bottom right to bottom left
- p_bottom = [
- char_boxes[idx][[2, 3], :]
- for idx in range(len(char_boxes) - 1, -1, -1)
- ]
-
- p = p_top + p_bottom
-
- boundary = np.concatenate(p).astype(int)
-
- return boundary
-
-
-def match_bbox_char_str(bboxes, char_bboxes, strs):
- """match the bboxes, char bboxes, and strs.
-
- Args:
- bboxes (ndarray): The text boxes of size (2, 4, num_box).
- char_bboxes (ndarray): The char boxes of size (2, 4, num_char_box).
- strs (ndarray): The string of size (num_strs,)
- """
- assert isinstance(bboxes, np.ndarray)
- assert isinstance(char_bboxes, np.ndarray)
- assert isinstance(strs, np.ndarray)
- bboxes = bboxes.astype(np.int32)
- char_bboxes = char_bboxes.astype(np.int32)
-
- if len(char_bboxes.shape) == 2:
- char_bboxes = np.expand_dims(char_bboxes, axis=2)
- char_bboxes = np.transpose(char_bboxes, (2, 1, 0))
- if len(bboxes.shape) == 2:
- bboxes = np.expand_dims(bboxes, axis=2)
- bboxes = np.transpose(bboxes, (2, 1, 0))
- chars = ''.join(strs).replace('\n', '').replace(' ', '')
- num_boxes = bboxes.shape[0]
-
- poly_list = [Polygon(bboxes[iter]) for iter in range(num_boxes)]
- poly_box_list = [bboxes[iter] for iter in range(num_boxes)]
-
- poly_char_list = [[] for iter in range(num_boxes)]
- poly_char_idx_list = [[] for iter in range(num_boxes)]
- poly_charbox_list = [[] for iter in range(num_boxes)]
-
- words = []
- for s in strs:
- words += s.split()
- words_len = [len(w) for w in words]
- words_end_inx = np.cumsum(words_len)
- start_inx = 0
- for word_inx, end_inx in enumerate(words_end_inx):
- for char_inx in range(start_inx, end_inx):
- poly_char_idx_list[word_inx].append(char_inx)
- poly_char_list[word_inx].append(chars[char_inx])
- poly_charbox_list[word_inx].append(char_bboxes[char_inx])
- start_inx = end_inx
-
- for box_inx in range(num_boxes):
- assert len(poly_charbox_list[box_inx]) > 0
-
- poly_boundary_list = []
- for item in poly_charbox_list:
- boundary = np.ndarray((0, 2))
- if len(item) > 0:
- boundary = trace_boundary(item)
- poly_boundary_list.append(boundary)
-
- return (poly_list, poly_box_list, poly_boundary_list, poly_charbox_list,
- poly_char_idx_list, poly_char_list)
-
-
-def convert_annotations(root_path, gt_name, lmdb_name):
- """Convert the annotation into lmdb dataset.
-
- Args:
- root_path (str): The root path of dataset.
- gt_name (str): The ground truth filename.
- lmdb_name (str): The output lmdb filename.
- """
- assert isinstance(root_path, str)
- assert isinstance(gt_name, str)
- assert isinstance(lmdb_name, str)
- start_time = time.time()
- gt = loadmat(gt_name)
- img_num = len(gt['imnames'][0])
- env = lmdb.open(lmdb_name, map_size=int(1e9 * 40))
- with env.begin(write=True) as txn:
- for img_id in range(img_num):
- if img_id % 1000 == 0 and img_id > 0:
- total_time_sec = time.time() - start_time
- avg_time_sec = total_time_sec / img_id
- eta_mins = (avg_time_sec * (img_num - img_id)) / 60
- print(f'\ncurrent_img/total_imgs {img_id}/{img_num} | '
- f'eta: {eta_mins:.3f} mins')
- # for each img
- img_file = osp.join(root_path, 'imgs', gt['imnames'][0][img_id][0])
- img = mmcv.imread(img_file, 'unchanged')
- height, width = img.shape[0:2]
- img_json = {}
- img_json['file_name'] = gt['imnames'][0][img_id][0]
- img_json['height'] = height
- img_json['width'] = width
- img_json['annotations'] = []
- wordBB = gt['wordBB'][0][img_id]
- charBB = gt['charBB'][0][img_id]
- txt = gt['txt'][0][img_id]
- poly_list, _, poly_boundary_list, _, _, _ = match_bbox_char_str(
- wordBB, charBB, txt)
- for poly_inx in range(len(poly_list)):
-
- polygon = poly_list[poly_inx]
- min_x, min_y, max_x, max_y = polygon.bounds
- bbox = [min_x, min_y, max_x - min_x, max_y - min_y]
- anno_info = dict()
- anno_info['iscrowd'] = 0
- anno_info['category_id'] = 1
- anno_info['bbox'] = bbox
- anno_info['segmentation'] = [
- poly_boundary_list[poly_inx].flatten().tolist()
- ]
-
- img_json['annotations'].append(anno_info)
- string = json.dumps(img_json)
- txn.put(str(img_id).encode('utf8'), string.encode('utf8'))
- key = b'total_number'
- value = str(img_num).encode('utf8')
- txn.put(key, value)
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Convert synthtext to lmdb dataset')
- parser.add_argument('synthtext_path', help='synthetic root path')
- parser.add_argument('-o', '--out-dir', help='output path')
- args = parser.parse_args()
- return args
-
-
-# TODO: Refactor synthtext
-def main():
- args = parse_args()
- synthtext_path = args.synthtext_path
- out_dir = args.out_dir if args.out_dir else synthtext_path
- mmengine.mkdir_or_exist(out_dir)
-
- gt_name = osp.join(synthtext_path, 'gt.mat')
- lmdb_name = 'synthtext.lmdb'
- convert_annotations(synthtext_path, gt_name, osp.join(out_dir, lmdb_name))
-
-
-if __name__ == '__main__':
- main()
diff --git a/tools/dataset_converters/textdet/textocr_converter.py b/tools/dataset_converters/textdet/textocr_converter.py
deleted file mode 100644
index 67a8e32f..00000000
--- a/tools/dataset_converters/textdet/textocr_converter.py
+++ /dev/null
@@ -1,76 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import math
-import os.path as osp
-
-import mmengine
-
-from mmocr.utils import dump_ocr_data
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Generate training and validation set of TextOCR ')
- parser.add_argument('root_path', help='Root dir path of TextOCR')
- args = parser.parse_args()
- return args
-
-
-def collect_textocr_info(root_path, annotation_filename, print_every=1000):
-
- annotation_path = osp.join(root_path, annotation_filename)
- if not osp.exists(annotation_path):
- raise Exception(
- f'{annotation_path} not exists, please check and try again.')
-
- annotation = mmengine.load(annotation_path)
-
- # img_idx = img_start_idx
- img_infos = []
- for i, img_info in enumerate(annotation['imgs'].values()):
- if i > 0 and i % print_every == 0:
- print(f'{i}/{len(annotation["imgs"].values())}')
-
- img_info['segm_file'] = annotation_path
- ann_ids = annotation['imgToAnns'][img_info['id']]
- anno_info = []
- for ann_id in ann_ids:
- ann = annotation['anns'][ann_id]
-
- # Ignore illegible or non-English words
- text_label = ann['utf8_string']
- iscrowd = 1 if text_label == '.' else 0
-
- x, y, w, h = ann['bbox']
- x, y = max(0, math.floor(x)), max(0, math.floor(y))
- w, h = math.ceil(w), math.ceil(h)
- bbox = [x, y, w, h]
- segmentation = [max(0, int(x)) for x in ann['points']]
- anno = dict(
- iscrowd=iscrowd,
- category_id=1,
- bbox=bbox,
- area=ann['area'],
- segmentation=[segmentation])
- anno_info.append(anno)
- img_info.update(anno_info=anno_info)
- img_infos.append(img_info)
- return img_infos
-
-
-def main():
- args = parse_args()
- root_path = args.root_path
- print('Processing training set...')
- training_infos = collect_textocr_info(root_path, 'TextOCR_0.1_train.json')
- dump_ocr_data(training_infos,
- osp.join(root_path, 'instances_training.json'), 'textdet')
- print('Processing validation set...')
- val_infos = collect_textocr_info(root_path, 'TextOCR_0.1_val.json')
- dump_ocr_data(val_infos, osp.join(root_path, 'instances_val.json'),
- 'textdet')
- print('Finish')
-
-
-if __name__ == '__main__':
- main()
diff --git a/tools/dataset_converters/textdet/totaltext_converter.py b/tools/dataset_converters/textdet/totaltext_converter.py
deleted file mode 100644
index 75e4cacc..00000000
--- a/tools/dataset_converters/textdet/totaltext_converter.py
+++ /dev/null
@@ -1,410 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import glob
-import os
-import os.path as osp
-import re
-
-import cv2
-import mmcv
-import mmengine
-import numpy as np
-import scipy.io as scio
-import yaml
-from shapely.geometry import Polygon
-
-from mmocr.utils import dump_ocr_data
-
-
-def collect_files(img_dir, gt_dir):
- """Collect all images and their corresponding groundtruth files.
-
- Args:
- img_dir (str): The image directory
- gt_dir (str): The groundtruth directory
-
- Returns:
- files (list): The list of tuples (img_file, groundtruth_file)
- """
- assert isinstance(img_dir, str)
- assert img_dir
- assert isinstance(gt_dir, str)
- assert gt_dir
-
- # note that we handle png and jpg only. Pls convert others such as gif to
- # jpg or png offline
- suffixes = ['.png', '.PNG', '.jpg', '.JPG', '.jpeg', '.JPEG']
- # suffixes = ['.png']
-
- imgs_list = []
- for suffix in suffixes:
- imgs_list.extend(glob.glob(osp.join(img_dir, '*' + suffix)))
-
- imgs_list = sorted(imgs_list)
- ann_list = sorted(
- osp.join(gt_dir, gt_file) for gt_file in os.listdir(gt_dir))
-
- files = list(zip(imgs_list, ann_list))
- assert len(files), f'No images found in {img_dir}'
- print(f'Loaded {len(files)} images from {img_dir}')
-
- return files
-
-
-def collect_annotations(files, nproc=1):
- """Collect the annotation information.
-
- Args:
- files (list): The list of tuples (image_file, groundtruth_file)
- nproc (int): The number of process to collect annotations
-
- Returns:
- images (list): The list of image information dicts
- """
- assert isinstance(files, list)
- assert isinstance(nproc, int)
-
- if nproc > 1:
- images = mmengine.track_parallel_progress(
- load_img_info, files, nproc=nproc)
- else:
- images = mmengine.track_progress(load_img_info, files)
-
- return images
-
-
-def get_contours_mat(gt_path):
- """Get the contours and words for each ground_truth mat file.
-
- Args:
- gt_path (str): The relative path of the ground_truth mat file
-
- Returns:
- contours (list[lists]): A list of lists of contours
- for the text instances
- words (list[list]): A list of lists of words (string)
- for the text instances
- """
- assert isinstance(gt_path, str)
-
- contours = []
- words = []
- data = scio.loadmat(gt_path)
- # 'gt' for the latest version; 'polygt' for the legacy version
- keys = data.keys()
- if 'gt' in keys:
- data_polygt = data.get('gt')
- elif 'polygt' in keys:
- data_polygt = data.get('polygt')
- else:
- raise NotImplementedError
-
- for i, lines in enumerate(data_polygt):
- X = np.array(lines[1])
- Y = np.array(lines[3])
-
- point_num = len(X[0])
- word = lines[4]
- if len(word) == 0 or word == '#':
- word = '###'
- else:
- word = word[0]
-
- words.append(word)
-
- arr = np.concatenate([X, Y]).T
- contour = []
- for i in range(point_num):
- contour.append(arr[i][0])
- contour.append(arr[i][1])
- contours.append(np.asarray(contour))
-
- return contours, words
-
-
-def load_mat_info(img_info, gt_file):
- """Load the information of one ground truth in .mat format.
-
- Args:
- img_info (dict): The dict of only the image information
- gt_file (str): The relative path of the ground_truth mat
- file for one image
-
- Returns:
- img_info(dict): The dict of the img and annotation information
- """
- assert isinstance(img_info, dict)
- assert isinstance(gt_file, str)
-
- contours, texts = get_contours_mat(gt_file)
- anno_info = []
- for contour, text in zip(contours, texts):
- if contour.shape[0] == 2:
- continue
- category_id = 1
- coordinates = np.array(contour).reshape(-1, 2)
- polygon = Polygon(coordinates)
- iscrowd = 1 if text == '###' else 0
-
- area = polygon.area
- # convert to COCO style XYWH format
- min_x, min_y, max_x, max_y = polygon.bounds
- bbox = [min_x, min_y, max_x - min_x, max_y - min_y]
-
- anno = dict(
- iscrowd=iscrowd,
- category_id=category_id,
- bbox=bbox,
- area=area,
- text=text,
- segmentation=[contour])
- anno_info.append(anno)
-
- img_info.update(anno_info=anno_info)
-
- return img_info
-
-
-def process_line(line, contours, words):
- """Get the contours and words by processing each line in the gt file.
-
- Args:
- line(str): The line in gt file containing annotation info
- contours(list[lists]): A list of lists of contours
- for the text instances
- words(list[list]): A list of lists of words (string)
- for the text instances
-
- Returns:
- contours (list[lists]): A list of lists of contours
- for the text instances
- words (list[list]): A list of lists of words (string)
- for the text instances
- """
-
- line = '{' + line.replace('[[', '[').replace(']]', ']') + '}'
- ann_dict = re.sub('([0-9]) +([0-9])', r'\1,\2', line)
- ann_dict = re.sub('([0-9]) +([ 0-9])', r'\1,\2', ann_dict)
- ann_dict = re.sub('([0-9]) -([0-9])', r'\1,-\2', ann_dict)
- ann_dict = ann_dict.replace("[u',']", "[u'#']")
- ann_dict = yaml.safe_load(ann_dict)
-
- X = np.array([ann_dict['x']])
- Y = np.array([ann_dict['y']])
-
- if len(ann_dict['transcriptions']) == 0:
- word = '###'
- else:
- word = ann_dict['transcriptions'][0]
- if len(ann_dict['transcriptions']) > 1:
- for ann_word in ann_dict['transcriptions'][1:]:
- word += ',' + ann_word
- word = str(eval(word))
- words.append(word)
-
- point_num = len(X[0])
-
- arr = np.concatenate([X, Y]).T
- contour = []
- for i in range(point_num):
- contour.append(arr[i][0])
- contour.append(arr[i][1])
- contours.append(np.asarray(contour))
-
- return contours, words
-
-
-def get_contours_txt(gt_path):
- """Get the contours and words for each ground_truth txt file.
-
- Args:
- gt_path (str): The relative path of the ground_truth mat file
-
- Returns:
- contours (list[lists]): A list of lists of contours
- for the text instances
- words (list[list]): A list of lists of words (string)
- for the text instances
- """
- assert isinstance(gt_path, str)
-
- contours = []
- words = []
-
- with open(gt_path) as f:
- tmp_line = ''
- for idx, line in enumerate(f):
- line = line.strip()
- if idx == 0:
- tmp_line = line
- continue
- if not line.startswith('x:'):
- tmp_line += ' ' + line
- continue
- else:
- complete_line = tmp_line
- tmp_line = line
- contours, words = process_line(complete_line, contours, words)
-
- if tmp_line != '':
- contours, words = process_line(tmp_line, contours, words)
-
- words = ['###' if word == '#' else word for word in words]
-
- return contours, words
-
-
-def load_txt_info(gt_file, img_info):
- """Load the information of one ground truth in .txt format.
-
- Args:
- img_info (dict): The dict of only the image information
- gt_file (str): The relative path of the ground_truth mat
- file for one image
-
- Returns:
- img_info(dict): The dict of the img and annotation information
- """
-
- contours, texts = get_contours_txt(gt_file)
- anno_info = []
- for contour, text in zip(contours, texts):
- if contour.shape[0] == 2:
- continue
- category_id = 1
- coordinates = np.array(contour).reshape(-1, 2)
- polygon = Polygon(coordinates)
- iscrowd = 1 if text == '###' else 0
-
- area = polygon.area
- # convert to COCO style XYWH format
- min_x, min_y, max_x, max_y = polygon.bounds
- bbox = [min_x, min_y, max_x - min_x, max_y - min_y]
-
- anno = dict(
- iscrowd=iscrowd,
- category_id=category_id,
- bbox=bbox,
- area=area,
- text=text,
- segmentation=[contour])
- anno_info.append(anno)
-
- img_info.update(anno_info=anno_info)
-
- return img_info
-
-
-def load_png_info(gt_file, img_info):
- """Load the information of one ground truth in .png format.
-
- Args:
- gt_file (str): The relative path of the ground_truth file for one image
- img_info (dict): The dict of only the image information
-
- Returns:
- img_info (dict): The dict of the img and annotation information
- """
- assert isinstance(gt_file, str)
- assert isinstance(img_info, dict)
- gt_img = cv2.imread(gt_file, 0)
- contours, _ = cv2.findContours(gt_img, cv2.RETR_EXTERNAL,
- cv2.CHAIN_APPROX_SIMPLE)
-
- anno_info = []
- for contour in contours:
- if contour.shape[0] == 2:
- continue
- category_id = 1
- xy = np.array(contour).flatten().tolist()
-
- coordinates = np.array(contour).reshape(-1, 2)
- polygon = Polygon(coordinates)
- iscrowd = 0
-
- area = polygon.area
- # convert to COCO style XYWH format
- min_x, min_y, max_x, max_y = polygon.bounds
- bbox = [min_x, min_y, max_x - min_x, max_y - min_y]
-
- anno = dict(
- iscrowd=iscrowd,
- category_id=category_id,
- bbox=bbox,
- area=area,
- segmentation=[xy])
- anno_info.append(anno)
-
- img_info.update(anno_info=anno_info)
-
- return img_info
-
-
-def load_img_info(files):
- """Load the information of one image.
-
- Args:
- files (tuple): The tuple of (img_file, groundtruth_file)
-
- Returns:
- img_info (dict): The dict of the img and annotation information
- """
- assert isinstance(files, tuple)
-
- img_file, gt_file = files
- # read imgs while ignoring orientations
- img = mmcv.imread(img_file, 'unchanged')
-
- split_name = osp.basename(osp.dirname(img_file))
- img_info = dict(
- # remove img_prefix for filename
- file_name=osp.join(split_name, osp.basename(img_file)),
- height=img.shape[0],
- width=img.shape[1],
- # anno_info=anno_info,
- segm_file=osp.join(split_name, osp.basename(gt_file)))
-
- if osp.splitext(gt_file)[1] == '.mat':
- img_info = load_mat_info(img_info, gt_file)
- elif osp.splitext(gt_file)[1] == '.txt':
- img_info = load_txt_info(gt_file, img_info)
- else:
- raise NotImplementedError
-
- return img_info
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Convert totaltext annotations to COCO format')
- parser.add_argument('root_path', help='Totaltext root path')
- parser.add_argument(
- '--nproc', default=1, type=int, help='Number of process')
- args = parser.parse_args()
- return args
-
-
-def main():
- args = parse_args()
- root_path = args.root_path
- img_dir = osp.join(root_path, 'imgs')
- gt_dir = osp.join(root_path, 'annotations')
-
- set_name = {}
- for split in ['training', 'test']:
- set_name.update({split: 'instances_' + split + '.json'})
- assert osp.exists(osp.join(img_dir, split))
-
- for split, json_name in set_name.items():
- print(f'Converting {split} into {json_name}')
- with mmengine.Timer(
- print_tmpl='It takes {}s to convert totaltext annotation'):
- files = collect_files(
- osp.join(img_dir, split), osp.join(gt_dir, split))
- image_infos = collect_annotations(files, nproc=args.nproc)
- dump_ocr_data(image_infos, osp.join(root_path, json_name),
- 'textdet')
-
-
-if __name__ == '__main__':
- main()
diff --git a/tools/dataset_converters/textrecog/ic13_converter.py b/tools/dataset_converters/textrecog/ic13_converter.py
deleted file mode 100644
index e5529a62..00000000
--- a/tools/dataset_converters/textrecog/ic13_converter.py
+++ /dev/null
@@ -1,67 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import os.path as osp
-
-from mmocr.utils import dump_ocr_data
-
-
-def convert_annotations(root_path, split):
- """Convert original annotations to mmocr format.
-
- The annotation format is as the following:
- word_1.png, "flying"
- word_2.png, "today"
- word_3.png, "means"
- See the format of converted annotation in mmocr.utils.dump_ocr_data.
-
- Args:
- root_path (str): The root path of the dataset
- split (str): The split of dataset. Namely: training or test
- """
- assert isinstance(root_path, str)
- assert isinstance(split, str)
-
- img_info = []
- with open(
- osp.join(root_path, 'annotations',
- f'Challenge2_{split}_Task3_GT.txt'),
- encoding='"utf-8-sig') as f:
- annos = f.readlines()
- for anno in annos:
- seg = ' ' if split == 'Test1015' else ', "'
- # text may contain comma ','
- dst_img_name, word = anno.split(seg)
- word = word.replace('"\n', '')
-
- img_info.append({
- 'file_name': osp.basename(dst_img_name),
- 'anno_info': [{
- 'text': word
- }]
- })
-
- return img_info
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Generate training and test set of IC13')
- parser.add_argument('root_path', help='Root dir path of IC13')
- args = parser.parse_args()
- return args
-
-
-def main():
- args = parse_args()
- root_path = args.root_path
-
- for split in ['Train', 'Test', 'Test1015']:
- img_info = convert_annotations(root_path, split)
- dump_ocr_data(img_info,
- osp.join(root_path, f'{split.lower()}_label.json'),
- 'textrecog')
- print(f'{split} split converted.')
-
-
-if __name__ == '__main__':
- main()
diff --git a/tools/dataset_converters/textrecog/svt_converter.py b/tools/dataset_converters/textrecog/svt_converter.py
deleted file mode 100644
index 55b52dc2..00000000
--- a/tools/dataset_converters/textrecog/svt_converter.py
+++ /dev/null
@@ -1,88 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import os
-import os.path as osp
-import xml.etree.ElementTree as ET
-
-import cv2
-
-from mmocr.utils import dump_ocr_data
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Generate testset of svt by cropping box image.')
- parser.add_argument(
- 'root_path',
- help='Root dir path of svt, where test.xml in,'
- 'for example, "data/mixture/svt/svt1/"')
- parser.add_argument(
- '--resize',
- action='store_true',
- help='Whether resize cropped image to certain size.')
- parser.add_argument('--height', default=32, help='Resize height.')
- parser.add_argument('--width', default=100, help='Resize width.')
- args = parser.parse_args()
- return args
-
-
-def main():
- args = parse_args()
- root_path = args.root_path
-
- # inputs
- src_label_file = osp.join(root_path, 'test.xml')
- if not osp.exists(src_label_file):
- raise Exception(
- f'{src_label_file} not exists, please check and try again.')
- src_image_root = root_path
-
- # outputs
- dst_label_file = osp.join(root_path, 'test_label.json')
- dst_image_root = osp.join(root_path, 'image')
- os.makedirs(dst_image_root, exist_ok=True)
-
- tree = ET.parse(src_label_file)
- root = tree.getroot()
-
- index = 1
- img_info = []
- total_img_num = len(root)
- i = 1
- for image_node in root.findall('image'):
- image_name = image_node.find('imageName').text
- print(f'[{i}/{total_img_num}] Process image: {image_name}')
- i += 1
- # lexicon = image_node.find('lex').text.lower()
- # lexicon_list = lexicon.split(',')
- # lex_size = len(lexicon_list)
- src_img = cv2.imread(osp.join(src_image_root, image_name))
- for rectangle in image_node.find('taggedRectangles'):
- x = int(rectangle.get('x'))
- y = int(rectangle.get('y'))
- w = int(rectangle.get('width'))
- h = int(rectangle.get('height'))
- rb, re = max(0, y), max(0, y + h)
- cb, ce = max(0, x), max(0, x + w)
- dst_img = src_img[rb:re, cb:ce]
- text_label = rectangle.find('tag').text.lower()
- if args.resize:
- dst_img = cv2.resize(dst_img, (args.width, args.height))
- dst_img_name = f'img_{index:04}' + '.jpg'
- index += 1
- dst_img_path = osp.join(dst_image_root, dst_img_name)
- cv2.imwrite(dst_img_path, dst_img)
- img_info.append({
- 'file_name': dst_img_name,
- 'anno_info': [{
- 'text': text_label
- }]
- })
-
- dump_ocr_data(img_info, dst_label_file, 'textrecog')
- print(f'Finish to generate svt testset, '
- f'with label file {dst_label_file}')
-
-
-if __name__ == '__main__':
- main()
diff --git a/tools/dataset_converters/textrecog/synthtext_converter.py b/tools/dataset_converters/textrecog/synthtext_converter.py
deleted file mode 100644
index 6b33a0c2..00000000
--- a/tools/dataset_converters/textrecog/synthtext_converter.py
+++ /dev/null
@@ -1,146 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import os
-from functools import partial
-
-import mmcv
-import mmengine
-import numpy as np
-from scipy.io import loadmat
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Crop images in Synthtext-style dataset in '
- 'prepration for MMOCR\'s use')
- parser.add_argument(
- 'anno_path', help='Path to gold annotation data (gt.mat)')
- parser.add_argument('img_path', help='Path to images')
- parser.add_argument('out_dir', help='Path of output images and labels')
- parser.add_argument(
- '--n_proc',
- default=1,
- type=int,
- help='Number of processes to run with')
- args = parser.parse_args()
- return args
-
-
-def load_gt_datum(datum):
- img_path, txt, wordBB, charBB = datum
- words = []
- word_bboxes = []
- char_bboxes = []
-
- # when there's only one word in txt
- # scipy will load it as a string
- if type(txt) is str:
- words = txt.split()
- else:
- for line in txt:
- words += line.split()
-
- # From (2, 4, num_boxes) to (num_boxes, 4, 2)
- if len(wordBB.shape) == 2:
- wordBB = wordBB[:, :, np.newaxis]
- cur_wordBB = wordBB.transpose(2, 1, 0)
- for box in cur_wordBB:
- word_bboxes.append(
- [max(round(coord), 0) for pt in box for coord in pt])
-
- # Validate word bboxes.
- if len(words) != len(word_bboxes):
- return
-
- # From (2, 4, num_boxes) to (num_boxes, 4, 2)
- cur_charBB = charBB.transpose(2, 1, 0)
- for box in cur_charBB:
- char_bboxes.append(
- [max(round(coord), 0) for pt in box for coord in pt])
-
- char_bbox_idx = 0
- char_bbox_grps = []
-
- for word in words:
- temp_bbox = char_bboxes[char_bbox_idx:char_bbox_idx + len(word)]
- char_bbox_idx += len(word)
- char_bbox_grps.append(temp_bbox)
-
- # Validate char bboxes.
- # If the length of the last char bbox is correct, then
- # all the previous bboxes are also valid
- if len(char_bbox_grps[len(words) - 1]) != len(words[-1]):
- return
-
- return img_path, words, word_bboxes, char_bbox_grps
-
-
-def load_gt_data(filename, n_proc):
- mat_data = loadmat(filename, simplify_cells=True)
- imnames = mat_data['imnames']
- txt = mat_data['txt']
- wordBB = mat_data['wordBB']
- charBB = mat_data['charBB']
- return mmengine.track_parallel_progress(
- load_gt_datum, list(zip(imnames, txt, wordBB, charBB)), nproc=n_proc)
-
-
-def process(data, img_path_prefix, out_dir):
- if data is None:
- return
- # Dirty hack for multi-processing
- img_path, words, word_bboxes, char_bbox_grps = data
- img_dir, img_name = os.path.split(img_path)
- img_name = os.path.splitext(img_name)[0]
- input_img = mmcv.imread(os.path.join(img_path_prefix, img_path))
-
- output_sub_dir = os.path.join(out_dir, img_dir)
- if not os.path.exists(output_sub_dir):
- try:
- os.makedirs(output_sub_dir)
- except FileExistsError:
- pass # occurs when multi-proessing
-
- for i, word in enumerate(words):
- output_image_patch_name = f'{img_name}_{i}.png'
- output_label_name = f'{img_name}_{i}.txt'
- output_image_patch_path = os.path.join(output_sub_dir,
- output_image_patch_name)
- output_label_path = os.path.join(output_sub_dir, output_label_name)
- if os.path.exists(output_image_patch_path) and os.path.exists(
- output_label_path):
- continue
-
- word_bbox = word_bboxes[i]
- min_x, max_x = int(min(word_bbox[::2])), int(max(word_bbox[::2]))
- min_y, max_y = int(min(word_bbox[1::2])), int(max(word_bbox[1::2]))
- cropped_img = input_img[min_y:max_y, min_x:max_x]
- if cropped_img.shape[0] <= 0 or cropped_img.shape[1] <= 0:
- continue
-
- char_bbox_grp = np.array(char_bbox_grps[i])
- char_bbox_grp[:, ::2] -= min_x
- char_bbox_grp[:, 1::2] -= min_y
-
- mmcv.imwrite(cropped_img, output_image_patch_path)
- with open(output_label_path, 'w') as output_label_file:
- output_label_file.write(word + '\n')
- for cbox in char_bbox_grp:
- output_label_file.write('%d %d %d %d %d %d %d %d\n' %
- tuple(cbox.tolist()))
-
-
-def main():
- args = parse_args()
- print('Loading annoataion data...')
- data = load_gt_data(args.anno_path, args.n_proc)
- process_with_outdir = partial(
- process, img_path_prefix=args.img_path, out_dir=args.out_dir)
- print('Creating cropped images and gold labels...')
- mmengine.track_parallel_progress(
- process_with_outdir, data, nproc=args.n_proc)
- print('Done')
-
-
-if __name__ == '__main__':
- main()
diff --git a/tools/dataset_converters/textrecog/textocr_converter.py b/tools/dataset_converters/textrecog/textocr_converter.py
deleted file mode 100644
index e69e24d1..00000000
--- a/tools/dataset_converters/textrecog/textocr_converter.py
+++ /dev/null
@@ -1,113 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import math
-import os
-import os.path as osp
-from functools import partial
-
-import mmcv
-import mmengine
-
-from mmocr.utils import dump_ocr_data
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Generate training and validation set of TextOCR '
- 'by cropping box image.')
- parser.add_argument('root_path', help='Root dir path of TextOCR')
- parser.add_argument(
- 'n_proc', default=1, type=int, help='Number of processes to run')
- args = parser.parse_args()
- return args
-
-
-def process_img(args, src_image_root, dst_image_root):
- # Dirty hack for multi-processing
- img_idx, img_info, anns = args
- src_img = mmcv.imread(osp.join(src_image_root, img_info['file_name']))
- labels = []
- for ann_idx, ann in enumerate(anns):
- text_label = ann['utf8_string']
-
- # Ignore illegible or non-English words
- if text_label == '.':
- continue
-
- x, y, w, h = ann['bbox']
- x, y = max(0, math.floor(x)), max(0, math.floor(y))
- w, h = math.ceil(w), math.ceil(h)
- dst_img = src_img[y:y + h, x:x + w]
- dst_img_name = f'img_{img_idx}_{ann_idx}.jpg'
- dst_img_path = osp.join(dst_image_root, dst_img_name)
- mmcv.imwrite(dst_img, dst_img_path)
- labels.append({
- 'file_name': dst_img_name,
- 'anno_info': [{
- 'text': text_label
- }]
- })
- return labels
-
-
-def convert_textocr(root_path,
- dst_image_path,
- dst_label_filename,
- annotation_filename,
- img_start_idx=0,
- nproc=1):
-
- annotation_path = osp.join(root_path, annotation_filename)
- if not osp.exists(annotation_path):
- raise Exception(
- f'{annotation_path} not exists, please check and try again.')
- src_image_root = root_path
-
- # outputs
- dst_label_file = osp.join(root_path, dst_label_filename)
- dst_image_root = osp.join(root_path, dst_image_path)
- os.makedirs(dst_image_root, exist_ok=True)
-
- annotation = mmengine.load(annotation_path)
-
- process_img_with_path = partial(
- process_img,
- src_image_root=src_image_root,
- dst_image_root=dst_image_root)
- tasks = []
- for img_idx, img_info in enumerate(annotation['imgs'].values()):
- ann_ids = annotation['imgToAnns'][img_info['id']]
- anns = [annotation['anns'][ann_id] for ann_id in ann_ids]
- tasks.append((img_idx + img_start_idx, img_info, anns))
- labels_list = mmengine.track_parallel_progress(
- process_img_with_path, tasks, keep_order=True, nproc=nproc)
- final_labels = []
- for label_list in labels_list:
- final_labels += label_list
- dump_ocr_data(final_labels, dst_label_file, 'textrecog')
- return len(annotation['imgs'])
-
-
-def main():
- args = parse_args()
- root_path = args.root_path
- print('Processing training set...')
- num_train_imgs = convert_textocr(
- root_path=root_path,
- dst_image_path='image',
- dst_label_filename='train_label.json',
- annotation_filename='TextOCR_0.1_train.json',
- nproc=args.n_proc)
- print('Processing validation set...')
- convert_textocr(
- root_path=root_path,
- dst_image_path='image',
- dst_label_filename='val_label.json',
- annotation_filename='TextOCR_0.1_val.json',
- img_start_idx=num_train_imgs,
- nproc=args.n_proc)
- print('Finish')
-
-
-if __name__ == '__main__':
- main()
diff --git a/tools/dataset_converters/textrecog/totaltext_converter.py b/tools/dataset_converters/textrecog/totaltext_converter.py
deleted file mode 100644
index cb93d6f9..00000000
--- a/tools/dataset_converters/textrecog/totaltext_converter.py
+++ /dev/null
@@ -1,388 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import glob
-import os
-import os.path as osp
-import re
-
-import mmcv
-import mmengine
-import numpy as np
-import scipy.io as scio
-import yaml
-from shapely.geometry import Polygon
-
-from mmocr.utils import crop_img, dump_ocr_data
-
-
-def collect_files(img_dir, gt_dir):
- """Collect all images and their corresponding groundtruth files.
-
- Args:
- img_dir (str): The image directory
- gt_dir (str): The groundtruth directory
-
- Returns:
- files(list): The list of tuples (img_file, groundtruth_file)
- """
- assert isinstance(img_dir, str)
- assert img_dir
- assert isinstance(gt_dir, str)
- assert gt_dir
-
- # note that we handle png and jpg only. Pls convert others such as gif to
- # jpg or png offline
- suffixes = ['.png', '.PNG', '.jpg', '.JPG', '.jpeg', '.JPEG']
- # suffixes = ['.png']
-
- imgs_list = []
- for suffix in suffixes:
- imgs_list.extend(glob.glob(osp.join(img_dir, '*' + suffix)))
-
- imgs_list = sorted(imgs_list)
- ann_list = sorted(
- osp.join(gt_dir, gt_file) for gt_file in os.listdir(gt_dir))
-
- files = [(img_file, gt_file)
- for (img_file, gt_file) in zip(imgs_list, ann_list)]
- assert len(files), f'No images found in {img_dir}'
- print(f'Loaded {len(files)} images from {img_dir}')
-
- return files
-
-
-def collect_annotations(files, nproc=1):
- """Collect the annotation information.
-
- Args:
- files (list): The list of tuples (image_file, groundtruth_file)
- nproc (int): The number of process to collect annotations
-
- Returns:
- images (list): The list of image information dicts
- """
- assert isinstance(files, list)
- assert isinstance(nproc, int)
-
- if nproc > 1:
- images = mmengine.track_parallel_progress(
- load_img_info, files, nproc=nproc)
- else:
- images = mmengine.track_progress(load_img_info, files)
-
- return images
-
-
-def get_contours_mat(gt_path):
- """Get the contours and words for each ground_truth mat file.
-
- Args:
- gt_path (str): The relative path of the ground_truth mat file
-
- Returns:
- contours (list[lists]): A list of lists of contours
- for the text instances
- words (list[list]): A list of lists of words (string)
- for the text instances
- """
- assert isinstance(gt_path, str)
-
- contours = []
- words = []
- data = scio.loadmat(gt_path)
- # 'gt' for the latest version; 'polygt' for the legacy version
- keys = data.keys()
- if 'gt' in keys:
- data_polygt = data.get('gt')
- elif 'polygt' in keys:
- data_polygt = data.get('polygt')
-
- for i, lines in enumerate(data_polygt):
- X = np.array(lines[1])
- Y = np.array(lines[3])
-
- point_num = len(X[0])
- word = lines[4]
- if len(word) == 0 or word == '#':
- word = '###'
- else:
- word = word[0]
-
- words.append(word)
-
- arr = np.concatenate([X, Y]).T
- contour = []
- for i in range(point_num):
- contour.append(arr[i][0])
- contour.append(arr[i][1])
- contours.append(np.asarray(contour))
-
- return contours, words
-
-
-def load_mat_info(img_info, gt_file):
- """Load the information of one ground truth in .mat format.
-
- Args:
- img_info (dict): The dict of only the image information
- gt_file (str): The relative path of the ground_truth mat
- file for one image
-
- Returns:
- img_info(dict): The dict of the img and annotation information
- """
- assert isinstance(img_info, dict)
- assert isinstance(gt_file, str)
-
- contours, words = get_contours_mat(gt_file)
- anno_info = []
- for contour, word in zip(contours, words):
- if contour.shape[0] == 2 or word == '###':
- continue
- coordinates = np.array(contour).reshape(-1, 2)
- polygon = Polygon(coordinates)
-
- # convert to COCO style XYWH format
- min_x, min_y, max_x, max_y = polygon.bounds
- bbox = [min_x, min_y, max_x, min_y, max_x, max_y, min_x, max_y]
- anno = dict(word=word, bbox=bbox)
- anno_info.append(anno)
-
- img_info.update(anno_info=anno_info)
- return img_info
-
-
-def process_line(line, contours, words):
- """Get the contours and words by processing each line in the gt file.
-
- Args:
- line (str): The line in gt file containing annotation info
- contours (list[lists]): A list of lists of contours
- for the text instances
- words (list[list]): A list of lists of words (string)
- for the text instances
-
- Returns:
- contours (list[lists]): A list of lists of contours
- for the text instances
- words (list[list]): A list of lists of words (string)
- for the text instances
- """
-
- line = '{' + line.replace('[[', '[').replace(']]', ']') + '}'
- ann_dict = re.sub('([0-9]) +([0-9])', r'\1,\2', line)
- ann_dict = re.sub('([0-9]) +([ 0-9])', r'\1,\2', ann_dict)
- ann_dict = re.sub('([0-9]) -([0-9])', r'\1,-\2', ann_dict)
- ann_dict = ann_dict.replace("[u',']", "[u'#']")
- ann_dict = yaml.safe_load(ann_dict)
-
- X = np.array([ann_dict['x']])
- Y = np.array([ann_dict['y']])
-
- if len(ann_dict['transcriptions']) == 0:
- word = '###'
- else:
- word = ann_dict['transcriptions'][0]
- if len(ann_dict['transcriptions']) > 1:
- for ann_word in ann_dict['transcriptions'][1:]:
- word += ',' + ann_word
- word = str(eval(word))
- words.append(word)
-
- point_num = len(X[0])
-
- arr = np.concatenate([X, Y]).T
- contour = []
- for i in range(point_num):
- contour.append(arr[i][0])
- contour.append(arr[i][1])
- contours.append(np.asarray(contour))
-
- return contours, words
-
-
-def get_contours_txt(gt_path):
- """Get the contours and words for each ground_truth txt file.
-
- Args:
- gt_path (str): The relative path of the ground_truth mat file
-
- Returns:
- contours (list[lists]): A list of lists of contours
- for the text instances
- words (list[list]): A list of lists of words (string)
- for the text instances
- """
- assert isinstance(gt_path, str)
-
- contours = []
- words = []
-
- with open(gt_path) as f:
- tmp_line = ''
- for idx, line in enumerate(f):
- line = line.strip()
- if idx == 0:
- tmp_line = line
- continue
- if not line.startswith('x:'):
- tmp_line += ' ' + line
- continue
- else:
- complete_line = tmp_line
- tmp_line = line
- contours, words = process_line(complete_line, contours, words)
-
- if tmp_line != '':
- contours, words = process_line(tmp_line, contours, words)
-
- for word in words:
- if word == '#':
- word = '###'
-
- return contours, words
-
-
-def load_txt_info(gt_file, img_info):
- """Load the information of one ground truth in .txt format.
-
- Args:
- img_info (dict): The dict of only the image information
- gt_file (str): The relative path of the ground_truth mat
- file for one image
-
- Returns:
- img_info (dict): The dict of the img and annotation information
- """
-
- contours, words = get_contours_txt(gt_file)
- anno_info = []
- for contour, word in zip(contours, words):
- if contour.shape[0] == 2 or word == '###':
- continue
- coordinates = np.array(contour).reshape(-1, 2)
- polygon = Polygon(coordinates)
-
- # convert to COCO style XYWH format
- min_x, min_y, max_x, max_y = polygon.bounds
- bbox = [min_x, min_y, max_x, min_y, max_x, max_y, min_x, max_y]
- anno = dict(word=word, bbox=bbox)
- anno_info.append(anno)
-
- img_info.update(anno_info=anno_info)
- return img_info
-
-
-def generate_ann(root_path, split, image_infos):
- """Generate cropped annotations and label txt file.
-
- Args:
- root_path (str): The relative path of the totaltext file
- split (str): The split of dataset. Namely: training or test
- image_infos (list[dict]): A list of dicts of the img and
- annotation information
- """
-
- dst_image_root = osp.join(root_path, 'dst_imgs', split)
- if split == 'training':
- dst_label_file = osp.join(root_path, 'train_label.json')
- elif split == 'test':
- dst_label_file = osp.join(root_path, 'test_label.json')
- os.makedirs(dst_image_root, exist_ok=True)
-
- img_info = []
- for image_info in image_infos:
- index = 1
- src_img_path = osp.join(root_path, 'imgs', image_info['file_name'])
- image = mmcv.imread(src_img_path)
- src_img_root = osp.splitext(image_info['file_name'])[0].split('/')[1]
-
- for anno in image_info['anno_info']:
- word = anno['word']
- dst_img = crop_img(image, anno['bbox'])
-
- # Skip invalid annotations
- if min(dst_img.shape) == 0 or word == '###':
- continue
-
- dst_img_name = f'{src_img_root}_{index}.png'
- index += 1
- dst_img_path = osp.join(dst_image_root, dst_img_name)
- mmcv.imwrite(dst_img, dst_img_path)
- img_info.append({
- 'file_name': dst_img_name,
- 'anno_info': [{
- 'text': word
- }]
- })
-
- dump_ocr_data(img_info, dst_label_file, 'textrecog')
-
-
-def load_img_info(files):
- """Load the information of one image.
-
- Args:
- files (tuple): The tuple of (img_file, groundtruth_file)
-
- Returns:
- img_info (dict): The dict of the img and annotation information
- """
- assert isinstance(files, tuple)
-
- img_file, gt_file = files
- # read imgs with ignoring orientations
- img = mmcv.imread(img_file, 'unchanged')
-
- split_name = osp.basename(osp.dirname(img_file))
- img_info = dict(
- # remove img_prefix for filename
- file_name=osp.join(split_name, osp.basename(img_file)),
- height=img.shape[0],
- width=img.shape[1],
- # anno_info=anno_info,
- segm_file=osp.join(split_name, osp.basename(gt_file)))
-
- if osp.splitext(gt_file)[1] == '.mat':
- img_info = load_mat_info(img_info, gt_file)
- elif osp.splitext(gt_file)[1] == '.txt':
- img_info = load_txt_info(gt_file, img_info)
- else:
- raise NotImplementedError
-
- return img_info
-
-
-def parse_args():
- parser = argparse.ArgumentParser(
- description='Convert totaltext annotations to COCO format')
- parser.add_argument('root_path', help='Totaltext root path')
- parser.add_argument(
- '--nproc', default=1, type=int, help='Number of process')
- args = parser.parse_args()
- return args
-
-
-def main():
- args = parse_args()
- root_path = args.root_path
- img_dir = osp.join(root_path, 'imgs')
- gt_dir = osp.join(root_path, 'annotations')
-
- set_name = {}
- for split in ['training', 'test']:
- set_name.update({split: split + '_label' + '.txt'})
- assert osp.exists(osp.join(img_dir, split))
-
- for split, ann_name in set_name.items():
- print(f'Converting {split} into {ann_name}')
- with mmengine.Timer(
- print_tmpl='It takes {}s to convert totaltext annotation'):
- files = collect_files(
- osp.join(img_dir, split), osp.join(gt_dir, split))
- image_infos = collect_annotations(files, nproc=args.nproc)
- generate_ann(root_path, split, image_infos)
-
-
-if __name__ == '__main__':
- main()