mirror of
https://github.com/open-mmlab/mmocr.git
synced 2025-06-03 21:54:47 +08:00
fix #13: update docs with toc
This commit is contained in:
Hongbin Sun
parent
dd120271ba
commit
a347a97c23
@ -1,5 +1,17 @@
|
||||
<a id="markdown-contributor-covenant-code-of-conduct" name="contributor-covenant-code-of-conduct"></a>
|
||||
# Contributor Covenant Code of Conduct
|
||||
[toc]
|
||||
<!-- TOC -->
|
||||
|
||||
- [Contributor Covenant Code of Conduct](#contributor-covenant-code-of-conduct)
|
||||
- [Our Pledge](#our-pledge)
|
||||
- [Our Standards](#our-standards)
|
||||
- [Our Responsibilities](#our-responsibilities)
|
||||
- [Scope](#scope)
|
||||
- [Enforcement](#enforcement)
|
||||
- [Attribution](#attribution)
|
||||
|
||||
<!-- /TOC -->
|
||||
<a id="markdown-our-pledge" name="our-pledge"></a>
|
||||
## Our Pledge
|
||||
|
||||
In the interest of fostering an open and welcoming environment, we as
|
||||
@ -9,6 +21,7 @@ size, disability, ethnicity, sex characteristics, gender identity and expression
|
||||
level of experience, education, socio-economic status, nationality, personal
|
||||
appearance, race, religion, or sexual identity and orientation.
|
||||
|
||||
<a id="markdown-our-standards" name="our-standards"></a>
|
||||
## Our Standards
|
||||
|
||||
Examples of behavior that contributes to creating a positive environment
|
||||
@ -31,6 +44,7 @@ Examples of unacceptable behavior by participants include:
|
||||
* Other conduct which could reasonably be considered inappropriate in a
|
||||
professional setting
|
||||
|
||||
<a id="markdown-our-responsibilities" name="our-responsibilities"></a>
|
||||
## Our Responsibilities
|
||||
|
||||
Project maintainers are responsible for clarifying the standards of acceptable
|
||||
@ -43,6 +57,7 @@ that are not aligned to this Code of Conduct, or to ban temporarily or
|
||||
permanently any contributor for other behaviors that they deem inappropriate,
|
||||
threatening, offensive, or harmful.
|
||||
|
||||
<a id="markdown-scope" name="scope"></a>
|
||||
## Scope
|
||||
|
||||
This Code of Conduct applies both within project spaces and in public spaces
|
||||
@ -52,6 +67,7 @@ address, posting via an official social media account, or acting as an appointed
|
||||
representative at an online or offline event. Representation of a project may be
|
||||
further defined and clarified by project maintainers.
|
||||
|
||||
<a id="markdown-enforcement" name="enforcement"></a>
|
||||
## Enforcement
|
||||
|
||||
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
||||
@ -65,6 +81,7 @@ Project maintainers who do not follow or enforce the Code of Conduct in good
|
||||
faith may face temporary or permanent repercussions as determined by other
|
||||
members of the project's leadership.
|
||||
|
||||
<a id="markdown-attribution" name="attribution"></a>
|
||||
## Attribution
|
||||
|
||||
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
||||
|
||||
@ -1,10 +1,35 @@
|
||||
<a id="markdown-contributing-to-mmocr" name="contributing-to-mmocr"></a>
|
||||
# Contributing to mmocr
|
||||
[toc]
|
||||
|
||||
All kinds of contributions are welcome, including but not limited to the following.
|
||||
|
||||
- Fixes (typo, bugs)
|
||||
- New features and components
|
||||
- Enhancement like function speedup
|
||||
<!-- TOC -->
|
||||
|
||||
- [Contributing to mmocr](#contributing-to-mmocr)
|
||||
- [Workflow](#workflow)
|
||||
- [Step 1: creating a Fork](#step-1-creating-a-fork)
|
||||
- [Step 2: develop a new feature](#step-2-develop-a-new-feature)
|
||||
- [Step 2.1: keeping your fork up to date](#step-21-keeping-your-fork-up-to-date)
|
||||
- [<span id = "step2.2">Step 2.2: creating a feature branch</span>](#step-22-creating-a-feature-branch)
|
||||
- [Creating an issue on github](#creating-an-issue-on-github)
|
||||
- [Create branch](#create-branch)
|
||||
- [Step 2.3: develop and test <your_new_feature>](#step-23-develop-and-test-your_new_feature)
|
||||
- [Step 2.4: prepare to PR](#step-24-prepare-to-pr)
|
||||
- [Merge official repo updates to your fork](#merge-official-repo-updates-to-your-fork)
|
||||
- [Push <your_new_feature> branch to your remote forked repo,](#push-your_new_feature-branch-to-your-remote-forked-repo)
|
||||
- [Step 2.5: send PR](#step-25-send-pr)
|
||||
- [Step 2.6: review code](#step-26-review-code)
|
||||
- [Step 2.7: revise <your_new_feature> (optional)](#step-27-revise-your_new_feature--optional)
|
||||
- [Step 2.8: del <your_new_feature> branch if your PR is accepted.](#step-28-del-your_new_feature-branch-if-your-pr-is-accepted)
|
||||
- [Code style](#code-style)
|
||||
- [Python](#python)
|
||||
- [C++ and CUDA](#c-and-cuda)
|
||||
|
||||
<!-- /TOC -->
|
||||
<a id="markdown-workflow" name="workflow"></a>
|
||||
## Workflow
|
||||
|
||||
This document describes the fork & merge request workflow that should be used when contributing to **MMOCR**.
|
||||
@ -23,6 +48,7 @@ Feature branches are used to develop new features for the upcoming or a distant
|
||||
|
||||
All new developers to **MMOCR** need to follow the following steps:
|
||||
|
||||
<a id="markdown-step-1-creating-a-fork" name="step-1-creating-a-fork"></a>
|
||||
### Step 1: creating a Fork
|
||||
|
||||
1. Fork the repo on GitHub or GitLab to your personal account. Click the `Fork` button on the [project page](https://github.com/open-mmlab/mmocr).
|
||||
@ -36,8 +62,10 @@ git clone https://github.com/<your name>/mmocr.git
|
||||
git remote add upstream https://github.com/open-mmlab/mmocr.git
|
||||
```
|
||||
|
||||
<a id="markdown-step-2-develop-a-new-feature" name="step-2-develop-a-new-feature"></a>
|
||||
### Step 2: develop a new feature
|
||||
|
||||
<a id="markdown-step-21-keeping-your-fork-up-to-date" name="step-21-keeping-your-fork-up-to-date"></a>
|
||||
#### Step 2.1: keeping your fork up to date
|
||||
|
||||
Whenever you want to update your fork with the latest upstream changes, you need to fetch the upstream repo's branches and latest commits to bring them into your repository:
|
||||
@ -57,11 +85,14 @@ git rebase upsteam/develop
|
||||
git push origin develop
|
||||
```
|
||||
|
||||
<a id="markdown-span-id--step22step-22-creating-a-feature-branchspan" name="span-id--step22step-22-creating-a-feature-branchspan"></a>
|
||||
#### <span id = "step2.2">Step 2.2: creating a feature branch</span>
|
||||
<a id="markdown-creating-an-issue-on-githubhttpsgithubcomopen-mmlabmmocr" name="creating-an-issue-on-githubhttpsgithubcomopen-mmlabmmocr"></a>
|
||||
##### Creating an issue on [github](https://github.com/open-mmlab/mmocr)
|
||||
- The title of the issue should be one of the following formats: `[Feature]: xxx`, `[Fix]: xxx`, `[Enhance]: xxx`, `[Refactor]: xxx`.
|
||||
- More details can be written in comments.
|
||||
|
||||
<a id="markdown-create-branch" name="create-branch"></a>
|
||||
##### Create branch
|
||||
```
|
||||
git checkout -b feature/iss_<index> develop
|
||||
@ -71,6 +102,7 @@ Till now, your fork has three branches as follows:
|
||||
|
||||
|
||||
|
||||
<a id="markdown-step-23-develop-and-test-your_new_feature" name="step-23-develop-and-test-your_new_feature"></a>
|
||||
#### Step 2.3: develop and test <your_new_feature>
|
||||
|
||||
Develop your new feature and test it to make sure it works well.
|
||||
@ -87,10 +119,12 @@ git commit -m "fix #<issue_index>: <commit_message>"
|
||||
**Note:**
|
||||
- <issue_index> is the [issue](#step2.2) number.
|
||||
|
||||
<a id="markdown-step-24-prepare-to-pr" name="step-24-prepare-to-pr"></a>
|
||||
#### Step 2.4: prepare to PR
|
||||
- Be sure to link your pull request to the related issue, refering to [link](https://docs.github.com/en/github/managing-your-work-on-github/linking-a-pull-request-to-an-issue)
|
||||
|
||||
|
||||
<a id="markdown-merge-official-repo-updates-to-your-fork" name="merge-official-repo-updates-to-your-fork"></a>
|
||||
##### Merge official repo updates to your fork
|
||||
|
||||
```
|
||||
@ -108,29 +142,36 @@ git rebase develop
|
||||
# solve conflicts if any and Test
|
||||
```
|
||||
|
||||
<a id="markdown-push-your_new_feature-branch-to-your-remote-forked-repo" name="push-your_new_feature-branch-to-your-remote-forked-repo"></a>
|
||||
##### Push <your_new_feature> branch to your remote forked repo,
|
||||
```
|
||||
git checkout <your_new_feature>
|
||||
git push origin <your_new_feature>
|
||||
```
|
||||
<a id="markdown-step-25-send-pr" name="step-25-send-pr"></a>
|
||||
#### Step 2.5: send PR
|
||||
|
||||
Go to the page for your fork on GitHub, select your new feature branch, and click the pull request button to integrate your feature branch into the upstream remote’s develop branch.
|
||||
|
||||
<a id="markdown-step-26-review-code" name="step-26-review-code"></a>
|
||||
#### Step 2.6: review code
|
||||
|
||||
|
||||
<a id="markdown-step-27-revise-your_new_feature--optional" name="step-27-revise-your_new_feature--optional"></a>
|
||||
#### Step 2.7: revise <your_new_feature> (optional)
|
||||
If PR is not accepted, pls follow Step 2.1, 2.3, 2.4 and 2.5 till your PR is accepted.
|
||||
|
||||
<a id="markdown-step-28-del-your_new_feature-branch-if-your-pr-is-accepted" name="step-28-del-your_new_feature-branch-if-your-pr-is-accepted"></a>
|
||||
#### Step 2.8: del <your_new_feature> branch if your PR is accepted.
|
||||
```
|
||||
git branch -d <your_new_feature>
|
||||
git push origin :<your_new_feature>
|
||||
```
|
||||
|
||||
<a id="markdown-code-style" name="code-style"></a>
|
||||
## Code style
|
||||
|
||||
<a id="markdown-python" name="python"></a>
|
||||
### Python
|
||||
We adopt [PEP8](https://www.python.org/dev/peps/pep-0008/) as the preferred code style.
|
||||
|
||||
@ -141,5 +182,6 @@ We use the following tools for linting and formatting:
|
||||
|
||||
>Before you create a PR, make sure that your code lints and is formatted by yapf.
|
||||
|
||||
<a id="markdown-c-and-cuda" name="c-and-cuda"></a>
|
||||
### C++ and CUDA
|
||||
We follow the [Google C++ Style Guide](https://google.github.io/styleguide/cppguide.html).
|
||||
|
||||
@ -1,6 +1,15 @@
|
||||
<a id="markdown-datasets-preparation" name="datasets-preparation"></a>
|
||||
# Datasets Preparation
|
||||
This page lists the datasets which are commonly used in text detection, text recognition and key information extraction, and their download links.
|
||||
[toc]
|
||||
<!-- TOC -->
|
||||
|
||||
- [Datasets Preparation](#datasets-preparation)
|
||||
- [Text Detection](#text-detection)
|
||||
- [Text Recognition](#text-recognition)
|
||||
- [Key Information Extraction](#key-information-extraction)
|
||||
|
||||
<!-- /TOC -->
|
||||
<a id="markdown-text-detection" name="text-detection"></a>
|
||||
## Text Detection
|
||||
**The structure of the text detection dataset directory is organized as follows.**
|
||||
```
|
||||
@ -18,20 +27,18 @@ This page lists the datasets which are commonly used in text detection, text rec
|
||||
│ └── instances_val.json
|
||||
├── synthtext
|
||||
│ ├── imgs
|
||||
│ ├── instances_training.json
|
||||
│ ├── instances_training.txt
|
||||
│ └── instances_training.lmdb
|
||||
```
|
||||
| Dataset | | Images | | | Annotation Files | | | Note | |
|
||||
|:---------:|:-:|:--------------------------:|:-:|:--------------------------------------------:|:---------------------------------------:|:----------------------------------------:|:-:|:----:|---|
|
||||
| | | | | training | validation | testing | | | |
|
||||
| CTW1500 | | [link](https://github.com/Yuliang-Liu/Curve-Text-Detector) | | [instances_training.json](https://download.openmmlab.com/mmocr/data/ctw1500/instances_training.json) | - | [instances_test.json](https://download.openmmlab.com/mmocr/data/ctw1500/instances_test.json) | | | |
|
||||
| ICDAR2015 | | [link](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 | | [link](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://openmmlab) | [instances_test.json](https://download.openmmlab.com/mmocr/data/icdar2017/instances_test.json) | | | |
|
||||
| Synthtext | | [link](https://www.robots.ox.ac.uk/~vgg/data/scenetext/) | | [instances_training.json](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.json) [instances_training.txt](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.txt)|-| | | |
|
||||
| CTW1500 | | [homepage](https://github.com/Yuliang-Liu/Curve-Text-Detector) | | [instances_training.json](https://download.openmmlab.com/mmocr/data/ctw1500/instances_training.json) | - | [instances_test.json](https://download.openmmlab.com/mmocr/data/ctw1500/instances_test.json) | | | |
|
||||
| ICDAR2015 | | [homepage](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 | | [homepage](https://rrc.cvc.uab.es/?ch=8&com=downloads) | [renamed_imgs](https://download.openmmlab.com/mmocr/data/icdar2017/renamed_imgs.tar) | [instances_training.json](https://download.openmmlab.com/mmocr/data/icdar2017/instances_training.json) | [instances_val.json](https://openmmlab) | [instances_test.json](https://download.openmmlab.com/mmocr/data/icdar2017/instances_test.json) | | | |
|
||||
| Synthtext | | [homepage](https://www.robots.ox.ac.uk/~vgg/data/scenetext/) | | [instances_training.lmdb](https://download.openmmlab.com/mmocr/data/synthtext/instances_training.lmdb)|-| | | |
|
||||
|
||||
- For `icdar2015`:
|
||||
- Step1: Download `ch4_training_images.zip` and `ch4_test_images.zip` from this [link](https://rrc.cvc.uab.es/?ch=4&com=downloads)
|
||||
- Step1: Download `ch4_training_images.zip` and `ch4_test_images.zip` from [homepage](https://rrc.cvc.uab.es/?ch=4&com=downloads)
|
||||
- Step2: Download [instances_training.json](https://download.openmmlab.com/mmocr/data/icdar2015/instances_training.json) and [instances_test.json](https://download.openmmlab.com/mmocr/data/icdar2015/instances_test.json)
|
||||
- Step3:
|
||||
```bash
|
||||
@ -43,7 +50,10 @@ This page lists the datasets which are commonly used in text detection, text rec
|
||||
ln -s /path/to/ch4_training_images training
|
||||
ln -s /path/to/ch4_test_images test
|
||||
```
|
||||
- For `icdar2017`:
|
||||
- To avoid the effect of rotation when load `jpg` with opencv, We provide re-saved `png` format image in [renamed_images](https://download.openmmlab.com/mmocr/data/icdar2017/renamed_imgs.tar). You can copy these images to `imgs`.
|
||||
|
||||
<a id="markdown-text-recognition" name="text-recognition"></a>
|
||||
## Text Recognition
|
||||
**The structure of the text recognition dataset directory is organized as follows.**
|
||||
|
||||
@ -95,40 +105,40 @@ This page lists the datasets which are commonly used in text detection, text rec
|
||||
| Dataset | | images | annotation file | annotation file | Note |
|
||||
|:----------:|:-:|:---------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:----:|
|
||||
|| | |training | test | |
|
||||
| coco_text ||[link](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 ||[link](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 | | [link](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 | | [link](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 | | [link](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) | |
|
||||
| coco_text ||[homepage](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 ||[homepage](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 | | [homepage](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 | | [homepage](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 | | [homepage](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 | | - |-|[test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/ct80/test_label.txt)||
|
||||
| svt | | [link](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) | |
|
||||
| svt | | [homepage](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 | | - | - | [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/svtp/test_label.txt) | |
|
||||
| Synth90k | | [link](https://www.robots.ox.ac.uk/~vgg/data/text/) | [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/Synth90k/shuffle_labels.txt) | - | |
|
||||
| SynthText | | [link](https://www.robots.ox.ac.uk/~vgg/data/scenetext/) | [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) | - | |
|
||||
| SynthAdd | | [link](https://download.openmmlab.com/mmocr/data/mixture/SynthAdd/SynthText_Add.zip) | [label.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthAdd/label.txt)|- | |
|
||||
| Synth90k | | [homepage](https://www.robots.ox.ac.uk/~vgg/data/text/) | [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/Synth90k/shuffle_labels.txt) | - | |
|
||||
| SynthText | | [homepage](https://www.robots.ox.ac.uk/~vgg/data/scenetext/) | [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) | - | |
|
||||
| SynthAdd | | [SynthText_Add.zip](https://download.openmmlab.com/mmocr/data/mixture/SynthAdd/SynthText_Add.zip) | [label.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthAdd/label.txt)|- | |
|
||||
|
||||
- For `icdar_2013`:
|
||||
- Step1: Download `Challenge2_Test_Task3_Images.zip` and `Challenge2_Training_Task3_Images_GT.zip` from this [link](https://rrc.cvc.uab.es/?ch=2&com=downloads)
|
||||
- Step1: Download `Challenge2_Test_Task3_Images.zip` and `Challenge2_Training_Task3_Images_GT.zip` from [homepage](https://rrc.cvc.uab.es/?ch=2&com=downloads)
|
||||
- Step2: Download [test_label_1015.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2013/test_label_1015.txt) and [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2013/train_label.txt)
|
||||
- For `icdar_2015`:
|
||||
- Step1: Download `ch4_training_word_images_gt.zip` and `ch4_test_word_images_gt.zip` from this [link](https://rrc.cvc.uab.es/?ch=4&com=downloads)
|
||||
- Step1: Download `ch4_training_word_images_gt.zip` and `ch4_test_word_images_gt.zip` from [homepage](https://rrc.cvc.uab.es/?ch=4&com=downloads)
|
||||
- Step2: Download [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)
|
||||
- For `IIIT5K`:
|
||||
- Step1: Download `IIIT5K-Word_V3.0.tar.gz` from this [link](http://cvit.iiit.ac.in/projects/SceneTextUnderstanding/IIIT5K.html)
|
||||
- Step1: Download `IIIT5K-Word_V3.0.tar.gz` from [homepage](http://cvit.iiit.ac.in/projects/SceneTextUnderstanding/IIIT5K.html)
|
||||
- Step2: Download [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/IIIT5K/train_label.txt) and [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/IIIT5K/test_label.txt)
|
||||
- For `svt`:
|
||||
- Step1: Download `svt.zip` form this [link](http://www.iapr-tc11.org/mediawiki/index.php/The_Street_View_Text_Dataset)
|
||||
- Step1: Download `svt.zip` form [homepage](http://www.iapr-tc11.org/mediawiki/index.php/The_Street_View_Text_Dataset)
|
||||
- Step2: Download [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/svt/test_label.txt)
|
||||
- For `ct80`:
|
||||
- Step1: Download [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/ct80/test_label.txt)
|
||||
- For `svtp`:
|
||||
- Step1: Download [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/svtp/test_label.txt)
|
||||
- For `coco_text`:
|
||||
- Step1: Download from this [link](https://rrc.cvc.uab.es/?ch=5&com=downloads)
|
||||
- Step1: Download from [homepage](https://rrc.cvc.uab.es/?ch=5&com=downloads)
|
||||
- Step2: Download [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/coco_text/train_label.txt)
|
||||
|
||||
- For `Syn90k`:
|
||||
- Step1: Download `mjsynth.tar.gz` from this [link](https://www.robots.ox.ac.uk/~vgg/data/text/)
|
||||
- Step1: Download `mjsynth.tar.gz` from [homepage](https://www.robots.ox.ac.uk/~vgg/data/text/)
|
||||
- Step2: Download [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/Synth90k/shuffle_labels.txt)
|
||||
- Step3:
|
||||
```bash
|
||||
@ -146,7 +156,7 @@ This page lists the datasets which are commonly used in text detection, text rec
|
||||
ln -s /path/to/Syn90k Syn90k
|
||||
```
|
||||
- For `SynthText`:
|
||||
- Step1: Download `SynthText.zip` from this [link](https://www.robots.ox.ac.uk/~vgg/data/scenetext/)
|
||||
- Step1: Download `SynthText.zip` from [homepage](https://www.robots.ox.ac.uk/~vgg/data/scenetext/)
|
||||
- Step2: Download [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/shuffle_labels.txt)
|
||||
- Step3: Download [instances_train.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/instances_train.txt)
|
||||
- Step4:
|
||||
@ -163,7 +173,7 @@ This page lists the datasets which are commonly used in text detection, text rec
|
||||
ln -s /path/to/SynthText SynthText
|
||||
```
|
||||
- For `SynthAdd`:
|
||||
- Step1: Download `SynthText_Add.zip` from this [link](https://download.openmmlab.com/mmocr/data/mixture/SynthAdd/SynthText_Add.zip)
|
||||
- Step1: Download `SynthText_Add.zip` from [SynthText_Add.zip](https://download.openmmlab.com/mmocr/data/mixture/SynthAdd/SynthText_Add.zip)
|
||||
- Step2: Download [label.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthAdd/label.txt)
|
||||
- Step3:
|
||||
```bash
|
||||
@ -181,6 +191,7 @@ This page lists the datasets which are commonly used in text detection, text rec
|
||||
ln -s /path/to/SynthAdd SynthAdd
|
||||
```
|
||||
|
||||
<a id="markdown-key-information-extraction" name="key-information-extraction"></a>
|
||||
## Key Information Extraction
|
||||
**The structure of the key information extraction dataset directory is organized as follows.**
|
||||
```
|
||||
|
||||
@ -1,13 +1,42 @@
|
||||
<a id="markdown-getting-started" name="getting-started"></a>
|
||||
# Getting Started
|
||||
[toc]
|
||||
|
||||
This page provides basic tutorials on the usage of MMOCR.
|
||||
For the installation instructions, please see [install.md](install.md).
|
||||
<!-- TOC -->
|
||||
|
||||
- [Getting Started](#getting-started)
|
||||
- [Inference with Pretrained Models](#inference-with-pretrained-models)
|
||||
- [Test a Single Image](#test-a-single-image)
|
||||
- [Test Multiple Images](#test-multiple-images)
|
||||
- [Test a Dataset](#test-a-dataset)
|
||||
- [Test with Single/Multiple GPUs](#test-with-singlemultiple-gpus)
|
||||
- [Optional Arguments](#optional-arguments)
|
||||
- [Test with Slurm](#test-with-slurm)
|
||||
- [Optional Arguments](#optional-arguments-1)
|
||||
- [Train a Model](#train-a-model)
|
||||
- [Train with Single/Multiple GPUs](#train-with-singlemultiple-gpus)
|
||||
- [Train with Toy Dataset.](#train-with-toy-dataset)
|
||||
- [Train with Slurm](#train-with-slurm)
|
||||
- [Launch Multiple Jobs on a Single Machine](#launch-multiple-jobs-on-a-single-machine)
|
||||
- [Useful Tools](#useful-tools)
|
||||
- [Publish a Model](#publish-a-model)
|
||||
- [Customized Settings](#customized-settings)
|
||||
- [Flexible Dataset](#flexible-dataset)
|
||||
- [Encoder-Decoder-Based Text Recognition Task](#encoder-decoder-based-text-recognition-task)
|
||||
- [Optional Arguments:](#optional-arguments-2)
|
||||
- [Segmentation-Based Text Recognition Task](#segmentation-based-text-recognition-task)
|
||||
- [Text Detection Task](#text-detection-task)
|
||||
- [COCO-like Dataset](#coco-like-dataset)
|
||||
|
||||
<!-- /TOC -->
|
||||
|
||||
<a id="markdown-inference-with-pretrained-models" name="inference-with-pretrained-models"></a>
|
||||
## Inference with Pretrained Models
|
||||
|
||||
We provide testing scripts to evaluate a full dataset, as well as some task-specific image demos.
|
||||
|
||||
<a id="markdown-test-a-single-image" name="test-a-single-image"></a>
|
||||
### Test a Single Image
|
||||
|
||||
You can use the following command to test a single image with one GPU.
|
||||
@ -24,6 +53,7 @@ python demo/image_demo.py demo/demo_text_det.jpg configs/xxx.py xxx.pth demo/dem
|
||||
|
||||
The predicted result will be saved as `demo/demo_text_det_pred.jpg`.
|
||||
|
||||
<a id="markdown-test-multiple-images" name="test-multiple-images"></a>
|
||||
### Test Multiple Images
|
||||
|
||||
```shell
|
||||
@ -35,10 +65,12 @@ sh tools/ocr_test_imgs.sh ${CONFIG_FILE} ${CHECKPOINT_FILE} ${IMG_ROOT_PATH} ${I
|
||||
```
|
||||
It will save both the prediction results and visualized images to `${RESULTS_DIR}`
|
||||
|
||||
<a id="markdown-test-a-dataset" name="test-a-dataset"></a>
|
||||
### Test a Dataset
|
||||
|
||||
MMOCR implements **distributed** testing with `MMDistributedDataParallel`. (Please refer to [datasets.md](datasets.md) to prepare your datasets)
|
||||
|
||||
<a id="markdown-test-with-singlemultiple-gpus" name="test-with-singlemultiple-gpus"></a>
|
||||
#### Test with Single/Multiple GPUs
|
||||
|
||||
You can use the following command to test a dataset with single/multiple GPUs.
|
||||
@ -51,10 +83,12 @@ For example,
|
||||
```shell
|
||||
./tools/dist_test.sh configs/example_config.py work_dirs/example_exp/example_model_20200202.pth 1 --eval hmean-iou
|
||||
```
|
||||
<a id="markdown-optional-arguments" name="optional-arguments"></a>
|
||||
##### Optional Arguments
|
||||
|
||||
- `--eval`: Specify the evaluation metric. For text detection, the metric should be either 'hmean-ic13' or 'hmean-iou'. For text recognition, the metric should be 'acc'.
|
||||
|
||||
<a id="markdown-test-with-slurm" name="test-with-slurm"></a>
|
||||
#### Test with Slurm
|
||||
|
||||
If you run MMOCR on a cluster managed with [Slurm](https://slurm.schedmd.com/), you can use the script `slurm_test.sh`.
|
||||
@ -71,11 +105,13 @@ GPUS=8 ./tools/slurm_test.sh dev test_job configs/example_config.py work_dirs/ex
|
||||
You can check [slurm_test.sh](https://github.com/open-mmlab/mmocr/blob/master/tools/slurm_test.sh) for full arguments and environment variables.
|
||||
|
||||
|
||||
<a id="markdown-optional-arguments-1" name="optional-arguments-1"></a>
|
||||
##### Optional Arguments
|
||||
|
||||
- `--eval`: Specify the evaluation metric. For text detection, the metric should be either 'hmean-ic13' or 'hmean-iou'. For text recognition, the metric should be 'acc'.
|
||||
|
||||
|
||||
<a id="markdown-train-a-model" name="train-a-model"></a>
|
||||
## Train a Model
|
||||
|
||||
MMOCR implements **distributed** training with `MMDistributedDataParallel`. (Please refer to [datasets.md](datasets.md) to prepare your datasets)
|
||||
@ -88,6 +124,7 @@ evaluation = dict(interval=1, by_epoch=True) # This evaluates the model per epo
|
||||
```
|
||||
|
||||
|
||||
<a id="markdown-train-with-singlemultiple-gpus" name="train-with-singlemultiple-gpus"></a>
|
||||
### Train with Single/Multiple GPUs
|
||||
|
||||
```shell
|
||||
@ -98,6 +135,7 @@ Optional Arguments:
|
||||
|
||||
- `--no-validate` (**not suggested**): By default, the codebase will perform evaluation at every k-th iteration during training. To disable this behavior, use `--no-validate`.
|
||||
|
||||
<a id="markdown-train-with-toy-dataset" name="train-with-toy-dataset"></a>
|
||||
#### Train with Toy Dataset.
|
||||
We provide a toy dataset under `tests/data`, and you can train a toy model directly, before the academic dataset is prepared.
|
||||
|
||||
@ -111,6 +149,7 @@ And train a text recognition task with `sar` method and toy dataset,
|
||||
./tools/dist_train.sh configs/textrecog/sar/sar_r31_parallel_decoder_toy_dataset.py work_dirs/sar 1
|
||||
```
|
||||
|
||||
<a id="markdown-train-with-slurm" name="train-with-slurm"></a>
|
||||
### Train with Slurm
|
||||
|
||||
If you run MMOCR on a cluster managed with [Slurm](https://slurm.schedmd.com/), you can use the script `slurm_train.sh`.
|
||||
@ -127,6 +166,7 @@ GPUS=8 ./tools/slurm_train.sh dev psenet-ic15 configs/textdet/psenet/psenet_r50_
|
||||
|
||||
You can check [slurm_train.sh](https://github.com/open-mmlab/mmocr/blob/master/tools/slurm_train.sh) for full arguments and environment variables.
|
||||
|
||||
<a id="markdown-launch-multiple-jobs-on-a-single-machine" name="launch-multiple-jobs-on-a-single-machine"></a>
|
||||
### Launch Multiple Jobs on a Single Machine
|
||||
|
||||
If you launch multiple jobs on a single machine, e.g., 2 jobs of 4-GPU training on a machine with 8 GPUs,
|
||||
@ -159,10 +199,12 @@ CUDA_VISIBLE_DEVICES=4,5,6,7 GPUS=4 ./tools/slurm_train.sh ${PARTITION} ${JOB_NA
|
||||
```
|
||||
|
||||
|
||||
<a id="markdown-useful-tools" name="useful-tools"></a>
|
||||
## Useful Tools
|
||||
|
||||
We provide numerous useful tools under `mmocr/tools` directory.
|
||||
|
||||
<a id="markdown-publish-a-model" name="publish-a-model"></a>
|
||||
### Publish a Model
|
||||
|
||||
Before you upload a model to AWS, you may want to
|
||||
@ -181,8 +223,10 @@ python tools/publish_model.py work_dirs/psenet/latest.pth psenet_r50_fpnf_sbn_1x
|
||||
|
||||
The final output filename will be `psenet_r50_fpnf_sbn_1x_20190801-{hash id}.pth`.
|
||||
|
||||
<a id="markdown-customized-settings" name="customized-settings"></a>
|
||||
## Customized Settings
|
||||
|
||||
<a id="markdown-flexible-dataset" name="flexible-dataset"></a>
|
||||
### Flexible Dataset
|
||||
To support the tasks of `text detection`, `text recognition` and `key information extraction`, we have designed a new type of dataset which consists of `loader` and `parser` to load and parse different types of annotation files.
|
||||
- **loader**: Load the annotation file. There are two types of loader, `HardDiskLoader` and `LmdbLoader`
|
||||
@ -194,6 +238,7 @@ To support the tasks of `text detection`, `text recognition` and `key informatio
|
||||
|
||||
Here we show some examples of using different combination of `loader` and `parser`.
|
||||
|
||||
<a id="markdown-encoder-decoder-based-text-recognition-task" name="encoder-decoder-based-text-recognition-task"></a>
|
||||
#### Encoder-Decoder-Based Text Recognition Task
|
||||
```python
|
||||
dataset_type = 'OCRDataset'
|
||||
@ -217,6 +262,7 @@ train = dict(
|
||||
You can check the content of the annotation file in `tests/data/ocr_toy_dataset/label.txt`.
|
||||
The combination of `HardDiskLoader` and `LineStrParser` will return a dict for each file by calling `__getitem__`: `{'filename': '1223731.jpg', 'text': 'GRAND'}`.
|
||||
|
||||
<a id="markdown-optional-arguments" name="optional-arguments"></a>
|
||||
##### Optional Arguments:
|
||||
|
||||
- `repeat`: The number of repeated lines in the annotation files. For example, if there are `10` lines in the annotation file, setting `repeat=10` will generate a corresponding annotation file with size `100`.
|
||||
@ -246,6 +292,7 @@ train = dict(
|
||||
test_mode=False)
|
||||
```
|
||||
|
||||
<a id="markdown-segmentation-based-text-recognition-task" name="segmentation-based-text-recognition-task"></a>
|
||||
#### Segmentation-Based Text Recognition Task
|
||||
```python
|
||||
prefix = 'tests/data/ocr_char_ann_toy_dataset/'
|
||||
@ -268,6 +315,7 @@ The combination of `HardDiskLoader` and `LineJsonParser` will return a dict for
|
||||
{"file_name": "resort_88_101_1.png", "annotations": [{"char_text": "F", "char_box": [11.0, 0.0, 22.0, 0.0, 12.0, 12.0, 0.0, 12.0]}, {"char_text": "r", "char_box": [23.0, 2.0, 31.0, 1.0, 24.0, 11.0, 16.0, 11.0]}, {"char_text": "o", "char_box": [33.0, 2.0, 43.0, 2.0, 36.0, 12.0, 25.0, 12.0]}, {"char_text": "m", "char_box": [46.0, 2.0, 61.0, 2.0, 53.0, 12.0, 39.0, 12.0]}, {"char_text": ":", "char_box": [61.0, 2.0, 69.0, 2.0, 63.0, 12.0, 55.0, 12.0]}], "text": "From:"}
|
||||
```
|
||||
|
||||
<a id="markdown-text-detection-task" name="text-detection-task"></a>
|
||||
#### Text Detection Task
|
||||
```python
|
||||
dataset_type = 'TextDetDataset'
|
||||
@ -294,6 +342,7 @@ The combination of `HardDiskLoader` and `LineJsonParser` will return a dict for
|
||||
```
|
||||
|
||||
|
||||
<a id="markdown-coco-like-dataset" name="coco-like-dataset"></a>
|
||||
### COCO-like Dataset
|
||||
For text detection, you can also use an annotation file in a COCO format that is defined in [mmdet](https://github.com/open-mmlab/mmdetection/blob/master/mmdet/datasets/coco.py):
|
||||
```python
|
||||
|
||||
@ -1,5 +1,16 @@
|
||||
<a id="markdown-installation" name="installation"></a>
|
||||
# Installation
|
||||
[toc]
|
||||
<!-- TOC -->
|
||||
|
||||
- [Installation](#installation)
|
||||
- [Prerequisites](#prerequisites)
|
||||
- [Step-by-Step Installation Instructions](#step-by-step-installation-instructions)
|
||||
- [Full Set-up Script](#full-set-up-script)
|
||||
- [Another option: Docker Image](#another-option-docker-image)
|
||||
- [Prepare Datasets](#prepare-datasets)
|
||||
|
||||
<!-- /TOC -->
|
||||
<a id="markdown-prerequisites" name="prerequisites"></a>
|
||||
## Prerequisites
|
||||
|
||||
- Linux (Windows is not officially supported)
|
||||
@ -22,6 +33,7 @@ We have tested the following versions of OS and softwares:
|
||||
|
||||
MMOCR depends on Pytorch and mmdetection v2.9.0.
|
||||
|
||||
<a id="markdown-step-by-step-installation-instructions" name="step-by-step-installation-instructions"></a>
|
||||
## Step-by-Step Installation Instructions
|
||||
|
||||
a. Create a conda virtual environment and activate it.
|
||||
@ -98,6 +110,7 @@ pip install -v -e . # or "python setup.py build_ext --inplace"
|
||||
export PYTHONPATH=$(pwd):$PYTHONPATH
|
||||
```
|
||||
|
||||
<a id="markdown-full-set-up-script" name="full-set-up-script"></a>
|
||||
## Full Set-up Script
|
||||
|
||||
Here is the full script for setting up mmocr with conda.
|
||||
@ -137,6 +150,7 @@ pip install -v -e . # or "python setup.py build_ext --inplace"
|
||||
export PYTHONPATH=$(pwd):$PYTHONPATH
|
||||
```
|
||||
|
||||
<a id="markdown-another-option-docker-image" name="another-option-docker-image"></a>
|
||||
## Another option: Docker Image
|
||||
|
||||
We provide a [Dockerfile](https://github.com/open-mmlab/mmocr/blob/master/docker/Dockerfile) to build an image.
|
||||
@ -152,6 +166,7 @@ Run it with
|
||||
docker run --gpus all --shm-size=8g -it -v {DATA_DIR}:/mmocr/data mmocr
|
||||
```
|
||||
|
||||
<a id="markdown-prepare-datasets" name="prepare-datasets"></a>
|
||||
## Prepare Datasets
|
||||
|
||||
It is recommended to symlink the dataset root to `mmocr/data`. Please refer to [datasets.md](datasets.md) to prepare your datasets.
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user