mirror of https://github.com/open-mmlab/mmocr.git
Revert "[TODO] Add LoadImageFromLMDB"
This reverts commit e716ae726f007f79effdf2d45b4955a887f3c1e3pull/1178/head
gaotongxiao
parent
19958fbf6f
commit
914c8af7bf
|
|
@ -14,22 +14,22 @@ appearance, race, religion, or sexual identity and orientation.
|
|||
Examples of behavior that contributes to creating a positive environment
|
||||
include:
|
||||
|
||||
- Using welcoming and inclusive language
|
||||
- Being respectful of differing viewpoints and experiences
|
||||
- Gracefully accepting constructive criticism
|
||||
- Focusing on what is best for the community
|
||||
- Showing empathy towards other community members
|
||||
* Using welcoming and inclusive language
|
||||
* Being respectful of differing viewpoints and experiences
|
||||
* Gracefully accepting constructive criticism
|
||||
* Focusing on what is best for the community
|
||||
* Showing empathy towards other community members
|
||||
|
||||
Examples of unacceptable behavior by participants include:
|
||||
|
||||
- The use of sexualized language or imagery and unwelcome sexual attention or
|
||||
advances
|
||||
- Trolling, insulting/derogatory comments, and personal or political attacks
|
||||
- Public or private harassment
|
||||
- Publishing others' private information, such as a physical or electronic
|
||||
address, without explicit permission
|
||||
- Other conduct which could reasonably be considered inappropriate in a
|
||||
professional setting
|
||||
* The use of sexualized language or imagery and unwelcome sexual attention or
|
||||
advances
|
||||
* Trolling, insulting/derogatory comments, and personal or political attacks
|
||||
* Public or private harassment
|
||||
* Publishing others' private information, such as a physical or electronic
|
||||
address, without explicit permission
|
||||
* Other conduct which could reasonably be considered inappropriate in a
|
||||
professional setting
|
||||
|
||||
## Our Responsibilities
|
||||
|
||||
|
|
@ -70,7 +70,7 @@ members of the project's leadership.
|
|||
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
||||
available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
|
||||
|
||||
[homepage]: https://www.contributor-covenant.org
|
||||
|
||||
For answers to common questions about this code of conduct, see
|
||||
https://www.contributor-covenant.org/faq
|
||||
|
||||
[homepage]: https://www.contributor-covenant.org
|
||||
|
|
|
|||
|
|
@ -18,18 +18,17 @@ Contents
|
|||
- [Step 3: Commit your changes](#step-3-commit-your-changes)
|
||||
- [Step 4: Prepare to Pull Request](#step-4-prepare-to-pull-request)
|
||||
- [Step 4.1: Merge official repo updates to your fork](#step-41-merge-official-repo-updates-to-your-fork)
|
||||
- [Step 4.2: Push \<your_feature_branch> branch to your remote forked repo,](#step-42-push-your_feature_branch-branch-to-your-remote-forked-repo)
|
||||
- [Step 4.2: Push <your_feature_branch> branch to your remote forked repo,](#step-42-push-your_feature_branch-branch-to-your-remote-forked-repo)
|
||||
- [Step 4.3: Create a Pull Request](#step-43-create-a-pull-request)
|
||||
- [Step 4.4: Review code](#step-44-review-code)
|
||||
- [Step 4.5: Revise \<your_feature_branch> (optional)](#step-45-revise-your_feature_branch--optional)
|
||||
- [Step 4.6: Delete \<your_feature_branch> branch if your PR is accepted.](#step-46-delete-your_feature_branch-branch-if-your-pr-is-accepted)
|
||||
- [Step 4.5: Revise <your_feature_branch> (optional)](#step-45-revise-your_feature_branch--optional)
|
||||
- [Step 4.6: Delete <your_feature_branch> branch if your PR is accepted.](#step-46-delete-your_feature_branch-branch-if-your-pr-is-accepted)
|
||||
- [Code style](#code-style)
|
||||
- [Python](#python)
|
||||
- [Installing pre-commit hooks](#installing-pre-commit-hooks)
|
||||
- [C++ and CUDA](#c-and-cuda)
|
||||
|
||||
## Workflow
|
||||
|
||||
### Main Steps
|
||||
|
||||
1. Fork and pull the latest MMOCR
|
||||
|
|
@ -58,13 +57,10 @@ All new developers to **MMOCR** need to follow the following steps:
|
|||
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).
|
||||
|
||||
2. Clone your new forked repo to your computer.
|
||||
|
||||
```
|
||||
git clone https://github.com/<your name>/mmocr.git
|
||||
```
|
||||
|
||||
3. Add the official repo as an upstream:
|
||||
|
||||
```
|
||||
git remote add upstream https://github.com/open-mmlab/mmocr.git
|
||||
```
|
||||
|
|
@ -86,12 +82,11 @@ git push origin main
|
|||
```
|
||||
|
||||
##### Step 2.2: Create a feature branch
|
||||
|
||||
- Create an issue on [github](https://github.com/open-mmlab/mmocr)
|
||||
|
||||
- Create a feature branch
|
||||
|
||||
- ```bash
|
||||
-
|
||||
```bash
|
||||
git checkout -b feature/iss_<index> main
|
||||
# index is the issue index on github above
|
||||
```
|
||||
|
|
@ -121,6 +116,7 @@ git commit -m "fix #<issue_index>: <commit_message>"
|
|||
|
||||
- Make sure to link your pull request to the related issue. Please refer to the [instructon](https://docs.github.com/en/github/managing-your-work-on-github/linking-a-pull-request-to-an-issue)
|
||||
|
||||
|
||||
##### Step 4.1: Merge official repo updates to your fork
|
||||
|
||||
```
|
||||
|
|
@ -138,34 +134,30 @@ git rebase main
|
|||
# solve conflicts if any and Test
|
||||
```
|
||||
|
||||
##### Step 4.2: Push \<your_feature_branch> branch to your remote forked repo,
|
||||
|
||||
##### Step 4.2: Push <your_feature_branch> branch to your remote forked repo,
|
||||
```
|
||||
git checkout <your_feature_branch>
|
||||
git push origin <your_feature_branch>
|
||||
```
|
||||
|
||||
##### Step 4.3: Create a Pull Request
|
||||
|
||||
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.
|
||||
|
||||
##### Step 4.4: Review code
|
||||
|
||||
##### Step 4.5: Revise \<your_feature_branch> (optional)
|
||||
|
||||
##### Step 4.5: Revise <your_feature_branch> (optional)
|
||||
If PR is not accepted, pls follow steps above till your PR is accepted.
|
||||
|
||||
##### Step 4.6: Delete \<your_feature_branch> branch if your PR is accepted.
|
||||
|
||||
##### Step 4.6: Delete <your_feature_branch> branch if your PR is accepted.
|
||||
```
|
||||
git branch -d <your_feature_branch>
|
||||
git push origin :<your_feature_branch>
|
||||
```
|
||||
|
||||
|
||||
## Code style
|
||||
|
||||
### Python
|
||||
|
||||
We adopt [PEP8](https://www.python.org/dev/peps/pep-0008/) as the preferred code style.
|
||||
|
||||
We use the following tools for linting and formatting:
|
||||
|
|
@ -177,7 +169,7 @@ We use the following tools for linting and formatting:
|
|||
Style configurations of yapf and isort can be found in [setup.cfg](../setup.cfg).
|
||||
|
||||
We use [pre-commit hook](https://pre-commit.com/) that checks and formats for `flake8`, `yapf`, `isort`, `trailing whitespaces`,
|
||||
fixes `end-of-files`, sorts `requirments.txt` automatically on every commit.
|
||||
fixes `end-of-files`, sorts `requirments.txt` automatically on every commit.
|
||||
The config for a pre-commit hook is stored in [.pre-commit-config](../.pre-commit-config.yaml).
|
||||
|
||||
#### Installing pre-commit hooks
|
||||
|
|
@ -188,6 +180,7 @@ After you clone the repository, you will need to install and initialize pre-comm
|
|||
pip install -U pre-commit
|
||||
```
|
||||
|
||||
|
||||
From the repository folder
|
||||
|
||||
```shell
|
||||
|
|
@ -196,8 +189,7 @@ pre-commit install
|
|||
|
||||
After this on every commit check code linters and formatter will be enforced.
|
||||
|
||||
> Before you create a PR, make sure that your code lints and is formatted by yapf.
|
||||
>Before you create a PR, make sure that your code lints and is formatted by yapf.
|
||||
|
||||
### C++ and CUDA
|
||||
|
||||
We follow the [Google C++ Style Guide](https://google.github.io/styleguide/cppguide.html).
|
||||
|
|
|
|||
|
|
@ -4,6 +4,7 @@ about: Create a report to help us improve
|
|||
title: ''
|
||||
labels: ''
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
||||
Thanks for your error report and we appreciate it a lot.
|
||||
|
|
@ -31,8 +32,8 @@ A placeholder for the command.
|
|||
|
||||
1. Please run `python mmocr/utils/collect_env.py` to collect necessary environment information and paste it here.
|
||||
2. You may add addition that may be helpful for locating the problem, such as
|
||||
- How you installed PyTorch \[e.g., pip, conda, source\]
|
||||
- Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.)
|
||||
- How you installed PyTorch [e.g., pip, conda, source]
|
||||
- Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.)
|
||||
|
||||
**Error traceback**
|
||||
If applicable, paste the error traceback here.
|
||||
|
|
|
|||
|
|
@ -4,14 +4,15 @@ about: Suggest an idea for this project
|
|||
title: ''
|
||||
labels: ''
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
||||
**Describe the feature**
|
||||
|
||||
**Motivation**
|
||||
A clear and concise description of the motivation of the feature.
|
||||
Ex1. It is inconvenient when \[....\].
|
||||
Ex2. There is a recent paper \[....\], which is very helpful for \[....\].
|
||||
Ex1. It is inconvenient when [....].
|
||||
Ex2. There is a recent paper [....], which is very helpful for [....].
|
||||
|
||||
**Related resources**
|
||||
If there is an official code release or third-party implementations, please also provide the information here, which would be very helpful.
|
||||
|
|
|
|||
|
|
@ -4,4 +4,5 @@ about: Ask general questions to get help
|
|||
title: ''
|
||||
labels: ''
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
|
|
|||
|
|
@ -2,8 +2,9 @@
|
|||
name: Reimplementation Questions
|
||||
about: Ask about questions during model reimplementation
|
||||
title: ''
|
||||
labels: reimplementation
|
||||
labels: 'reimplementation'
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
||||
**Notice**
|
||||
|
|
@ -51,7 +52,7 @@ A placeholder for the config.
|
|||
|
||||
1. Please run `python mmocr/utils/collect_env.py` to collect necessary environment information and paste it here.
|
||||
2. You may add addition that may be helpful for locating the problem, such as
|
||||
1. How you installed PyTorch \[e.g., pip, conda, source\]
|
||||
1. How you installed PyTorch [e.g., pip, conda, source]
|
||||
2. Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.)
|
||||
|
||||
**Results**
|
||||
|
|
|
|||
|
|
@ -1,4 +1,3 @@
|
|||
|
||||
exclude: ^tests/data/
|
||||
repos:
|
||||
- repo: https://github.com/PyCQA/flake8
|
||||
|
|
@ -21,8 +20,10 @@ repos:
|
|||
rev: v3.1.0
|
||||
hooks:
|
||||
- id: trailing-whitespace
|
||||
exclude: ^dicts/
|
||||
- id: check-yaml
|
||||
- id: end-of-file-fixer
|
||||
exclude: ^dicts/
|
||||
- id: requirements-txt-fixer
|
||||
- id: double-quote-string-fixer
|
||||
- id: check-merge-conflict
|
||||
|
|
@ -30,20 +31,22 @@ repos:
|
|||
args: ["--remove"]
|
||||
- id: mixed-line-ending
|
||||
args: ["--fix=lf"]
|
||||
- repo: https://github.com/executablebooks/mdformat
|
||||
rev: 0.7.9
|
||||
- repo: https://github.com/markdownlint/markdownlint
|
||||
rev: v0.11.0
|
||||
hooks:
|
||||
- id: mdformat
|
||||
args: ["--number", "--table-width", "200"]
|
||||
additional_dependencies:
|
||||
- mdformat-openmmlab
|
||||
- mdformat_frontmatter
|
||||
- linkify-it-py
|
||||
- id: markdownlint
|
||||
args: ["-r", "~MD002,~MD013,~MD029,~MD033,~MD034",
|
||||
"-t", "allow_different_nesting"]
|
||||
- repo: https://github.com/myint/docformatter
|
||||
rev: v1.3.1
|
||||
hooks:
|
||||
- id: docformatter
|
||||
args: ["--in-place", "--wrap-descriptions", "79"]
|
||||
- repo: https://github.com/asottile/pyupgrade
|
||||
rev: v2.32.1
|
||||
hooks:
|
||||
- id: pyupgrade
|
||||
args: ["--py36-plus"]
|
||||
- repo: https://github.com/open-mmlab/pre-commit-hooks
|
||||
rev: v0.2.0 # Use the ref you want to point at
|
||||
hooks:
|
||||
|
|
|
|||
|
|
@ -54,7 +54,7 @@ The main branch works with **PyTorch 1.6+**.
|
|||
|
||||
- **Comprehensive Pipeline**
|
||||
|
||||
The toolbox supports not only text detection and text recognition, but also their downstream tasks such as key information extraction.
|
||||
The toolbox supports not only text detection and text recognition, but also their downstream tasks such as key information extraction.
|
||||
|
||||
- **Multiple Models**
|
||||
|
||||
|
|
|
|||
|
|
@ -54,15 +54,15 @@ MMOCR 是基于 PyTorch 和 mmdetection 的开源工具箱，专注于文本检
|
|||
|
||||
-**全流程**
|
||||
|
||||
该工具箱不仅支持文本检测和文本识别，还支持其下游任务，例如关键信息提取。
|
||||
该工具箱不仅支持文本检测和文本识别，还支持其下游任务，例如关键信息提取。
|
||||
|
||||
-**多种模型**
|
||||
|
||||
该工具箱支持用于文本检测，文本识别和关键信息提取的各种最新模型。
|
||||
该工具箱支持用于文本检测，文本识别和关键信息提取的各种最新模型。
|
||||
|
||||
-**模块化设计**
|
||||
|
||||
MMOCR 的模块化设计使用户可以定义自己的优化器，数据预处理器，模型组件如主干模块，颈部模块和头部模块，以及损失函数。有关如何构建自定义模型的信
|
||||
MMOCR 的模块化设计使用户可以定义自己的优化器，数据预处理器，模型组件如主干模块，颈部模块和头部模块，以及损失函数。有关如何构建自定义模型的信
|
||||
息，请参考[快速入门](https://mmocr.readthedocs.io/zh_CN/latest/getting_started.html)。
|
||||
|
||||
-**众多实用工具**
|
||||
|
|
@ -174,6 +174,7 @@ MMOCR 是一款由来自不同高校和企业的研发人员共同参与贡献
|
|||
|
||||
## OpenMMLab 的其他项目
|
||||
|
||||
|
||||
- [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab 计算机视觉基础库
|
||||
- [MIM](https://github.com/open-mmlab/mim): MIM 是 OpenMMlab 项目、算法、模型的统一入口
|
||||
- [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab 图像分类工具箱
|
||||
|
|
|
|||
|
|
@ -1,6 +1,5 @@
|
|||
# SDMGR
|
||||
|
||||
> [Spatial Dual-Modality Graph Reasoning for Key Information Extraction](https://arxiv.org/abs/2103.14470)
|
||||
>[Spatial Dual-Modality Graph Reasoning for Key Information Extraction](https://arxiv.org/abs/2103.14470)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
|
|
|
|||
|
|
@ -3,7 +3,6 @@
|
|||
> [Real-time Scene Text Detection with Differentiable Binarization](https://arxiv.org/abs/1911.08947)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
## Abstract
|
||||
|
||||
Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text. However, the post-processing of binarization is essential for segmentation-based detection, which converts probability maps produced by a segmentation method into bounding boxes/regions of text. In this paper, we propose a module named Differentiable Binarization (DB), which can perform the binarization process in a segmentation network. Optimized along with a DB module, a segmentation network can adaptively set the thresholds for binarization, which not only simplifies the post-processing but also enhances the performance of text detection. Based on a simple segmentation network, we validate the performance improvements of DB on five benchmark datasets, which consistently achieves state-of-the-art results, in terms of both detection accuracy and speed. In particular, with a light-weight backbone, the performance improvements by DB are significant so that we can look for an ideal tradeoff between detection accuracy and efficiency. Specifically, with a backbone of ResNet-18, our detector achieves an F-measure of 82.8, running at 62 FPS, on the MSRA-TD500 dataset.
|
||||
|
|
@ -16,11 +15,12 @@ Recently, segmentation-based methods are quite popular in scene text detection,
|
|||
|
||||
### ICDAR2015
|
||||
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :---------------------------------------: | :-------------------------------------------------: | :-------------: | :------------: | :-----: | :-------: | :----: | :-------: | :---: | :-----------------------------------------: |
|
||||
| [DBNet_r18](/configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py) | ImageNet | ICDAR2015 Train | ICDAR2015 Test | 1200 | 736 | 0.731 | 0.871 | 0.795 | [model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r18_fpnc_sbn_1200e_icdar2015_20210329-ba3ab597.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r18_fpnc_sbn_1200e_icdar2015_20210329-ba3ab597.log.json) |
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :---------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------: | :-------------: | :------------: | :-----: | :-------: | :----: | :-------: | :---: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| [DBNet_r18](/configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py) | ImageNet | ICDAR2015 Train | ICDAR2015 Test | 1200 | 736 | 0.731 | 0.871 | 0.795 | [model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r18_fpnc_sbn_1200e_icdar2015_20210329-ba3ab597.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r18_fpnc_sbn_1200e_icdar2015_20210329-ba3ab597.log.json) |
|
||||
| [DBNet_r50dcn](/configs/textdet/dbnet/dbnet_r50dcnv2_fpnc_1200e_icdar2015.py) | [Synthtext](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_2e_synthtext_20210325-aa96e477.pth) | ICDAR2015 Train | ICDAR2015 Test | 1200 | 1024 | 0.814 | 0.868 | 0.840 | [model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_1200e_icdar2015_20211025-9fe3b590.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_1200e_icdar2015_20211025-9fe3b590.log.json) |
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
|
|
|
|||
|
|
@ -16,9 +16,9 @@ Recently, segmentation-based scene text detection methods have drawn extensive a
|
|||
|
||||
### ICDAR2015
|
||||
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :---------------------------------------: | :-------------------------------------------------: | :-------------: | :------------: | :-----: | :-------: | :----: | :-------: | :---: | :-----------------------------------------: |
|
||||
| [DBNetpp_r50dcn](/configs/textdet/dbnetpp/dbnetpp_r50dcnv2_fpnc_1200e_icdar2015.py) | [Synthtext](/configs/textdet/dbnetpp/dbnetpp_r50dcnv2_fpnc_100k_iter_synthtext.py) ([model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnetpp_r50dcnv2_fpnc_100k_iter_synthtext-20220502-db297554.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnetpp_r50dcnv2_fpnc_100k_iter_synthtext-20220502-db297554.log.json)) | ICDAR2015 Train | ICDAR2015 Test | 1200 | 1024 | 0.822 | 0.901 | 0.860 | [model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnetpp_r50dcnv2_fpnc_1200e_icdar2015-20220502-d7a76fff.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnetpp_r50dcnv2_fpnc_1200e_icdar2015-20220502-d7a76fff.log.json) |
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :---------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------: | :-------------: | :------------: | :-----: | :-------: | :----: | :-------: | :---: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| [DBNetpp_r50dcn](/configs/textdet/dbnetpp/dbnetpp_r50dcnv2_fpnc_1200e_icdar2015.py) | [Synthtext](/configs/textdet/dbnetpp/dbnetpp_r50dcnv2_fpnc_100k_iter_synthtext.py) ([model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnetpp_r50dcnv2_fpnc_100k_iter_synthtext-20220502-db297554.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnetpp_r50dcnv2_fpnc_100k_iter_synthtext-20220502-db297554.log.json))| ICDAR2015 Train | ICDAR2015 Test | 1200 | 1024 | 0.822 | 0.901 | 0.860 | [model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnetpp_r50dcnv2_fpnc_1200e_icdar2015-20220502-d7a76fff.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnetpp_r50dcnv2_fpnc_1200e_icdar2015-20220502-d7a76fff.log.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -5,7 +5,6 @@
|
|||
<!-- [ALGORITHM] -->
|
||||
|
||||
## Abstract
|
||||
|
||||
Arbitrary shape text detection is a challenging task due to the high variety and complexity of scenes texts. In this paper, we propose a novel unified relational reasoning graph network for arbitrary shape text detection. In our method, an innovative local graph bridges a text proposal model via Convolutional Neural Network (CNN) and a deep relational reasoning network via Graph Convolutional Network (GCN), making our network end-to-end trainable. To be concrete, every text instance will be divided into a series of small rectangular components, and the geometry attributes (e.g., height, width, and orientation) of the small components will be estimated by our text proposal model. Given the geometry attributes, the local graph construction model can roughly establish linkages between different text components. For further reasoning and deducing the likelihood of linkages between the component and its neighbors, we adopt a graph-based network to perform deep relational reasoning on local graphs. Experiments on public available datasets demonstrate the state-of-the-art performance of our method.
|
||||
|
||||
<div align=center>
|
||||
|
|
@ -24,6 +23,7 @@ Arbitrary shape text detection is a challenging task due to the high variety and
|
|||
We've upgraded our IoU backend from `Polygon3` to `shapely`. There are some performance differences for some models due to the backends' different logics to handle invalid polygons (more info [here](https://github.com/open-mmlab/mmocr/issues/465)). **New evaluation result is presented in brackets** and new logs will be uploaded soon.
|
||||
```
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
|
|
|
|||
|
|
@ -12,18 +12,19 @@ One of the main challenges for arbitrary-shaped text detection is to design a go
|
|||
<img src="https://user-images.githubusercontent.com/22607038/142791859-1b0ebde4-b151-4c25-ba1b-f354bd8ddc8c.png"/>
|
||||
</div>
|
||||
|
||||
|
||||
## Results and models
|
||||
|
||||
### CTW1500
|
||||
|
||||
| Method | Backbone | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :-------------------------------------------------: | :--------------: | :--------------: | :-----------: | :----------: | :-----: | :---------: | :----: | :-------: | :---: | :----------------------------------------------------: |
|
||||
| Method | Backbone | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :--------------------------------------------------------------------: | :--------------: | :--------------: | :-----------: | :----------: | :-----: | :---------: | :----: | :-------: | :---: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| [FCENet](/configs/textdet/fcenet/fcenet_r50dcnv2_fpn_1500e_ctw1500.py) | ResNet50 + DCNv2 | ImageNet | CTW1500 Train | CTW1500 Test | 1500 | (736, 1080) | 0.828 | 0.875 | 0.851 | [model](https://download.openmmlab.com/mmocr/textdet/fcenet/fcenet_r50dcnv2_fpn_1500e_ctw1500_20211022-e326d7ec.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/fcenet/20210511_181328.log.json) |
|
||||
|
||||
### ICDAR2015
|
||||
|
||||
| Method | Backbone | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :-------------------------------------------------------: | :------: | :--------------: | :----------: | :-------: | :-----: | :----------: | :----: | :-------: | :---: | :---------------------------------------------------------: |
|
||||
| Method | Backbone | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :-----------------------------------------------------------------: | :------: | :--------------: | :----------: | :-------: | :-----: | :----------: | :----: | :-------: | :---: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| [FCENet](/configs/textdet/fcenet/fcenet_r50_fpn_1500e_icdar2015.py) | ResNet50 | ImageNet | IC15 Train | IC15 Test | 1500 | (2260, 2260) | 0.819 | 0.880 | 0.849 | [model](https://download.openmmlab.com/mmocr/textdet/fcenet/fcenet_r50_fpn_1500e_icdar2015_20211022-daefb6ed.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/fcenet/20210601_222655.log.json) |
|
||||
|
||||
## Citation
|
||||
|
|
|
|||
|
|
@ -1,11 +1,9 @@
|
|||
# Mask R-CNN
|
||||
|
||||
> [Mask R-CNN](https://arxiv.org/abs/1703.06870)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
## Abstract
|
||||
|
||||
We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection. Without bells and whistles, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition.
|
||||
|
||||
<div align=center>
|
||||
|
|
@ -16,20 +14,20 @@ We present a conceptually simple, flexible, and general framework for object ins
|
|||
|
||||
### CTW1500
|
||||
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :----------------------------------------------------------: | :--------------: | :-----------: | :----------: | :-----: | :-------: | :----: | :-------: | :---: | :-------------------------------------------------------------: |
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :---------------------------------------------------------------------: | :--------------: | :-----------: | :----------: | :-----: | :-------: | :----: | :-------: | :---: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| [MaskRCNN](/configs/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_ctw1500.py) | ImageNet | CTW1500 Train | CTW1500 Test | 160 | 1600 | 0.753 | 0.712 | 0.732 | [model](https://download.openmmlab.com/mmocr/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_ctw1500_20210219-96497a76.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_ctw1500_20210219-96497a76.log.json) |
|
||||
|
||||
### ICDAR2015
|
||||
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :--------------------------------------------------------: | :--------------: | :-------------: | :------------: | :-----: | :-------: | :----: | :-------: | :---: | :-----------------------------------------------------------: |
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :-----------------------------------------------------------------------: | :--------------: | :-------------: | :------------: | :-----: | :-------: | :----: | :-------: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| [MaskRCNN](/configs/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_icdar2015.py) | ImageNet | ICDAR2015 Train | ICDAR2015 Test | 160 | 1920 | 0.783 | 0.872 | 0.825 | [model](https://download.openmmlab.com/mmocr/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_icdar2015_20210219-8eb340a3.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_icdar2015_20210219-8eb340a3.log.json) |
|
||||
|
||||
### ICDAR2017
|
||||
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :---------------------------------------------------------: | :--------------: | :-------------: | :-----------: | :-----: | :-------: | :----: | :-------: | :---: | :-----------------------------------------------------------: |
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :-----------------------------------------------------------------------: | :--------------: | :-------------: | :-----------: | :-----: | :-------: | :----: | :-------: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| [MaskRCNN](/configs/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_icdar2017.py) | ImageNet | ICDAR2017 Train | ICDAR2017 Val | 160 | 1600 | 0.754 | 0.827 | 0.789 | [model](https://download.openmmlab.com/mmocr/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_icdar2017_20210218-c6ec3ebb.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_icdar2017_20210218-c6ec3ebb.log.json) |
|
||||
|
||||
```{note}
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# PSENet
|
||||
|
||||
> [Shape robust text detection with progressive scale expansion network](https://arxiv.org/abs/1903.12473)
|
||||
>[Shape robust text detection with progressive scale expansion network](https://arxiv.org/abs/1903.12473)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
|
|
@ -12,6 +12,7 @@ Scene text detection has witnessed rapid progress especially with the recent dev
|
|||
<img src="https://user-images.githubusercontent.com/22607038/142795864-9b455b10-8a19-45bb-aeaf-4b733f341afc.png"/>
|
||||
</div>
|
||||
|
||||
|
||||
## Results and models
|
||||
|
||||
### CTW1500
|
||||
|
|
@ -31,6 +32,7 @@ Scene text detection has witnessed rapid progress especially with the recent dev
|
|||
We've upgraded our IoU backend from `Polygon3` to `shapely`. There are some performance differences for some models due to the backends' different logics to handle invalid polygons (more info [here](https://github.com/open-mmlab/mmocr/issues/465)). **New evaluation result is presented in brackets** and new logs will be uploaded soon.
|
||||
```
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Textsnake
|
||||
|
||||
> [TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes](https://arxiv.org/abs/1807.01544)
|
||||
>[TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes](https://arxiv.org/abs/1807.01544)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
|
|
@ -16,9 +16,9 @@ Driven by deep neural networks and large scale datasets, scene text detection me
|
|||
|
||||
### CTW1500
|
||||
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :----------------------------------------------------------: | :--------------: | :-----------: | :----------: | :-----: | :-------: | :----: | :-------: | :---: | :-------------------------------------------------------------: |
|
||||
| [TextSnake](/configs/textdet/textsnake/textsnake_r50_fpn_unet_600e_ctw1500.py) | ImageNet | CTW1500 Train | CTW1500 Test | 1200 | 736 | 0.795 | 0.840 | 0.817 | [model](https://download.openmmlab.com/mmocr/textdet/textsnake/textsnake_r50_fpn_unet_1200e_ctw1500-27f65b64.pth) \| [log](<>) |
|
||||
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
|
||||
| :----------------------------------------------------------------------------: | :--------------: | :-----------: | :----------: | :-----: | :-------: | :----: | :-------: | :---: | :--------------------------------------------------------------------------------------------------------------------------: |
|
||||
| [TextSnake](/configs/textdet/textsnake/textsnake_r50_fpn_unet_600e_ctw1500.py) | ImageNet | CTW1500 Train | CTW1500 Test | 1200 | 736 | 0.795 | 0.840 | 0.817 | [model](https://download.openmmlab.com/mmocr/textdet/textsnake/textsnake_r50_fpn_unet_1200e_ctw1500-27f65b64.pth) \| [log]() |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -1,9 +1,8 @@
|
|||
# ABINet
|
||||
|
||||
> [Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition](https://arxiv.org/abs/2103.06495)
|
||||
>[Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition](https://arxiv.org/abs/2103.06495)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
## Abstract
|
||||
|
||||
Linguistic knowledge is of great benefit to scene text recognition. However, how to effectively model linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language models comes from: 1) implicitly language modeling; 2) unidirectional feature representation; and 3) language model with noise input. Correspondingly, we propose an autonomous, bidirectional and iterative ABINet for scene text recognition. Firstly, the autonomous suggests to block gradient flow between vision and language models to enforce explicitly language modeling. Secondly, a novel bidirectional cloze network (BCN) as the language model is proposed based on bidirectional feature representation. Thirdly, we propose an execution manner of iterative correction for language model which can effectively alleviate the impact of noise input. Additionally, based on the ensemble of iterative predictions, we propose a self-training method which can learn from unlabeled images effectively. Extensive experiments indicate that ABINet has superiority on low-quality images and achieves state-of-the-art results on several mainstream benchmarks. Besides, the ABINet trained with ensemble self-training shows promising improvement in realizing human-level recognition.
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# CRNN
|
||||
|
||||
> [An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition](https://arxiv.org/abs/1507.05717)
|
||||
>[An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition](https://arxiv.org/abs/1507.05717)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
|
|
@ -33,10 +33,10 @@ Image-based sequence recognition has been a long-standing research topic in comp
|
|||
|
||||
## Results and models
|
||||
|
||||
| methods | | Regular Text | | | | Irregular Text | | download |
|
||||
| :------------------------------------------------------: | :----: | :----------: | :--: | :-: | :--: | :------------: | :--: | :-----------------------------------------------------------------------------------------------: |
|
||||
| methods | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 | |
|
||||
| [CRNN](/configs/textrecog/crnn/crnn_academic_dataset.py) | 80.5 | 81.5 | 86.5 | | 54.1 | 59.1 | 55.6 | [model](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_academic-a723a1c5.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/crnn/20210326_111035.log.json) |
|
||||
| methods | | Regular Text | | | | Irregular Text | | download |
|
||||
| :------------------------------------------------------: | :----: | :----------: | :---: | :---: | :---: | :------------: | :---: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| methods | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 |
|
||||
| [CRNN](/configs/textrecog/crnn/crnn_academic_dataset.py) | 80.5 | 81.5 | 86.5 | | 54.1 | 59.1 | 55.6 | [model](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_academic-a723a1c5.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/crnn/20210326_111035.log.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# MASTER
|
||||
|
||||
> [MASTER: Multi-aspect non-local network for scene text recognition](https://arxiv.org/abs/1910.02562)
|
||||
>[MASTER: Multi-aspect non-local network for scene text recognition](https://arxiv.org/abs/1910.02562)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# NRTR
|
||||
|
||||
> [NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition](https://arxiv.org/abs/1806.00926)
|
||||
>[NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition](https://arxiv.org/abs/1806.00926)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,12 @@
|
|||
# RobustScanner
|
||||
|
||||
> [RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition](https://arxiv.org/abs/2007.07542)
|
||||
>[RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition](https://arxiv.org/abs/2007.07542)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
## Abstract
|
||||
|
||||
The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts (e.g., random character sequences) which is unacceptable in most of real application scenarios. In this paper, we first deeply investigate the decoding process of the decoder. We empirically find that a representative character-level sequence decoder utilizes not only context information but also positional information. Contextual information, which the existing approaches heavily rely on, causes the problem of attention drift. To suppress such side-effect, we propose a novel position enhancement branch, and dynamically fuse its outputs with those of the decoder attention module for scene text recognition. Specifically, it contains a position aware module to enable the encoder to output feature vectors encoding their own spatial positions, and an attention module to estimate glimpses using the positional clue (i.e., the current decoding time step) only. The dynamic fusion is conducted for more robust feature via an element-wise gate mechanism. Theoretically, our proposed method, dubbed \\emph{RobustScanner}, decodes individual characters with dynamic ratio between context and positional clues, and utilizes more positional ones when the decoding sequences with scarce context, and thus is robust and practical. Empirically, it has achieved new state-of-the-art results on popular regular and irregular text recognition benchmarks while without much performance drop on contextless benchmarks, validating its robustness in both contextual and contextless application scenarios.
|
||||
The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts (e.g., random character sequences) which is unacceptable in most of real application scenarios. In this paper, we first deeply investigate the decoding process of the decoder. We empirically find that a representative character-level sequence decoder utilizes not only context information but also positional information. Contextual information, which the existing approaches heavily rely on, causes the problem of attention drift. To suppress such side-effect, we propose a novel position enhancement branch, and dynamically fuse its outputs with those of the decoder attention module for scene text recognition. Specifically, it contains a position aware module to enable the encoder to output feature vectors encoding their own spatial positions, and an attention module to estimate glimpses using the positional clue (i.e., the current decoding time step) only. The dynamic fusion is conducted for more robust feature via an element-wise gate mechanism. Theoretically, our proposed method, dubbed \emph{RobustScanner}, decodes individual characters with dynamic ratio between context and positional clues, and utilizes more positional ones when the decoding sequences with scarce context, and thus is robust and practical. Empirically, it has achieved new state-of-the-art results on popular regular and irregular text recognition benchmarks while without much performance drop on contextless benchmarks, validating its robustness in both contextual and contextless application scenarios.
|
||||
|
||||
<div align=center>
|
||||
<img src="https://user-images.githubusercontent.com/22607038/142798010-eee8795e-8cda-4a7f-a81d-ff9c94af58dc.png"/>
|
||||
|
|
@ -16,38 +16,38 @@ The attention-based encoder-decoder framework has recently achieved impressive r
|
|||
|
||||
### Train Dataset
|
||||
|
||||
| trainset | instance_num | repeat_num | source |
|
||||
| :--------: | :----------: | :--------: | :------------------------: |
|
||||
| icdar_2011 | 3567 | 20 | real |
|
||||
| icdar_2013 | 848 | 20 | real |
|
||||
| icdar2015 | 4468 | 20 | real |
|
||||
| coco_text | 42142 | 20 | real |
|
||||
| IIIT5K | 2000 | 20 | real |
|
||||
| SynthText | 2400000 | 1 | synth |
|
||||
| SynthAdd | 1216889 | 1 | synth, 1.6m in [\[1\]](#1) |
|
||||
| Syn90k | 2400000 | 1 | synth |
|
||||
| trainset | instance_num | repeat_num | source |
|
||||
| :--------: | :----------: | :--------: | :----------------------: |
|
||||
| icdar_2011 | 3567 | 20 | real |
|
||||
| icdar_2013 | 848 | 20 | real |
|
||||
| icdar2015 | 4468 | 20 | real |
|
||||
| coco_text | 42142 | 20 | real |
|
||||
| IIIT5K | 2000 | 20 | real |
|
||||
| SynthText | 2400000 | 1 | synth |
|
||||
| SynthAdd | 1216889 | 1 | synth, 1.6m in [[1]](#1) |
|
||||
| Syn90k | 2400000 | 1 | synth |
|
||||
|
||||
### Test Dataset
|
||||
|
||||
| testset | instance_num | type |
|
||||
| :-----: | :----------: | :---------------------------: |
|
||||
| IIIT5K | 3000 | regular |
|
||||
| SVT | 647 | regular |
|
||||
| IC13 | 1015 | regular |
|
||||
| IC15 | 2077 | irregular |
|
||||
| SVTP | 645 | irregular, 639 in [\[1\]](#1) |
|
||||
| CT80 | 288 | irregular |
|
||||
| testset | instance_num | type |
|
||||
| :-----: | :----------: | :-------------------------: |
|
||||
| IIIT5K | 3000 | regular |
|
||||
| SVT | 647 | regular |
|
||||
| IC13 | 1015 | regular |
|
||||
| IC15 | 2077 | irregular |
|
||||
| SVTP | 645 | irregular, 639 in [[1]](#1) |
|
||||
| CT80 | 288 | irregular |
|
||||
|
||||
## Results and Models
|
||||
|
||||
| Methods | GPUs | | Regular Text | | | | Irregular Text | | download |
|
||||
| :------------------------------------------------------------------------: | :--: | :----: | :----------: | :--: | :-: | :--: | :------------: | :--: | :-------------------------------------------------------------------------: |
|
||||
| | | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 | |
|
||||
| [RobustScanner](configs/textrecog/robust_scanner/robustscanner_r31_academic.py) | 16 | 95.1 | 89.2 | 93.1 | | 77.8 | 80.3 | 90.3 | [model](https://download.openmmlab.com/mmocr/textrecog/robustscanner/robustscanner_r31_academic-5f05874f.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/robustscanner/20210401_170932.log.json) |
|
||||
| Methods | GPUs | | Regular Text | | | | Irregular Text | | download |
|
||||
| :-----------------------------------------------------------------------------: | :---: | :----: | :----------: | :---: | :---: | :---: | :------------: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| | | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 |
|
||||
| [RobustScanner](configs/textrecog/robust_scanner/robustscanner_r31_academic.py) | 16 | 95.1 | 89.2 | 93.1 | | 77.8 | 80.3 | 90.3 | [model](https://download.openmmlab.com/mmocr/textrecog/robustscanner/robustscanner_r31_academic-5f05874f.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/robustscanner/20210401_170932.log.json) |
|
||||
|
||||
## References
|
||||
|
||||
<a id="1">\[1\]</a> Li, Hui and Wang, Peng and Shen, Chunhua and Zhang, Guyu. Show, attend and read: A simple and strong baseline for irregular text recognition. In AAAI 2019.
|
||||
<a id="1">[1]</a> Li, Hui and Wang, Peng and Shen, Chunhua and Zhang, Guyu. Show, attend and read: A simple and strong baseline for irregular text recognition. In AAAI 2019.
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -1,5 +1,4 @@
|
|||
# SAR
|
||||
|
||||
> [Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition](https://arxiv.org/abs/1811.00751)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
|
@ -12,31 +11,33 @@ Recognizing irregular text in natural scene images is challenging due to the lar
|
|||
<img src="https://user-images.githubusercontent.com/22607038/142798157-ac68907f-5a8a-473f-a29f-f0532b7fdba0.png"/>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
## Dataset
|
||||
|
||||
### Train Dataset
|
||||
|
||||
| trainset | instance_num | repeat_num | source |
|
||||
| :--------: | :----------: | :--------: | :------------------------: |
|
||||
| icdar_2011 | 3567 | 20 | real |
|
||||
| icdar_2013 | 848 | 20 | real |
|
||||
| icdar2015 | 4468 | 20 | real |
|
||||
| coco_text | 42142 | 20 | real |
|
||||
| IIIT5K | 2000 | 20 | real |
|
||||
| SynthText | 2400000 | 1 | synth |
|
||||
| SynthAdd | 1216889 | 1 | synth, 1.6m in [\[1\]](#1) |
|
||||
| Syn90k | 2400000 | 1 | synth |
|
||||
| trainset | instance_num | repeat_num | source |
|
||||
| :--------: | :----------: | :--------: | :----------------------: |
|
||||
| icdar_2011 | 3567 | 20 | real |
|
||||
| icdar_2013 | 848 | 20 | real |
|
||||
| icdar2015 | 4468 | 20 | real |
|
||||
| coco_text | 42142 | 20 | real |
|
||||
| IIIT5K | 2000 | 20 | real |
|
||||
| SynthText | 2400000 | 1 | synth |
|
||||
| SynthAdd | 1216889 | 1 | synth, 1.6m in [[1]](#1) |
|
||||
| Syn90k | 2400000 | 1 | synth |
|
||||
|
||||
### Test Dataset
|
||||
|
||||
| testset | instance_num | type |
|
||||
| :-----: | :----------: | :---------------------------: |
|
||||
| IIIT5K | 3000 | regular |
|
||||
| SVT | 647 | regular |
|
||||
| IC13 | 1015 | regular |
|
||||
| IC15 | 2077 | irregular |
|
||||
| SVTP | 645 | irregular, 639 in [\[1\]](#1) |
|
||||
| CT80 | 288 | irregular |
|
||||
| testset | instance_num | type |
|
||||
| :-----: | :----------: | :-------------------------: |
|
||||
| IIIT5K | 3000 | regular |
|
||||
| SVT | 647 | regular |
|
||||
| IC13 | 1015 | regular |
|
||||
| IC15 | 2077 | irregular |
|
||||
| SVTP | 645 | irregular, 639 in [[1]](#1) |
|
||||
| CT80 | 288 | irregular |
|
||||
|
||||
## Results and Models
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# SATRN
|
||||
|
||||
> [On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention](https://arxiv.org/abs/1910.04396)
|
||||
>[On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention](https://arxiv.org/abs/1910.04396)
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
|
|
@ -12,6 +12,7 @@ Scene text recognition (STR) is the task of recognizing character sequences in n
|
|||
<img src="https://user-images.githubusercontent.com/22607038/142798828-cc4ded5d-3fb8-478c-9f3e-74edbcf41982.png"/>
|
||||
</div>
|
||||
|
||||
|
||||
## Dataset
|
||||
|
||||
### Train Dataset
|
||||
|
|
@ -34,11 +35,11 @@ Scene text recognition (STR) is the task of recognizing character sequences in n
|
|||
|
||||
## Results and Models
|
||||
|
||||
| Methods | | Regular Text | | | | Irregular Text | | download |
|
||||
| :----------------------------------------------------: | :----: | :----------: | :--: | :-: | :--: | :------------: | :--: | :-------------------------------------------------------------------------------------------------: |
|
||||
| | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 | |
|
||||
| [Satrn](/configs/textrecog/satrn/satrn_academic.py) | 96.1 | 93.5 | 95.7 | | 84.1 | 88.5 | 90.3 | [model](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_academic_20211009-cb8b1580.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/satrn/20210809_093244.log.json) |
|
||||
| [Satrn_small](/configs/textrecog/satrn/satrn_small.py) | 94.7 | 91.3 | 95.4 | | 81.9 | 85.9 | 86.5 | [model](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_small_20211009-2cf13355.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/satrn/20210811_053047.log.json) |
|
||||
| Methods | | Regular Text | | | | Irregular Text | | download |
|
||||
| :----------------------------------------------------: | :----: | :----------: | :---: | :---: | :---: | :------------: | :---: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 |
|
||||
| [Satrn](/configs/textrecog/satrn/satrn_academic.py) | 96.1 | 93.5 | 95.7 | | 84.1 | 88.5 | 90.3 | [model](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_academic_20211009-cb8b1580.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/satrn/20210809_093244.log.json) |
|
||||
| [Satrn_small](/configs/textrecog/satrn/satrn_small.py) | 94.7 | 91.3 | 95.4 | | 81.9 | 85.9 | 86.5 | [model](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_small_20211009-2cf13355.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/satrn/20210811_053047.log.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -1,11 +1,11 @@
|
|||
# SegOCR
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
## Abstract
|
||||
|
||||
Just a simple Seg-based baseline for text recognition tasks.
|
||||
|
||||
|
||||
## Dataset
|
||||
|
||||
### Train Dataset
|
||||
|
|
|
|||
|
|
@ -35,10 +35,10 @@ We use STN from this paper as the preprocessor and CRNN as the recognition netwo
|
|||
|
||||
## Results and models
|
||||
|
||||
| methods | | Regular Text | | | | Irregular Text | | download |
|
||||
| :-------------------------------------------------------------: | :----: | :----------: | :--: | :-: | :--: | :------------: | :--: | :----------------------------------------------------------------------------------------: |
|
||||
| | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 | |
|
||||
| [CRNN-STN](/configs/textrecog/tps/crnn_tps_academic_dataset.py) | 80.8 | 81.3 | 85.0 | | 59.6 | 68.1 | 53.8 | [model](https://download.openmmlab.com/mmocr/textrecog/tps/crnn_tps_academic_dataset_20210510-d221a905.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/tps/20210510_204353.log.json) |
|
||||
| methods | | Regular Text | | | | Irregular Text | | download |
|
||||
| :-------------------------------------------------------------: | :----: | :----------: | :---: | :---: | :---: | :------------: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 |
|
||||
| [CRNN-STN](/configs/textrecog/tps/crnn_tps_academic_dataset.py) | 80.8 | 81.3 | 85.0 | | 59.6 | 68.1 | 53.8 | [model](https://download.openmmlab.com/mmocr/textrecog/tps/crnn_tps_academic_dataset_20210510-d221a905.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/tps/20210510_204353.log.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@ We provide an easy-to-use API for the demo and application purpose in [ocr.py](h
|
|||
The API can be called through command line (CL) or by calling it from another python script.
|
||||
It exposes all the models in MMOCR to API as individual modules that can be called and chained together. [Tesseract](https://tesseract-ocr.github.io/) is integrated as a text detector and/or recognizer in the task pipeline.
|
||||
|
||||
______________________________________________________________________
|
||||
---
|
||||
|
||||
## Example 1: Text Detection
|
||||
|
||||
|
|
@ -95,7 +95,7 @@ ocr = MMOCR()
|
|||
results = ocr.readtext('demo/demo_text_ocr.jpg', print_result=True, imshow=True)
|
||||
```
|
||||
|
||||
______________________________________________________________________
|
||||
---
|
||||
|
||||
## Example 4: Text Detection + Recognition + Key Information Extraction
|
||||
|
||||
|
|
@ -130,7 +130,7 @@ ocr = MMOCR(det='PS_CTW', recog='SAR', kie='SDMGR')
|
|||
results = ocr.readtext('demo/demo_kie.jpeg', print_result=True, imshow=True)
|
||||
```
|
||||
|
||||
______________________________________________________________________
|
||||
---
|
||||
|
||||
## API Arguments
|
||||
|
||||
|
|
@ -142,7 +142,7 @@ The API has an extensive list of arguments that you can use. The following table
|
|||
| -------------- | --------------------- | ---------- | ---------------------------------------------------------------------------------------------------- |
|
||||
| `det` | see [models](#models) | PANet_IC15 | Text detection algorithm |
|
||||
| `recog` | see [models](#models) | SAR | Text recognition algorithm |
|
||||
| `kie` \[1\] | see [models](#models) | None | Key information extraction algorithm |
|
||||
| `kie` [1] | see [models](#models) | None | Key information extraction algorithm |
|
||||
| `config_dir` | str | configs/ | Path to the config directory where all the config files are located |
|
||||
| `det_config` | str | None | Path to the custom config file of the selected det model |
|
||||
| `det_ckpt` | str | None | Path to the custom checkpoint file of the selected det model |
|
||||
|
|
@ -152,7 +152,7 @@ The API has an extensive list of arguments that you can use. The following table
|
|||
| `kie_ckpt` | str | None | Path to the custom checkpoint file of the selected kie model |
|
||||
| `device` | str | None | Device used for inference, accepting all allowed strings by `torch.device`. E.g., 'cuda:0' or 'cpu'. |
|
||||
|
||||
\[1\]: `kie` is only effective when both text detection and recognition models are specified.
|
||||
[1]: `kie` is only effective when both text detection and recognition models are specified.
|
||||
|
||||
```{note}
|
||||
|
||||
|
|
@ -166,7 +166,7 @@ User can use default pretrained models by specifying `det` and/or `recog`, which
|
|||
| ------------------- | ----------------------- | ------------ | ---------------------------------------------------------------------- |
|
||||
| `img` | str/list/tuple/np.array | **required** | img, folder path, np array or list/tuple (with img paths or np arrays) |
|
||||
| `output` | str | None | Output result visualization - img path or folder path |
|
||||
| `batch_mode` | bool | False | Whether use batch mode for inference \[1\] |
|
||||
| `batch_mode` | bool | False | Whether use batch mode for inference [1] |
|
||||
| `det_batch_size` | int | 0 | Batch size for text detection (0 for max size) |
|
||||
| `recog_batch_size` | int | 0 | Batch size for text recognition (0 for max size) |
|
||||
| `single_batch_size` | int | 0 | Batch size for only detection or recognition |
|
||||
|
|
@ -175,12 +175,12 @@ User can use default pretrained models by specifying `det` and/or `recog`, which
|
|||
| `details` | bool | False | Whether include the text boxes coordinates and confidence values |
|
||||
| `imshow` | bool | False | Whether to show the result visualization on screen |
|
||||
| `print_result` | bool | False | Whether to show the result for each image |
|
||||
| `merge` | bool | False | Whether to merge neighboring boxes \[2\] |
|
||||
| `merge` | bool | False | Whether to merge neighboring boxes [2] |
|
||||
| `merge_xdist` | float | 20 | The maximum x-axis distance to merge boxes |
|
||||
|
||||
\[1\]: Make sure that the model is compatible with batch mode.
|
||||
[1]: Make sure that the model is compatible with batch mode.
|
||||
|
||||
\[2\]: Only effective when the script is running in det + recog mode.
|
||||
[2]: Only effective when the script is running in det + recog mode.
|
||||
|
||||
All arguments are the same for the cli, all you need to do is add 2 hyphens at the beginning of the argument and replace underscores by hyphens.
|
||||
(*Example:* `det_batch_size` becomes `--det-batch-size`)
|
||||
|
|
@ -189,7 +189,7 @@ For bool type arguments, putting the argument in the command stores it as true.
|
|||
(*Example:* `python mmocr/utils/ocr.py demo/demo_text_det.jpg --batch_mode --print_result`
|
||||
means that `batch_mode` and `print_result` are set to `True`)
|
||||
|
||||
______________________________________________________________________
|
||||
---
|
||||
|
||||
## Models
|
||||
|
||||
|
|
@ -199,7 +199,7 @@ ______________________________________________________________________
|
|||
| ------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------: |
|
||||
| DB_r18 | [link](https://mmocr.readthedocs.io/en/latest/textdet_models.html#real-time-scene-text-detection-with-differentiable-binarization) | :x: |
|
||||
| DB_r50 | [link](https://mmocr.readthedocs.io/en/latest/textdet_models.html#real-time-scene-text-detection-with-differentiable-binarization) | :x: |
|
||||
| DBPP_r50 | [link](https://mmocr.readthedocs.io/en/latest/textdet_models.html#dbnetpp) | :x: |
|
||||
| DBPP_r50 | [link](https://mmocr.readthedocs.io/en/latest/textdet_models.html#dbnetpp) | :x: |
|
||||
| DRRG | [link](https://mmocr.readthedocs.io/en/latest/textdet_models.html#drrg) | :x: |
|
||||
| FCE_IC15 | [link](https://mmocr.readthedocs.io/en/latest/textdet_models.html#fourier-contour-embedding-for-arbitrary-shaped-text-detection) | :x: |
|
||||
| FCE_CTW_DCNv2 | [link](https://mmocr.readthedocs.io/en/latest/textdet_models.html#fourier-contour-embedding-for-arbitrary-shaped-text-detection) | :x: |
|
||||
|
|
@ -215,21 +215,21 @@ ______________________________________________________________________
|
|||
|
||||
**Text recognition:**
|
||||
|
||||
| Name | Reference | `batch_mode` inference support |
|
||||
| ------------- | :-----------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------: |
|
||||
| ABINet | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#read-like-humans-autonomous-bidirectional-and-iterative-language-modeling-for-scene-text-recognition) | :heavy_check_mark: |
|
||||
| Name | Reference | `batch_mode` inference support |
|
||||
| ------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------: |
|
||||
| ABINet | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#read-like-humans-autonomous-bidirectional-and-iterative-language-modeling-for-scene-text-recognition) | :heavy_check_mark: |
|
||||
| CRNN | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#an-end-to-end-trainable-neural-network-for-image-based-sequence-recognition-and-its-application-to-scene-text-recognition) | :x: |
|
||||
| CRNN_TPS | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#crnn-with-tps-based-stn) | :heavy_check_mark: |
|
||||
| MASTER | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#master) | :heavy_check_mark: |
|
||||
| NRTR_1/16-1/8 | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#nrtr) | :heavy_check_mark: |
|
||||
| NRTR_1/8-1/4 | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#nrtr) | :heavy_check_mark: |
|
||||
| RobustScanner | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#robustscanner-dynamically-enhancing-positional-clues-for-robust-text-recognition) | :heavy_check_mark: |
|
||||
| SAR | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#show-attend-and-read-a-simple-and-strong-baseline-for-irregular-text-recognition) | :heavy_check_mark: |
|
||||
| SAR_CN \* | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#show-attend-and-read-a-simple-and-strong-baseline-for-irregular-text-recognition) | :heavy_check_mark: |
|
||||
| SATRN | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#satrn) | :heavy_check_mark: |
|
||||
| SATRN_sm | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#satrn) | :heavy_check_mark: |
|
||||
| SEG | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#segocr-simple-baseline) | :x: |
|
||||
| Tesseract | [link](https://tesseract-ocr.github.io/) | :x: |
|
||||
| CRNN_TPS | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#crnn-with-tps-based-stn) | :heavy_check_mark: |
|
||||
| MASTER | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#master) | :heavy_check_mark: |
|
||||
| NRTR_1/16-1/8 | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#nrtr) | :heavy_check_mark: |
|
||||
| NRTR_1/8-1/4 | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#nrtr) | :heavy_check_mark: |
|
||||
| RobustScanner | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#robustscanner-dynamically-enhancing-positional-clues-for-robust-text-recognition) | :heavy_check_mark: |
|
||||
| SAR | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#show-attend-and-read-a-simple-and-strong-baseline-for-irregular-text-recognition) | :heavy_check_mark: |
|
||||
| SAR_CN * | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#show-attend-and-read-a-simple-and-strong-baseline-for-irregular-text-recognition) | :heavy_check_mark: |
|
||||
| SATRN | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#satrn) | :heavy_check_mark: |
|
||||
| SATRN_sm | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#satrn) | :heavy_check_mark: |
|
||||
| SEG | [link](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#segocr-simple-baseline) | :x: |
|
||||
| Tesseract | [link](https://tesseract-ocr.github.io/) | :x: |
|
||||
|
||||
```{warning}
|
||||
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ MMOCR 为示例和应用，以 [ocr.py](https://github.com/open-mmlab/mmocr/blob
|
|||
|
||||
该 API 可以通过命令行执行，也可以在 python 脚本内调用。在该 API 里，MMOCR 里的所有模型能以独立模块的形式被调用或串联。它还支持将 [Tesseract](https://tesseract-ocr.github.io/) 作为文字检测或识别的一个组件调用。
|
||||
|
||||
______________________________________________________________________
|
||||
---
|
||||
|
||||
## 案例一：文本检测
|
||||
|
||||
|
|
@ -93,7 +93,7 @@ ocr = MMOCR()
|
|||
results = ocr.readtext('demo/demo_text_ocr.jpg', print_result=True, imshow=True)
|
||||
```
|
||||
|
||||
______________________________________________________________________
|
||||
---
|
||||
|
||||
## 案例 4： 文本检测+识别+关键信息提取
|
||||
|
||||
|
|
@ -128,7 +128,7 @@ ocr = MMOCR(det='PS_CTW', recog='SAR', kie='SDMGR')
|
|||
results = ocr.readtext('demo/demo_kie.jpeg', print_result=True, imshow=True)
|
||||
```
|
||||
|
||||
______________________________________________________________________
|
||||
---
|
||||
|
||||
## API 参数
|
||||
|
||||
|
|
@ -140,7 +140,7 @@ ______________________________________________________________________
|
|||
| -------------- | ------------------ | ---------- | ---------------------------------------------------------------------------------------- |
|
||||
| `det` | 参考 **模型** 章节 | PANet_IC15 | 文本检测算法 |
|
||||
| `recog` | 参考 **模型** 章节 | SAR | 文本识别算法 |
|
||||
| `kie` \[1\] | 参考 **模型** 章节 | None | 关键信息提取算法 |
|
||||
| `kie` [1] | 参考 **模型** 章节 | None | 关键信息提取算法 |
|
||||
| `config_dir` | str | configs/ | 用于存放所有配置文件的文件夹路径 |
|
||||
| `det_config` | str | None | 指定检测模型的自定义配置文件路径 |
|
||||
| `det_ckpt` | str | None | 指定检测模型的自定义参数文件路径 |
|
||||
|
|
@ -150,7 +150,7 @@ ______________________________________________________________________
|
|||
| `kie_ckpt` | str | None | 指定关键信息提取的自定义参数文件路径 |
|
||||
| `device` | str | None | 推理时使用的设备标识, 支持 `torch.device` 所包含的所有设备字符. 例如, 'cuda:0' 或 'cpu'. |
|
||||
|
||||
\[1\]: `kie` 当且仅当同时指定了文本检测和识别模型时才有效。
|
||||
[1]: `kie` 当且仅当同时指定了文本检测和识别模型时才有效。
|
||||
|
||||
```{note}
|
||||
|
||||
|
|
@ -164,7 +164,7 @@ mmocr 为了方便使用提供了预置的模型配置和对应的预训练权
|
|||
| ------------------- | ----------------------- | -------- | --------------------------------------------------------------------- |
|
||||
| `img` | str/list/tuple/np.array | **必填** | 图像，文件夹路径，np array 或 list/tuple （包含图片路径或 np arrays） |
|
||||
| `output` | str | None | 可视化输出结果 - 图片路径或文件夹路径 |
|
||||
| `batch_mode` | bool | False | 是否使用批处理模式推理 \[1\] |
|
||||
| `batch_mode` | bool | False | 是否使用批处理模式推理 [1] |
|
||||
| `det_batch_size` | int | 0 | 文本检测的批处理大小（设置为 0 则与待推理图片个数相同） |
|
||||
| `recog_batch_size` | int | 0 | 文本识别的批处理大小（设置为 0 则与待推理图片个数相同） |
|
||||
| `single_batch_size` | int | 0 | 仅用于检测或识别使用的批处理大小 |
|
||||
|
|
@ -173,12 +173,12 @@ mmocr 为了方便使用提供了预置的模型配置和对应的预训练权
|
|||
| `details` | bool | False | 是否包含文本框的坐标和置信度的值 |
|
||||
| `imshow` | bool | False | 是否在屏幕展示可视化结果 |
|
||||
| `print_result` | bool | False | 是否展示每个图片的结果 |
|
||||
| `merge` | bool | False | 是否对相邻框进行合并 \[2\] |
|
||||
| `merge` | bool | False | 是否对相邻框进行合并 [2] |
|
||||
| `merge_xdist` | float | 20 | 合并相邻框的最大x-轴距离 |
|
||||
|
||||
\[1\]: `batch_mode` 需确保模型兼容批处理模式（见下表模型是否支持批处理）。
|
||||
[1]: `batch_mode` 需确保模型兼容批处理模式（见下表模型是否支持批处理）。
|
||||
|
||||
\[2\]: `merge` 只有同时运行检测+识别模式，参数才有效。
|
||||
[2]: `merge` 只有同时运行检测+识别模式，参数才有效。
|
||||
|
||||
以上所有参数在命令行同样适用，只需要在参数前简单添加两个连接符，并且将下参数中的下划线替换为连接符即可。
|
||||
（*例如：* `det_batch_size` 变成了 `--det-batch-size`）
|
||||
|
|
@ -186,7 +186,7 @@ mmocr 为了方便使用提供了预置的模型配置和对应的预训练权
|
|||
对于布尔类型参数，添加在命令中默认为true。
|
||||
（*例如：* `python mmocr/utils/ocr.py demo/demo_text_det.jpg --batch_mode --print_result` 意为 `batch_mode` 和 `print_result` 的参数值设置为 `True`）
|
||||
|
||||
______________________________________________________________________
|
||||
---
|
||||
|
||||
## 模型
|
||||
|
||||
|
|
@ -196,7 +196,7 @@ ______________________________________________________________________
|
|||
| ------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------: |
|
||||
| DB_r18 | [链接](https://mmocr.readthedocs.io/en/latest/textdet_models.html#real-time-scene-text-detection-with-differentiable-binarization) | :x: |
|
||||
| DB_r50 | [链接](https://mmocr.readthedocs.io/en/latest/textdet_models.html#real-time-scene-text-detection-with-differentiable-binarization) | :x: |
|
||||
| DBPP_r50 | [链接](https://mmocr.readthedocs.io/en/latest/textdet_models.html#dbnetpp) | :x: |
|
||||
| DBPP_r50 | [链接](https://mmocr.readthedocs.io/en/latest/textdet_models.html#dbnetpp) | :x: |
|
||||
| DRRG | [链接](https://mmocr.readthedocs.io/en/latest/textdet_models.html#drrg) | :x: |
|
||||
| FCE_IC15 | [链接](https://mmocr.readthedocs.io/en/latest/textdet_models.html#fourier-contour-embedding-for-arbitrary-shaped-text-detection) | :x: |
|
||||
| FCE_CTW_DCNv2 | [链接](https://mmocr.readthedocs.io/en/latest/textdet_models.html#fourier-contour-embedding-for-arbitrary-shaped-text-detection) | :x: |
|
||||
|
|
@ -212,21 +212,21 @@ ______________________________________________________________________
|
|||
|
||||
**文本识别：**
|
||||
|
||||
| 名称 | 引用 | `batch_mode` 推理支持 |
|
||||
| ------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------: |
|
||||
| ABINet | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#read-like-humans-autonomous-bidirectional-and-iterative-language-modeling-for-scene-text-recognition) | :heavy_check_mark: |
|
||||
| 名称 | 引用 | `batch_mode` 推理支持 |
|
||||
| ------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------: |
|
||||
| ABINet | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#read-like-humans-autonomous-bidirectional-and-iterative-language-modeling-for-scene-text-recognition) | :heavy_check_mark: |
|
||||
| CRNN | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#an-end-to-end-trainable-neural-network-for-image-based-sequence-recognition-and-its-application-to-scene-text-recognition) | :x: |
|
||||
| CRNN_TPS | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#crnn-with-tps-based-stn) | :heavy_check_mark: |
|
||||
| MASTER | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#master) | :heavy_check_mark: |
|
||||
| NRTR_1/16-1/8 | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#nrtr) | :heavy_check_mark: |
|
||||
| NRTR_1/8-1/4 | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#nrtr) | :heavy_check_mark: |
|
||||
| RobustScanner | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#robustscanner-dynamically-enhancing-positional-clues-for-robust-text-recognition) | :heavy_check_mark: |
|
||||
| SAR | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#show-attend-and-read-a-simple-and-strong-baseline-for-irregular-text-recognition) | :heavy_check_mark: |
|
||||
| SAR_CN \* | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#show-attend-and-read-a-simple-and-strong-baseline-for-irregular-text-recognition) | :heavy_check_mark: |
|
||||
| SATRN | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#satrn) | :heavy_check_mark: |
|
||||
| SATRN_sm | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#satrn) | :heavy_check_mark: |
|
||||
| SEG | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#segocr-simple-baseline) | :x: |
|
||||
| Tesseract | [链接](https://tesseract-ocr.github.io/) | :heavy_check_mark: |
|
||||
| CRNN_TPS | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#crnn-with-tps-based-stn) | :heavy_check_mark: |
|
||||
| MASTER | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#master) | :heavy_check_mark: |
|
||||
| NRTR_1/16-1/8 | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#nrtr) | :heavy_check_mark: |
|
||||
| NRTR_1/8-1/4 | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#nrtr) | :heavy_check_mark: |
|
||||
| RobustScanner | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#robustscanner-dynamically-enhancing-positional-clues-for-robust-text-recognition) | :heavy_check_mark: |
|
||||
| SAR | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#show-attend-and-read-a-simple-and-strong-baseline-for-irregular-text-recognition) | :heavy_check_mark: |
|
||||
| SAR_CN * | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#show-attend-and-read-a-simple-and-strong-baseline-for-irregular-text-recognition) | :heavy_check_mark: |
|
||||
| SATRN | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#satrn) | :heavy_check_mark: |
|
||||
| SATRN_sm | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#satrn) | :heavy_check_mark: |
|
||||
| SEG | [链接](https://mmocr.readthedocs.io/en/latest/textrecog_models.html#segocr-simple-baseline) | :x: |
|
||||
| Tesseract | [链接](https://tesseract-ocr.github.io/) | :heavy_check_mark: |
|
||||
|
||||
```{note}
|
||||
|
||||
|
|
|
|||
|
|
@ -11374,4 +11374,4 @@ z
|
|||
～
|
||||
￥
|
||||
𡒄
|
||||
𨱏
|
||||
𨱏
|
||||
|
|
@ -87,4 +87,4 @@ $
|
|||
]
|
||||
_
|
||||
`
|
||||
~
|
||||
~
|
||||
|
|
@ -88,3 +88,4 @@ $
|
|||
_
|
||||
`
|
||||
~
|
||||
|
||||
|
|
@ -33,4 +33,4 @@ v
|
|||
w
|
||||
x
|
||||
y
|
||||
z
|
||||
z
|
||||
|
|
@ -34,3 +34,4 @@ w
|
|||
x
|
||||
y
|
||||
z
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -14,22 +14,22 @@ appearance, race, religion, or sexual identity and orientation.
|
|||
Examples of behavior that contributes to creating a positive environment
|
||||
include:
|
||||
|
||||
- Using welcoming and inclusive language
|
||||
- Being respectful of differing viewpoints and experiences
|
||||
- Gracefully accepting constructive criticism
|
||||
- Focusing on what is best for the community
|
||||
- Showing empathy towards other community members
|
||||
* Using welcoming and inclusive language
|
||||
* Being respectful of differing viewpoints and experiences
|
||||
* Gracefully accepting constructive criticism
|
||||
* Focusing on what is best for the community
|
||||
* Showing empathy towards other community members
|
||||
|
||||
Examples of unacceptable behavior by participants include:
|
||||
|
||||
- The use of sexualized language or imagery and unwelcome sexual attention or
|
||||
advances
|
||||
- Trolling, insulting/derogatory comments, and personal or political attacks
|
||||
- Public or private harassment
|
||||
- Publishing others' private information, such as a physical or electronic
|
||||
address, without explicit permission
|
||||
- Other conduct which could reasonably be considered inappropriate in a
|
||||
professional setting
|
||||
* The use of sexualized language or imagery and unwelcome sexual attention or
|
||||
advances
|
||||
* Trolling, insulting/derogatory comments, and personal or political attacks
|
||||
* Public or private harassment
|
||||
* Publishing others' private information, such as a physical or electronic
|
||||
address, without explicit permission
|
||||
* Other conduct which could reasonably be considered inappropriate in a
|
||||
professional setting
|
||||
|
||||
## Our Responsibilities
|
||||
|
||||
|
|
@ -70,7 +70,7 @@ members of the project's leadership.
|
|||
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
||||
available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
|
||||
|
||||
[homepage]: https://www.contributor-covenant.org
|
||||
|
||||
For answers to common questions about this code of conduct, see
|
||||
https://www.contributor-covenant.org/faq
|
||||
|
||||
[homepage]: https://www.contributor-covenant.org
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
|
||||
# Text Detection
|
||||
|
||||
## Overview
|
||||
|
|
@ -61,7 +62,6 @@ inconsistency results in false examples in the training set. Therefore, users sh
|
|||
## 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
|
||||
|
|
@ -180,9 +180,7 @@ inconsistency results in false examples in the training set. Therefore, users sh
|
|||
## ICDAR 2015
|
||||
|
||||
- Step0: Read [Important Note](#important-note)
|
||||
|
||||
- Step1: Download `ch4_training_images.zip`, `ch4_test_images.zip`, `ch4_training_localization_transcription_gt.zip`, `Challenge4_Test_Task1_GT.zip` from [homepage](https://rrc.cvc.uab.es/?ch=4&com=downloads)
|
||||
|
||||
- Step2:
|
||||
|
||||
```bash
|
||||
|
|
@ -197,7 +195,6 @@ inconsistency results in false examples in the training set. Therefore, users sh
|
|||
```
|
||||
|
||||
- Step3: 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) and move them to `icdar2015`
|
||||
|
||||
- Or, generate `instances_training.json` and `instances_test.json` with the following command:
|
||||
|
||||
```bash
|
||||
|
|
@ -217,7 +214,6 @@ inconsistency results in false examples in the training set. Therefore, users sh
|
|||
## ICDAR 2017
|
||||
|
||||
- Follow similar steps as [ICDAR 2015](#icdar-2015).
|
||||
|
||||
- The resulting directory structure looks like the following:
|
||||
|
||||
```text
|
||||
|
|
@ -230,7 +226,7 @@ inconsistency results in false examples in the training set. Therefore, users sh
|
|||
|
||||
## SynthText
|
||||
|
||||
- Step1: Download SynthText.zip from \[homepage\](<https://www.robots.ox.ac.uk/~vgg/data/scenetext/> and extract its content to `synthtext/img`.
|
||||
- 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/`.
|
||||
|
||||
|
|
@ -279,7 +275,6 @@ inconsistency results in false examples in the training set. Therefore, users sh
|
|||
## Totaltext
|
||||
|
||||
- Step0: Read [Important Note](#important-note)
|
||||
|
||||
- Step1: Download `totaltext.zip` from [github dataset](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Dataset) and `groundtruth_text.zip` or `TT_new_train_GT.zip` (if you prefer to use the latest version of training annotations) from [github Groundtruth](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Groundtruth/Text) (Our totaltext_converter.py supports groundtruth with both .mat and .txt format).
|
||||
|
||||
```bash
|
||||
|
|
@ -322,7 +317,6 @@ inconsistency results in false examples in the training set. Therefore, users sh
|
|||
## 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/`.
|
||||
|
||||
- Step2:
|
||||
|
||||
```bash
|
||||
|
|
@ -338,7 +332,6 @@ inconsistency results in false examples in the training set. Therefore, users sh
|
|||
```
|
||||
|
||||
- Step3: Download [instances_training.json](https://download.openmmlab.com/mmocr/data/curvedsyntext/instances_training.json) to `CurvedSynText150k/`
|
||||
|
||||
- Or, generate `instances_training.json` with following command:
|
||||
|
||||
```bash
|
||||
|
|
@ -902,7 +895,6 @@ inconsistency results in false examples in the training set. Therefore, users sh
|
|||
## HierText
|
||||
|
||||
- Step1 (optional): Install [AWS CLI](https://mmocr.readthedocs.io/en/latest/datasets/det.html#install-aws-cli-optional).
|
||||
|
||||
- Step2: Clone [HierText](https://github.com/google-research-datasets/hiertext) repo to get annotations
|
||||
|
||||
```bash
|
||||
|
|
|
|||
|
|
@ -25,7 +25,6 @@ The structure of the key information extraction dataset directory is organized a
|
|||
|
||||
- Step0: have [WildReceipt](#WildReceipt) prepared.
|
||||
- Step1: Convert annotation files to OpenSet format:
|
||||
|
||||
```bash
|
||||
# You may find more available arguments by running
|
||||
# python tools/data/kie/closeset_to_openset.py -h
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@
|
|||
| HierText | [homepage](https://github.com/google-research-datasets/hiertext) | - | - |
|
||||
| ArT | [homepage](https://rrc.cvc.uab.es/?ch=14) | - | - |
|
||||
|
||||
(\*) Since the official homepage is unavailable now, we provide an alternative for quick reference. However, we do not guarantee the correctness of the dataset.
|
||||
(*) Since the official homepage is unavailable now, we provide an alternative for quick reference. However, we do not guarantee the correctness of the dataset.
|
||||
|
||||
### Install AWS CLI (optional)
|
||||
|
||||
|
|
@ -132,14 +132,12 @@
|
|||
│ └── test_label.jsonl
|
||||
```
|
||||
|
||||
## ICDAR 2013 \[Deprecated\]
|
||||
## ICDAR 2013 [Deprecated]
|
||||
|
||||
- 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)
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── icdar_2013
|
||||
|
|
@ -153,11 +151,9 @@
|
|||
## ICDAR 2015
|
||||
|
||||
- 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)
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── icdar_2015
|
||||
|
|
@ -170,11 +166,9 @@
|
|||
## IIIT5K
|
||||
|
||||
- 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)
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── III5K
|
||||
|
|
@ -187,9 +181,7 @@
|
|||
## svt
|
||||
|
||||
- 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)
|
||||
|
||||
- Step3:
|
||||
|
||||
```bash
|
||||
|
|
@ -197,7 +189,7 @@
|
|||
```
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── svt
|
||||
|
|
@ -224,7 +216,7 @@
|
|||
```
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── ct80
|
||||
|
|
@ -235,9 +227,8 @@
|
|||
## svtp
|
||||
|
||||
- Step1: Download [test_label.txt](https://download.openmmlab.com/mmocr/data/mixture/svtp/test_label.txt)
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── svtp
|
||||
|
|
@ -248,11 +239,9 @@
|
|||
## coco_text
|
||||
|
||||
- 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)
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── coco_text
|
||||
|
|
@ -263,7 +252,6 @@
|
|||
## MJSynth (Syn90k)
|
||||
|
||||
- Step1: Download `mjsynth.tar.gz` from [homepage](https://www.robots.ox.ac.uk/~vgg/data/text/)
|
||||
|
||||
- Step2: Download [label.txt](https://download.openmmlab.com/mmocr/data/mixture/Syn90k/label.txt) (8,919,273 annotations) and [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/Syn90k/shuffle_labels.txt) (2,400,000 randomly sampled annotations).
|
||||
|
||||
```{note}
|
||||
|
|
@ -293,7 +281,7 @@ Please make sure you're using the right annotation to train the model by checkin
|
|||
```
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── Syn90k
|
||||
|
|
@ -344,7 +332,7 @@ Please make sure you're using the right annotation to train the model by checkin
|
|||
```
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── SynthText
|
||||
|
|
@ -359,9 +347,7 @@ Please make sure you're using the right annotation to train the model by checkin
|
|||
## SynthAdd
|
||||
|
||||
- Step1: Download `SynthText_Add.zip` from [SynthAdd](https://pan.baidu.com/s/1uV0LtoNmcxbO-0YA7Ch4dg) (code:627x))
|
||||
|
||||
- Step2: Download [label.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthAdd/label.txt)
|
||||
|
||||
- Step3:
|
||||
|
||||
```bash
|
||||
|
|
@ -384,7 +370,7 @@ Please make sure you're using the right annotation to train the model by checkin
|
|||
```
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── SynthAdd
|
||||
|
|
@ -432,7 +418,7 @@ python tools/data/utils/lmdb_converter.py data/mixture/Syn90k/label.txt data/mix
|
|||
```
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── TextOCR
|
||||
|
|
@ -484,7 +470,6 @@ python tools/data/utils/lmdb_converter.py data/mixture/Syn90k/label.txt data/mix
|
|||
## OpenVINO
|
||||
|
||||
- Step1 (optional): Install [AWS CLI](https://mmocr.readthedocs.io/en/latest/datasets/recog.html#install-aws-cli-optional).
|
||||
|
||||
- Step2: Download [Open Images](https://github.com/cvdfoundation/open-images-dataset#download-images-with-bounding-boxes-annotations) subsets `train_1`, `train_2`, `train_5`, `train_f`, and `validation` to `openvino/`.
|
||||
|
||||
```bash
|
||||
|
|
@ -517,7 +502,7 @@ python tools/data/utils/lmdb_converter.py data/mixture/Syn90k/label.txt data/mix
|
|||
```
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── OpenVINO
|
||||
|
|
@ -600,8 +585,6 @@ python tools/data/utils/lmdb_converter.py data/mixture/Syn90k/label.txt data/mix
|
|||
# vertical images will be filtered and stored in PATH/TO/naf/ignores
|
||||
python tools/data/textrecog/naf_converter.py PATH/TO/naf --nproc 4
|
||||
|
||||
```
|
||||
|
||||
- After running the above codes, the directory structure should be as follows:
|
||||
|
||||
```text
|
||||
|
|
@ -758,7 +741,7 @@ The LV dataset has already provided cropped images and the corresponding annotat
|
|||
```
|
||||
|
||||
- After running the above codes, the directory structure
|
||||
should be as follows:
|
||||
should be as follows:
|
||||
|
||||
```text
|
||||
├── funsd
|
||||
|
|
@ -1103,7 +1086,6 @@ The LV dataset has already provided cropped images and the corresponding annotat
|
|||
## HierText
|
||||
|
||||
- Step1 (optional): Install [AWS CLI](https://mmocr.readthedocs.io/en/latest/datasets/recog.html#install-aws-cli-optional).
|
||||
|
||||
- Step2: Clone [HierText](https://github.com/google-research-datasets/hiertext) repo to get annotations
|
||||
|
||||
```bash
|
||||
|
|
|
|||
|
|
@ -64,6 +64,7 @@ The table below lists the models that are guaranteed to be exportable to ONNX an
|
|||
|
||||
We also provide a script to convert [ONNX](https://github.com/onnx/onnx) model to [TensorRT](https://github.com/NVIDIA/TensorRT) format. Besides, we support comparing the output results between ONNX and TensorRT model.
|
||||
|
||||
|
||||
```bash
|
||||
python tools/deployment/onnx2tensorrt.py
|
||||
${MODEL_CONFIG_PATH} \
|
||||
|
|
@ -125,7 +126,6 @@ The table below lists the models that are guaranteed to be exportable to TensorR
|
|||
We provide methods to evaluate TensorRT and ONNX models in `tools/deployment/deploy_test.py`.
|
||||
|
||||
### Prerequisite
|
||||
|
||||
To evaluate ONNX and TensorRT models, ONNX, ONNXRuntime and TensorRT should be installed first. Install `mmcv-full` with ONNXRuntime custom ops and TensorRT plugins follow [ONNXRuntime in mmcv](https://mmcv.readthedocs.io/en/latest/onnxruntime_op.html) and [TensorRT plugin in mmcv](https://github.com/open-mmlab/mmcv/blob/master/docs/tensorrt_plugin.md).
|
||||
|
||||
### Usage
|
||||
|
|
@ -153,6 +153,7 @@ python tools/deploy_test.py \
|
|||
|
||||
## Results and Models
|
||||
|
||||
|
||||
<table class="tg">
|
||||
<thead>
|
||||
<tr>
|
||||
|
|
@ -308,7 +309,6 @@ python tools/deploy_test.py \
|
|||
```
|
||||
|
||||
## C++ Inference example with OpenCV
|
||||
|
||||
The example below is tested with Visual Studio 2019 as console application, CPU inference only.
|
||||
|
||||
### Prerequisites
|
||||
|
|
@ -332,7 +332,6 @@ Be sure, that verifications of both models are successful - look through the exp
|
|||
```
|
||||
|
||||
### Example
|
||||
|
||||
Example usage of exported models with C++ is in the code below (don't forget to change paths to \*.onnx files). It's applicable to these two models only, other models have another preprocessing and postprocessing logics.
|
||||
|
||||
```C++
|
||||
|
|
@ -547,7 +546,6 @@ int main(int argc, const char* argv[]) {
|
|||
```
|
||||
|
||||
The output should look something like this.
|
||||
|
||||
```
|
||||
Loading models...
|
||||
Loading models done in 5715 ms
|
||||
|
|
|
|||
|
|
@ -27,13 +27,11 @@ Its detection result will be printed out and a new window will pop up with resul
|
|||
We provide a toy dataset under `tests/data` on which you can get a sense of training before the academic dataset is prepared.
|
||||
|
||||
For example, to train a text recognition task with `seg` method and toy dataset,
|
||||
|
||||
```shell
|
||||
python tools/train.py configs/textrecog/seg/seg_r31_1by16_fpnocr_toy_dataset.py --work-dir seg
|
||||
```
|
||||
|
||||
To train a text recognition task with `sar` method and toy dataset,
|
||||
|
||||
```shell
|
||||
python tools/train.py configs/textrecog/sar/sar_r31_parallel_decoder_toy_dataset.py --work-dir sar
|
||||
```
|
||||
|
|
@ -41,7 +39,6 @@ python tools/train.py configs/textrecog/sar/sar_r31_parallel_decoder_toy_dataset
|
|||
### Training with Academic Dataset
|
||||
|
||||
Once you have prepared required academic dataset following our instruction, the only last thing to check is if the model's config points MMOCR to the correct dataset path. Suppose we want to train DBNet on ICDAR 2015, and part of `configs/_base_/det_datasets/icdar2015.py` looks like the following:
|
||||
|
||||
```python
|
||||
dataset_type = 'IcdarDataset'
|
||||
data_root = 'data/icdar2015'
|
||||
|
|
@ -58,9 +55,7 @@ test = dict(
|
|||
train_list = [train]
|
||||
test_list = [test]
|
||||
```
|
||||
|
||||
You would need to check if `data/icdar2015` is right. Then you can start training with the command:
|
||||
|
||||
```shell
|
||||
python tools/train.py configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py --work-dir dbnet
|
||||
```
|
||||
|
|
@ -70,13 +65,11 @@ You can find full training instructions, explanations and useful training config
|
|||
## Testing
|
||||
|
||||
Suppose now you have finished the training of DBNet and the latest model has been saved in `dbnet/latest.pth`. You can evaluate its performance on the test set using the `hmean-iou` metric with the following command:
|
||||
|
||||
```shell
|
||||
python tools/test.py configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py dbnet/latest.pth --eval hmean-iou
|
||||
```
|
||||
|
||||
Evaluating any pretrained model accessible online is also allowed:
|
||||
|
||||
```shell
|
||||
python tools/test.py configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r18_fpnc_sbn_1200e_icdar2015_20210329-ba3ab597.pth --eval hmean-iou
|
||||
```
|
||||
|
|
|
|||
|
|
@ -14,16 +14,16 @@
|
|||
|
||||
MMOCR has different version requirements on MMCV and MMDetection at each release to guarantee the implementation correctness. Please refer to the table below and ensure the package versions fit the requirement.
|
||||
|
||||
| MMOCR | MMCV | MMDetection |
|
||||
| ------------ | ------------------------ | --------------------------- |
|
||||
| main | 1.3.8 \<= mmcv \<= 1.6.0 | 2.21.0 \<= mmdet \<= 3.0.0 |
|
||||
| 0.6.0 | 1.3.8 \<= mmcv \<= 1.6.0 | 2.21.0 \<= mmdet \<= 3.0.0 |
|
||||
| 0.5.0 | 1.3.8 \<= mmcv \<= 1.5.0 | 2.14.0 \<= mmdet \<= 3.0.0 |
|
||||
| 0.4.0, 0.4.1 | 1.3.8 \<= mmcv \<= 1.5.0 | 2.14.0 \<= mmdet \<= 2.20.0 |
|
||||
| 0.3.0 | 1.3.8 \<= mmcv \<= 1.4.0 | 2.14.0 \<= mmdet \<= 2.20.0 |
|
||||
| 0.2.1 | 1.3.8 \<= mmcv \<= 1.4.0 | 2.13.0 \<= mmdet \<= 2.20.0 |
|
||||
| 0.2.0 | 1.3.4 \<= mmcv \<= 1.4.0 | 2.11.0 \<= mmdet \<= 2.13.0 |
|
||||
| 0.1.0 | 1.2.6 \<= mmcv \<= 1.3.4 | 2.9.0 \<= mmdet \<= 2.11.0 |
|
||||
| MMOCR | MMCV | MMDetection |
|
||||
| ------------ | ---------------------- | ------------------------- |
|
||||
| main | 1.3.8 <= mmcv <= 1.6.0 | 2.21.0 <= mmdet <= 3.0.0 |
|
||||
| 0.6.0 | 1.3.8 <= mmcv <= 1.6.0 | 2.21.0 <= mmdet <= 3.0.0 |
|
||||
| 0.5.0 | 1.3.8 <= mmcv <= 1.5.0 | 2.14.0 <= mmdet <= 3.0.0 |
|
||||
| 0.4.0, 0.4.1 | 1.3.8 <= mmcv <= 1.5.0 | 2.14.0 <= mmdet <= 2.20.0 |
|
||||
| 0.3.0 | 1.3.8 <= mmcv <= 1.4.0 | 2.14.0 <= mmdet <= 2.20.0 |
|
||||
| 0.2.1 | 1.3.8 <= mmcv <= 1.4.0 | 2.13.0 <= mmdet <= 2.20.0 |
|
||||
| 0.2.0 | 1.3.4 <= mmcv <= 1.4.0 | 2.11.0 <= mmdet <= 2.13.0 |
|
||||
| 0.1.0 | 1.2.6 <= mmcv <= 1.3.4 | 2.9.0 <= mmdet <= 2.11.0 |
|
||||
|
||||
We have tested the following versions of OS and software:
|
||||
|
||||
|
|
@ -63,7 +63,7 @@ c. Install [mmcv](https://github.com/open-mmlab/mmcv), we recommend you to insta
|
|||
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/{cu_version}/{torch_version}/index.html
|
||||
```
|
||||
|
||||
Please replace `{cu_version}` and `{torch_version}` in the url with your desired one. For example, to install the latest `mmcv-full` with CUDA 11 and PyTorch 1.7.0, use the following command:
|
||||
Please replace ``{cu_version}`` and ``{torch_version}`` in the url with your desired one. For example, to install the latest ``mmcv-full`` with CUDA 11 and PyTorch 1.7.0, use the following command:
|
||||
|
||||
```shell
|
||||
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu110/torch1.7.0/index.html
|
||||
|
|
@ -126,7 +126,7 @@ We recommend checking the environment after installing `albumentations` to
|
|||
ensure that `opencv-python` and `opencv-python-headless` are not installed together, otherwise it might cause unexpected issues. If that's unfortunately the case, please uninstall `opencv-python-headless` to make sure MMOCR's visualization utilities can work.
|
||||
|
||||
Refer
|
||||
to ['albumentations\`'s official documentation](https://albumentations.ai/docs/getting_started/installation/#note-on-opencv-dependencies) for more details.
|
||||
to ['albumentations`'s official documentation](https://albumentations.ai/docs/getting_started/installation/#note-on-opencv-dependencies) for more details.
|
||||
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -50,11 +50,11 @@ Then you can access inference, management and metrics services
|
|||
through TorchServe's REST API.
|
||||
You can find their usages in [TorchServe REST API](https://github.com/pytorch/serve/blob/master/docs/rest_api.md).
|
||||
|
||||
| Service | Address |
|
||||
| ---------- | ----------------------- |
|
||||
| Inference | `http://127.0.0.1:8080` |
|
||||
| Service | Address |
|
||||
| ------------------- | ----------------------- |
|
||||
| Inference | `http://127.0.0.1:8080` |
|
||||
| Management | `http://127.0.0.1:8081` |
|
||||
| Metrics | `http://127.0.0.1:8082` |
|
||||
| Metrics | `http://127.0.0.1:8082` |
|
||||
|
||||
````{note}
|
||||
By default, TorchServe binds port number `8080`, `8081` and `8082` to its services.
|
||||
|
|
@ -71,6 +71,7 @@ model_store=/home/model-server/model-store
|
|||
|
||||
````
|
||||
|
||||
|
||||
### From Docker
|
||||
|
||||
A better alternative to serve your models is through Docker. We provide a Dockerfile
|
||||
|
|
@ -108,11 +109,13 @@ Upon running the docker, you can access inference, management and metrics servic
|
|||
through TorchServe's REST API.
|
||||
You can find their usages in [TorchServe REST API](https://github.com/pytorch/serve/blob/master/docs/rest_api.md).
|
||||
|
||||
| Service | Address |
|
||||
| ---------- | ----------------------- |
|
||||
| Inference | `http://127.0.0.1:8080` |
|
||||
| Service | Address |
|
||||
| ------------------- | ----------------------- |
|
||||
| Inference | `http://127.0.0.1:8080` |
|
||||
| Management | `http://127.0.0.1:8081` |
|
||||
| Metrics | `http://127.0.0.1:8082` |
|
||||
| Metrics | `http://127.0.0.1:8082` |
|
||||
|
||||
|
||||
|
||||
## 4. Test deployment
|
||||
|
||||
|
|
|
|||
|
|
@ -25,21 +25,21 @@ CUDA_VISIBLE_DEVICES= python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [AR
|
|||
|
||||
````
|
||||
|
||||
| ARGS | Type | Description |
|
||||
| ------------------ | -------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| `--out` | str | Output result file in pickle format. |
|
||||
| `--fuse-conv-bn` | bool | Path to the custom config of the selected det model. |
|
||||
| `--format-only` | bool | Format the output results without performing evaluation. It is useful when you want to format the results to a specific format and submit them to the test server. |
|
||||
| `--gpu-id` | int | GPU id to use. Only applicable to non-distributed training. |
|
||||
| `--eval` | 'hmean-ic13', 'hmean-iou', 'acc', 'macro-f1' | The evaluation metrics. Options: 'hmean-ic13', 'hmean-iou' for text detection tasks, 'acc' for text recognition tasks, and 'macro-f1' for key information extraction tasks. |
|
||||
| `--show` | bool | Whether to show results. |
|
||||
| `--show-dir` | str | Directory where the output images will be saved. |
|
||||
| `--show-score-thr` | float | Score threshold (default: 0.3). |
|
||||
| `--gpu-collect` | bool | Whether to use gpu to collect results. |
|
||||
| `--tmpdir` | str | The tmp directory used for collecting results from multiple workers, available when gpu-collect is not specified. |
|
||||
| `--cfg-options` | str | Override some settings in the used config, the key-value pair in xxx=yyy format will be merged into the config file. If the value to be overwritten is a list, it should be of the form of either key="\[a,b\]" or key=a,b. The argument also allows nested list/tuple values, e.g. key="\[(a,b),(c,d)\]". Note that the quotation marks are necessary and that no white space is allowed. |
|
||||
| `--eval-options` | str | Custom options for evaluation, the key-value pair in xxx=yyy format will be kwargs for dataset.evaluate() function. |
|
||||
| `--launcher` | 'none', 'pytorch', 'slurm', 'mpi' | Options for job launcher. |
|
||||
| ARGS | Type | Description |
|
||||
| ------------------ | -------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `--out` | str | Output result file in pickle format. |
|
||||
| `--fuse-conv-bn` | bool | Path to the custom config of the selected det model. |
|
||||
| `--format-only` | bool | Format the output results without performing evaluation. It is useful when you want to format the results to a specific format and submit them to the test server. |
|
||||
| `--gpu-id` | int | GPU id to use. Only applicable to non-distributed training. |
|
||||
| `--eval` | 'hmean-ic13', 'hmean-iou', 'acc', 'macro-f1' | The evaluation metrics. Options: 'hmean-ic13', 'hmean-iou' for text detection tasks, 'acc' for text recognition tasks, and 'macro-f1' for key information extraction tasks. |
|
||||
| `--show` | bool | Whether to show results. |
|
||||
| `--show-dir` | str | Directory where the output images will be saved. |
|
||||
| `--show-score-thr` | float | Score threshold (default: 0.3). |
|
||||
| `--gpu-collect` | bool | Whether to use gpu to collect results. |
|
||||
| `--tmpdir` | str | The tmp directory used for collecting results from multiple workers, available when gpu-collect is not specified. |
|
||||
| `--cfg-options` | str | Override some settings in the used config, the key-value pair in xxx=yyy format will be merged into the config file. If the value to be overwritten is a list, it should be of the form of either key="[a,b]" or key=a,b. The argument also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]". Note that the quotation marks are necessary and that no white space is allowed. |
|
||||
| `--eval-options` | str | Custom options for evaluation, the key-value pair in xxx=yyy format will be kwargs for dataset.evaluate() function. |
|
||||
| `--launcher` | 'none', 'pytorch', 'slurm', 'mpi' | Options for job launcher. |
|
||||
|
||||
## Testing on Multiple GPUs
|
||||
|
||||
|
|
|
|||
|
|
@ -8,20 +8,20 @@ Before you upload a model to AWS, you may want to
|
|||
(1) convert the model weights to CPU tensors, (2) delete the optimizer states and
|
||||
(3) compute the hash of the checkpoint file and append the hash id to the filename. These functionalities could be achieved by `tools/publish_model.py`.
|
||||
|
||||
```shell
|
||||
python tools/publish_model.py ${INPUT_FILENAME} ${OUTPUT_FILENAME}
|
||||
```
|
||||
```shell
|
||||
python tools/publish_model.py ${INPUT_FILENAME} ${OUTPUT_FILENAME}
|
||||
```
|
||||
|
||||
For example,
|
||||
|
||||
```shell
|
||||
python tools/publish_model.py work_dirs/psenet/latest.pth psenet_r50_fpnf_sbn_1x_20190801.pth
|
||||
```
|
||||
```shell
|
||||
python tools/publish_model.py work_dirs/psenet/latest.pth psenet_r50_fpnf_sbn_1x_20190801.pth
|
||||
```
|
||||
|
||||
The final output filename will be `psenet_r50_fpnf_sbn_1x_20190801-{hash id}.pth`.
|
||||
|
||||
## Convert text recognition dataset to lmdb format
|
||||
|
||||
## Convert text recognition dataset to lmdb format
|
||||
Reading images or labels from files can be slow when data are excessive, e.g. on a scale of millions. Besides, in academia, most of the scene text recognition datasets are stored in lmdb format, including images and labels. To get closer to the mainstream practice and enhance the data storage efficiency, MMOCR now provides `tools/data/utils/lmdb_converter.py` to convert text recognition datasets to lmdb format.
|
||||
|
||||
| Arguments | Type | Description |
|
||||
|
|
@ -61,20 +61,21 @@ Generate a label-only lmdb file with label.jsonl:
|
|||
python tools/data/utils/lmdb_converter.py label.json label.lmdb --label-only -f jsonl
|
||||
```
|
||||
|
||||
## Convert annotations from Labelme
|
||||
|
||||
## Convert annotations from Labelme
|
||||
[Labelme](https://github.com/wkentaro/labelme) is a popular graphical image annotation tool. You can convert the labels generated by labelme to the MMOCR data format using `tools/data/common/labelme_converter.py`. Both detection and recognition tasks are supported.
|
||||
|
||||
```bash
|
||||
# tasks can be "det" or both "det", "recog"
|
||||
python tools/data/common/labelme_converter.py <json_dir> <image_dir> <out_dir> --tasks <tasks>
|
||||
```
|
||||
```bash
|
||||
# tasks can be "det" or both "det", "recog"
|
||||
python tools/data/common/labelme_converter.py <json_dir> <image_dir> <out_dir> --tasks <tasks>
|
||||
```
|
||||
|
||||
For example, converting the labelme format annotation in `tests/data/toy_dataset/labelme` to MMOCR detection labels `instances_training.txt` and cropping the image patches for recognition task to `tests/data/toy_dataset/crops` with the labels `train_label.jsonl`:
|
||||
|
||||
```bash
|
||||
python tools/data/common/labelme_converter.py tests/data/toy_dataset/labelme tests/data/toy_dataset/imgs tests/data/toy_dataset --tasks det recog
|
||||
```
|
||||
```bash
|
||||
python tools/data/common/labelme_converter.py tests/data/toy_dataset/labelme tests/data/toy_dataset/imgs tests/data/toy_dataset --tasks det recog
|
||||
```
|
||||
|
||||
|
||||
## Log Analysis
|
||||
|
||||
|
|
@ -82,9 +83,9 @@ You can use `tools/analyze_logs.py` to plot loss/hmean curves given a training l
|
|||
|
||||
|
||||
|
||||
```shell
|
||||
```shell
|
||||
python tools/analyze_logs.py plot_curve [--keys ${KEYS}] [--title ${TITLE}] [--legend ${LEGEND}] [--backend ${BACKEND}] [--style ${STYLE}] [--out ${OUT_FILE}]
|
||||
```
|
||||
```
|
||||
|
||||
| Arguments | Type | Description |
|
||||
| ----------- | ---- | --------------------------------------------------------------------------------------------------------------- |
|
||||
|
|
@ -98,7 +99,6 @@ python tools/analyze_logs.py plot_curve [--keys ${KEYS}] [--title ${TITLE}] [--l
|
|||
**Examples:**
|
||||
|
||||
Download the following DBNet and CRNN training logs to run demos.
|
||||
|
||||
```shell
|
||||
wget https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r18_fpnc_sbn_1200e_icdar2015_20210329-ba3ab597.log.json -O DBNet_log.json
|
||||
|
||||
|
|
|
|||
|
|
@ -19,22 +19,22 @@ CUDA_VISIBLE_DEVICES= python tools/train.py ${CONFIG_FILE} [ARGS]
|
|||
|
||||
````
|
||||
|
||||
| ARGS | Type | Description |
|
||||
| ----------------- | --------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| `--work-dir` | str | The target folder to save logs and checkpoints. Defaults to `./work_dirs`. |
|
||||
| `--load-from` | str | Path to the pre-trained model, which will be used to initialize the network parameters. |
|
||||
| `--resume-from` | str | Resume training from a previously saved checkpoint, which will inherit the training epoch and optimizer parameters. |
|
||||
| `--no-validate` | bool | Disable checkpoint evaluation during training. Defaults to `False`. |
|
||||
| `--gpus` | int | **Deprecated, please use --gpu-id.** Numbers of gpus to use. Only applicable to non-distributed training. |
|
||||
| `--gpu-ids` | int\*N | **Deprecated, please use --gpu-id.** A list of GPU ids to use. Only applicable to non-distributed training. |
|
||||
| `--gpu-id` | int | The GPU id to use. Only applicable to non-distributed training. |
|
||||
| `--seed` | int | Random seed. |
|
||||
| `--diff-seed` | bool | Whether or not set different seeds for different ranks. |
|
||||
| `--deterministic` | bool | Whether to set deterministic options for CUDNN backend. |
|
||||
| `--cfg-options` | str | Override some settings in the used config, the key-value pair in xxx=yyy format will be merged into the config file. If the value to be overwritten is a list, it should be of the form of either key="\[a,b\]" or key=a,b. The argument also allows nested list/tuple values, e.g. key="\[(a,b),(c,d)\]". Note that the quotation marks are necessary and that no white space is allowed. |
|
||||
| `--launcher` | 'none', 'pytorch', 'slurm', 'mpi' | Options for job launcher. |
|
||||
| `--local_rank` | int | Used for distributed training. |
|
||||
| `--mc-config` | str | Memory cache config for image loading speed-up during training. |
|
||||
| ARGS | Type | Description |
|
||||
| ----------------- | --------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `--work-dir` | str | The target folder to save logs and checkpoints. Defaults to `./work_dirs`. |
|
||||
| `--load-from` | str | Path to the pre-trained model, which will be used to initialize the network parameters. |
|
||||
| `--resume-from` | str | Resume training from a previously saved checkpoint, which will inherit the training epoch and optimizer parameters. |
|
||||
| `--no-validate` | bool | Disable checkpoint evaluation during training. Defaults to `False`. |
|
||||
| `--gpus` | int | **Deprecated, please use --gpu-id.** Numbers of gpus to use. Only applicable to non-distributed training. |
|
||||
| `--gpu-ids` | int*N | **Deprecated, please use --gpu-id.** A list of GPU ids to use. Only applicable to non-distributed training. |
|
||||
| `--gpu-id` | int | The GPU id to use. Only applicable to non-distributed training. |
|
||||
| `--seed` | int | Random seed. |
|
||||
| `--diff-seed` | bool | Whether or not set different seeds for different ranks. |
|
||||
| `--deterministic` | bool | Whether to set deterministic options for CUDNN backend. |
|
||||
| `--cfg-options` | str | Override some settings in the used config, the key-value pair in xxx=yyy format will be merged into the config file. If the value to be overwritten is a list, it should be of the form of either key="[a,b]" or key=a,b. The argument also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]". Note that the quotation marks are necessary and that no white space is allowed. |
|
||||
| `--launcher` | 'none', 'pytorch', 'slurm', 'mpi' | Options for job launcher. |
|
||||
| `--local_rank` | int | Used for distributed training. |
|
||||
| `--mc-config` | str | Memory cache config for image loading speed-up during training. |
|
||||
|
||||
## Training on Multiple GPUs
|
||||
|
||||
|
|
@ -44,13 +44,13 @@ MMOCR implements **distributed** training with `MMDistributedDataParallel`. (Ple
|
|||
[PORT={PORT}] ./tools/dist_train.sh ${CONFIG_FILE} ${WORK_DIR} ${GPU_NUM} [PY_ARGS]
|
||||
```
|
||||
|
||||
| Arguments | Type | Description |
|
||||
| ------------- | ---- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Arguments | Type | Description |
|
||||
| ------------- | ---- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| `PORT` | int | The master port that will be used by the machine with rank 0. Defaults to 29500. **Note:** If you are launching multiple distrbuted training jobs on a single machine, you need to specify different ports for each job to avoid port conflicts. |
|
||||
| `CONFIG_FILE` | str | The path to config. |
|
||||
| `WORK_DIR` | str | The path to the working directory. |
|
||||
| `GPU_NUM` | int | The number of GPUs to be used per node. Defaults to 8. |
|
||||
| `PY_ARGS` | str | Arguments to be parsed by `tools/train.py`. |
|
||||
| `CONFIG_FILE` | str | The path to config. |
|
||||
| `WORK_DIR` | str | The path to the working directory. |
|
||||
| `GPU_NUM` | int | The number of GPUs to be used per node. Defaults to 8. |
|
||||
| `PY_ARGS` | str | Arguments to be parsed by `tools/train.py`. |
|
||||
|
||||
## Training on Multiple Machines
|
||||
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@ test/img 2.jpg Hello Open MMLab!
|
|||
test/img 3.jpg Hello MMOCR!
|
||||
```
|
||||
|
||||
The `LineStrParser` will split the above annotation line to pieces (e.g. \['test/img', '1.jpg', 'Hello', 'World!'\]) that cannot be matched to the `keys` (e.g. \['filename', 'text'\]). Therefore, we need to convert it to a json line format by `json.dumps` (check [here](https://github.com/open-mmlab/mmocr/blob/main/tools/data/textrecog/funsd_converter.py#L175-L180) to see how to dump `jsonl`), and then the annotation file will look like as follows:
|
||||
The `LineStrParser` will split the above annotation line to pieces (e.g. ['test/img', '1.jpg', 'Hello', 'World!']) that cannot be matched to the `keys` (e.g. ['filename', 'text']). Therefore, we need to convert it to a json line format by `json.dumps` (check [here](https://github.com/open-mmlab/mmocr/blob/main/tools/data/textrecog/funsd_converter.py#L175-L180) to see how to dump `jsonl`), and then the annotation file will look like as follows:
|
||||
|
||||
```txt
|
||||
% A json line annotation file that contains blank spaces
|
||||
|
|
|
|||
|
|
@ -21,7 +21,7 @@ When submitting jobs using "tools/train.py" or "tools/test.py", you may specify
|
|||
- Update values of list/tuples.
|
||||
|
||||
If the value to be updated is a list or a tuple. For example, the config file normally sets `workflow=[('train', 1)]`. If you want to
|
||||
change this key, you may specify `--cfg-options workflow="[(train,1),(val,1)]"`. Note that the quotation mark " is necessary to
|
||||
change this key, you may specify `--cfg-options workflow="[(train,1),(val,1)]"`. Note that the quotation mark \" is necessary to
|
||||
support list/tuple data types, and that **NO** white space is allowed inside the quotation marks in the specified value.
|
||||
|
||||
## Config Name Style
|
||||
|
|
@ -38,20 +38,17 @@ We follow the below style to name full config files (`configs/TASK/*.py`). Contr
|
|||
- `[ARCHITECTURE]`: expands some invoked modules following the order of data flow, and the content depends on the model framework. The following examples show how it is generally expanded.
|
||||
- For text detection tasks, key information tasks, and SegOCR in text recognition task: `{model}_[backbone]_[neck]_[schedule]_{dataset}.py`
|
||||
- For other text recognition tasks, `{model}_[backbone]_[encoder]_[decoder]_[schedule]_{dataset}.py`
|
||||
Note that `backbone`, `neck`, `encoder`, `decoder` are the names of modules, e.g. `r50`, `fpnocr`, etc.
|
||||
Note that `backbone`, `neck`, `encoder`, `decoder` are the names of modules, e.g. `r50`, `fpnocr`, etc.
|
||||
- `{schedule}`: training schedule. For instance, `1200e` denotes 1200 epochs.
|
||||
- `{dataset}`: dataset. It can either be the name of a dataset (`icdar2015`), or a collection of datasets for brevity (e.g. `academic` usually refers to a common practice in academia, which uses MJSynth + SynthText as training set, and IIIT5K, SVT, IC13, IC15, SVTP and CT80 as test set).
|
||||
|
||||
Most configs are composed of basic _primitive_ configs in `configs/_base_`, where each _primitive_ config in different subdirectory has a slightly different name style. We present them as follows.
|
||||
|
||||
- det_datasets, recog_datasets: `{dataset_name(s)}_[train|test].py`. If \[train|test\] is not specified, the config should contain both training and test set.
|
||||
- det_datasets, recog_datasets: `{dataset_name(s)}_[train|test].py`. If [train|test] is not specified, the config should contain both training and test set.
|
||||
|
||||
There are two exceptions: toy_data.py and seg_toy_data.py. In recog_datasets, the first one works for most while the second one contains character level annotations and works for seg baseline only as of Dec 2021.
|
||||
|
||||
- det_models, recog_models: `{model}_[ARCHITECTURE].py`.
|
||||
|
||||
- det_pipelines, recog_pipelines: `{model}_pipeline.py`.
|
||||
|
||||
- schedules: `schedule_{optimizer}_{num_epochs}e.py`.
|
||||
|
||||
## Config Structure
|
||||
|
|
|
|||
|
|
@ -65,6 +65,7 @@ data = dict(
|
|||
|
||||
#### Example Configuration
|
||||
|
||||
|
||||
```python
|
||||
dataset_type = 'IcdarDataset'
|
||||
prefix = 'tests/data/toy_dataset/'
|
||||
|
|
@ -91,7 +92,7 @@ Icdar 2015/2017 and ctw1500 annotations need to be converted into the COCO forma
|
|||
In particular, filtering predictions with a reasonable score threshold greatly impacts the performance measurement. MMOCR alleviates such hyperparameter effect by sweeping through the hyperparameter space and returns the best performance every evaluation time.
|
||||
User can tune the searching scheme by passing `min_score_thr`, `max_score_thr` and `step` into the evaluation hook in the config.
|
||||
|
||||
For example, with the following configuration, you can evaluate the model's output on a list of boundary score thresholds \[0.1, 0.2, 0.3, 0.4, 0.5\] and get the best score from them **during training**.
|
||||
For example, with the following configuration, you can evaluate the model's output on a list of boundary score thresholds [0.1, 0.2, 0.3, 0.4, 0.5] and get the best score from them **during training**.
|
||||
|
||||
```python
|
||||
evaluation = dict(
|
||||
|
|
@ -115,7 +116,6 @@ Check out our [API doc](https://mmocr.readthedocs.io/en/latest/api.html#mmocr.co
|
|||
*Dataset with annotation file in line-json txt format*
|
||||
|
||||
We have designed new types of dataset consisting of **loader** , **backend**, and **parser** to load and parse different types of annotation files.
|
||||
|
||||
- **loader**: Load the annotation file. We now have a unified loader, `AnnFileLoader`, which can use different `backend` to load annotation from txt. The original `HardDiskLoader` and `LmdbLoader` will be deprecated.
|
||||
- **backend**: Load annotation from different format and backend.
|
||||
- `LmdbAnnFileBackend`: Load annotation from lmdb dataset.
|
||||
|
|
@ -151,7 +151,6 @@ test = dict(
|
|||
The results are generated in the same way as the segmentation-based text recognition task above.
|
||||
You can check the content of the annotation file in `tests/data/toy_dataset/instances_test.txt`.
|
||||
The combination of `HardDiskLoader` and `LineJsonParser` will return a dict for each file by calling `__getitem__`:
|
||||
|
||||
```python
|
||||
{"file_name": "test/img_10.jpg", "height": 720, "width": 1280, "annotations": [{"iscrowd": 1, "category_id": 1, "bbox": [260.0, 138.0, 24.0, 20.0], "segmentation": [[261, 138, 284, 140, 279, 158, 260, 158]]}, {"iscrowd": 0, "category_id": 1, "bbox": [288.0, 138.0, 129.0, 23.0], "segmentation": [[288, 138, 417, 140, 416, 161, 290, 157]]}, {"iscrowd": 0, "category_id": 1, "bbox": [743.0, 145.0, 37.0, 18.0], "segmentation": [[743, 145, 779, 146, 780, 163, 746, 163]]}, {"iscrowd": 0, "category_id": 1, "bbox": [783.0, 129.0, 50.0, 26.0], "segmentation": [[783, 129, 831, 132, 833, 155, 785, 153]]}, {"iscrowd": 1, "category_id": 1, "bbox": [831.0, 133.0, 43.0, 23.0], "segmentation": [[831, 133, 870, 135, 874, 156, 835, 155]]}, {"iscrowd": 1, "category_id": 1, "bbox": [159.0, 204.0, 72.0, 15.0], "segmentation": [[159, 205, 230, 204, 231, 218, 159, 219]]}, {"iscrowd": 1, "category_id": 1, "bbox": [785.0, 158.0, 75.0, 21.0], "segmentation": [[785, 158, 856, 158, 860, 178, 787, 179]]}, {"iscrowd": 1, "category_id": 1, "bbox": [1011.0, 157.0, 68.0, 16.0], "segmentation": [[1011, 157, 1079, 160, 1076, 173, 1011, 170]]}]}
|
||||
```
|
||||
|
|
@ -160,6 +159,7 @@ The combination of `HardDiskLoader` and `LineJsonParser` will return a dict for
|
|||
|
||||
`TextDetDataset` shares a similar implementation with `IcdarDataset`. Please refer to the evaluation section of ['IcdarDataset'](#icdardataset).
|
||||
|
||||
|
||||
## Text Recognition
|
||||
|
||||
### OCRDataset
|
||||
|
|
@ -267,6 +267,7 @@ python tools/test.py configs/textrecog/crnn/crnn_toy_dataset.py crnn.pth --eval
|
|||
|
||||
It shares a similar architecture with `TextDetDataset`. Check out the [introduction](#textdetdataset) for details.
|
||||
|
||||
|
||||
#### Example Configuration
|
||||
|
||||
```python
|
||||
|
|
|
|||
|
|
@ -37,38 +37,38 @@ You can merge `background` to `others` if telling background apart is not import
|
|||
|
||||
We provide a [conversion script](../datasets/kie.md) that converts WildRecipt-like dataset to OpenSet format. This script links every `key`-`value` pairs following the rules above. Here's an example illustration: (For better understanding, all the node labels are presented as texts)
|
||||
|
||||
| box_content | closeset_node_label | closeset_edge_label | openset_node_label | openset_edge_label |
|
||||
| :---------: | :-----------------: | :-----------------: | :----------------: | :----------------: |
|
||||
| hello | Ignore | - | Others | 0 |
|
||||
| world | Ignore | - | Others | 1 |
|
||||
| Actor | Actor_key | - | Key | 2 |
|
||||
| Tom | Actor_value | - | Value | 2 |
|
||||
| Tony | Actor_value | - | Value | 2 |
|
||||
| Tim | Actor_value | - | Value | 2 |
|
||||
| something | Ignore | - | Others | 3 |
|
||||
| Actress | Actress_key | - | Key | 4 |
|
||||
| Lucy | Actress_value | - | Value | 4 |
|
||||
| Zora | Actress_value | - | Value | 4 |
|
||||
|box_content | closeset_node_label| closeset_edge_label | openset_node_label | openset_edge_label |
|
||||
| :----: | :---: | :----: | :---: | :---: |
|
||||
| hello | Ignore | - | Others | 0 |
|
||||
| world | Ignore | - | Others | 1 |
|
||||
| Actor | Actor_key | - | Key | 2 |
|
||||
| Tom | Actor_value | - | Value | 2 |
|
||||
| Tony | Actor_value | - | Value | 2 |
|
||||
| Tim | Actor_value | - | Value | 2 |
|
||||
| something | Ignore | - | Others | 3 |
|
||||
| Actress | Actress_key | - | Key | 4 |
|
||||
| Lucy | Actress_value | - | Value | 4 |
|
||||
| Zora | Actress_value | - | Value | 4 |
|
||||
|
||||
```{warning}
|
||||
|
||||
A common request from our community is to extract the relations between food items and food prices. In this case, this conversion script ***is not you need***.
|
||||
Wildrecipt doesn't provide necessary information to recover this relation. For instance, there are four text boxes "Hamburger", "Hotdog", "$1" and "$2" on the receipt, and here's how they actually look like before and after the conversion:
|
||||
|
||||
| box_content | closeset_node_label | closeset_edge_label | openset_node_label | openset_edge_label |
|
||||
| :---------: | :-----------------: | :-----------------: | :----------------: | :----------------: |
|
||||
| Hamburger | Prod_item_value | - | Value | 0 |
|
||||
| Hotdog | Prod_item_value | - | Value | 0 |
|
||||
| $1 | Prod_price_value | - | Value | 1 |
|
||||
| $2 | Prod_price_value | - | Value | 1 |
|
||||
|box_content | closeset_node_label| closeset_edge_label | openset_node_label | openset_edge_label |
|
||||
| :----: | :---: | :----: | :---: | :---: |
|
||||
| Hamburger | Prod_item_value | - | Value | 0 |
|
||||
| Hotdog | Prod_item_value | - | Value | 0 |
|
||||
| $1 | Prod_price_value | - | Value | 1 |
|
||||
| $2 | Prod_price_value | - | Value | 1 |
|
||||
|
||||
So there won't be any valid edges connecting them. Nevertheless, OpenSet format is far more general than CloseSet, so this task can be achieved by annotating the data from scratch.
|
||||
|
||||
| box_content | openset_node_label | openset_edge_label |
|
||||
| :---------: | :----------------: | :----------------: |
|
||||
| Hamburger | Value | 0 |
|
||||
| Hotdog | Value | 1 |
|
||||
| $1 | Value | 0 |
|
||||
| $2 | Value | 1 |
|
||||
|box_content | openset_node_label | openset_edge_label |
|
||||
| :----: | :---: | :---: |
|
||||
| Hamburger | Value | 0 |
|
||||
| Hotdog | Value | 1 |
|
||||
| $1 | Value | 0 |
|
||||
| $2 | Value | 1 |
|
||||
|
||||
```
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
|
||||
# 文字检测
|
||||
|
||||
## 概览
|
||||
|
|
@ -49,13 +50,12 @@
|
|||
**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
|
||||
|
|
@ -66,19 +66,15 @@ mv ch4_test_images imgs/test
|
|||
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
|
||||
|
|
@ -99,7 +95,6 @@ wget -O test_images.zip https://universityofadelaide.box.com/shared/static/t4w48
|
|||
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
|
||||
|
|
@ -111,52 +106,45 @@ python tools/data/textdet/ctw1500_converter.py /path/to/ctw1500 -o /path/to/ctw1
|
|||
- 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
|
||||
|
||||
- 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。
|
||||
# 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
|
||||
|
||||
```bash
|
||||
mkdir textocr && cd textocr
|
||||
# 把图片移到对应目录
|
||||
unzip -q train_val_images.zip
|
||||
mv train_images train
|
||||
```
|
||||
|
||||
# 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
|
||||
```
|
||||
- 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
|
||||
|
||||
- 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。）
|
||||
# 图像
|
||||
# 在 ./totaltext 中执行
|
||||
unzip totaltext.zip
|
||||
mv Images/Train imgs/training
|
||||
mv Images/Test imgs/test
|
||||
|
||||
```bash
|
||||
mkdir totaltext && cd totaltext
|
||||
mkdir imgs && mkdir annotations
|
||||
# 标注文件
|
||||
unzip groundtruth_text.zip
|
||||
cd Groundtruth
|
||||
mv Polygon/Train ../annotations/training
|
||||
mv Polygon/Test ../annotations/test
|
||||
|
||||
# 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
|
||||
```
|
||||
```
|
||||
- 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
|
||||
```
|
||||
|
|
|
|||
|
|
@ -23,7 +23,6 @@
|
|||
|
||||
- 准备好 [WildReceipt](#WildReceipt)。
|
||||
- 转换 WildReceipt 成 OpenSet 格式:
|
||||
|
||||
```bash
|
||||
# 你可以运行以下命令以获取更多可用参数：
|
||||
# python tools/data/kie/closeset_to_openset.py -h
|
||||
|
|
|
|||
|
|
@ -93,217 +93,189 @@
|
|||
| 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。
|
||||
(*) 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。
|
||||
|
||||
## 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)
|
||||
- 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：
|
||||
|
||||
- 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
|
||||
|
||||
```bash
|
||||
mkdir Syn90k && cd Syn90k
|
||||
mv /path/to/mjsynth.tar.gz .
|
||||
|
||||
mv /path/to/mjsynth.tar.gz .
|
||||
tar -xzf mjsynth.tar.gz
|
||||
|
||||
tar -xzf mjsynth.tar.gz
|
||||
mv /path/to/shuffle_labels.txt .
|
||||
mv /path/to/label.txt .
|
||||
|
||||
mv /path/to/shuffle_labels.txt .
|
||||
mv /path/to/label.txt .
|
||||
# 创建软链接
|
||||
cd /path/to/mmocr/data/mixture
|
||||
|
||||
# 创建软链接
|
||||
cd /path/to/mmocr/data/mixture
|
||||
|
||||
ln -s /path/to/Syn90k Syn90k
|
||||
```
|
||||
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：
|
||||
|
||||
- 第三步：
|
||||
```bash
|
||||
mkdir SynthText && cd SynthText
|
||||
mv /path/to/SynthText.zip .
|
||||
unzip SynthText.zip
|
||||
mv SynthText synthtext
|
||||
|
||||
```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 .
|
||||
|
||||
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
|
||||
```
|
||||
|
||||
# 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：
|
||||
|
||||
- 第四步：生成裁剪后的图像和标注：
|
||||
```bash
|
||||
cd /path/to/mmocr
|
||||
|
||||
```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
|
||||
```
|
||||
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：
|
||||
|
||||
- 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
|
||||
|
||||
```bash
|
||||
mkdir SynthAdd && cd SynthAdd
|
||||
mv /path/to/SynthText_Add.zip .
|
||||
|
||||
mv /path/to/SynthText_Add.zip .
|
||||
unzip SynthText_Add.zip
|
||||
|
||||
unzip SynthText_Add.zip
|
||||
mv /path/to/label.txt .
|
||||
|
||||
mv /path/to/label.txt .
|
||||
|
||||
# 创建软链接
|
||||
cd /path/to/mmocr/data/mixture
|
||||
|
||||
ln -s /path/to/SynthAdd SynthAdd
|
||||
```
|
||||
# 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
|
||||
|
||||
- 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.
|
||||
# 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
|
||||
|
||||
```bash
|
||||
mkdir textocr && cd textocr
|
||||
# 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
|
||||
```
|
||||
|
||||
# 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
|
||||
|
||||
- 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）
|
||||
# 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
|
||||
|
||||
```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
|
||||
```
|
||||
# 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
|
||||
|
||||
- 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/`。
|
||||
# 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 .
|
||||
|
||||
```bash
|
||||
mkdir openvino && cd openvino
|
||||
# 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_${s}.json
|
||||
done
|
||||
wget https://storage.openvinotoolkit.org/repositories/openvino_training_extensions/datasets/open_images_v5_text/text_spotting_openimages_v5_validation.json
|
||||
|
||||
# 下载 Open Images 的子数据集
|
||||
for s in 1 2 5 f; do
|
||||
aws s3 --no-sign-request cp s3://open-images-dataset/tar/train_${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
|
||||
```
|
||||
# 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
|
||||
```
|
||||
|
|
|
|||
|
|
@ -60,10 +60,11 @@ python tools/deployment/pytorch2onnx.py
|
|||
- 因为这个特性是试验性的，可能变动很快，请尽量使用最新版的 `mmcv` 和 `mmocr` 尝试。
|
||||
```
|
||||
|
||||
## ONNX 转 TensorRT （试验性的）
|
||||
## ONNX 转 TensorRT （试验性的）
|
||||
|
||||
我们也提供了从 [ONNX](https://github.com/onnx/onnx) 模型转换至 [TensorRT](https://github.com/NVIDIA/TensorRT) 格式的脚本。另外，我们支持比较 ONNX 和 TensorRT 模型的输出结果。
|
||||
|
||||
|
||||
```bash
|
||||
python tools/deployment/onnx2tensorrt.py
|
||||
${MODEL_CONFIG_PATH} \
|
||||
|
|
@ -125,7 +126,6 @@ python tools/deployment/onnx2tensorrt.py
|
|||
我们在 `tools/deployment/deploy_test.py ` 中提供了评估 TensorRT 和 ONNX 模型的方法。
|
||||
|
||||
### 前提条件
|
||||
|
||||
在评估 ONNX 和 TensorRT 模型之前，首先需要安装 ONNX，ONNXRuntime 和 TensorRT。根据 [ONNXRuntime in mmcv](https://mmcv.readthedocs.io/en/latest/onnxruntime_op.html) 和 [TensorRT plugin in mmcv](https://github.com/open-mmlab/mmcv/blob/master/docs/tensorrt_plugin.md) 安装 ONNXRuntime 定制操作和 TensorRT 插件。
|
||||
|
||||
### 使用
|
||||
|
|
|
|||
|
|
@ -27,13 +27,11 @@ python mmocr/utils/ocr.py demo/demo_text_ocr.jpg --print-result --imshow
|
|||
在`tests/data`目录下提供了一个用于训练演示的小数据集，在准备学术数据集之前，它可以演示一个初步的训练。
|
||||
|
||||
例如：用 `seg` 方法和小数据集来训练文本识别任务，
|
||||
|
||||
```shell
|
||||
python tools/train.py configs/textrecog/seg/seg_r31_1by16_fpnocr_toy_dataset.py --work-dir seg
|
||||
```
|
||||
|
||||
用 `sar` 方法和小数据集训练文本识别,
|
||||
|
||||
```shell
|
||||
python tools/train.py configs/textrecog/sar/sar_r31_parallel_decoder_toy_dataset.py --work-dir sar
|
||||
```
|
||||
|
|
@ -41,7 +39,6 @@ python tools/train.py configs/textrecog/sar/sar_r31_parallel_decoder_toy_dataset
|
|||
### 使用学术数据集进行训练
|
||||
|
||||
按照说明准备好所需的学术数据集后，最后要检查模型的配置是否将 MMOCR 指向正确的数据集路径。假设在 ICDAR2015 数据集上训练 DBNet,部分配置如 `configs/_base_/det_datasets/icdar2015.py` 所示:
|
||||
|
||||
```python
|
||||
dataset_type = 'IcdarDataset'
|
||||
data_root = 'data/icdar2015'
|
||||
|
|
@ -58,9 +55,7 @@ test = dict(
|
|||
train_list = [train]
|
||||
test_list = [test]
|
||||
```
|
||||
|
||||
这里需要检查数据集路径 `data/icdar2015` 是否正确. 然后可以启动训练命令：
|
||||
|
||||
```shell
|
||||
python tools/train.py configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py --work-dir dbnet
|
||||
```
|
||||
|
|
@ -70,13 +65,11 @@ python tools/train.py configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py --
|
|||
## 测试
|
||||
|
||||
假设我们完成了 DBNet 模型训练，并将最新的模型保存在 `dbnet/latest.pth`。则可以使用以下命令，及`hmean-iou`指标来评估其在测试集上的性能：
|
||||
|
||||
```shell
|
||||
python tools/test.py configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py dbnet/latest.pth --eval hmean-iou
|
||||
```
|
||||
|
||||
还可以在线评估预训练模型，命令如下：
|
||||
|
||||
```shell
|
||||
python tools/test.py configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r18_fpnc_sbn_1200e_icdar2015_20210329-ba3ab597.pth --eval hmean-iou
|
||||
```
|
||||
|
|
|
|||
|
|
@ -14,16 +14,16 @@
|
|||
|
||||
为了确保代码实现的正确性，MMOCR 每个版本都有可能改变对 MMCV 和 MMDetection 版本的依赖。请根据以下表格确保版本之间的相互匹配。
|
||||
|
||||
| MMOCR | MMCV | MMDetection |
|
||||
| ------------ | ------------------------ | --------------------------- |
|
||||
| main | 1.3.8 \<= mmcv \<= 1.6.0 | 2.21.0 \<= mmdet \<= 3.0.0 |
|
||||
| 0.6.0 | 1.3.8 \<= mmcv \<= 1.6.0 | 2.21.0 \<= mmdet \<= 3.0.0 |
|
||||
| 0.5.0 | 1.3.8 \<= mmcv \<= 1.5.0 | 2.14.0 \<= mmdet \<= 3.0.0 |
|
||||
| 0.4.0, 0.4.1 | 1.3.8 \<= mmcv \<= 1.5.0 | 2.14.0 \<= mmdet \<= 2.20.0 |
|
||||
| 0.3.0 | 1.3.8 \<= mmcv \<= 1.4.0 | 2.14.0 \<= mmdet \<= 2.20.0 |
|
||||
| 0.2.1 | 1.3.8 \<= mmcv \<= 1.4.0 | 2.13.0 \<= mmdet \<= 2.20.0 |
|
||||
| 0.2.0 | 1.3.4 \<= mmcv \<= 1.4.0 | 2.11.0 \<= mmdet \<= 2.13.0 |
|
||||
| 0.1.0 | 1.2.6 \<= mmcv \<= 1.3.4 | 2.9.0 \<= mmdet \<= 2.11.0 |
|
||||
| MMOCR | MMCV | MMDetection |
|
||||
| ------------ | ---------------------- | ------------------------- |
|
||||
| main | 1.3.8 <= mmcv <= 1.6.0 | 2.21.0 <= mmdet <= 3.0.0 |
|
||||
| 0.6.0 | 1.3.8 <= mmcv <= 1.6.0 | 2.21.0 <= mmdet <= 3.0.0 |
|
||||
| 0.5.0 | 1.3.8 <= mmcv <= 1.5.0 | 2.14.0 <= mmdet <= 3.0.0 |
|
||||
| 0.4.0, 0.4.1 | 1.3.8 <= mmcv <= 1.5.0 | 2.14.0 <= mmdet <= 2.20.0 |
|
||||
| 0.3.0 | 1.3.8 <= mmcv <= 1.4.0 | 2.14.0 <= mmdet <= 2.20.0 |
|
||||
| 0.2.1 | 1.3.8 <= mmcv <= 1.4.0 | 2.13.0 <= mmdet <= 2.20.0 |
|
||||
| 0.2.0 | 1.3.4 <= mmcv <= 1.4.0 | 2.11.0 <= mmdet <= 2.13.0 |
|
||||
| 0.1.0 | 1.2.6 <= mmcv <= 1.3.4 | 2.9.0 <= mmdet <= 2.11.0 |
|
||||
|
||||
我们已经测试了以下操作系统和软件版本:
|
||||
|
||||
|
|
@ -62,7 +62,7 @@ c. 安装 [mmcv](https://github.com/open-mmlab/mmcv)，推荐以下方式进行
|
|||
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/{cu_version}/{torch_version}/index.html
|
||||
```
|
||||
|
||||
请将上述 url 中 `{cu_version}` 和 `{torch_version}`替换成你环境中对应的 CUDA 版本和 PyTorch 版本。例如，如果想要安装最新版基于 CUDA 11 和 PyTorch 1.7.0 的最新版 `mmcv-full`，请输入以下命令:
|
||||
请将上述 url 中 ``{cu_version}`` 和 ``{torch_version}``替换成你环境中对应的 CUDA 版本和 PyTorch 版本。例如，如果想要安装最新版基于 CUDA 11 和 PyTorch 1.7.0 的最新版 `mmcv-full`，请输入以下命令:
|
||||
|
||||
```shell
|
||||
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu110/torch1.7.0/index.html
|
||||
|
|
@ -175,7 +175,7 @@ docker run --gpus all --shm-size=8g -it -v {实际数据目录}:/mmocr/data mmoc
|
|||
我们推荐建立一个 symlink 路径映射，连接数据集路径到 `mmocr/data`。 详细数据集准备方法请阅读**数据集**章节。
|
||||
如果你需要的文件夹路径不同，你可能需要在 configs 文件中修改对应的文件路径信息。
|
||||
|
||||
`mmocr` 文件夹路径结构如下：
|
||||
`mmocr` 文件夹路径结构如下：
|
||||
|
||||
```
|
||||
├── configs/
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@
|
|||
你可以根据[官网](https://github.com/pytorch/serve#install-torchserve-and-torch-model-archiver)步骤来安装 `TorchServe` 和
|
||||
`torch-model-archiver` 两个模块。
|
||||
|
||||
## 将 MMOCR 模型转换为 TorchServe 模型格式
|
||||
## 将 MMOCR 模型转换为 TorchServe 模型格式
|
||||
|
||||
我们提供了一个便捷的工具可以将任何以 `.pth` 为后缀的模型转换为以 `.mar` 结尾的模型来满足 TorchServe 使用要求。
|
||||
|
||||
|
|
@ -46,11 +46,12 @@ torchserve --start --model-store ./checkpoints --models dbnet=dbnet.mar
|
|||
|
||||
然后，你可以通过 TorchServe 的 REST API 访问 Inference、 Management、 Metrics 等服务。你可以在[TorchServe REST API](https://github.com/pytorch/serve/blob/master/docs/rest_api.md) 中找到它们的用法。
|
||||
|
||||
| 服务 | 地址 |
|
||||
| ---------- | ----------------------- |
|
||||
| Inference | `http://127.0.0.1:8080` |
|
||||
| Management | `http://127.0.0.1:8081` |
|
||||
| Metrics | `http://127.0.0.1:8082` |
|
||||
|
||||
| 服务 | 地址 |
|
||||
| ------------------- | ----------------------- |
|
||||
| Inference | `http://127.0.0.1:8080` |
|
||||
| Management | `http://127.0.0.1:8081` |
|
||||
| Metrics | `http://127.0.0.1:8082` |
|
||||
|
||||
````{note}
|
||||
TorchServe 默认会将服务绑定到端口 `8080`、 `8081` 、 `8082` 上。你可以通过修改 `config.properties` 来更改端口及存储位置等内容，并通过可选项 `--ts-config config.preperties` 来运行 TorchServe 服务。
|
||||
|
|
@ -66,6 +67,7 @@ model_store=/home/model-server/model-store
|
|||
|
||||
````
|
||||
|
||||
|
||||
### 通过 Docker 启动
|
||||
|
||||
通过 Docker 提供模型服务不失为一种更好的方法。我们提供了一个 Dockerfile，可以让你摆脱那些繁琐且容易出错的环境设置步骤。
|
||||
|
|
@ -97,11 +99,13 @@ mmocr-serve:latest
|
|||
|
||||
运行docker后，你可以通过 TorchServe 的 REST API 访问 Inference、 Management、 Metrics 等服务。具体你可以在[TorchServe REST API](https://github.com/pytorch/serve/blob/master/docs/rest_api.md) 中找到它们的用法。
|
||||
|
||||
| 服务 | 地址 |
|
||||
| ---------- | --------------------- |
|
||||
| Inference | http://127.0.0.1:8080 |
|
||||
| 服务 | 地址 |
|
||||
| ------------------- | ----------------------- |
|
||||
| Inference | http://127.0.0.1:8080 |
|
||||
| Management | http://127.0.0.1:8081 |
|
||||
| Metrics | http://127.0.0.1:8082 |
|
||||
| Metrics | http://127.0.0.1:8082 |
|
||||
|
||||
|
||||
|
||||
## 4. 测试单张图片推理
|
||||
|
||||
|
|
@ -118,7 +122,6 @@ curl http://127.0.0.1:8080/predictions/dbnet -T demo/demo_text_det.jpg
|
|||
```
|
||||
|
||||
对于检测模型，你会获取到名为 boundary_result 的 json 对象。内部的每个数组包含以浮点数格式的，按顺时针排序的 x， y 边界顶点坐标。数组的最后一位为置信度分数。
|
||||
|
||||
```json
|
||||
{
|
||||
"boundary_result": [
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
|
||||
## 使用单 GPU 进行测试
|
||||
|
||||
您可以使用 `tools/test.py` 执行单 CPU/GPU 推理。例如，要在 IC15 上评估 DBNet: ( 可以从 [Model Zoo](../../README_zh-CN.md#模型库) 下载预训练模型 )：
|
||||
您可以使用 `tools/test.py` 执行单 CPU/GPU 推理。例如，要在 IC15 上评估 DBNet: ( 可以从 [Model Zoo]( ../../README_zh-CN.md#模型库) 下载预训练模型 )：
|
||||
|
||||
```shell
|
||||
./tools/dist_test.sh configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py dbnet_r18_fpnc_sbn_1200e_icdar2015_20210329-ba3ab597.pth --eval hmean-iou
|
||||
|
|
@ -25,21 +25,23 @@ CUDA_VISIBLE_DEVICES= python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [AR
|
|||
|
||||
````
|
||||
|
||||
| 参数 | 类型 | 描述 |
|
||||
| ------------------ | --------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `--out` | str | 以 pickle 格式输出结果文件。 |
|
||||
| `--fuse-conv-bn` | bool | 所选 det 模型的自定义配置的路径。 |
|
||||
| `--format-only` | bool | 格式化输出结果文件而不执行评估。 当您想将结果格式化为特定格式并将它们提交到测试服务器时，它很有用。 |
|
||||
| `--gpu-id` | int | 要使用的 GPU ID。仅适用于非分布式训练。 |
|
||||
| `--eval` | 'hmean-ic13', 'hmean-iou', 'acc' | 不同的任务使用不同的评估指标。对于文本检测任务，指标是 'hmean-ic13' 或者 'hmean-iou'。对于文本识别任务，指标是 'acc'。 |
|
||||
| `--show` | bool | 是否显示结果。 |
|
||||
| `--show-dir` | str | 将用于保存输出图像的目录。 |
|
||||
| `--show-score-thr` | float | 分数阈值 (默认值: 0.3)。 |
|
||||
| `--gpu-collect` | bool | 是否使用 gpu 收集结果。 |
|
||||
| `--tmpdir` | str | 用于从多个 workers 收集结果的 tmp 目录，在未指定 gpu-collect 时可用。 |
|
||||
| `--cfg-options` | str | 覆盖使用的配置中的一些设置，xxx=yyy 格式的键值对将被合并到配置文件中。如果要覆盖的值是一个列表，它应当是 key ="\[a,b\]" 或者 key=a,b 的形式。该参数还允许嵌套列表/元组值，例如 key="\[(a,b),(c,d)\]"。请注意，引号是必需的，并且不允许使用空格。 |
|
||||
| `--eval-options` | str | 用于评估的自定义选项，xxx=yyy 格式的键值对将是 dataset.evaluate() 函数的 kwargs。 |
|
||||
| `--launcher` | 'none', 'pytorch', 'slurm', 'mpi' | 工作启动器的选项。 |
|
||||
|
||||
|
||||
| 参数 | 类型 | 描述 |
|
||||
| ------------------ | --------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `--out` | str | 以 pickle 格式输出结果文件。 |
|
||||
| `--fuse-conv-bn` | bool | 所选 det 模型的自定义配置的路径。 |
|
||||
| `--format-only` | bool | 格式化输出结果文件而不执行评估。 当您想将结果格式化为特定格式并将它们提交到测试服务器时，它很有用。 |
|
||||
| `--gpu-id` | int | 要使用的 GPU ID。仅适用于非分布式训练。 |
|
||||
| `--eval` | 'hmean-ic13', 'hmean-iou', 'acc' | 不同的任务使用不同的评估指标。对于文本检测任务，指标是 'hmean-ic13' 或者 'hmean-iou'。对于文本识别任务，指标是 'acc'。 |
|
||||
| `--show` | bool | 是否显示结果。 |
|
||||
| `--show-dir` | str | 将用于保存输出图像的目录。 |
|
||||
| `--show-score-thr` | float | 分数阈值 (默认值: 0.3)。 |
|
||||
| `--gpu-collect` | bool | 是否使用 gpu 收集结果。 |
|
||||
| `--tmpdir` | str | 用于从多个 workers 收集结果的 tmp 目录，在未指定 gpu-collect 时可用。 |
|
||||
| `--cfg-options` | str | 覆盖使用的配置中的一些设置，xxx=yyy 格式的键值对将被合并到配置文件中。如果要覆盖的值是一个列表，它应当是 key ="[a,b]" 或者 key=a,b 的形式。该参数还允许嵌套列表/元组值，例如 key="[(a,b),(c,d)]"。请注意，引号是必需的，并且不允许使用空格。 |
|
||||
| `--eval-options` | str | 用于评估的自定义选项，xxx=yyy 格式的键值对将是 dataset.evaluate() 函数的 kwargs。 |
|
||||
| `--launcher` | 'none', 'pytorch', 'slurm', 'mpi' | 工作启动器的选项。 |
|
||||
|
||||
## 使用多 GPU 进行测试
|
||||
|
||||
|
|
@ -47,14 +49,15 @@ MMOCR 使用 `MMDistributedDataParallel` 实现 **分布式**测试。
|
|||
|
||||
您可以使用以下命令测试具有多个 GPU 的数据集。
|
||||
|
||||
|
||||
```shell
|
||||
[PORT={PORT}] ./tools/dist_test.sh ${CONFIG_FILE} ${CHECKPOINT_FILE} ${GPU_NUM} [PY_ARGS]
|
||||
```
|
||||
|
||||
| 参数 | 类型 | 描述 |
|
||||
| --------- | ---- | ---------------------------------------------- |
|
||||
| 参数 | 类型 | 描述 |
|
||||
| --------- | ---- | -------------------------------------------------------------------------------- |
|
||||
| `PORT` | int | rank 为 0 的机器将使用的主端口。默认为 29500。 |
|
||||
| `PY_ARGS` | str | 由 `tools/test.py` 解析的参数。 |
|
||||
| `PY_ARGS` | str | 由 `tools/test.py` 解析的参数。 |
|
||||
|
||||
例如，
|
||||
|
||||
|
|
@ -70,12 +73,12 @@ MMOCR 使用 `MMDistributedDataParallel` 实现 **分布式**测试。
|
|||
[GPUS=${GPUS}] [GPUS_PER_NODE=${GPUS_PER_NODE}] [SRUN_ARGS=${SRUN_ARGS}] ./tools/slurm_test.sh ${PARTITION} ${JOB_NAME} ${CONFIG_FILE} ${CHECKPOINT_FILE} [PY_ARGS]
|
||||
```
|
||||
|
||||
| 参数 | 类型 | 描述 |
|
||||
| --------------- | ---- | -------------------------------------------------------------------------------- |
|
||||
| `GPUS` | int | 此任务要使用的 GPU 数量。默认为 8。 |
|
||||
| `GPUS_PER_NODE` | int | 每个节点要分配的 GPU 数量。默认为 8。 |
|
||||
| `SRUN_ARGS` | str | srun 解析的参数。可以在[此处](https://slurm.schedmd.com/srun.html)找到可用选项。 |
|
||||
| `PY_ARGS` | str | 由 `tools/test.py` 解析的参数。 |
|
||||
| 参数 | 类型 | 描述 |
|
||||
| --------------- | ---- | ----------------------------------------------------------------------------------------------------------- |
|
||||
| `GPUS` | int | 此任务要使用的 GPU 数量。默认为 8。 |
|
||||
| `GPUS_PER_NODE` | int | 每个节点要分配的 GPU 数量。默认为 8。 |
|
||||
| `SRUN_ARGS` | str | srun 解析的参数。可以在[此处](https://slurm.schedmd.com/srun.html)找到可用选项。|
|
||||
| `PY_ARGS` | str | 由 `tools/test.py` 解析的参数。 |
|
||||
|
||||
下面是一个在 "dev" 分区上运行任务的示例。该任务名为 "test_job"，其调用了 8 个 GPU 对示例模型进行评估 。
|
||||
|
||||
|
|
@ -89,7 +92,6 @@ GPUS=8 ./tools/slurm_test.sh dev test_job configs/example_config.py work_dirs/ex
|
|||
`data.val_dataloader.samples_per_gpu` 和 `data.test_dataloader.samples_per_gpu` 字段。
|
||||
|
||||
例如，
|
||||
|
||||
```
|
||||
data = dict(
|
||||
...
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
from .adapters import MMDet2MMOCR, MMOCR2MMDet
|
||||
from .formatting import PackKIEInputs, PackTextDetInputs, PackTextRecogInputs
|
||||
from .loading import LoadImageFromLMDB, LoadKIEAnnotations, LoadOCRAnnotations
|
||||
from .loading import LoadKIEAnnotations, LoadOCRAnnotations
|
||||
from .ocr_transforms import RandomCrop, RandomRotate, Resize
|
||||
from .textdet_transforms import (BoundedScaleAspectJitter, FixInvalidPolygon,
|
||||
RandomFlip, ShortScaleAspectJitter,
|
||||
|
|
@ -17,5 +17,5 @@ __all__ = [
|
|||
'PackTextRecogInputs', 'RescaleToHeight', 'PadToWidth',
|
||||
'ShortScaleAspectJitter', 'RandomFlip', 'BoundedScaleAspectJitter',
|
||||
'PackKIEInputs', 'LoadKIEAnnotations', 'FixInvalidPolygon', 'MMDet2MMOCR',
|
||||
'MMOCR2MMDet', 'LoadImageFromLMDB'
|
||||
'MMOCR2MMDet'
|
||||
]
|
||||
|
|
|
|||
|
|
@ -1,11 +1,8 @@
|
|||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import copy
|
||||
import os
|
||||
from typing import Optional
|
||||
|
||||
import mmcv
|
||||
import numpy as np
|
||||
from mmcv.transforms import BaseTransform
|
||||
from mmcv.transforms import LoadAnnotations as MMCV_LoadAnnotations
|
||||
|
||||
from mmocr.registry import TRANSFORMS
|
||||
|
|
@ -336,90 +333,3 @@ class LoadKIEAnnotations(MMCV_LoadAnnotations):
|
|||
repr_str += f'with_label={self.with_label}, '
|
||||
repr_str += f'with_text={self.with_text})'
|
||||
return repr_str
|
||||
|
||||
|
||||
@TRANSFORMS.register_module()
|
||||
class LoadImageFromLMDB(BaseTransform):
|
||||
"""Load an image from lmdb file. Only support LMDB file at disk.
|
||||
|
||||
LMDB file is organized with the following structure:
|
||||
lmdb
|
||||
|__data.mdb
|
||||
|__lock.mdb
|
||||
|
||||
Required Keys:
|
||||
|
||||
- img_path (In LMDB img_path is a key in the format of "image-{i:09d}".)
|
||||
|
||||
Modified Keys:
|
||||
|
||||
- img
|
||||
- img_shape
|
||||
- ori_shape
|
||||
|
||||
Args:
|
||||
to_float32 (bool): Whether to convert the loaded image to a float32
|
||||
numpy array. If set to False, the loaded image is an uint8 array.
|
||||
Defaults to False.
|
||||
color_type (str): The flag argument for :func:``mmcv.imfrombytes``.
|
||||
Defaults to 'color'.
|
||||
imdecode_backend (str): The image decoding backend type. The backend
|
||||
argument for :func:``mmcv.imfrombytes``.
|
||||
See :func:``mmcv.imfrombytes`` for details.
|
||||
Defaults to 'cv2'.
|
||||
file_client_args (dict): Arguments to instantiate a FileClient.
|
||||
See :class:`mmcv.fileio.FileClient` for details.
|
||||
Defaults to ``dict(backend='lmdb', db_path='')``.
|
||||
ignore_empty (bool): Whether to allow loading empty image or file path
|
||||
not existent. Defaults to False.
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
to_float32: bool = False,
|
||||
color_type: str = 'color',
|
||||
imdecode_backend: str = 'cv2',
|
||||
file_client_args: dict = dict(backend='lmdb', db_path=''),
|
||||
ignore_empty: bool = False) -> None:
|
||||
self.ignore_empty = ignore_empty
|
||||
self.to_float32 = to_float32
|
||||
self.color_type = color_type
|
||||
self.imdecode_backend = imdecode_backend
|
||||
self.file_client_args = file_client_args.copy()
|
||||
self.file_client = mmcv.FileClient(**self.file_client_args)
|
||||
|
||||
def transform(self, results: dict) -> Optional[dict]:
|
||||
"""Functions to load image from LMDB file.
|
||||
|
||||
Args:
|
||||
results (dict): Result dict from :obj:``mmcv.BaseDataset``.
|
||||
|
||||
Returns:
|
||||
dict: The dict contains loaded image and meta information.
|
||||
"""
|
||||
filename = results['img_path']
|
||||
lmdb_path = os.path.dirname(filename)
|
||||
image_key = os.path.basename(filename)
|
||||
self.file_client.client.db_path = lmdb_path
|
||||
img_bytes = self.file_client.get(image_key)
|
||||
if img_bytes is None:
|
||||
return None
|
||||
try:
|
||||
img = mmcv.imfrombytes(img_bytes, flag=self.color_type)
|
||||
except OSError:
|
||||
return None
|
||||
if self.to_float32:
|
||||
img = img.astype(np.float32)
|
||||
|
||||
results['img'] = img
|
||||
results['img_shape'] = img.shape[:2]
|
||||
results['ori_shape'] = img.shape[:2]
|
||||
return results
|
||||
|
||||
def __repr__(self):
|
||||
repr_str = (f'{self.__class__.__name__}('
|
||||
f'ignore_empty={self.ignore_empty}, '
|
||||
f'to_float32={self.to_float32}, '
|
||||
f"color_type='{self.color_type}', "
|
||||
f"imdecode_backend='{self.imdecode_backend}', "
|
||||
f'file_client_args={self.file_client_args})')
|
||||
return repr_str
|
||||
|
|
|
|||
|
|
@ -4,8 +4,7 @@ from unittest import TestCase
|
|||
|
||||
import numpy as np
|
||||
|
||||
from mmocr.datasets.transforms import (LoadImageFromLMDB, LoadKIEAnnotations,
|
||||
LoadOCRAnnotations)
|
||||
from mmocr.datasets.transforms import LoadKIEAnnotations, LoadOCRAnnotations
|
||||
|
||||
|
||||
class TestLoadOCRAnnotations(TestCase):
|
||||
|
|
@ -135,53 +134,3 @@ class TestLoadKIEAnnotations(TestCase):
|
|||
repr(self.load),
|
||||
'LoadKIEAnnotations(with_bbox=True, with_label=True, '
|
||||
'with_text=True)')
|
||||
|
||||
|
||||
class TestLoadImageFromLMDB(TestCase):
|
||||
|
||||
def setUp(self):
|
||||
img_key = 'image-%09d' % 1
|
||||
self.results1 = {
|
||||
'img_path': f'tests/data/recog_toy_dataset/imgs.lmdb/{img_key}'
|
||||
}
|
||||
|
||||
img_key = 'image-%09d' % 100
|
||||
self.results2 = {
|
||||
'img_path': f'tests/data/recog_toy_dataset/imgs.lmdb/{img_key}'
|
||||
}
|
||||
|
||||
def test_transform(self):
|
||||
transform = LoadImageFromLMDB()
|
||||
results = transform(copy.deepcopy(self.results1))
|
||||
self.assertIn('img', results)
|
||||
self.assertIsInstance(results['img'], np.ndarray)
|
||||
self.assertEqual(results['img'].shape[:2], results['img_shape'])
|
||||
self.assertEqual(results['ori_shape'], results['img_shape'])
|
||||
|
||||
def test_invalid_key(self):
|
||||
transform = LoadImageFromLMDB()
|
||||
results = transform(copy.deepcopy(self.results2))
|
||||
self.assertEqual(results, None)
|
||||
|
||||
def test_to_float32(self):
|
||||
transform = LoadImageFromLMDB(to_float32=True)
|
||||
results = transform(copy.deepcopy(self.results1))
|
||||
self.assertIn('img', results)
|
||||
self.assertIsInstance(results['img'], np.ndarray)
|
||||
self.assertTrue(results['img'].dtype, np.float32)
|
||||
self.assertEqual(results['img'].shape[:2], results['img_shape'])
|
||||
self.assertEqual(results['ori_shape'], results['img_shape'])
|
||||
|
||||
def test_repr(self):
|
||||
transform = LoadImageFromLMDB()
|
||||
assert repr(transform) == (
|
||||
'LoadImageFromLMDB(ignore_empty=False, '
|
||||
"to_float32=False, color_type='color', "
|
||||
"imdecode_backend='cv2', "
|
||||
"file_client_args={'backend': 'lmdb', 'db_path': ''})")
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
test = TestLoadImageFromLMDB()
|
||||
test.setUp()
|
||||
test.test_transform()
|
||||
|
|
|
|||
Loading…
Reference in New Issue