mmselfsup/README_zh-CN.md

229 lines
14 KiB
Markdown
Raw Normal View History

2021-12-15 19:06:36 +08:00
<div align="center">
<img src="./resources/mmselfsup_logo.png" width="500"/>
<div>&nbsp;</div>
<div align="center">
<b><font size="5">OpenMMLab 官网</font></b>
<sup>
<a href="https://openmmlab.com">
<i><font size="4">HOT</font></i>
</a>
</sup>
&nbsp;&nbsp;&nbsp;&nbsp;
<b><font size="5">OpenMMLab 开放平台</font></b>
<sup>
<a href="https://platform.openmmlab.com">
<i><font size="4">TRY IT OUT</font></i>
</a>
</sup>
</div>
<div>&nbsp;</div>
2021-12-15 19:06:36 +08:00
[![PyPI](https://img.shields.io/pypi/v/mmselfsup)](https://pypi.org/project/mmselfsup)
[![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmselfsup.readthedocs.io/en/dev-1.x/)
[![badge](https://github.com/open-mmlab/mmselfsup/workflows/build/badge.svg)](https://github.com/open-mmlab/mmselfsup/actions)
[![codecov](https://codecov.io/gh/open-mmlab/mmselfsup/branch/master/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmselfsup)
[![license](https://img.shields.io/github/license/open-mmlab/mmselfsup.svg)](https://github.com/open-mmlab/mmselfsup/blob/master/LICENSE)
[![open issues](https://isitmaintained.com/badge/open/open-mmlab/mmselfsup.svg)](https://github.com/open-mmlab/mmselfsup/issues)
2021-12-15 19:06:36 +08:00
[📘使用文档](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/) |
[🛠️安装教程](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/get_started.html) |
[👀模型库](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/model_zoo.html) |
[🆕更新日志](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/notes/changelog.html) |
[🤔报告问题](https://github.com/open-mmlab/mmselfsup/issues/new/choose)
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
</div>
2021-12-15 19:06:36 +08:00
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
<div align="center">
2021-12-15 19:06:36 +08:00
[English](README.md) | 简体中文
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
</div>
## 介绍
MMSelfSup 是一个基于 PyTorch 实现的开源自监督表征学习工具箱,是 [OpenMMLab](https://openmmlab.com/) 项目成员之一。
2021-12-15 19:06:36 +08:00
主分支代码支持 **PyTorch 1.6** 及以上的版本。
2021-12-15 19:06:36 +08:00
### 主要特性
- **多方法集成**
MMSelfSup 提供了多种前沿的自监督学习算法,大部分的自监督预训练学习都设置相同,以在基准中获得更加公平的比较。
- **模块化设计**
MMSelfSup 遵照 OpenMMLab 项目一贯的设计理念,进行模块化设计,便于用户自定义实现自己的算法。
- **标准化的性能评测**
MMSelfSup 拥有丰富的基准进行评估和测试,包括线性评估, 线性特征的 SVM / Low-shot SVM, 半监督分类, 目标检测和语义分割。
2021-12-15 20:36:00 +08:00
- **兼容性**
兼容 OpenMMLab 各大算法库,拥有丰富的下游评测任务和预训练模型的应用。
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
## 更新
2021-12-15 19:06:36 +08:00
**v1.0.0rc3** 版本已经在 2022.12.07 发布。
- 支持 BEiT 和 MILAN 预训练
- 支持 low-level 重建可视化
- 更新模型库算法页面文档
**v1.0.0rc3** 版本已经在 2022.11.01 发布。
- 支持 MaskFeat
请参考 [更新日志](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/notes/changelog.html) 获取更多细节和历史版本信息。
MMSelfSup 1.x 和 0.x 的不同点写在 [迁移文档](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/migration.html) 中。
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
## 安装
MMSelfSup 依赖 [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open-mmlab/mmcv), [MMEngine](https://github.com/open-mmlab/mmengine) 和 [MMClassification](https://github.com/open-mmlab/mmclassification)。
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
请参考 [安装文档](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/get_started.html) 获取更详细的安装指南。
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
## 快速入门
我们针对基础使用和进阶用法提供了 [用户指引](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/index.html)
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
Pretrain
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
- [Config](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/1_config.html)
- [Prepare Dataset](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/2_dataset_prepare.html)
- [Pretrain with Existing Models](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/3_pretrain.html)
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
Downetream Tasks
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
- [Classification](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/classification.html)
- [Detection](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/detection.html)
- [Segmentation](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/segmentation.html)
Useful Tools
- [Visualization](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/visualization.html)
- [Analysis Tools](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/analysis_tools.html)
我们也提供了 [进阶指引](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/advanced_guides/index.html) 和 [Colab 教程](https://github.com/open-mmlab/mmselfsup/blob/master/demo/mmselfsup_colab_tutorial.ipynb)。
如果遇到问题,请参考 [常见问题解答](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/notes/faq.html)。
2021-12-15 20:36:00 +08:00
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
## 模型库
2021-12-15 19:06:36 +08:00
请参考 [模型库](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/model_zoo.html) 查看我们更加全面的模型基准结果。
2021-12-15 19:06:36 +08:00
目前已支持的算法:
- [x] [Relative Location (ICCV'2015)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/relavive_loc)
- [x] [Rotation Prediction (ICLR'2018)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/rotation_pred)
- [x] [DeepCluster (ECCV'2018)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/deepcluster)
- [x] [NPID (CVPR'2018)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/npid)
- [x] [ODC (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/odc)
- [x] [MoCo v1 (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mocov1)
- [x] [SimCLR (ICML'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/simclr)
- [x] [MoCo v2 (arXiv'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/byol)
- [x] [BYOL (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mocov2)
- [x] [SwAV (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/swav)
- [x] [DenseCL (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/densecl)
- [x] [SimSiam (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/simsiam)
- [x] [Barlow Twins (ICML'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/barlowtwins)
- [x] [MoCo v3 (ICCV'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mocov3)
- [x] [BEiT (ICLR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/beit)
- [x] [MAE (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mae)
- [x] [SimMIM (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/simmim)
- [x] [MaskFeat (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/maskfeat)
- [x] [CAE (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/cae)
- [x] [MILAN (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/milan)
- [x] [BEiT v2 (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/beitv2)
2021-12-15 19:06:36 +08:00
更多的算法实现已经在我们的计划中。
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
## 基准测试
2021-12-15 20:36:00 +08:00
| 基准测试方法 | 参考设置 |
| -------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| ImageNet Linear Classification (Multi-head) | [Goyal2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Goyal_Scaling_and_Benchmarking_Self-Supervised_Visual_Representation_Learning_ICCV_2019_paper.pdf) |
| ImageNet Linear Classification (Last) | |
| ImageNet Semi-Sup Classification | |
| Places205 Linear Classification (Multi-head) | [Goyal2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Goyal_Scaling_and_Benchmarking_Self-Supervised_Visual_Representation_Learning_ICCV_2019_paper.pdf) |
| iNaturalist2018 Linear Classification (Multi-head) | [Goyal2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Goyal_Scaling_and_Benchmarking_Self-Supervised_Visual_Representation_Learning_ICCV_2019_paper.pdf) |
| PASCAL VOC07 SVM | [Goyal2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Goyal_Scaling_and_Benchmarking_Self-Supervised_Visual_Representation_Learning_ICCV_2019_paper.pdf) |
| PASCAL VOC07 Low-shot SVM | [Goyal2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Goyal_Scaling_and_Benchmarking_Self-Supervised_Visual_Representation_Learning_ICCV_2019_paper.pdf) |
| PASCAL VOC07+12 Object Detection | [MoCo](http://openaccess.thecvf.com/content_CVPR_2020/papers/He_Momentum_Contrast_for_Unsupervised_Visual_Representation_Learning_CVPR_2020_paper.pdf) |
| COCO17 Object Detection | [MoCo](http://openaccess.thecvf.com/content_CVPR_2020/papers/He_Momentum_Contrast_for_Unsupervised_Visual_Representation_Learning_CVPR_2020_paper.pdf) |
| Cityscapes Segmentation | [MMSeg](configs/benchmarks/mmsegmentation/cityscapes/fcn_r50-d8_769x769_40k_cityscapes.py) |
| PASCAL VOC12 Aug Segmentation | [MMSeg](configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_512x512_20k_voc12aug.py) |
2021-12-15 19:06:36 +08:00
## 参与贡献
我们非常欢迎任何有助于提升 MMSelfSup 的贡献,请参考 [贡献指南](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/notes/contribution_guide.html) 来了解如何参与贡献。
2021-12-15 19:06:36 +08:00
## 致谢
MMSelfSup 是一款由不同学校和公司共同贡献的开源项目,我们感谢所有为项目提供算法复现和新功能支持的贡献者,以及提供宝贵反馈的用户;同时,我们非常感谢 OpenSelfSup 的原开发者和贡献者。
2021-12-15 20:36:00 +08:00
2021-12-15 19:06:36 +08:00
我们希望该工具箱和基准测试可以为社区提供灵活的代码工具,供用户复现现有算法并开发自己的新模型,从而不断为开源社区提供贡献。
## 引用
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
2021-12-15 19:06:36 +08:00
如果您发现此项目对您的研究有用,请考虑引用:
```bibtex
@misc{mmselfsup2021,
title={{MMSelfSup}: OpenMMLab Self-Supervised Learning Toolbox and Benchmark},
2021-12-15 19:06:36 +08:00
author={MMSelfSup Contributors},
howpublished = {\url{https://github.com/open-mmlab/mmselfsup}},
year={2021}
}
```
Bump version to v0.9.1 (#322) * [Fix]: Set qkv bias to False for cae and True for mae (#303) * [Fix]: Add mmcls transformer layer choice * [Fix]: Fix transformer encoder layer bug * [Fix]: Change UT of cae * [Feature]: Change the file name of cosine annealing hook (#304) * [Feature]: Change cosine annealing hook file name * [Feature]: Add UT for cosine annealing hook * [Fix]: Fix lint * read tutorials and fix typo (#308) * [Fix] fix config errors in MAE (#307) * update readthedocs algorithm readme (#310) * [Docs] Replace markdownlint with mdformat (#311) * Replace markdownlint with mdformat to avoid installing ruby * fix typo * add 'ba' to codespell ignore-words-list * Configure Myst-parser to parse anchor tag (#309) * [Docs] rewrite install.md (#317) * rewrite the install.md * add faq.md * fix lint * add FAQ to README * add Chinese version * fix typo * fix format * remove modification * fix format * [Docs] refine README.md file (#318) * refine README.md file * fix lint * format language button * rename getting_started.md * revise index.rst * add model_zoo.md to index.rst * fix lint * refine readme Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com> * [Enhance] update byol models and results (#319) * Update version information (#321) Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: Yi Lu <21515006@zju.edu.cn> Co-authored-by: RenQin <45731309+soonera@users.noreply.github.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
2022-06-01 09:59:05 +08:00
## 开源许可证
该项目采用 [Apache 2.0 开源许可证](LICENSE)。
2021-12-15 19:06:36 +08:00
## OpenMMLab 的其他项目
- [MMEngine](https://github.com/open-mmlab/mmengine): OpenMMLab 深度学习模型训练基础库
2021-12-15 19:06:36 +08:00
- [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab 计算机视觉基础库
- [MMEval](https://github.com/open-mmlab/mmeval): 统一开放的跨框架算法评测库
Bump version to v0.7.0 (#229) * [Enhance] add pre-commit hook for algo-readme and copyright (#213) * [Enhance] add test windows in workflows (#215) * [Enhance] add test windows in workflows * fix lint * add optional requirements * add try-except judgement * add opencv installation in windows test steps * fix path error on windows * update * update path * update * add pytest skip for algorithm test * update requirements/runtime.txt * update pytest skip * [Docs] translate 0_config.md into Chinese (#216) * [Docs] translate 0_config.md into Chinese * [Fix] fix format description in 0_config.md * Update: 0_config.md * [Fix] fix tsne 'no `init_cfg`' error (#222) * [Fix] fix tsne 'no init_cfg' and pool_type errors * [Refactor] fix linting of tsne vis * [Docs] reorganizing OpenMMLab projects and update algorithms in readme (#219) * [Docs] reorganizing OpenMMLab projects and update algorithms in readme * using small letters * fix typo * [Fix] fix image channel bgr/rgb bug and update benchmarks (#210) * [Fix] fix image channel bgr/rgb bug * update model zoo * update readme and metafile * [Fix] fix typo * [Fix] fix typo * [Fix] fix lint * modify Places205 directory according to the downloaded dataset * update results * [Fix] Fix the bug when using prefetch under multi-view methods, e.g., DenseCL (#218) * fig bug for prefetch_loader under multi-view setting * fix lint problem Co-authored-by: liming <liming.ai@bytedance.com> * [Feature]: MAE official (#221) * [Feature]: MAE single image pre-training * [Fix]: Fix config * [Fix]: Fix dataset link * [Feature]: Add run * [Refactor]: Delete spot * [Feature]: ignore nohup output file * [Feature]: Add auto script to generate run cmd * [Refactor]: Refactor mae config file * [Feature]: sz20 settings * [Feature]: Add auto resume * [Fix]: Fix lint * [Feature]: Make git ignore txt * [Refactor]: Delete gpus in script * [Fix]: Make generate_cmd to add --async * [Feature]: Initial version of Vit fine-tune * [Fix]: Add 1424 specific settings * [Fix]: Fix missing file client bug for 1424 * [Feature]: 1424 customized settings * [Fix]: Make drop in eval to False * [Feature]: Change the finetune and pre-training settings * [Feature]: Add debug setting * [Refactor]: Refactor the model * [Feature]: Customized settings * [Feature]: Add A100 settings * [Fix]: Change mae to imagenet * [Feature]: Change mae pretrain num workers to 32 * [Feature]: Change num workers to 16 * [Feature]: Add A100 setting for pre_release ft version * [Feature]: Add img_norm_cfg * [Fix]: Fix mae cls test missing logits bug * [Fix]: Fix mae cls head bias initialize to zero * [Feature]: Rename mae config name * [Feature]: Add MAE README.md * [Fix]: Fix lint * [Feature]: Fix typo * [Fix]: Fix typo * [Feature]: Fix invalid link * [Fix]: Fix finetune config file name * [Feature]: Official pretrain v1 * [Feature]: Change log interval to 100 * [Feature]: pretrain 1600 epochs * [Fix]: Change encoder num head to 12 * [Feature]: Mix precision * [Feature]: Add default value to random masking * [Feature]: Official MAE finetune * [Feature]: Finetune img per gpu 32 * [Feature]: Add multi machine training for lincls * [Fix]: Fix lincls master port master addr * [Feature]: Change img per gpu to 128 * [Feature]: Add linear eval and Refactor * [Fix]: Fix debug mode * [Fix]: Delete MAE dataset in __init__.py * [Feature]: normalize pixel for mae * [Fix]: Fix lint * [Feature]: LARS for linear eval * [Feature]: Add lars for mae linear eval * [Feature]: Change mae linear lars num workers to 32 * [Feature]: Change mae linear lars num workers to 8 * [Feature]: log every 25 iter for mae linear eval lars * [Feature]: Add 1600 epoch and 800 epoch pretraining * [Fix]: Change linear eval to 902 * [Fix]: Add random flip to linear eval * [Fix]: delete fp16 in mae * [Refactor]: Change backbone to mmcls * [Fix]: Align finetune settings * [Fix]: replace timm trunc_normal with mmcv trunc_normal * [Fix]: Change finetune layer_decay to 0.65 * [Fix]: Delete pretrain last norm when global_pooling * [Fix]: set requires_grad of norm1 to False * [Fix]: delete norm1 * [Fix]: Fix docstring bug * [Fix]: Fix lint * [Fix]: Add external link * [Fix]: Delete auto_resume and reformat config readme. * [Fix]: Fix pytest bug * [Fix]: Fix lint * [Refactor]: Rename filename * [Feature]: Add docstring * [Fix]: Rename config file name * [Fix]: Fix name inconsistency bug * [Fix]: Change the default value of persistent_worker in builder to True * [Fix]: Change the default value of CPUS_PER_TASK to 5 * [Fix]: Add a blank line to line136 in tools/train.py * [Fix]: Fix MAE algorithm docstring format and add paper name and url * [Feature]: Add MAE paper name and link, and store mae teaser on github * [Refactor]: Delete mae.png * [Fix]: Fix config file name” * [Fix]: Fix name bug * [Refactor]: Change default GPUS to 8 * [Fix]: Abandon change to drop_last * [Fix]: Fix docstring in mae algorithm * [Fix]: Fix lint * [Fix]: Fix lint * [Fix]: Fix mae finetune algo type bug * [Feature]: Add unit test for algorithm * [Feature]: Add unit test for remaining parts * [Fix]: Fix lint * [Fix]: Fix typo * [Fix]: Delete some unnecessary modification in gitignore * [Feature]: Change finetune setting in mae algo to mixup setting * [Fix]: Change norm_pix_loss to norm_pix in pretrain head * [Fix]: Delete modification in dist_train_linear.sh * [Refactor]: Delete global pool in mae_cls_vit.py * [Fix]: Change finetune param to mixup in test_mae_classification * [Fix]: Change norm_pix_loss to norm_pix of mae_pretrain_head in unit test * [Fix]: Change norm_pix_loss to norm_pix in unit test * [Refactor]: Create init_weights for mae_finetune_head and mae_linprobe_head * [Refactor]: Construct 2d sin-cosine position embedding using torch * [Refactor]: Using classification and using mixup from mmcls * [Fix]: Fix lint * [Fix]: Add False to finetune mae linprobe‘ “ * [Fix]: Set drop_last to False * [Fix]: Fix MAE finetune layerwise lr bug * [Refactor]: Delete redundant MAE when registering MAE * [Refactor]: Split initialize_weights in MAE to submodules * [Fix]: Change the min_lr of mae pretrain to 0.0 * [Refactor]: Delete unused _init_weights in mae_cls_vit * [Refactor]: Change MAE cls vit to a more general name * [Feature]: Add Epoch Fix cosine annealing lr updater * [Fix]: Fix lint * [Feature]: Add layer wise lr decay in optimizer constructor * [Fix]: Fix lint * [Fix]: Fix set layer wise lr decay bug * [Fix]: Fix UT for MAE * [Fix]: Fix lint * [Fix]: update algorithm readme format for MAE * [Fix]: Fix isort * [Fix]: Add Returns inmae_pretrain_vit * [Fix]: Change bgr to rgb * [Fix]: Change norm pix to True * [Fix]: Use cls_token to linear prob * [Fix]: Delete mixup.py * [Fix]: Fix MAE readme * [Feature]: Delete linprobe * [Refactor]: Merge MAE head into one file * [Fix]: Fix lint * [Fix]: rename mae_pretrain_head to mae_head * [Fix]: Fix import error in __init__.py * [Feature]: skip MAE algo UT when running on windows * [Fix]: Fix UT bug * [Feature]: Update model_zoo * [Fix]: Rename MAE pretrain model name * [Fix]: Delete mae ft prefix * [Feature]: Change b to base * [Refactor]: Change b in MAE pt config to base * [Fix]: Fix typo in docstring * [Fix]: Fix name bug * [Feature]: Add new constructor for MAE finetune * [Fix]: Fix model_zoo link * [Fix]: Skip UT for MAE * [Fix]: Change fixed channel order to param Co-authored-by: LIU Yuan <liuyuuan@pjlab.org.cn> Co-authored-by: liu yuan <liuyuan@pjlab.org.cn> * [Feature]: Add diff seeds to diff ranks and set torch seed in worker_init_fn (#228) * [Feature]: Add set diff seeds to diff ranks * [Fix]: Set diff seed to diff workers * Bump version to v0.7.0 (#227) * Bump version to v0.7.0 * [Docs] update readme Co-authored-by: wang11wang <95845452+wang11wang@users.noreply.github.com> Co-authored-by: Liangyu Chen <45140242+c-liangyu@users.noreply.github.com> Co-authored-by: Ming Li <73068772+mitming@users.noreply.github.com> Co-authored-by: liming <liming.ai@bytedance.com> Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: LIU Yuan <liuyuuan@pjlab.org.cn> Co-authored-by: liu yuan <liuyuan@pjlab.org.cn>
2022-03-04 13:43:49 +08:00
- [MIM](https://github.com/open-mmlab/mim): MIM 是 OpenMMlab 项目、算法、模型的统一入口
- [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab 图像分类工具箱
- [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab 目标检测工具箱
- [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab 新一代通用 3D 目标检测平台
- [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab 旋转框检测工具箱与测试基准
- [MMYOLO](https://github.com/open-mmlab/mmyolo): OpenMMLab YOLO 系列工具箱和基准测试
Bump version to v0.7.0 (#229) * [Enhance] add pre-commit hook for algo-readme and copyright (#213) * [Enhance] add test windows in workflows (#215) * [Enhance] add test windows in workflows * fix lint * add optional requirements * add try-except judgement * add opencv installation in windows test steps * fix path error on windows * update * update path * update * add pytest skip for algorithm test * update requirements/runtime.txt * update pytest skip * [Docs] translate 0_config.md into Chinese (#216) * [Docs] translate 0_config.md into Chinese * [Fix] fix format description in 0_config.md * Update: 0_config.md * [Fix] fix tsne 'no `init_cfg`' error (#222) * [Fix] fix tsne 'no init_cfg' and pool_type errors * [Refactor] fix linting of tsne vis * [Docs] reorganizing OpenMMLab projects and update algorithms in readme (#219) * [Docs] reorganizing OpenMMLab projects and update algorithms in readme * using small letters * fix typo * [Fix] fix image channel bgr/rgb bug and update benchmarks (#210) * [Fix] fix image channel bgr/rgb bug * update model zoo * update readme and metafile * [Fix] fix typo * [Fix] fix typo * [Fix] fix lint * modify Places205 directory according to the downloaded dataset * update results * [Fix] Fix the bug when using prefetch under multi-view methods, e.g., DenseCL (#218) * fig bug for prefetch_loader under multi-view setting * fix lint problem Co-authored-by: liming <liming.ai@bytedance.com> * [Feature]: MAE official (#221) * [Feature]: MAE single image pre-training * [Fix]: Fix config * [Fix]: Fix dataset link * [Feature]: Add run * [Refactor]: Delete spot * [Feature]: ignore nohup output file * [Feature]: Add auto script to generate run cmd * [Refactor]: Refactor mae config file * [Feature]: sz20 settings * [Feature]: Add auto resume * [Fix]: Fix lint * [Feature]: Make git ignore txt * [Refactor]: Delete gpus in script * [Fix]: Make generate_cmd to add --async * [Feature]: Initial version of Vit fine-tune * [Fix]: Add 1424 specific settings * [Fix]: Fix missing file client bug for 1424 * [Feature]: 1424 customized settings * [Fix]: Make drop in eval to False * [Feature]: Change the finetune and pre-training settings * [Feature]: Add debug setting * [Refactor]: Refactor the model * [Feature]: Customized settings * [Feature]: Add A100 settings * [Fix]: Change mae to imagenet * [Feature]: Change mae pretrain num workers to 32 * [Feature]: Change num workers to 16 * [Feature]: Add A100 setting for pre_release ft version * [Feature]: Add img_norm_cfg * [Fix]: Fix mae cls test missing logits bug * [Fix]: Fix mae cls head bias initialize to zero * [Feature]: Rename mae config name * [Feature]: Add MAE README.md * [Fix]: Fix lint * [Feature]: Fix typo * [Fix]: Fix typo * [Feature]: Fix invalid link * [Fix]: Fix finetune config file name * [Feature]: Official pretrain v1 * [Feature]: Change log interval to 100 * [Feature]: pretrain 1600 epochs * [Fix]: Change encoder num head to 12 * [Feature]: Mix precision * [Feature]: Add default value to random masking * [Feature]: Official MAE finetune * [Feature]: Finetune img per gpu 32 * [Feature]: Add multi machine training for lincls * [Fix]: Fix lincls master port master addr * [Feature]: Change img per gpu to 128 * [Feature]: Add linear eval and Refactor * [Fix]: Fix debug mode * [Fix]: Delete MAE dataset in __init__.py * [Feature]: normalize pixel for mae * [Fix]: Fix lint * [Feature]: LARS for linear eval * [Feature]: Add lars for mae linear eval * [Feature]: Change mae linear lars num workers to 32 * [Feature]: Change mae linear lars num workers to 8 * [Feature]: log every 25 iter for mae linear eval lars * [Feature]: Add 1600 epoch and 800 epoch pretraining * [Fix]: Change linear eval to 902 * [Fix]: Add random flip to linear eval * [Fix]: delete fp16 in mae * [Refactor]: Change backbone to mmcls * [Fix]: Align finetune settings * [Fix]: replace timm trunc_normal with mmcv trunc_normal * [Fix]: Change finetune layer_decay to 0.65 * [Fix]: Delete pretrain last norm when global_pooling * [Fix]: set requires_grad of norm1 to False * [Fix]: delete norm1 * [Fix]: Fix docstring bug * [Fix]: Fix lint * [Fix]: Add external link * [Fix]: Delete auto_resume and reformat config readme. * [Fix]: Fix pytest bug * [Fix]: Fix lint * [Refactor]: Rename filename * [Feature]: Add docstring * [Fix]: Rename config file name * [Fix]: Fix name inconsistency bug * [Fix]: Change the default value of persistent_worker in builder to True * [Fix]: Change the default value of CPUS_PER_TASK to 5 * [Fix]: Add a blank line to line136 in tools/train.py * [Fix]: Fix MAE algorithm docstring format and add paper name and url * [Feature]: Add MAE paper name and link, and store mae teaser on github * [Refactor]: Delete mae.png * [Fix]: Fix config file name” * [Fix]: Fix name bug * [Refactor]: Change default GPUS to 8 * [Fix]: Abandon change to drop_last * [Fix]: Fix docstring in mae algorithm * [Fix]: Fix lint * [Fix]: Fix lint * [Fix]: Fix mae finetune algo type bug * [Feature]: Add unit test for algorithm * [Feature]: Add unit test for remaining parts * [Fix]: Fix lint * [Fix]: Fix typo * [Fix]: Delete some unnecessary modification in gitignore * [Feature]: Change finetune setting in mae algo to mixup setting * [Fix]: Change norm_pix_loss to norm_pix in pretrain head * [Fix]: Delete modification in dist_train_linear.sh * [Refactor]: Delete global pool in mae_cls_vit.py * [Fix]: Change finetune param to mixup in test_mae_classification * [Fix]: Change norm_pix_loss to norm_pix of mae_pretrain_head in unit test * [Fix]: Change norm_pix_loss to norm_pix in unit test * [Refactor]: Create init_weights for mae_finetune_head and mae_linprobe_head * [Refactor]: Construct 2d sin-cosine position embedding using torch * [Refactor]: Using classification and using mixup from mmcls * [Fix]: Fix lint * [Fix]: Add False to finetune mae linprobe‘ “ * [Fix]: Set drop_last to False * [Fix]: Fix MAE finetune layerwise lr bug * [Refactor]: Delete redundant MAE when registering MAE * [Refactor]: Split initialize_weights in MAE to submodules * [Fix]: Change the min_lr of mae pretrain to 0.0 * [Refactor]: Delete unused _init_weights in mae_cls_vit * [Refactor]: Change MAE cls vit to a more general name * [Feature]: Add Epoch Fix cosine annealing lr updater * [Fix]: Fix lint * [Feature]: Add layer wise lr decay in optimizer constructor * [Fix]: Fix lint * [Fix]: Fix set layer wise lr decay bug * [Fix]: Fix UT for MAE * [Fix]: Fix lint * [Fix]: update algorithm readme format for MAE * [Fix]: Fix isort * [Fix]: Add Returns inmae_pretrain_vit * [Fix]: Change bgr to rgb * [Fix]: Change norm pix to True * [Fix]: Use cls_token to linear prob * [Fix]: Delete mixup.py * [Fix]: Fix MAE readme * [Feature]: Delete linprobe * [Refactor]: Merge MAE head into one file * [Fix]: Fix lint * [Fix]: rename mae_pretrain_head to mae_head * [Fix]: Fix import error in __init__.py * [Feature]: skip MAE algo UT when running on windows * [Fix]: Fix UT bug * [Feature]: Update model_zoo * [Fix]: Rename MAE pretrain model name * [Fix]: Delete mae ft prefix * [Feature]: Change b to base * [Refactor]: Change b in MAE pt config to base * [Fix]: Fix typo in docstring * [Fix]: Fix name bug * [Feature]: Add new constructor for MAE finetune * [Fix]: Fix model_zoo link * [Fix]: Skip UT for MAE * [Fix]: Change fixed channel order to param Co-authored-by: LIU Yuan <liuyuuan@pjlab.org.cn> Co-authored-by: liu yuan <liuyuan@pjlab.org.cn> * [Feature]: Add diff seeds to diff ranks and set torch seed in worker_init_fn (#228) * [Feature]: Add set diff seeds to diff ranks * [Fix]: Set diff seed to diff workers * Bump version to v0.7.0 (#227) * Bump version to v0.7.0 * [Docs] update readme Co-authored-by: wang11wang <95845452+wang11wang@users.noreply.github.com> Co-authored-by: Liangyu Chen <45140242+c-liangyu@users.noreply.github.com> Co-authored-by: Ming Li <73068772+mitming@users.noreply.github.com> Co-authored-by: liming <liming.ai@bytedance.com> Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: LIU Yuan <liuyuuan@pjlab.org.cn> Co-authored-by: liu yuan <liuyuan@pjlab.org.cn>
2022-03-04 13:43:49 +08:00
- [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab 语义分割工具箱
- [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab 全流程文字检测识别理解工具箱
- [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab 姿态估计工具箱
2021-12-15 19:06:36 +08:00
- [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 人体参数化模型工具箱与测试基准
- [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab 自监督学习工具箱与测试基准
- [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab 模型压缩工具箱与测试基准
Bump version to v0.7.0 (#229) * [Enhance] add pre-commit hook for algo-readme and copyright (#213) * [Enhance] add test windows in workflows (#215) * [Enhance] add test windows in workflows * fix lint * add optional requirements * add try-except judgement * add opencv installation in windows test steps * fix path error on windows * update * update path * update * add pytest skip for algorithm test * update requirements/runtime.txt * update pytest skip * [Docs] translate 0_config.md into Chinese (#216) * [Docs] translate 0_config.md into Chinese * [Fix] fix format description in 0_config.md * Update: 0_config.md * [Fix] fix tsne 'no `init_cfg`' error (#222) * [Fix] fix tsne 'no init_cfg' and pool_type errors * [Refactor] fix linting of tsne vis * [Docs] reorganizing OpenMMLab projects and update algorithms in readme (#219) * [Docs] reorganizing OpenMMLab projects and update algorithms in readme * using small letters * fix typo * [Fix] fix image channel bgr/rgb bug and update benchmarks (#210) * [Fix] fix image channel bgr/rgb bug * update model zoo * update readme and metafile * [Fix] fix typo * [Fix] fix typo * [Fix] fix lint * modify Places205 directory according to the downloaded dataset * update results * [Fix] Fix the bug when using prefetch under multi-view methods, e.g., DenseCL (#218) * fig bug for prefetch_loader under multi-view setting * fix lint problem Co-authored-by: liming <liming.ai@bytedance.com> * [Feature]: MAE official (#221) * [Feature]: MAE single image pre-training * [Fix]: Fix config * [Fix]: Fix dataset link * [Feature]: Add run * [Refactor]: Delete spot * [Feature]: ignore nohup output file * [Feature]: Add auto script to generate run cmd * [Refactor]: Refactor mae config file * [Feature]: sz20 settings * [Feature]: Add auto resume * [Fix]: Fix lint * [Feature]: Make git ignore txt * [Refactor]: Delete gpus in script * [Fix]: Make generate_cmd to add --async * [Feature]: Initial version of Vit fine-tune * [Fix]: Add 1424 specific settings * [Fix]: Fix missing file client bug for 1424 * [Feature]: 1424 customized settings * [Fix]: Make drop in eval to False * [Feature]: Change the finetune and pre-training settings * [Feature]: Add debug setting * [Refactor]: Refactor the model * [Feature]: Customized settings * [Feature]: Add A100 settings * [Fix]: Change mae to imagenet * [Feature]: Change mae pretrain num workers to 32 * [Feature]: Change num workers to 16 * [Feature]: Add A100 setting for pre_release ft version * [Feature]: Add img_norm_cfg * [Fix]: Fix mae cls test missing logits bug * [Fix]: Fix mae cls head bias initialize to zero * [Feature]: Rename mae config name * [Feature]: Add MAE README.md * [Fix]: Fix lint * [Feature]: Fix typo * [Fix]: Fix typo * [Feature]: Fix invalid link * [Fix]: Fix finetune config file name * [Feature]: Official pretrain v1 * [Feature]: Change log interval to 100 * [Feature]: pretrain 1600 epochs * [Fix]: Change encoder num head to 12 * [Feature]: Mix precision * [Feature]: Add default value to random masking * [Feature]: Official MAE finetune * [Feature]: Finetune img per gpu 32 * [Feature]: Add multi machine training for lincls * [Fix]: Fix lincls master port master addr * [Feature]: Change img per gpu to 128 * [Feature]: Add linear eval and Refactor * [Fix]: Fix debug mode * [Fix]: Delete MAE dataset in __init__.py * [Feature]: normalize pixel for mae * [Fix]: Fix lint * [Feature]: LARS for linear eval * [Feature]: Add lars for mae linear eval * [Feature]: Change mae linear lars num workers to 32 * [Feature]: Change mae linear lars num workers to 8 * [Feature]: log every 25 iter for mae linear eval lars * [Feature]: Add 1600 epoch and 800 epoch pretraining * [Fix]: Change linear eval to 902 * [Fix]: Add random flip to linear eval * [Fix]: delete fp16 in mae * [Refactor]: Change backbone to mmcls * [Fix]: Align finetune settings * [Fix]: replace timm trunc_normal with mmcv trunc_normal * [Fix]: Change finetune layer_decay to 0.65 * [Fix]: Delete pretrain last norm when global_pooling * [Fix]: set requires_grad of norm1 to False * [Fix]: delete norm1 * [Fix]: Fix docstring bug * [Fix]: Fix lint * [Fix]: Add external link * [Fix]: Delete auto_resume and reformat config readme. * [Fix]: Fix pytest bug * [Fix]: Fix lint * [Refactor]: Rename filename * [Feature]: Add docstring * [Fix]: Rename config file name * [Fix]: Fix name inconsistency bug * [Fix]: Change the default value of persistent_worker in builder to True * [Fix]: Change the default value of CPUS_PER_TASK to 5 * [Fix]: Add a blank line to line136 in tools/train.py * [Fix]: Fix MAE algorithm docstring format and add paper name and url * [Feature]: Add MAE paper name and link, and store mae teaser on github * [Refactor]: Delete mae.png * [Fix]: Fix config file name” * [Fix]: Fix name bug * [Refactor]: Change default GPUS to 8 * [Fix]: Abandon change to drop_last * [Fix]: Fix docstring in mae algorithm * [Fix]: Fix lint * [Fix]: Fix lint * [Fix]: Fix mae finetune algo type bug * [Feature]: Add unit test for algorithm * [Feature]: Add unit test for remaining parts * [Fix]: Fix lint * [Fix]: Fix typo * [Fix]: Delete some unnecessary modification in gitignore * [Feature]: Change finetune setting in mae algo to mixup setting * [Fix]: Change norm_pix_loss to norm_pix in pretrain head * [Fix]: Delete modification in dist_train_linear.sh * [Refactor]: Delete global pool in mae_cls_vit.py * [Fix]: Change finetune param to mixup in test_mae_classification * [Fix]: Change norm_pix_loss to norm_pix of mae_pretrain_head in unit test * [Fix]: Change norm_pix_loss to norm_pix in unit test * [Refactor]: Create init_weights for mae_finetune_head and mae_linprobe_head * [Refactor]: Construct 2d sin-cosine position embedding using torch * [Refactor]: Using classification and using mixup from mmcls * [Fix]: Fix lint * [Fix]: Add False to finetune mae linprobe‘ “ * [Fix]: Set drop_last to False * [Fix]: Fix MAE finetune layerwise lr bug * [Refactor]: Delete redundant MAE when registering MAE * [Refactor]: Split initialize_weights in MAE to submodules * [Fix]: Change the min_lr of mae pretrain to 0.0 * [Refactor]: Delete unused _init_weights in mae_cls_vit * [Refactor]: Change MAE cls vit to a more general name * [Feature]: Add Epoch Fix cosine annealing lr updater * [Fix]: Fix lint * [Feature]: Add layer wise lr decay in optimizer constructor * [Fix]: Fix lint * [Fix]: Fix set layer wise lr decay bug * [Fix]: Fix UT for MAE * [Fix]: Fix lint * [Fix]: update algorithm readme format for MAE * [Fix]: Fix isort * [Fix]: Add Returns inmae_pretrain_vit * [Fix]: Change bgr to rgb * [Fix]: Change norm pix to True * [Fix]: Use cls_token to linear prob * [Fix]: Delete mixup.py * [Fix]: Fix MAE readme * [Feature]: Delete linprobe * [Refactor]: Merge MAE head into one file * [Fix]: Fix lint * [Fix]: rename mae_pretrain_head to mae_head * [Fix]: Fix import error in __init__.py * [Feature]: skip MAE algo UT when running on windows * [Fix]: Fix UT bug * [Feature]: Update model_zoo * [Fix]: Rename MAE pretrain model name * [Fix]: Delete mae ft prefix * [Feature]: Change b to base * [Refactor]: Change b in MAE pt config to base * [Fix]: Fix typo in docstring * [Fix]: Fix name bug * [Feature]: Add new constructor for MAE finetune * [Fix]: Fix model_zoo link * [Fix]: Skip UT for MAE * [Fix]: Change fixed channel order to param Co-authored-by: LIU Yuan <liuyuuan@pjlab.org.cn> Co-authored-by: liu yuan <liuyuan@pjlab.org.cn> * [Feature]: Add diff seeds to diff ranks and set torch seed in worker_init_fn (#228) * [Feature]: Add set diff seeds to diff ranks * [Fix]: Set diff seed to diff workers * Bump version to v0.7.0 (#227) * Bump version to v0.7.0 * [Docs] update readme Co-authored-by: wang11wang <95845452+wang11wang@users.noreply.github.com> Co-authored-by: Liangyu Chen <45140242+c-liangyu@users.noreply.github.com> Co-authored-by: Ming Li <73068772+mitming@users.noreply.github.com> Co-authored-by: liming <liming.ai@bytedance.com> Co-authored-by: Yuan Liu <30762564+YuanLiuuuuuu@users.noreply.github.com> Co-authored-by: LIU Yuan <liuyuuan@pjlab.org.cn> Co-authored-by: liu yuan <liuyuan@pjlab.org.cn>
2022-03-04 13:43:49 +08:00
- [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab 少样本学习工具箱与测试基准
- [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab 新一代视频理解工具箱
- [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab 一体化视频目标感知平台
- [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab 光流估计工具箱与测试基准
- [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab 图像视频编辑工具箱
- [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab 图片视频生成模型工具箱
- [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab 模型部署框架
2021-12-15 20:36:00 +08:00
2021-12-15 19:06:36 +08:00
## 欢迎加入 OpenMMLab 社区
扫描下方的二维码可关注 OpenMMLab 团队的 [知乎官方账号](https://www.zhihu.com/people/openmmlab),加入 OpenMMLab 团队的 [官方交流 QQ 群](https://jq.qq.com/?_wv=1027&k=GJP18SjI)添加OpenMMLab 官方小助手微信,加入 MMSelfSup 微信社区。
2021-12-15 19:06:36 +08:00
<div align="center">
<img src="./resources/zhihu_qrcode.jpg" height="400"/> <img src="./resources/qq_group_qrcode.jpg" height="400"/> <img src="./resources/xiaozhushou_weixin_qrcode.jpeg" height="400"/>
2021-12-15 19:06:36 +08:00
</div>
我们会在 OpenMMLab 社区为大家
- 📢 分享 AI 框架的前沿核心技术
- 💻 解读 PyTorch 常用模块源码
- 📰 发布 OpenMMLab 的相关新闻
- 🚀 介绍 OpenMMLab 开发的前沿算法
- 🏃 获取更高效的问题答疑和意见反馈
- 🔥 提供与各行各业开发者充分交流的平台
干货满满 📘,等你来撩 💗OpenMMLab 社区期待您的加入 👬