From 519381fd4c6a1597f689d51f3f3cf55c3b6b17f0 Mon Sep 17 00:00:00 2001 From: Yixiao Fang <36138628+fangyixiao18@users.noreply.github.com> Date: Fri, 16 Sep 2022 18:00:27 +0800 Subject: [PATCH] [Docs] update readme (#474) * update readme * update readme zh-cn * fix lint * refine * update simmim and mocov3 --- README.md | 59 +++++++++++++++++++++++++++++++------------------ README_zh-CN.md | 55 +++++++++++++++++++++++++++++---------------- 2 files changed, 74 insertions(+), 40 deletions(-) diff --git a/README.md b/README.md index 6a831f6f..35765abc 100644 --- a/README.md +++ b/README.md @@ -65,6 +65,8 @@ The master branch works with **PyTorch 1.5** or higher. ## What's New +### Stable version + MMSelfSup **v0.9.2** was released in 28/07/2022. Highlights of the new version: @@ -75,17 +77,33 @@ Please refer to [changelog.md](docs/en/changelog.md) for details and release his Differences between MMSelfSup and OpenSelfSup codebases can be found in [compatibility.md](docs/en/compatibility.md). +### Preview of 1.x version + +A brand new version of **MMSelfSup v1.0.0rc1** was released in 01/09/2022: + +Highlights of the new version: + +- Based on [MMEngine](https://github.com/open-mmlab/mmengine) and [MMCV](https://github.com/open-mmlab/mmcv/tree/2.x). +- Released with refactor. +- Refine all [documents](https://mmselfsup.readthedocs.io/en/1.x/). +- Support `MAE`, `SimMIM`, `MoCoV3` with different pre-training epochs and backbones of different scales. +- More concise API. +- More powerful data pipeline. +- Higher accurcy for some algorithms. + +Find more new features in [1.x branch](https://github.com/open-mmlab/mmselfsup/tree/1.x). Issues and PRs are welcome! + ## Installation -MMSelfSup depends on [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open-mmlab/mmcv) and [MMClassification](https://github.com/open-mmlab/mmclassification). +MMSelfSup relies on [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open-mmlab/mmcv) and [MMClassification](https://github.com/open-mmlab/mmclassification). Please refer to [install.md](docs/en/install.md) for more detailed instruction. ## Get Started -Please refer to [prepare_data.md](docs/en/prepare_data.md) for dataset preparation and [get_started.md](docs/en/get_started.md) for the basic usage of MMSelfSup. +Please refer to [prepare_data.md](docs/en/prepare_data.md) for dataset preparation, [get_started.md](docs/en/get_started.md) for the basic usage and [benchmarks.md](docs/en/tutorials/6_benchmarks.md) for running benchmarks. -We also provides tutorials for more details: +We also provides more detailed tutorials: - [config](docs/en/tutorials/0_config.md) - [add new dataset](docs/en/tutorials/1_new_dataset.md) @@ -93,7 +111,6 @@ We also provides tutorials for more details: - [add new module](docs/en/tutorials/3_new_module.md) - [customize schedules](docs/en/tutorials/4_schedule.md) - [customize runtime](docs/en/tutorials/5_runtime.md) -- [benchmarks](docs/en/tutorials/6_benchmarks.md) Besides, we provide [colab tutorial](https://github.com/open-mmlab/mmselfsup/blob/master/demo/mmselfsup_colab_tutorial.ipynb) for basic usage. @@ -105,23 +122,23 @@ Please refer to [model_zoo.md](docs/en/model_zoo.md) for a comprehensive set of Supported algorithms: -- [x] [Relative Location (ICCV'2015)](https://arxiv.org/abs/1505.05192) -- [x] [Rotation Prediction (ICLR'2018)](https://arxiv.org/abs/1803.07728) -- [x] [DeepCluster (ECCV'2018)](https://arxiv.org/abs/1807.05520) -- [x] [NPID (CVPR'2018)](https://arxiv.org/abs/1805.01978) -- [x] [ODC (CVPR'2020)](https://arxiv.org/abs/2006.10645) -- [x] [MoCo v1 (CVPR'2020)](https://arxiv.org/abs/1911.05722) -- [x] [SimCLR (ICML'2020)](https://arxiv.org/abs/2002.05709) -- [x] [MoCo v2 (ArXiv'2020)](https://arxiv.org/abs/2003.04297) -- [x] [BYOL (NeurIPS'2020)](https://arxiv.org/abs/2006.07733) -- [x] [SwAV (NeurIPS'2020)](https://arxiv.org/abs/2006.09882) -- [x] [DenseCL (CVPR'2021)](https://arxiv.org/abs/2011.09157) -- [x] [SimSiam (CVPR'2021)](https://arxiv.org/abs/2011.10566) -- [x] [Barlow Twins (ICML'2021)](https://arxiv.org/abs/2103.03230) -- [x] [MoCo v3 (ICCV'2021)](https://arxiv.org/abs/2104.02057) -- [x] [MAE (CVPR'2022)](https://arxiv.org/abs/2111.06377) -- [x] [SimMIM (CVPR'2022)](https://arxiv.org/abs/2111.09886) -- [x] [CAE (ArXiv'2022)](https://arxiv.org/abs/2202.03026) +- [x] [Relative Location (ICCV'2015)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/relative_loc) +- [x] [Rotation Prediction (ICLR'2018)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/rotation_pred) +- [x] [DeepCluster (ECCV'2018)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/deepcluster) +- [x] [NPID (CVPR'2018)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/npid) +- [x] [ODC (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/odc) +- [x] [MoCo v1 (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/mocov1) +- [x] [SimCLR (ICML'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/simclr) +- [x] [MoCo v2 (ArXiv'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/byol) +- [x] [BYOL (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/mocov2) +- [x] [SwAV (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/swav) +- [x] [DenseCL (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/densecl) +- [x] [SimSiam (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/simsiam) +- [x] [Barlow Twins (ICML'2021)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/barlowtwins) +- [x] [MoCo v3 (ICCV'2021)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/mocov3) +- [x] [MAE (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/mae) +- [x] [SimMIM (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/simmim) +- [x] [CAE (ArXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/cae) More algorithms are in our plan. diff --git a/README_zh-CN.md b/README_zh-CN.md index 9dfbc425..a685185b 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -65,6 +65,8 @@ MMSelfSup 是一个基于 PyTorch 实现的开源自监督表征学习工具箱 ## 更新 +### 稳定版本 + 最新的 **v0.9.2** 版本已经在 2022.07.28 发布。 新版本亮点： @@ -75,6 +77,22 @@ MMSelfSup 是一个基于 PyTorch 实现的开源自监督表征学习工具箱 MMSelfSup 和 OpenSelfSup 的不同点写在 [对比文档](docs/en/compatibility.md) 中。 +### 1.x 预览版本 + +全新的 **MMSelfSup v1.0.0rc1** 版本已在 2022.09.01 发布。 + +新版本亮点： + +- 基于全新的 [MMEngine](https://github.com/open-mmlab/mmengine) 和 [MMCV](https://github.com/open-mmlab/mmcv/tree/2.x)。 +- 代码库重构，统一接口。 +- 完善了新版本 [文档](https://mmselfsup.readthedocs.io/en/1.x/)。 +- 支持了不同训练时间、不同尺寸的 `MAE`, `SimMIM`, `MoCoV3` 的预训练模型。 +- 更加简洁的 API。 +- 更加强大的数据管道。 +- 部分模型具有更高的准确率。 + +在 [1.x 分支](https://github.com/open-mmlab/mmselfsup/tree/1.x) 查看更多新特性。 欢迎大家提 Issues 和 PRs! + ## 安装 MMSelfSup 依赖 [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open-mmlab/mmcv) 和 [MMClassification](https://github.com/open-mmlab/mmclassification). @@ -83,7 +101,7 @@ MMSelfSup 依赖 [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open ## 快速入门 -请参考 [准备数据](docs/zh_cn/prepare_data.md) 准备数据集和 [入门指南](docs/zh_cn/get_started.md) 获取 MMSelfSup 的基本使用方法. +请参考 [准备数据](docs/zh_cn/prepare_data.md) 准备数据集, [入门指南](docs/zh_cn/get_started.md) 获取 MMSelfSup 的基本使用方法和 [基准测试](docs/zh_cn/tutorials/6_benchmarks.md) 来运行下游任务。 我们也提供了更加全面的教程，包括: @@ -93,7 +111,6 @@ MMSelfSup 依赖 [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open - [添加新模块](docs/zh_cn/tutorials/3_new_module.md) - [自定义流程](docs/zh_cn/tutorials/4_schedule.md) - [自定义运行](docs/zh_cn/tutorials/5_runtime.md) -- [基准测试](docs/zh_cn/tutorials/6_benchmarks.md) 另外，我们提供了 [colab 教程](https://github.com/open-mmlab/mmselfsup/blob/master/demo/mmselfsup_colab_tutorial.ipynb)。 @@ -105,23 +122,23 @@ MMSelfSup 依赖 [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open 目前已支持的算法: -- [x] [Relative Location (ICCV'2015)](https://arxiv.org/abs/1505.05192) -- [x] [Rotation Prediction (ICLR'2018)](https://arxiv.org/abs/1803.07728) -- [x] [DeepCLuster (ECCV'2018)](https://arxiv.org/abs/1807.05520) -- [x] [NPID (CVPR'2018)](https://arxiv.org/abs/1805.01978) -- [x] [ODC (CVPR'2020)](https://arxiv.org/abs/2006.10645) -- [x] [MoCo v1 (CVPR'2020)](https://arxiv.org/abs/1911.05722) -- [x] [SimCLR (ICML'2020)](https://arxiv.org/abs/2002.05709) -- [x] [MoCo v2 (ArXiv'2020)](https://arxiv.org/abs/2003.04297) -- [x] [BYOL (NeurIPS'2020)](https://arxiv.org/abs/2006.07733) -- [x] [SwAV (NeurIPS'2020)](https://arxiv.org/abs/2006.09882) -- [x] [DenseCL (CVPR'2021)](https://arxiv.org/abs/2011.09157) -- [x] [SimSiam (CVPR'2021)](https://arxiv.org/abs/2011.10566) -- [x] [Barlow Twins (ICML'2021)](https://arxiv.org/abs/2103.03230) -- [x] [MoCo v3 (ICCV'2021)](https://arxiv.org/abs/2104.02057) -- [x] [MAE (CVPR'2022)](https://arxiv.org/abs/2111.06377) -- [x] [SimMIM (CVPR'2022)](https://arxiv.org/abs/2111.09886) -- [x] [CAE (ArXiv'2022)](https://arxiv.org/abs/2202.03026) +- [x] [Relative Location (ICCV'2015)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/relative_loc) +- [x] [Rotation Prediction (ICLR'2018)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/rotation_pred) +- [x] [DeepCluster (ECCV'2018)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/deepcluster) +- [x] [NPID (CVPR'2018)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/npid) +- [x] [ODC (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/odc) +- [x] [MoCo v1 (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/mocov1) +- [x] [SimCLR (ICML'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/simclr) +- [x] [MoCo v2 (ArXiv'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/byol) +- [x] [BYOL (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/mocov2) +- [x] [SwAV (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/swav) +- [x] [DenseCL (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/densecl) +- [x] [SimSiam (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/simsiam) +- [x] [Barlow Twins (ICML'2021)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/barlowtwins) +- [x] [MoCo v3 (ICCV'2021)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/mocov3) +- [x] [MAE (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/mae) +- [x] [SimMIM (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/simmim) +- [x] [CAE (ArXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/master/configs/selfsup/cae) 更多的算法实现已经在我们的计划中。