Bump version to v1.0.0 (#743)

* Bump version to v1.0.0 * fix lint * update * update * update dockerfile * update font color * update readtherdocs * update annoucement * update * update
2023-04-06 15:49:37 +08:00 · 2023-04-06 15:49:37 +08:00 · 6ae4ee5f74
parent db6fb76cf1
commit 6ae4ee5f74
19 changed files with 125 additions and 37 deletions
--- a/README.md
+++ b/README.md
@ -31,9 +31,11 @@
 [🆕Update News](https://mmselfsup.readthedocs.io/en/latest/notes/changelog.html) |
 [🤔Reporting Issues](https://github.com/open-mmlab/mmselfsup/issues/new/choose)

-🌟 MMSelfSup will be integrated into MMPreTrain， which is a newly upgraded open-source framework for visual pre-training. It has set out to provide multiple powerful pre-trained backbones and support different pre-training strategies.
+<img src="https://user-images.githubusercontent.com/36138628/230306412-43a5f316-bd54-4d2a-b196-210656e74683.png" width="500"/>

-:point_right: **MMPreTrain 1.0 branch is in trial, welcome every to [try it](https://github.com/open-mmlab/mmclassification/tree/pretrain) and [discuss with us](https://github.com/open-mmlab/mmclassification/discussions)!** :point_left:
+🌟 MMPreTrain is a newly upgraded open-source framework for visual pre-training. It has set out to provide multiple powerful pre-trained backbones and support different pre-training strategies.
+
+:point_right: **MMPreTrain 1.0 branch is in trial, welcome every to [try it](https://github.com/open-mmlab/mmclassification) and [discuss with us](https://github.com/open-mmlab/mmclassification/discussions)!** :point_left:

 </div>

@ -67,7 +69,7 @@ English | [简体中文](README_zh-CN.md)

 MMSelfSup is an open source self-supervised representation learning toolbox based on PyTorch. It is a part of the [OpenMMLab](https://openmmlab.com/) project.

-The master branch works with **PyTorch 1.6** or higher.
+The master branch works with **PyTorch 1.8** or higher.

 ### Major features

@ -89,7 +91,14 @@ The master branch works with **PyTorch 1.6** or higher.

 ## What's New

-**The default branch has been switched to `1.x` from `master`, and we encourage users to migrate to the latest version, though it comes with some cost. Please refer to [Migration Guide](https://mmselfsup.readthedocs.io/en/latest/migration.html) for more details.**
+**MMSelfSup v1.0.0 was released based on `main` branch. Please refer to [Migration Guide](https://mmselfsup.readthedocs.io/en/latest/migration.html) for more details.**
+
+MMSelfSup **v1.0.0** was released in 06/04/2023.
+
+- Support `PixMIM`.
+- Support `DINO` in `projects/dino/`.
+- Refactor file io interface.
+- Refine documentations.

 MMSelfSup **v1.0.0rc6** was released in 10/02/2023.

@ -165,7 +174,7 @@ Supported algorithms:
 - [x] [CAE (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/cae)
 - [x] [MILAN (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/milan)
 - [x] [BEiT v2 (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/beitv2)
- [x] [EVA (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/eva)
+- [x] [EVA (CVPR'2023)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/eva)
 - [x] [MixMIM (ArXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mixmim)
 - [x] [PixMIM (ArXiv'2023)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/pixmim)

--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@ -31,11 +31,11 @@
 [🆕更新日志](https://mmselfsup.readthedocs.io/zh_CN/latest/notes/changelog.html) |
 [🤔报告问题](https://github.com/open-mmlab/mmselfsup/issues/new/choose)

-🌟 MMSelfSup 将整合进 MMPreTrain，一个全新升级的预训练开源算法框架。
+<img src="https://user-images.githubusercontent.com/36138628/230306412-43a5f316-bd54-4d2a-b196-210656e74683.png" width="500"/>

-MMPreTrain 旨在提供各种强大的预训练主干网络，并支持了不同的预训练策略。
+🌟 MMPreTrain 旨在提供各种强大的预训练主干网络，并支持了不同的预训练策略。

-:point_right: **MMPreTrain 1.0 版本即将正式发布，欢迎大家 [试用](https://github.com/open-mmlab/mmclassification/tree/pretrain) 并 [参与讨论](https://github.com/open-mmlab/mmclassification/discussions)！** :point_left:
+:point_right: **MMPreTrain 1.0 版本即将正式发布，欢迎大家 [试用](https://github.com/open-mmlab/mmclassification) 并 [参与讨论](https://github.com/open-mmlab/mmclassification/discussions)！** :point_left:

 </div>

@ -71,7 +71,7 @@ MMPreTrain 旨在提供各种强大的预训练主干网络，并支持了不同

 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。

-主分支代码支持 **PyTorch 1.6** 及以上的版本。
+主分支代码支持 **PyTorch 1.8** 及以上的版本。

 ### 主要特性

@ -93,7 +93,14 @@ MMSelfSup 是一个基于 PyTorch 实现的开源自监督表征学习工具箱

 ## 更新

-**默认分支已经从 `master` 切换到 `1.x`。我们鼓励用户迁移到最新版本，请参考 [迁移指南](https://mmselfsup.readthedocs.io/zh_CN/1.x/migration.html) 以了解更多细节。**
+**MMSelfSup v1.0.0 正式版已发布，请参考 [迁移指南](https://mmselfsup.readthedocs.io/zh_CN/1.x/migration.html) 以了解更多细节。**
+
+**v1.0.0** 版本已经在 2023.4.6 发布。
+
+- 支持了 `PixMIM` 自监督算法
+- 在 `projects/dino/` 支持了 `DINO`
+- 重构 file io 接口
+- 完善部分文档

 **v1.0.0rc6** 版本已经在 2023.2.10 发布。

@ -169,7 +176,7 @@ Useful Tools
 - [x] [CAE (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/cae)
 - [x] [MILAN (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/milan)
 - [x] [BEiT v2 (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/beitv2)
- [x] [EVA (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/eva)
+- [x] [EVA (CVPR'2023)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/eva)
 - [x] [MixMIM (ArXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mixmim)
 - [x] [PixMIM (ArXiv'2023)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/pixmim)

--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@ -14,7 +14,7 @@ RUN apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build

 # Install MMEngine and MMCV
 RUN pip install openmim
-RUN mim install mmengine "mmcv>=2.0.0rc1"
+RUN mim install mmengine "mmcv>=2.0.0"
 RUN mim install mmsegmentation mmdet

 # Install MMSelfSup
@ -22,5 +22,4 @@ RUN conda clean --all
 RUN git clone https://github.com/open-mmlab/mmselfsup.git  /mmselfsup
 WORKDIR /mmselfsup
 ENV FORCE_CUDA="1"
-RUN git checkout 1.x
 RUN pip install --no-cache-dir -e .
--- a/docs/en/conf.py
+++ b/docs/en/conf.py
@ -104,13 +104,13 @@ html_theme_options = {
            'children': [
                {
                    'name': 'MMSelfSup 0.x',
-                    'url': 'https://mmselfsup.readthedocs.io/en/latest/',
-                    'description': 'Main branch docs'
+                    'url': 'https://mmselfsup.readthedocs.io/en/0.x/',
+                    'description': '0.x branch docs'
                },
                {
                    'name': 'MMSelfSup 1.x',
-                    'url': 'https://mmselfsup.readthedocs.io/en/1.x/',
-                    'description': '1.x branch docs'
+                    'url': 'https://mmselfsup.readthedocs.io/en/latest/',
+                    'description': 'Main branch docs'
                },
            ],
            'active':
--- a/docs/en/notes/changelog.md
+++ b/docs/en/notes/changelog.md
@ -2,6 +2,41 @@

 ## MMSelfSup

+### v1.0.0 (06/04/2023)
+
+#### Highlight
+
+- Support `PixMIM`.
+- Support `DINO` in `projects/dino/`.
+
+#### New Features
+
+- Support `PixMIM` ([#721](https://github.com/open-mmlab/mmselfsup/pull/721))
+- Support `DINO` in `projects/dino/` ([#658](https://github.com/open-mmlab/mmselfsup/pull/658))
+- Support auto import modules from registry ([#660](https://github.com/open-mmlab/mmselfsup/pull/660))
+
+#### Bug Fixes
+
+- Fix registry import error of MMDet ([#732](https://github.com/open-mmlab/mmselfsup/pull/732))
+- Fix local-rank in pytorch2.0 ([#728](https://github.com/open-mmlab/mmselfsup/pull/728))
+- Update MAE 300e pt results ([#722](https://github.com/open-mmlab/mmselfsup/pull/722))
+- Add missing data preprocessor in tsne configs ([#715](https://github.com/open-mmlab/mmselfsup/pull/715))
+- Fix the bug in shape bias ([#717](https://github.com/open-mmlab/mmselfsup/pull/717))
+- Fix T-SNE TypeError ([#708](https://github.com/open-mmlab/mmselfsup/pull/708))
+
+#### Improvements
+
+- Update CI ([#742](https://github.com/open-mmlab/mmselfsup/pull/742), [#739](https://github.com/open-mmlab/mmselfsup/pull/739))
+- Remove file_client_args and apply new interface of fileio ([#662](https://github.com/open-mmlab/mmselfsup/pull/662))
+
+#### Docs
+
+- Update doc links ([#738](https://github.com/open-mmlab/mmselfsup/pull/738))
+- Translate customize_runtime.md ([#734](https://github.com/open-mmlab/mmselfsup/pull/734))
+- Add media links and mmpretrain announcement ([#730](https://github.com/open-mmlab/mmselfsup/pull/730), [#693](https://github.com/open-mmlab/mmselfsup/pull/693))
+- Translate two docs ([#725](https://github.com/open-mmlab/mmselfsup/pull/725))
+- Translate docs ([#723](https://github.com/open-mmlab/mmselfsup/pull/723))
+
 ### v1.0.0rc6 (10/02/2023)

 The `master` branch is still 0.x version and we will checkout a new `1.x` branch to release 1.x version. The two versions will be maintained simultaneously in the future.
--- a/docs/en/notes/faq.md
+++ b/docs/en/notes/faq.md
@ -12,7 +12,8 @@ Compatible MMEngine, MMCV, MMClassification, MMDetection and MMSegmentation vers

 | MMSelfSup version |      MMEngine version       |        MMCV version        |  MMClassification version   | MMSegmentation version | MMDetection version |
 | :---------------: | :-------------------------: | :------------------------: | :-------------------------: | :--------------------: | :-----------------: |
-|  1.0.0rc6 (1.x)   | mmengine >= 0.4.0, \< 1.0.0 | mmcv >= 2.0.0rc1, \< 2.1.0 | mmcls >= 1.0.0rc5, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
+|   1.0.0 (main)    | mmengine >= 0.4.0, \< 1.0.0 | mmcv >= 2.0.0rc4, \< 2.1.0 | mmcls >= 1.0.0rc6, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
+|     1.0.0rc6      | mmengine >= 0.4.0, \< 1.0.0 | mmcv >= 2.0.0rc1, \< 2.1.0 | mmcls >= 1.0.0rc5, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
 |     1.0.0rc5      | mmengine >= 0.4.0, \< 1.0.0 | mmcv >= 2.0.0rc1, \< 2.1.0 | mmcls >= 1.0.0rc5, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
 |     1.0.0rc4      | mmengine >= 0.3.0, \< 1.0.0 | mmcv >= 2.0.0rc1, \< 2.1.0 | mmcls >= 1.0.0rc4, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
 |     1.0.0rc3      | mmengine >= 0.3.0, \< 1.0.0 | mmcv >= 2.0.0rc1, \< 2.1.0 | mmcls >= 1.0.0rc0, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
--- a/docs/en/overview.md
+++ b/docs/en/overview.md
@ -42,9 +42,9 @@ Typically, SSL is considered as the pre-training algorithm for various model arc

 - For the pre-training stage, we refer the user to [Pre-train](user_guides/3_pretrain.md) for using various SSL algorithms to obtain the pre-trained model.

- For the benchmark stage, we refer the user to [Benchmark](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/#downstream-tasks) for examples and usage of applying the pre-trained models in many downstream tasks.
+- For the benchmark stage, we refer the user to [Benchmark](https://mmselfsup.readthedocs.io/en/latest/user_guides/#downstream-tasks) for examples and usage of applying the pre-trained models in many downstream tasks.

- Also, we provide some analysis tools and visualization tools [Useful Tools](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/#useful-tools) to help  diagnose the algorithm.
+- Also, we provide some analysis tools and visualization tools [Useful Tools](https://mmselfsup.readthedocs.io/en/latest/user_guides/#useful-tools) to help  diagnose the algorithm.

 ### Learn SSL with MMSelfSup

--- a/docs/en/user_guides/segmentation.md
+++ b/docs/en/user_guides/segmentation.md
@ -13,7 +13,7 @@ mim install 'mmsegmentation>=1.0.0rc0'

 It is very easy to install the package.

-Besides, please refer to MMSegmentation for [installation](https://mmsegmentation.readthedocs.io/en/dev-1.x/get_started.html) and [data preparation](https://mmsegmentation.readthedocs.io/en/dev-1.x/user_guides/2_dataset_prepare.html).
+Besides, please refer to MMSegmentation for [installation](https://mmsegmentation.readthedocs.io/en/latest/get_started.html) and [data preparation](https://mmsegmentation.readthedocs.io/en/latest/user_guides/2_dataset_prepare.html).

 ## Train

--- a/docs/zh_cn/conf.py
+++ b/docs/zh_cn/conf.py
@ -100,13 +100,13 @@ html_theme_options = {
            'children': [
                {
                    'name': 'MMSelfSup 0.x',
-                    'url': 'https://mmselfsup.readthedocs.io/zh_CN/latest/',
-                    'description': 'Main 分支文档'
+                    'url': 'https://mmselfsup.readthedocs.io/zh_CN/0.x/',
+                    'description': '0.x 分支文档'
                },
                {
                    'name': 'MMSelfSup 1.x',
-                    'url': 'https://mmselfsup.readthedocs.io/zh_CN/1.x/',
-                    'description': '1.x 分支文档'
+                    'url': 'https://mmselfsup.readthedocs.io/zh_CN/latest/',
+                    'description': 'Main 分支文档'
                },
            ],
            'active':
--- a/docs/zh_cn/notes/changelog.md
+++ b/docs/zh_cn/notes/changelog.md
@ -2,6 +2,41 @@

 ## MMSelfSup

+### v1.0.0 (06/04/2023)
+
+#### Highlight
+
+- 支持了 `PixMIM`
+- 在 `projects/dino/` 支持了 `DINO`
+
+#### New Features
+
+- 支持了 `PixMIM` ([#721](https://github.com/open-mmlab/mmselfsup/pull/721))
+- 在 `projects/dino/` 支持了 `DINO`  ([#658](https://github.com/open-mmlab/mmselfsup/pull/658))
+- 支持自动模块导入 ([#660](https://github.com/open-mmlab/mmselfsup/pull/660))
+
+#### Bug Fixes
+
+- 修复注册错误 ([#732](https://github.com/open-mmlab/mmselfsup/pull/732))
+- 修复 local-rank 在 pytorch2.0 ([#728](https://github.com/open-mmlab/mmselfsup/pull/728))
+- 更新 MAE 结果 ([#722](https://github.com/open-mmlab/mmselfsup/pull/722))
+- 修复 t-SNE 配置文件缺漏项 ([#715](https://github.com/open-mmlab/mmselfsup/pull/715))
+- 修复 shape bias 的 bug ([#717](https://github.com/open-mmlab/mmselfsup/pull/717))
+- 修复 T-SNE 类型错误 ([#708](https://github.com/open-mmlab/mmselfsup/pull/708))
+
+#### Improvements
+
+- 更新 CI ([#742](https://github.com/open-mmlab/mmselfsup/pull/742), [#739](https://github.com/open-mmlab/mmselfsup/pull/739))
+- 更新 file io 接口([#662](https://github.com/open-mmlab/mmselfsup/pull/662))
+
+#### Docs
+
+- 更新文档链接 ([#738](https://github.com/open-mmlab/mmselfsup/pull/738))
+- 翻译 customize_runtime.md ([#734](https://github.com/open-mmlab/mmselfsup/pull/734))
+- 添加社区链接和相关通知 ([#730](https://github.com/open-mmlab/mmselfsup/pull/730), [#693](https://github.com/open-mmlab/mmselfsup/pull/693))
+- 翻译文档 ([#725](https://github.com/open-mmlab/mmselfsup/pull/725))
+- 翻译文档 ([#723](https://github.com/open-mmlab/mmselfsup/pull/723))
+
 ### v1.0.0rc6 (10/02/2023)

 `master` 仍然是 0.x 版本，我们将会 checkout 一个新的 `1.x` 用来发布 1.x 版本。 未来我们会同时维护两个版本。
--- a/docs/zh_cn/notes/faq.md
+++ b/docs/zh_cn/notes/faq.md
@ -12,7 +12,8 @@ MMCV, MMClassification, MMDetection and MMSegmentation 的版本兼容性如下

 | MMSelfSup version |      MMEngine version       |        MMCV version        |  MMClassification version   | MMSegmentation version | MMDetection version |
 | :---------------: | :-------------------------: | :------------------------: | :-------------------------: | :--------------------: | :-----------------: |
-|  1.0.0rc6 (1.x)   | mmengine >= 0.4.0, \< 1.0.0 | mmcv >= 2.0.0rc1, \< 2.1.0 | mmcls >= 1.0.0rc5, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
+|   1.0.0 (main)    | mmengine >= 0.4.0, \< 1.0.0 | mmcv >= 2.0.0rc4, \< 2.1.0 | mmcls >= 1.0.0rc6, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
+|     1.0.0rc6      | mmengine >= 0.4.0, \< 1.0.0 | mmcv >= 2.0.0rc1, \< 2.1.0 | mmcls >= 1.0.0rc5, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
 |     1.0.0rc5      | mmengine >= 0.4.0, \< 1.0.0 | mmcv >= 2.0.0rc1, \< 2.1.0 | mmcls >= 1.0.0rc5, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
 |     1.0.0rc4      | mmengine >= 0.3.0, \< 1.0.0 | mmcv >= 2.0.0rc1, \< 2.1.0 | mmcls >= 1.0.0rc4, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
 |     1.0.0rc3      | mmengine >= 0.3.0, \< 1.0.0 | mmcv >= 2.0.0rc1, \< 2.1.0 | mmcls >= 1.0.0rc0, \< 1.1.0 |   mmseg >= 1.0.0rc0    |  mmdet >= 3.0.0rc0  |
--- a/docs/zh_cn/overview.md
+++ b/docs/zh_cn/overview.md
@ -41,9 +41,9 @@

 - 对于**预训练阶段**，我们推荐你参考[Pre-train](user_guides/3_pretrain.md) 来尝试各类预训练算法，获得预训练模型。

- 对于**下游任务迁移学习阶段**，我们推荐你参考[Benchmark](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/#downstream-tasks) 当中提供的示例，来使用预训练模型来尝试各种下游任务。
+- 对于**下游任务迁移学习阶段**，我们推荐你参考[Benchmark](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/#downstream-tasks) 当中提供的示例，来使用预训练模型来尝试各种下游任务。

- 除此之外，我们也提供了多种分析工具和可视化工具[Useful Tools](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/#useful-tools)来帮助用户更方便地对算法进行诊断和分析。
+- 除此之外，我们也提供了多种分析工具和可视化工具[Useful Tools](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/#useful-tools)来帮助用户更方便地对算法进行诊断和分析。

 ### 基于MMSelfSup学习自监督算法

--- a/docs/zh_cn/user_guides/segmentation.md
+++ b/docs/zh_cn/user_guides/segmentation.md
@ -13,7 +13,7 @@ mim install 'mmsegmentation>=1.0.0rc0'

 非常容易安装这个包。

-此外，请参考 MMSegmentation 的[安装](https://mmsegmentation.readthedocs.io/en/dev-1.x/get_started.html)和[数据准备](https://mmsegmentation.readthedocs.io/en/dev-1.x/user_guides/2_dataset_prepare.html)。
+此外，请参考 MMSegmentation 的[安装](https://mmsegmentation.readthedocs.io/zh_CN/latest/get_started.html)和[数据准备](https://mmsegmentation.readthedocs.io/zh_CN/latest/user_guides/2_dataset_prepare.html)。

 ## 训练

--- a/mmselfsup/init.py
+++ b/mmselfsup/init.py
@ -14,7 +14,7 @@ mmcv_minimum_version = '2.0.0rc4'
 mmcv_maximum_version = '2.1.0'
 mmcv_version = digit_version(mmcv.__version__)

-mmcls_minimum_version = '1.0.0rc5'
+mmcls_minimum_version = '1.0.0rc6'
 mmcls_maximum_version = '1.1.0'
 mmcls_version = digit_version(mmcls.__version__)

--- a/mmselfsup/version.py
+++ b/mmselfsup/version.py
@ -1,6 +1,6 @@
 # Copyright (c) Open-MMLab. All rights reserved.

-__version__ = '1.0.0rc6'
+__version__ = '1.0.0'


 def parse_version_info(version_str):
--- a/model-index.yml
+++ b/model-index.yml
@ -22,3 +22,4 @@ Import:
  - configs/selfsup/beitv2/metafile.yml
  - configs/selfsup/eva/metafile.yml
  - configs/selfsup/mixmim/metafile.yml
+  - configs/selfsup/pixmim/metafile.yml
--- a/requirements/mminstall.txt
+++ b/requirements/mminstall.txt
@ -1,5 +1,5 @@
-mmcls>=1.0.0rc5,<1.1.0
-mmcv>=2.0.0rc1,<2.1.0
+mmcls>=1.0.0rc6,<1.1.0
+mmcv>=2.0.0rc4,<2.1.0
 # mmdet>=3.0.0rc0,<3.1.0
 mmengine>=0.4.0,<1.0.0
 # mmsegmentation>=1.0.0rc0,<1.1.0
--- a/requirements/readthedocs.txt
+++ b/requirements/readthedocs.txt
@ -1,8 +1,8 @@
-mmcls>=1.0.0rc5
-mmcv>=2.0.0rc1
+mmcls>=1.0.0rc6
+mmcv>=2.0.0rc4
 mmdet>=3.0.0rc0
 mmengine>=0.4.0
-mmselfsup>=1.0.0rc1
+mmselfsup>=1.0.0rc6
 scikit-learn
 torch
 torchvision
--- a/requirements/runtime.txt
+++ b/requirements/runtime.txt
@ -2,7 +2,7 @@ attrs
 einops
 future
 matplotlib
-mmcls>=1.0.0rc5,<1.1.0
+mmcls>=1.0.0rc6,<1.1.0
 numpy
 packaging
 scikit-learn