Update version (#296)

* [Feature]: Update to 0.9.0 * [Feature]: Add version constrain for mmcls * [Fix]: Fix bug * [Fix]: Fix version bug * [Feature]: Update version in install.md * update changelog * update readme * [Fix] fix uppercase * [Fix] fix uppercase * [Fix] fix uppercase * update version dependency * add cae to readme Co-authored-by: fangyixiao18 <fangyx18@hotmail.com> Co-authored-by: Jiahao Xie <52497952+Jiahao000@users.noreply.github.com>
open-mmlab · Apr 29, 2022 · 2bc4d31 · 2bc4d31
1 parent 7516b5b
commit 2bc4d31
Show file tree

Hide file tree

Showing 10 changed files with 91 additions and 26 deletions.
diff --git a/README.md b/README.md
@@ -66,13 +66,12 @@ This project is released under the [Apache 2.0 license](LICENSE).
 
 ## ChangeLog
 
-MMSelfSup **v0.8.0** was released in 31/03/2022.
+MMSelfSup **v0.9.0** was released in 29/04/2022.
 
 Highlights of the new version:
 
-* Support **SimMIM**
-* Add **KNN** benchmark, support KNN test with checkpoint and extracted backbone weights
-* Support ImageNet-21k dataset
+* Support **CAE**
+* Support **Barlow Twins**
 
 Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
 
@@ -123,7 +122,7 @@ More algorithms are in our plan.
 
 ## Installation
 
-MMSelfSup depends on [PyTorch](https://pytorch.org/)], [MMCV](https://github.com/open-mmlab/mmcv) and [MMClassification](https://github.com/open-mmlab/mmclassification).
+MMSelfSup depends 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.
 

diff --git a/README_zh-CN.md b/README_zh-CN.md
@@ -64,13 +64,12 @@ MMSelfSup 是一个基于 PyTorch 实现的开源自监督表征学习工具箱
 
 ## 更新日志
 
-最新的 **v0.8.0** 版本已经在 2022.03.31 发布。
+最新的 **v0.9.0** 版本已经在 2022.04.29 发布。
 
 新版本亮点：
 
-* 支持 **SimMIM**
-* 增加 **KNN** 基准测试，支持中间 checkpoint 和提取的 backbone 权重进行评估
-* 支持 ImageNet-21k 数据集
+* 支持 **CAE**
+* 支持 **Barlow Twins**
 
 请参考 [更新日志](docs/zh_cn/changelog.md) 获取更多细节和历史版本信息。
 
@@ -100,6 +99,7 @@ MMSelfSup 和 OpenSelfSup 的不同点写在 [对比文档](docs/en/compatibilit
 - [x] [MoCo v3 (ICCV'2021)](https://arxiv.org/abs/2104.02057)
 - [x] [MAE](https://arxiv.org/abs/2111.06377)
 - [x] [SimMIM](https://arxiv.org/abs/2111.09886)
+- [x] [CAE](https://arxiv.org/abs/2202.03026)
 
 更多的算法实现已经在我们的计划中。
 
@@ -121,7 +121,7 @@ MMSelfSup 和 OpenSelfSup 的不同点写在 [对比文档](docs/en/compatibilit
 
 ## 安装
 
-MMSelfSup 依赖 [PyTorch](https://pytorch.org/)], [MMCV](https://github.com/open-mmlab/mmcv) 和 [MMClassification](https://github.com/open-mmlab/mmclassification).
+MMSelfSup 依赖 [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open-mmlab/mmcv) 和 [MMClassification](https://github.com/open-mmlab/mmclassification).
 
 请参考 [安装文档](docs/zh_cn/install.md) 获取更详细的安装指南。
 

diff --git a/docs/en/changelog.md b/docs/en/changelog.md
@@ -2,6 +2,34 @@
 
 ## MMSelfSup
 
+### v0.9.0 (29/04/2022)
+
+#### Highlight
+* Support **CAE** ([#284](https://github.com/open-mmlab/mmselfsup/pull/284))
+* Support **Barlow Twins** ([#207](https://github.com/open-mmlab/mmselfsup/pull/207))
+
+#### New Features
+* Support CAE ([#284](https://github.com/open-mmlab/mmselfsup/pull/284))
+* Support Barlow twins ([#207](https://github.com/open-mmlab/mmselfsup/pull/207))
+* Add SimMIM 192 pretrain and 224 fine-tuning results ([#280](https://github.com/open-mmlab/mmselfsup/pull/280))
+* Add MAE pretrain with fp16 ([#271](https://github.com/open-mmlab/mmselfsup/pull/271))
+
+#### Bug Fixes
+* Fix args error ([#290](https://github.com/open-mmlab/mmselfsup/pull/290))
+* Change imgs_per_gpu to samples_per_gpu in MAE config ([#278](https://github.com/open-mmlab/mmselfsup/pull/278))
+* Avoid GPU memory leak with prefetch dataloader ([#277](https://github.com/open-mmlab/mmselfsup/pull/277))
+* Fix key error bug when registering custom hooks ([#273](https://github.com/open-mmlab/mmselfsup/pull/273))
+
+#### Improvements
+* Update SimCLR models and results ([#295](https://github.com/open-mmlab/mmselfsup/pull/295))
+* Reduce memory usage while running unit test ([#291](https://github.com/open-mmlab/mmselfsup/pull/291))
+* Remove pytorch1.5 test ([#288](https://github.com/open-mmlab/mmselfsup/pull/288))
+* Rename linear probing config file names ([#281](https://github.com/open-mmlab/mmselfsup/pull/281))
+* add unit test for apis ([#276](https://github.com/open-mmlab/mmselfsup/pull/276))
+
+#### Docs
+* Fix SimMIM config link, and add SimMIM to model_zoo ([#272](https://github.com/open-mmlab/mmselfsup/pull/272))
+
 ### v0.8.0 (31/03/2022)
 
 #### Highlight

diff --git a/docs/en/install.md b/docs/en/install.md
@@ -7,16 +7,17 @@
 - PyTorch 1.5+
 - CUDA 9.2+
 - GCC 5+
-- [mmcv](https://github.com/open-mmlab/mmcv) 1.3.16+
-- [mmcls](https://mmclassification.readthedocs.io/en/latest/install.html) 0.19.0+
+- [mmcv](https://github.com/open-mmlab/mmcv) 1.4.2+
+- [mmcls](https://mmclassification.readthedocs.io/en/latest/install.html) 0.21.0+
 - [mmdet](https://mmdetection.readthedocs.io/en/latest/get_started.html#installation) 2.16.0+
 - [mmseg](https://mmsegmentation.readthedocs.io/en/latest/get_started.html#installation) 0.20.2+
 
 Compatible MMCV, MMClassification, MMDetection and MMSegmentation versions are shown below. Please install the correct version of them to avoid installation issues.
 
 | MMSelfSup version |    MMCV version     |  MMClassification version  | MMSegmentation version | MMDetection version |
 | :---------------: | :-----------------: | :------------------------: | :--------------------: | :-----------------: |
-|  0.8.0 (master)   | mmcv-full >= 1.3.16 |      mmcls >= 0.21.0       |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |
+|  0.9.0 (master)   | mmcv-full >= 1.4.2  |      mmcls >= 0.21.0       |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |
+|       0.8.0       | mmcv-full >= 1.4.2  |      mmcls >= 0.21.0       |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |
 |       0.7.1       | mmcv-full >= 1.3.16 | mmcls >= 0.19.0, <= 0.20.1 |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |
 |       0.6.0       | mmcv-full >= 1.3.16 |      mmcls >= 0.19.0       |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |
 |       0.5.0       | mmcv-full >= 1.3.16 |             /              |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |

diff --git a/docs/zh_cn/changelog.md b/docs/zh_cn/changelog.md
@@ -2,31 +2,59 @@
 
 ## MMSelfSup
 
+### v0.9.0 (29/04/2022)
+
+#### 亮点
+* 支持 **CAE** ([#284](https://github.com/open-mmlab/mmselfsup/pull/284))
+* 支持 **Barlow Twins** ([#207](https://github.com/open-mmlab/mmselfsup/pull/207))
+
+#### 新特性
+* 支持 CAE ([#284](https://github.com/open-mmlab/mmselfsup/pull/284))
+* 支持 Barlow twins ([#207](https://github.com/open-mmlab/mmselfsup/pull/207))
+* 增加 SimMIM 192 预训练及 224 微调的结果 ([#280](https://github.com/open-mmlab/mmselfsup/pull/280))
+* 增加 MAE fp16 预训练设置 ([#271](https://github.com/open-mmlab/mmselfsup/pull/271))
+
+#### Bug 修复
+* 修复参数问题 ([#290](https://github.com/open-mmlab/mmselfsup/pull/290))
+* 在 MAE 配置中修改 imgs_per_gpu 为 samples_per_gpu ([#278](https://github.com/open-mmlab/mmselfsup/pull/278))
+* 使用 prefetch dataloader 时避免 GPU 内存溢出 ([#277](https://github.com/open-mmlab/mmselfsup/pull/277))
+* 修复在注册自定义钩子时键值错误的问题 ([#273](https://github.com/open-mmlab/mmselfsup/pull/273))
+
+#### 改进
+* 更新 SimCLR 模型和结果 ([#295](https://github.com/open-mmlab/mmselfsup/pull/295))
+* 单元测试减少内存使用 ([#291](https://github.com/open-mmlab/mmselfsup/pull/291))
+* 去除 pytorch 1.5 测试 ([#288](https://github.com/open-mmlab/mmselfsup/pull/288))
+* 重命名线性评估配置文件 ([#281](https://github.com/open-mmlab/mmselfsup/pull/281))
+* 为 api 增加单元测试 ([#276](https://github.com/open-mmlab/mmselfsup/pull/276))
+
+#### 文档
+* 在模型库增加 SimMIM 并修复链接 ([#272](https://github.com/open-mmlab/mmselfsup/pull/272))
+
 ### v0.8.0 (31/03/2022)
 
 #### 亮点
 * 支持 **SimMIM** ([#239](https://github.com/open-mmlab/mmselfsup/pull/239))
 * 增加 **KNN** 基准测试，支持中间 checkpoint 和提取的 backbone 权重进行评估 ([#243](https://github.com/open-mmlab/mmselfsup/pull/243))
 * 支持 ImageNet-21k 数据集 ([#225](https://github.com/open-mmlab/mmselfsup/pull/225))
 
-#### New Features
+#### 新特性
 * 支持 SimMIM ([#239](https://github.com/open-mmlab/mmselfsup/pull/239))
 * 增加 KNN 基准测试，支持中间 checkpoint 和提取的 backbone 权重进行评估 ([#243](https://github.com/open-mmlab/mmselfsup/pull/243))
 * 支持 ImageNet-21k 数据集 ([#225](https://github.com/open-mmlab/mmselfsup/pull/225))
 * 支持自动继续 checkpoint 文件的训练 ([#245](https://github.com/open-mmlab/mmselfsup/pull/245))
 
-#### Bug Fixes
+#### Bug 修复
 * 在分布式 sampler 中增加种子 ([#250](https://github.com/open-mmlab/mmselfsup/pull/250))
 * 修复 dist_test_svm_epoch.sh 中参数位置问题 ([#260](https://github.com/open-mmlab/mmselfsup/pull/260))
 * 修复 prepare_voc07_cls.sh 中 mkdir 潜在错误 ([#261](https://github.com/open-mmlab/mmselfsup/pull/261))
 
-#### Improvements
+#### 改进
 * 更新命令行参数模式 ([#253](https://github.com/open-mmlab/mmselfsup/pull/253))
 
-#### Docs
+#### 文档
 * 修复 6_benchmarks.md 中命令文档([#263](https://github.com/open-mmlab/mmselfsup/pull/263))
 * 翻译 6_benchmarks.md 到中文 ([#262](https://github.com/open-mmlab/mmselfsup/pull/262))
-*
+
 ### v0.7.0 (03/03/2022)
 
 #### 亮点

diff --git a/docs/zh_cn/install.md b/docs/zh_cn/install.md
@@ -7,16 +7,17 @@
 - PyTorch 1.5+
 - CUDA 9.2+
 - GCC 5+
-- [mmcv](https://github.com/open-mmlab/mmcv) 1.3.16+
-- [mmcls](https://mmclassification.readthedocs.io/en/latest/install.html) 0.19.0+
+- [mmcv](https://github.com/open-mmlab/mmcv) 1.4.2+
+- [mmcls](https://mmclassification.readthedocs.io/en/latest/install.html) 0.21.0+
 - [mmdet](https://mmdetection.readthedocs.io/en/latest/get_started.html#installation) 2.16.0+
 - [mmseg](https://mmsegmentation.readthedocs.io/en/latest/get_started.html#installation) 0.20.2+
 
 下表显示了与 MMSelfSup 适配的 MMCV, MMClassification, MMDetection 和 MMSegmentation 的版本号。 为避免安装过程中出现问题，请参照下表安装适配的版本。
 
 | MMSelfSup version |    MMCV version     |  MMClassification version  | MMSegmentation version | MMDetection version |
 | :---------------: | :-----------------: | :------------------------: | :--------------------: | :-----------------: |
-|  0.8.0 (master)   | mmcv-full >= 1.3.16 |      mmcls >= 0.21.0       |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |
+|  0.9.0 (master)   | mmcv-full >= 1.4.2  |      mmcls >= 0.21.0       |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |
+|       0.8.0       | mmcv-full >= 1.4.2  |      mmcls >= 0.21.0       |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |
 |       0.7.1       | mmcv-full >= 1.3.16 | mmcls >= 0.19.0, <= 0.20.1 |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |
 |       0.6.0       | mmcv-full >= 1.3.16 |      mmcls >= 0.19.0       |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |
 |       0.5.0       | mmcv-full >= 1.3.16 |             /              |    mmseg >= 0.20.2     |   mmdet >= 2.16.0   |

diff --git a/mmselfsup/__init__.py b/mmselfsup/__init__.py
@@ -1,6 +1,7 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 import warnings
 
+import mmcls
 import mmcv
 from packaging.version import parse
 
@@ -47,14 +48,21 @@ def digit_version(version_str: str, length: int = 4):
     return tuple(release)
 
 
-mmcv_minimum_version = '1.3.16'
-mmcv_maximum_version = '1.5.0'
+mmcv_minimum_version = '1.4.2'
+mmcv_maximum_version = '1.6.0'
 mmcv_version = digit_version(mmcv.__version__)
 
+mmcls_minimum_version = '0.21.0'
+mmcls_version = digit_version(mmcls.__version__)
+
 
 assert (mmcv_version >= digit_version(mmcv_minimum_version)
         and mmcv_version <= digit_version(mmcv_maximum_version)), \
     f'MMCV=={mmcv.__version__} is used but incompatible. ' \
     f'Please install mmcv>={mmcv_minimum_version}, <={mmcv_maximum_version}.'
 
+assert mmcls_version >= digit_version(mmcls_minimum_version), \
+    f'MMClassification=={mmcls.__version__} is used but incompatible. ' \
+    f'Please install mmcls>={mmcls_minimum_version}.'
+
 __all__ = ['__version__', 'digit_version']
diff --git a/mmselfsup/version.py b/mmselfsup/version.py
@@ -1,6 +1,6 @@
 # Copyright (c) Open-MMLab. All rights reserved.
 
-__version__ = '0.8.0'
+__version__ = '0.9.0'
 
 
 def parse_version_info(version_str):

diff --git a/requirements/mminstall.txt b/requirements/mminstall.txt
@@ -1,4 +1,4 @@
 mmcls >= 0.21.0
-mmcv-full>=1.3.16
+mmcv-full>=1.4.2
 mmdet >= 2.16.0
 mmsegmentation >= 0.20.2
diff --git a/requirements/readthedocs.txt b/requirements/readthedocs.txt
@@ -1,5 +1,5 @@
 faiss-cpu
-mmcv>=1.3.16
+mmcv>=1.4.2
 mmselfsup
 sklearn
 torch