Update version information (#383)

* Update version information

* update faq

* update paper information

* update description of changelog
pull/386/head v0.9.2
Yixiao Fang 2022-07-28 15:54:01 +08:00
parent 3f530f085e
commit 3ac192dad2
9 changed files with 80 additions and 38 deletions

View File

@ -65,12 +65,11 @@ The master branch works with **PyTorch 1.5** or higher.
## What's New
MMSelfSup **v0.9.1** was released in 31/05/2022.
MMSelfSup **v0.9.2** was released in 28/07/2022.
Highlights of the new version:
- Update **BYOL** model and results
- Refine some documentation
- Support MAE Reconstructed Image Visualization
Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
@ -120,9 +119,9 @@ Supported algorithms:
- [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](https://arxiv.org/abs/2111.06377)
- [x] [SimMIM](https://arxiv.org/abs/2111.09886)
- [x] [CAE](https://arxiv.org/abs/2202.03026)
- [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)
More algorithms are in our plan.

View File

@ -65,12 +65,11 @@ MMSelfSup 是一个基于 PyTorch 实现的开源自监督表征学习工具箱
## 更新
最新的 **v0.9.1** 版本已经在 2022.05.31 发布。
最新的 **v0.9.2** 版本已经在 2022.07.28 发布。
新版本亮点:
- 更新 **BYOL** 模型和结果
- 更新优化部分文档
- 支持 MAE 重建图像的可视化
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。
@ -120,9 +119,9 @@ MMSelfSup 依赖 [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open
- [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](https://arxiv.org/abs/2111.06377)
- [x] [SimMIM](https://arxiv.org/abs/2111.09886)
- [x] [CAE](https://arxiv.org/abs/2202.03026)
- [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)
更多的算法实现已经在我们的计划中。

View File

@ -2,6 +2,27 @@
## MMSelfSup
### v0.9.2 (28/07/2022)
#### New Features
- Support MAE Reconstructed Image Visualization ([#376](https://github.com/open-mmlab/mmselfsup/pull/376))
#### Bug Fixes
- Fix args/cfg bug in extract.py, use cfg.work_dir to save files ([#357](https://github.com/open-mmlab/mmselfsup/pull/357))
- Fix SimMIM mask generator config bug ([#360](https://github.com/open-mmlab/mmselfsup/pull/360))
#### Improvements
- Update mdformat settings ([#323](https://github.com/open-mmlab/mmselfsup/pull/323))
- Add circleci ([#374](https://github.com/open-mmlab/mmselfsup/pull/374))
#### Docs
- Fix the link of switch language ([#327](https://github.com/open-mmlab/mmselfsup/pull/327))
- Update lr_updater.py links in tutorials/4_schedule.md ([#354](https://github.com/open-mmlab/mmselfsup/pull/354))
### v0.9.1 (31/05/2022)
#### Highlight

View File

@ -6,14 +6,15 @@ We list some common troubles faced by many users and their corresponding solutio
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 |
| :---------------: | :-----------------: | :-------------------------: | :--------------------: | :-----------------: |
| 0.9.1 (master) | mmcv-full >= 1.4.2 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 0.9.0 | mmcv-full >= 1.4.2 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 0.8.0 | mmcv-full >= 1.4.2 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 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 |
| MMSelfSup version | MMCV version | MMClassification version | MMSegmentation version | MMDetection version |
| :---------------: | :--------------------------: | :-------------------------: | :--------------------: | :-----------------: |
| 0.9.2 (master) | mmcv-full >= 1.4.2, \< 1.7.0 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 0.9.1 | mmcv-full >= 1.4.2, \< 1.6.0 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 0.9.0 | mmcv-full >= 1.4.2 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 0.8.0 | mmcv-full >= 1.4.2 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 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 |
**Note:**

View File

@ -2,6 +2,27 @@
## MMSelfSup
### v0.9.2 (28/07/2022)
#### New Features
- 支持 MAE 重建图像的可视化 ([#376](https://github.com/open-mmlab/mmselfsup/pull/376))
#### Bug Fixes
- 修复 extract.py 文件中 cfg/args 路径问题,应用 cfg 中的路径进行处理 ([#357](https://github.com/open-mmlab/mmselfsup/pull/357))
- 修复 SimMIM 配置文件中掩码生成器类型名称的错误 ([#360](https://github.com/open-mmlab/mmselfsup/pull/360))
#### Improvements
- 更新 mdformat 设置 ([#323](https://github.com/open-mmlab/mmselfsup/pull/323))
- 添加 circle ci 配置 ([#374](https://github.com/open-mmlab/mmselfsup/pull/374))
#### Docs
- 修复语言更换链接问题 ([#327](https://github.com/open-mmlab/mmselfsup/pull/327))
- 更新 tutorials/4_schedule.md 中的文档链接([#354](https://github.com/open-mmlab/mmselfsup/pull/354))
### v0.9.1 (31/05/2022)
#### 亮点

View File

@ -6,14 +6,15 @@
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 |
| :---------------: | :-----------------: | :-------------------------: | :--------------------: | :-----------------: |
| 0.9.1 (master) | mmcv-full >= 1.4.2 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 0.9.0 | mmcv-full >= 1.4.2 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 0.8.0 | mmcv-full >= 1.4.2 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 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 |
| MMSelfSup version | MMCV version | MMClassification version | MMSegmentation version | MMDetection version |
| :---------------: | :--------------------------: | :-------------------------: | :--------------------: | :-----------------: |
| 0.9.2 (master) | mmcv-full >= 1.4.2, \< 1.7.0 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 0.9.1 | mmcv-full >= 1.4.2, \< 1.6.0 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 0.9.0 | mmcv-full >= 1.4.2 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 0.8.0 | mmcv-full >= 1.4.2 | mmcls >= 0.21.0 | mmseg >= 0.20.2 | mmdet >= 2.19.0 |
| 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 |
**注意:**

View File

@ -57,9 +57,9 @@ mmcls_version = digit_version(mmcls.__version__)
assert (mmcv_version >= digit_version(mmcv_minimum_version)
and mmcv_version <= digit_version(mmcv_maximum_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}.'
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. ' \

View File

@ -1,5 +1,5 @@
# Copyright (c) OpenMMLab. All rights reserved.
from typing import Optional, Dict, Tuple
from typing import Dict, Optional, Tuple
import torch
@ -15,17 +15,17 @@ class MAE(BaseModel):
<https://arxiv.org/abs/2111.06377>`_.
Args:
backbone (dict, optional): Config dict for encoder. Defaults to None.
neck (dict, optional): Config dict for encoder. Defaults to None.
head (dict, optional): Config dict for loss functions. Defaults to None.
backbone (dict): Config dict for encoder. Defaults to None.
neck (dict): Config dict for encoder. Defaults to None.
head (dict): Config dict for loss functions. Defaults to None.
init_cfg (dict, optional): Config dict for weight initialization.
Defaults to None.
"""
def __init__(self,
backbone: Optional[dict] = None,
neck: Optional[dict] = None,
head: Optional[dict] = None,
backbone: dict,
neck: dict,
head: dict,
init_cfg: Optional[dict] = None) -> None:
super().__init__(init_cfg)
assert backbone is not None

View File

@ -1,6 +1,6 @@
# Copyright (c) Open-MMLab. All rights reserved.
__version__ = '0.9.1'
__version__ = '0.9.2'
def parse_version_info(version_str):