Bump v0.28.0 (open-mmlab#2047)

* bump v0.28.0

* update

Author: xiexinch

README.md

@@ -75,10 +75,12 @@ The master branch works with **PyTorch 1.5+**.
 
 ## What's New
 
-v0.27.0 was released in 7/28/2022:
+### 💎 Stable version
 
-- Add Swin-L Transformer models
-- Update ERFNet result on Cityscapes
+v0.28.0 was released in 9/08/2022:
+
+- Support Tversky Loss
+- Fix binary segmentation
 
 Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
 

README_zh-CN.md

@@ -72,10 +72,12 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 
 ## 最新进展
 
-最新版本 v0.27.0 在 2022.7.28 发布：
+### 💎 稳定版本
 
-- 添加 Swin-L Transformer 模型
-- 更新了 ERFNet 在 Cityscapes 上的结果
+最新版本 v0.28.0 在 2022.9.8 发布：
+
+- 支持 Tversky Loss
+- 修复二值分割
 
 如果想了解更多版本更新细节和历史信息，请阅读[更新日志](docs/en/changelog.md)。
 

docker/serve/Dockerfile

@@ -4,7 +4,7 @@ ARG CUDNN="8"
 FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
 
 ARG MMCV="1.5.0"
-ARG MMSEG="0.27.0"
+ARG MMSEG="0.28.0"
 
 ENV PYTHONUNBUFFERED TRUE
 

docs/en/changelog.md

@@ -1,5 +1,24 @@
 ## Changelog
 
+### V0.28.0 (9/8/2022)
+
+**New Features**
+
+- Support Tversky Loss ([#1896](https://github.com/open-mmlab/mmsegmentation/pull/1986))
+
+**Bug Fixes**
+
+- Fix binary segmentation ([#2016](https://github.com/open-mmlab/mmsegmentation/pull/2016))
+- Fix config files ([#1901](https://github.com/open-mmlab/mmsegmentation/pull/1901), [#1893](https://github.com/open-mmlab/mmsegmentation/pull/1893), [#1871](https://github.com/open-mmlab/mmsegmentation/pull/1871))
+- Revise documentation ([#1844](https://github.com/open-mmlab/mmsegmentation/pull/1844), [#1980](https://github.com/open-mmlab/mmsegmentation/pull/1980), [#2025](https://github.com/open-mmlab/mmsegmentation/pull/2025), [#1982](https://github.com/open-mmlab/mmsegmentation/pull/1982))
+- Fix confusion matrix calculation ([#1992](https://github.com/open-mmlab/mmsegmentation/pull/1992))
+- Fix decode head forward_train error ([#1997](https://github.com/open-mmlab/mmsegmentation/pull/1997))
+
+**Contributors**
+
+- @suchot made their first contribution in https://github.com/open-mmlab/mmsegmention/pull/1844
+- @TimoK93 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1992
+
 ### V0.27.0 (7/28/2022)
 
 **Enhancement**

docs/en/faq.md

@@ -9,6 +9,7 @@ The compatible MMSegmentation and MMCV versions are as below. Please install the
 | MMSegmentation version |        MMCV version         | MMClassification version |
 | :--------------------: | :-------------------------: | :----------------------: |
 |         master         |  mmcv-full>=1.5.0, \<1.7.0  | mmcls>=0.20.1, \<=1.0.0  |
+|         0.28.0         |  mmcv-full>=1.5.0, \<1.7.0  | mmcls>=0.20.1, \<=1.0.0  |
 |         0.27.0         |  mmcv-full>=1.5.0, \<1.7.0  | mmcls>=0.20.1, \<=1.0.0  |
 |         0.26.0         | mmcv-full>=1.5.0, \<=1.6.0  | mmcls>=0.20.1, \<=1.0.0  |
 |         0.25.0         | mmcv-full>=1.5.0, \<=1.6.0  | mmcls>=0.20.1, \<=1.0.0  |

docs/zh_cn/faq.md

@@ -9,6 +9,7 @@
 | MMSegmentation version |        MMCV version         | MMClassification version |
 | :--------------------: | :-------------------------: | :----------------------: |
 |         master         |  mmcv-full>=1.5.0, \<1.7.0  | mmcls>=0.20.1, \<=1.0.0  |
+|         0.28.0         |  mmcv-full>=1.5.0, \<1.7.0  | mmcls>=0.20.1, \<=1.0.0  |
 |         0.27.0         |  mmcv-full>=1.5.0, \<1.7.0  | mmcls>=0.20.1, \<=1.0.0  |
 |         0.26.0         | mmcv-full>=1.5.0, \<=1.6.0  | mmcls>=0.20.1, \<=1.0.0  |
 |         0.25.0         | mmcv-full>=1.5.0, \<=1.6.0  | mmcls>=0.20.1, \<=1.0.0  |

mmseg/version.py

@@ -1,6 +1,6 @@
 # Copyright (c) Open-MMLab. All rights reserved.
 
-__version__ = '0.27.0'
+__version__ = '0.28.0'
 
 
 def parse_version_info(version_str):