Skip to content

Commit a7c2f68

Browse files
MengzhangLIMengzhangLI
authored
Bump v0.22.0 (open-mmlab#1347)
* change version to v0.22.0 * change version to v0.22.0 * add mmcls version in get_started.md * add mmcls installation and move PR1299 into enhancement * add mmcls installation and move PR1299 into enhancement * remove MMCLS and make mmcv <=1.5.0 version in get_started.md * fix typo
1 parent 7ddd2fe commit a7c2f68

File tree

8 files changed

+93
-45
lines changed

8 files changed

+93
-45
lines changed

‎README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -66,7 +66,7 @@ This project is released under the [Apache 2.0 license](LICENSE).
6666

6767
## Changelog
6868

69-
v0.21.0 was released in 2/9/2022.
69+
v0.22.0 was released in 3/4/2022.
7070
Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
7171

7272
## Benchmark and model zoo

‎README_zh-CN.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -65,7 +65,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
6565

6666
## 更新日志
6767

68-
最新版本 v0.21.1 在 2022.2.9 发布。
68+
最新版本 v0.22.0 在 2022.3.4 发布。
6969
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)。
7070

7171
## 基准测试和模型库

‎configs/convnext/README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -32,7 +32,7 @@ The "Roaring 20s" of visual recognition began with the introduction of Vision Tr
3232

3333
### Usage
3434

35-
- This backbone need to install [MMClassification](https://github.com/open-mmlab/mmclassification) first, which has abundant backbones for downstream tasks.
35+
- ConvNeXt backbone needs to install [MMClassification](https://github.com/open-mmlab/mmclassification) first, which has abundant backbones for downstream tasks.
3636

3737
```shell
3838
pip install mmcls>=0.20.1

‎docker/serve/Dockerfile‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ ARG CUDNN="7"
44
FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
55

66
ARG MMCV="1.4.4"
7-
ARG MMSEG="0.21.0"
7+
ARG MMSEG="0.22.0"
88

99
ENV PYTHONUNBUFFERED TRUE
1010

‎docs/en/changelog.md‎

Lines changed: 46 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,52 @@
11
## Changelog
22

33

4+
### V0.22 (3/04/2022)
5+
6+
**Highlights**
7+
8+
- Officially Support ConvNeXt: A ConvNet for the 2020s. Please use the latest MMClassification (0.21.0) to try it out.
9+
- Support iSAID aerial Dataset.
10+
- Officially Support inference on Windows OS.
11+
12+
**New Features**
13+
14+
- Support ConvNeXt: A ConvNet for the 2020s. ([#1216](https://github.com/open-mmlab/mmsegmentation/pull/1216))
15+
- Support iSAID aerial Dataset. ([#1115](https://github.com/open-mmlab/mmsegmentation/pull/1115)
16+
- Generating and plotting confusion matrix. ([#1301](https://github.com/open-mmlab/mmsegmentation/pull/1301))
17+
18+
**Improvements**
19+
20+
- Refactor 4 decoder heads (ASPP, FCN, PSP, UPer): Split forward function into `_forward_feature` and `cls_seg`. ([#1299](https://github.com/open-mmlab/mmsegmentation/pull/1299))
21+
- Add `min_size` arg in `Resize` to keep the shape after resize bigger than slide window. ([#1318](https://github.com/open-mmlab/mmsegmentation/pull/1318))
22+
- Revise pre-commit-hooks. ([#1315](https://github.com/open-mmlab/mmsegmentation/pull/1315))
23+
- Add win-ci. ([#1296](https://github.com/open-mmlab/mmsegmentation/pull/1296))
24+
25+
**Bug Fixes**
26+
27+
- Fix `mlp_ratio` type in Swin Transformer. ([#1274](https://github.com/open-mmlab/mmsegmentation/pull/1274))
28+
- Fix path errors in `./demo` . ([#1269](https://github.com/open-mmlab/mmsegmentation/pull/1269))
29+
- Fix bug in conversion of potsdam. ([#1279](https://github.com/open-mmlab/mmsegmentation/pull/1279))
30+
- Make accuracy take into account `ignore_index`. ([#1259](https://github.com/open-mmlab/mmsegmentation/pull/1259))
31+
- Add Pytorch HardSwish assertion in unit test. ([#1294](https://github.com/open-mmlab/mmsegmentation/pull/1294))
32+
- Fix wrong palette value in vaihingen. ([#1292](https://github.com/open-mmlab/mmsegmentation/pull/1292))
33+
- Fix the bug that SETR cannot load pretrain. ([#1293](https://github.com/open-mmlab/mmsegmentation/pull/1293))
34+
- Update correct `In Collection` in metafile of each configs. ([#1239](https://github.com/open-mmlab/mmsegmentation/pull/1239))
35+
- Upload completed STDC models. ([#1332](https://github.com/open-mmlab/mmsegmentation/pull/1332))
36+
- Fix `DNLHead` exports onnx inference difference type Cast error. ([#1161](https://github.com/open-mmlab/mmsegmentation/pull/1332))
37+
38+
39+
**Contributors**
40+
41+
- @JiaYanhao made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1269
42+
- @andife made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1281
43+
- @SBCV made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1279
44+
- @HJoonKwon made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1259
45+
- @Tsingularity made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1290
46+
- @Waterman0524 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1115
47+
- @MeowZheng made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1315
48+
- @linfangjian01 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1318
49+
450
### V0.21.1 (2/9/2022)
551

652
**Bug Fixes**

‎docs/en/get_started.md‎

Lines changed: 21 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -9,26 +9,27 @@
99

1010
The compatible MMSegmentation and MMCV versions are as below. Please install the correct version of MMCV to avoid installation issues.
1111

12-
| MMSegmentation version | MMCV version |
13-
|:----------------------:|:--------------------------:|
14-
| master | mmcv-full>=1.4.4, <1.5.0 |
15-
| 0.21.0 | mmcv-full>=1.4.4, <1.5.0 |
16-
| 0.20.0 | mmcv-full>=1.3.13, <1.5.0 |
17-
| 0.19.0 | mmcv-full>=1.3.13, <1.3.17 |
18-
| 0.18.0 | mmcv-full>=1.3.13, <1.3.17 |
19-
| 0.17.0 | mmcv-full>=1.3.7, <1.3.17 |
20-
| 0.16.0 | mmcv-full>=1.3.7, <1.3.17 |
21-
| 0.15.0 | mmcv-full>=1.3.7, <1.3.17 |
22-
| 0.14.1 | mmcv-full>=1.3.7, <1.3.17 |
23-
| 0.14.0 | mmcv-full>=1.3.1, <1.3.2 |
24-
| 0.13.0 | mmcv-full>=1.3.1, <1.3.2 |
25-
| 0.12.0 | mmcv-full>=1.1.4, <1.3.2 |
26-
| 0.11.0 | mmcv-full>=1.1.4, <1.3.0 |
27-
| 0.10.0 | mmcv-full>=1.1.4, <1.3.0 |
28-
| 0.9.0 | mmcv-full>=1.1.4, <1.3.0 |
29-
| 0.8.0 | mmcv-full>=1.1.4, <1.2.0 |
30-
| 0.7.0 | mmcv-full>=1.1.2, <1.2.0 |
31-
| 0.6.0 | mmcv-full>=1.1.2, <1.2.0 |
12+
| MMSegmentation version | MMCV version | MMClassification version |
13+
|:----------------------:|:--------------------------:|:------------------------:|
14+
| master | mmcv-full>=1.4.4, <=1.5.0 | mmcls>=0.20.1, <=1.0.0 |
15+
| 0.22.0 | mmcv-full>=1.4.4, <=1.5.0 | mmcls>=0.20.1, <=1.0.0 |
16+
| 0.21.1 | mmcv-full>=1.4.4, <=1.5.0 | Not required |
17+
| 0.20.2 | mmcv-full>=1.3.13, <=1.5.0 | Not required |
18+
| 0.19.0 | mmcv-full>=1.3.13, <1.3.17 | Not required |
19+
| 0.18.0 | mmcv-full>=1.3.13, <1.3.17 | Not required |
20+
| 0.17.0 | mmcv-full>=1.3.7, <1.3.17 | Not required |
21+
| 0.16.0 | mmcv-full>=1.3.7, <1.3.17 | Not required |
22+
| 0.15.0 | mmcv-full>=1.3.7, <1.3.17 | Not required |
23+
| 0.14.1 | mmcv-full>=1.3.7, <1.3.17 | Not required |
24+
| 0.14.0 | mmcv-full>=1.3.1, <1.3.2 | Not required |
25+
| 0.13.0 | mmcv-full>=1.3.1, <1.3.2 | Not required |
26+
| 0.12.0 | mmcv-full>=1.1.4, <1.3.2 | Not required |
27+
| 0.11.0 | mmcv-full>=1.1.4, <1.3.0 | Not required |
28+
| 0.10.0 | mmcv-full>=1.1.4, <1.3.0 | Not required |
29+
| 0.9.0 | mmcv-full>=1.1.4, <1.3.0 | Not required |
30+
| 0.8.0 | mmcv-full>=1.1.4, <1.2.0 | Not required |
31+
| 0.7.0 | mmcv-full>=1.1.2, <1.2.0 | Not required |
32+
| 0.6.0 | mmcv-full>=1.1.2, <1.2.0 | Not required |
3233

3334
:::{note}
3435
You need to run `pip uninstall mmcv` first if you have mmcv installed.

‎docs/zh_cn/get_started.md‎

Lines changed: 21 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -9,26 +9,27 @@
99

1010
可编译的 MMSegmentation 和 MMCV 版本如下所示，请对照对应版本安装以避免安装问题。
1111

12-
| MMSegmentation 版本 | MMCV 版本 |
13-
|:-----------------:|:--------------------------:|
14-
| master | mmcv-full>=1.4.4, <1.5.0 |
15-
| 0.21.0 | mmcv-full>=1.4.4, <1.5.0 |
16-
| 0.20.0 | mmcv-full>=1.3.13, <1.5.0 |
17-
| 0.19.0 | mmcv-full>=1.3.13, <1.3.17 |
18-
| 0.18.0 | mmcv-full>=1.3.13, <1.3.17 |
19-
| 0.17.0 | mmcv-full>=1.3.7, <1.3.17 |
20-
| 0.16.0 | mmcv-full>=1.3.7, <1.3.17 |
21-
| 0.15.0 | mmcv-full>=1.3.7, <1.3.17 |
22-
| 0.14.1 | mmcv-full>=1.3.7, <1.3.17 |
23-
| 0.14.0 | mmcv-full>=1.3.1, <1.3.2 |
24-
| 0.13.0 | mmcv-full>=1.3.1, <1.3.2 |
25-
| 0.12.0 | mmcv-full>=1.1.4, <1.3.2 |
26-
| 0.11.0 | mmcv-full>=1.1.4, <1.3.0 |
27-
| 0.10.0 | mmcv-full>=1.1.4, <1.3.0 |
28-
| 0.9.0 | mmcv-full>=1.1.4, <1.3.0 |
29-
| 0.8.0 | mmcv-full>=1.1.4, <1.2.0 |
30-
| 0.7.0 | mmcv-full>=1.1.2, <1.2.0 |
31-
| 0.6.0 | mmcv-full>=1.1.2, <1.2.0 |
12+
| MMSegmentation 版本 | MMCV 版本 | MMClassification 版本 |
13+
|:-----------------:|:--------------------------:|:----------------------:|
14+
| master | mmcv-full>=1.4.4, <=1.5.0 | mmcls>=0.20.1, <=1.0.0 |
15+
| 0.22.0 | mmcv-full>=1.4.4, <=1.5.0 | mmcls>=0.20.1, <=1.0.0 |
16+
| 0.21.1 | mmcv-full>=1.4.4, <=1.5.0 | Not required |
17+
| 0.20.2 | mmcv-full>=1.3.13, <=1.5.0 | Not required |
18+
| 0.19.0 | mmcv-full>=1.3.13, <1.3.17 | Not required |
19+
| 0.18.0 | mmcv-full>=1.3.13, <1.3.17 | Not required |
20+
| 0.17.0 | mmcv-full>=1.3.7, <1.3.17 | Not required |
21+
| 0.16.0 | mmcv-full>=1.3.7, <1.3.17 | Not required |
22+
| 0.15.0 | mmcv-full>=1.3.7, <1.3.17 | Not required |
23+
| 0.14.1 | mmcv-full>=1.3.7, <1.3.17 | Not required |
24+
| 0.14.0 | mmcv-full>=1.3.1, <1.3.2 | Not required |
25+
| 0.13.0 | mmcv-full>=1.3.1, <1.3.2 | Not required |
26+
| 0.12.0 | mmcv-full>=1.1.4, <1.3.2 | Not required |
27+
| 0.11.0 | mmcv-full>=1.1.4, <1.3.0 | Not required |
28+
| 0.10.0 | mmcv-full>=1.1.4, <1.3.0 | Not required |
29+
| 0.9.0 | mmcv-full>=1.1.4, <1.3.0 | Not required |
30+
| 0.8.0 | mmcv-full>=1.1.4, <1.2.0 | Not required |
31+
| 0.7.0 | mmcv-full>=1.1.2, <1.2.0 | Not required |
32+
| 0.6.0 | mmcv-full>=1.1.2, <1.2.0 | Not required |
3233

3334
注意: 如果您已经安装好 mmcv， 您首先需要运行 `pip uninstall mmcv`。
3435
如果 mmcv 和 mmcv-full 同时被安装，会报错 `ModuleNotFoundError`。

‎mmseg/version.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Copyright (c) Open-MMLab. All rights reserved.
22

3-
__version__ = '0.21.1'
3+
__version__ = '0.22.0'
44

55

66
def parse_version_info(version_str):

0 commit comments

Comments
 (0)