|
1 | 1 | ## Changelog
|
2 | 2 |
|
| 3 | +### V0.20 (12/10/2021) |
| 4 | + |
| 5 | +**Highlights** |
| 6 | + |
| 7 | +- Support Twins ([#989](https://github.com/open-mmlab/mmsegmentation/pull/989)) |
| 8 | +- Support a real-time segmentation model STDC ([#995](https://github.com/open-mmlab/mmsegmentation/pull/995)) |
| 9 | +- Support a widely-used segmentation model in lane detection ERFNet ([#960](https://github.com/open-mmlab/mmsegmentation/pull/960)) |
| 10 | +- Support A Remote Sensing Land-Cover Dataset LoveDA ([#1028](https://github.com/open-mmlab/mmsegmentation/pull/1028)) |
| 11 | +- Support focal loss ([#1024](https://github.com/open-mmlab/mmsegmentation/pull/1024)) |
| 12 | + |
| 13 | +**New Features** |
| 14 | + |
| 15 | +- Support Twins ([#989](https://github.com/open-mmlab/mmsegmentation/pull/989)) |
| 16 | +- Support a real-time segmentation model STDC ([#995](https://github.com/open-mmlab/mmsegmentation/pull/995)) |
| 17 | +- Support a widely-used segmentation model in lane detection ERFNet ([#960](https://github.com/open-mmlab/mmsegmentation/pull/960)) |
| 18 | +- Add SETR cityscapes benchmark ([#1087](https://github.com/open-mmlab/mmsegmentation/pull/1087)) |
| 19 | +- Add BiSeNetV1 COCO-Stuff 164k benchmark ([#1019](https://github.com/open-mmlab/mmsegmentation/pull/1019)) |
| 20 | +- Support focal loss ([#1024](https://github.com/open-mmlab/mmsegmentation/pull/1024)) |
| 21 | +- Add Cutout transform ([#1022](https://github.com/open-mmlab/mmsegmentation/pull/1022)) |
| 22 | + |
| 23 | +**Improvements** |
| 24 | + |
| 25 | +- Set a random seed when the user does not set a seed ([#1039](https://github.com/open-mmlab/mmsegmentation/pull/1039)) |
| 26 | +- Add CircleCI setup ([#1086](https://github.com/open-mmlab/mmsegmentation/pull/1086)) |
| 27 | +- Skip CI on ignoring given paths ([#1078](https://github.com/open-mmlab/mmsegmentation/pull/1078)) |
| 28 | +- Add abstract and image for every paper ([#1060](https://github.com/open-mmlab/mmsegmentation/pull/1060)) |
| 29 | +- Create a symbolic link on windows ([#1090](https://github.com/open-mmlab/mmsegmentation/pull/1090)) |
| 30 | +- Support video demo using trained model ([#1014](https://github.com/open-mmlab/mmsegmentation/pull/1014)) |
| 31 | + |
| 32 | +**Bug Fixes** |
| 33 | + |
| 34 | +- Fix incorrectly loading init_cfg or pretrained models of several transformer models ([#999](https://github.com/open-mmlab/mmsegmentation/pull/999), [#1069](https://github.com/open-mmlab/mmsegmentation/pull/1069), [#1102](https://github.com/open-mmlab/mmsegmentation/pull/1102)) |
| 35 | +- Fix EfficientMultiheadAttention in SegFormer ([#1003](https://github.com/open-mmlab/mmsegmentation/pull/1037)) |
| 36 | +- Remove `fp16` folder in `configs` ([#1031](https://github.com/open-mmlab/mmsegmentation/pull/1031)) |
| 37 | +- Fix several typos in .yml file (Dice Metric [#1041](https://github.com/open-mmlab/mmsegmentation/pull/1041), ADE20K dataset [#1120](https://github.com/open-mmlab/mmsegmentation/pull/1120), Training Memory (GB) [#1083](https://github.com/open-mmlab/mmsegmentation/pull/1083)) |
| 38 | +- Fix test error when using `--show-dir` ([#1091](https://github.com/open-mmlab/mmsegmentation/pull/1091)) |
| 39 | +- Fix dist training infinite waiting issue ([#1035](https://github.com/open-mmlab/mmsegmentation/pull/1035)) |
| 40 | +- Change the upper version of mmcv to 1.5.0 ([#1096](https://github.com/open-mmlab/mmsegmentation/pull/1096)) |
| 41 | +- Fix symlink failure on Windows ([#1038](https://github.com/open-mmlab/mmsegmentation/pull/1038)) |
| 42 | +- Cancel previous runs that are not completed ([#1118](https://github.com/open-mmlab/mmsegmentation/pull/1118)) |
| 43 | +- Unified links of readthedocs in docs ([#1119](https://github.com/open-mmlab/mmsegmentation/pull/1119)) |
| 44 | + |
| 45 | +**Contributors** |
| 46 | + |
| 47 | +- @Junjue-Wang made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1028 |
| 48 | +- @ddebby made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1066 |
| 49 | +- @del-zhenwu made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1078 |
| 50 | +- @KangBK0120 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1106 |
| 51 | +- @zergzzlun made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1091 |
| 52 | +- @fingertap made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1035 |
| 53 | +- @irvingzhang0512 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1014 |
| 54 | +- @littleSunlxy made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/989 |
| 55 | +- @lkm2835 |
| 56 | +- @RockeyCoss |
| 57 | +- @MengzhangLI |
| 58 | +- @Junjun2016 |
| 59 | +- @xiexinch |
| 60 | +- @xvjiarui |
| 61 | + |
3 | 62 | ### V0.19 (11/02/2021)
|
4 | 63 |
|
5 | 64 | **Highlights**
|
|
0 commit comments