|
1 | 1 | ## Changelog
|
2 | 2 |
|
| 3 | +### V0.24.0 (4/29/2022) |
| 4 | + |
| 5 | +**Highlights** |
| 6 | + |
| 7 | +- Support MAE: Masked Autoencoders Are Scalable Vision Learners |
| 8 | +- Support Resnet strikes back |
| 9 | + |
| 10 | +**New Features** |
| 11 | + |
| 12 | +- Support MAE: Masked Autoencoders Are Scalable Vision Learners ([1307](https://github.com/open-mmlab/mmsegmentation/pull/1307), [1523](https://github.com/open-mmlab/mmsegmentation/pull/1523)) |
| 13 | +- Support Resnet strikes back ([1390](https://github.com/open-mmlab/mmsegmentation/pull/1390)) |
| 14 | +- Support extra dataloader settings in configs ([1435](https://github.com/open-mmlab/mmsegmentation/pull/1435)) |
| 15 | + |
| 16 | +**Bug Fixes** |
| 17 | + |
| 18 | +- Fix input previous results for the last cascade_decode_head ([#1450](https://github.com/open-mmlab/mmsegmentation/pull/1450)) |
| 19 | +- Fix validation loss logging ([#1494](https://github.com/open-mmlab/mmsegmentation/pull/1494)) |
| 20 | +- Fix the bug in binary_cross_entropy ([1527](https://github.com/open-mmlab/mmsegmentation/pull/1527)) |
| 21 | +- Support single channel prediction for Binary Cross Entropy Loss ([#1454](https://github.com/open-mmlab/mmsegmentation/pull/1454)) |
| 22 | +- Fix potential bugs in accuracy.py ([1496](https://github.com/open-mmlab/mmsegmentation/pull/1496)) |
| 23 | +- Avoid converting label ids twice by label map during evaluation ([1417](https://github.com/open-mmlab/mmsegmentation/pull/1417)) |
| 24 | +- Fix bug about label_map ([1445](https://github.com/open-mmlab/mmsegmentation/pull/1445)) |
| 25 | +- Fix image save path bug in Windows ([1423](https://github.com/open-mmlab/mmsegmentation/pull/1423)) |
| 26 | +- Fix MMSegmentation Colab demo ([1501](https://github.com/open-mmlab/mmsegmentation/pull/1501), [1452](https://github.com/open-mmlab/mmsegmentation/pull/1452)) |
| 27 | +- Migrate azure blob for beit checkpoints ([1503](https://github.com/open-mmlab/mmsegmentation/pull/1503)) |
| 28 | +- Fix bug in `tools/analyse_logs.py` caused by wrong plot_iter in some cases ([1428](https://github.com/open-mmlab/mmsegmentation/pull/1428)) |
| 29 | + |
| 30 | +**Improvements** |
| 31 | + |
| 32 | +- Merge BEiT and ConvNext's LR decay optimizer constructors ([#1438](https://github.com/open-mmlab/mmsegmentation/pull/1438)) |
| 33 | +- Register optimizer constructor with mmseg ([#1456](https://github.com/open-mmlab/mmsegmentation/pull/1456)) |
| 34 | +- Refactor transformer encode layer in ViT and BEiT backbone ([#1481](https://github.com/open-mmlab/mmsegmentation/pull/1481)) |
| 35 | +- Add `build_pos_embed` and `build_layers` for BEiT ([1517](https://github.com/open-mmlab/mmsegmentation/pull/1517)) |
| 36 | +- Add `with_cp` to mit and vit ([1431](https://github.com/open-mmlab/mmsegmentation/pull/1431)) |
| 37 | +- Fix inconsistent dtype of `seg_label` in stdc decode ([1463](https://github.com/open-mmlab/mmsegmentation/pull/1463)) |
| 38 | +- Delete random seed for training in `dist_train.sh` ([1519](https://github.com/open-mmlab/mmsegmentation/pull/1519)) |
| 39 | +- Revise high `workers_per_gpus` in config file ([#1506](https://github.com/open-mmlab/mmsegmentation/pull/1506)) |
| 40 | +- Add GPG keys and del mmcv version in Dockerfile ([1534](https://github.com/open-mmlab/mmsegmentation/pull/1534)) |
| 41 | +- Update checkpoint for model in deeplabv3plus ([#1487](https://github.com/open-mmlab/mmsegmentation/pull/1487)) |
| 42 | +- Add `DistSamplerSeedHook` to set epoch number to dataloader when runner is `EpochBasedRunner` ([1449](https://github.com/open-mmlab/mmsegmentation/pull/1449)) |
| 43 | +- Provide URLs of Swin Transformer pretrained models ([1389](https://github.com/open-mmlab/mmsegmentation/pull/1389)) |
| 44 | +- Updating Dockerfiles From Docker Directory and `get_started.md` to reach latest stable version of Python, PyTorch and MMCV ([1446](https://github.com/open-mmlab/mmsegmentation/pull/1446)) |
| 45 | + |
| 46 | +**Documentation** |
| 47 | + |
| 48 | +- Add more clearly statement of CPU training/inference ([1518](https://github.com/open-mmlab/mmsegmentation/pull/1518)) |
| 49 | + |
| 50 | +**Contributors** |
| 51 | + |
| 52 | +* @jiangyitong made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1431 |
| 53 | +* @kahkeng made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1447 |
| 54 | +* @Nourollah made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1446 |
| 55 | +* @androbaza made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1452 |
| 56 | +* @Yzichen made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1445 |
| 57 | +* @whu-pzhang made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1423 |
| 58 | +* @panfeng-hover made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1417 |
| 59 | +* @Johnson-Wang made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1496 |
| 60 | +* @jere357 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1460 |
| 61 | +* @mfernezir made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1494 |
| 62 | +* @donglixp made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1503 |
| 63 | +* @YuanLiuuuuuu made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1307 |
| 64 | +* @Dawn-bin made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1527 |
| 65 | + |
3 | 66 | ### V0.23.0 (4/1/2022)
|
4 | 67 |
|
5 | 68 | **Highlights**
|
|
0 commit comments