diff --git a/README.md b/README.md index 0ce31cf8820..0deccbab347 100644 --- a/README.md +++ b/README.md @@ -94,11 +94,10 @@ We are excited to announce our latest work on real-time object recognition tasks -**v3.0.0rc4** was released in 25/11/2022: +**v3.0.0rc5** was released in 26/12/2022: -- Support [CondInst](https://arxiv.org/abs/2003.05664) -- Add [`projects/`](./projects/) folder and give an [example](./projects/example_project/README.md) for communities to contribute their projects. -- Support [SparseInst](https://arxiv.org/abs/2203.12827) in [`projects`](./projects/SparseInst/README.md) +- Support [RTMDet](https://arxiv.org/abs/2212.07784) instance segmentation models. The technical report of RTMDet is on [arxiv](https://arxiv.org/abs/2212.07784) +- Support SSHContextModule in paper [SSH: Single Stage Headless Face Detector](https://arxiv.org/abs/1708.03979) ## Installation diff --git a/README_zh-CN.md b/README_zh-CN.md index a8359cfcefc..21c133f876e 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -77,7 +77,7 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope ### 亮点 -我们很高兴向大家介绍我们在实时目标识别任务方面的最新成果 RTMDet，包含了一系列的全卷积单阶段检测模型。 RTMDet 不仅在从 tiny 到 extra-large 尺寸的目标检测模型上上实现了最佳的参数量和精度的平衡，而且在实时实例分割和旋转目标检测任务上取得了最先进的成果。 更多细节请参阅[技术报告](https://arxiv.org/abs/2212.07784)。 预训练模型可以在[这里](configs/rtmdet)找到。 +我们很高兴向大家介绍我们在实时目标识别任务方面的最新成果 RTMDet，包含了一系列的全卷积单阶段检测模型。 RTMDet 不仅在从 tiny 到 extra-large 尺寸的目标检测模型上实现了最佳的参数量和精度的平衡，而且在实时实例分割和旋转目标检测任务上取得了最先进的成果。 更多细节请参阅[技术报告](https://arxiv.org/abs/2212.07784)。 预训练模型可以在[这里](configs/rtmdet)找到。 [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/rtmdet-an-empirical-study-of-designing-real/real-time-instance-segmentation-on-mscoco)](https://paperswithcode.com/sota/real-time-instance-segmentation-on-mscoco?p=rtmdet-an-empirical-study-of-designing-real) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/rtmdet-an-empirical-study-of-designing-real/object-detection-in-aerial-images-on-dota-1)](https://paperswithcode.com/sota/object-detection-in-aerial-images-on-dota-1?p=rtmdet-an-empirical-study-of-designing-real) @@ -93,11 +93,10 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope -**v3.0.0rc4** 版本已经在 2022.11.25 发布： +**v3.0.0rc5** 版本已经在 2022.12.26 发布： -- 支持了 [CondInst](https://arxiv.org/abs/2003.05664) -- 添加了 [`projects/`](./projects/) 文件夹并提供了[示例](./projects/example_project/README.md)，方便社区快速地贡献相关项目 -- 在 [`projects`](./projects/SparseInst/README.md) 中支持了 [SparseInst](https://arxiv.org/abs/2203.12827) +- 支持了 [RTMDet](https://arxiv.org/abs/2212.07784) 的实例分割模型。RTMDet 的技术报告发布在了 [arxiv](https://arxiv.org/abs/2212.07784) 上。 +- 支持了 [SSH: Single Stage Headless Face Detector](https://arxiv.org/abs/1708.03979) 论文中的 SSHContextModule ## 安装 diff --git a/docker/serve/Dockerfile b/docker/serve/Dockerfile index 047ea117001..d10f79682d9 100644 --- a/docker/serve/Dockerfile +++ b/docker/serve/Dockerfile @@ -4,7 +4,7 @@ ARG CUDNN="8" FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel ARG MMCV="2.0.0rc1" -ARG MMDET="3.0.0rc4" +ARG MMDET="3.0.0rc5" ENV PYTHONUNBUFFERED TRUE diff --git a/docs/en/notes/changelog.md b/docs/en/notes/changelog.md index 9b5957c7581..d382012b57f 100644 --- a/docs/en/notes/changelog.md +++ b/docs/en/notes/changelog.md @@ -1,5 +1,65 @@ # Changelog of v3.x +## v3.0.0rc5 (26/12/2022) + +### Highlights + +- Support [RTMDet](https://arxiv.org/abs/2212.07784) instance segmentation models. The technical report of RTMDet is on [arxiv](https://arxiv.org/abs/2212.07784) +- Support SSHContextModule in paper [SSH: Single Stage Headless Face Detector](https://arxiv.org/abs/1708.03979). + +### New Features + +- Support [RTMDet](https://arxiv.org/abs/2212.07784) instance segmentation models and improve RTMDet test config (#9494) +- Support SSHContextModule in paper [SSH: Single Stage Headless Face Detector](https://arxiv.org/abs/1708.03979) (#8953) +- Release [CondInst](https://arxiv.org/abs/2003.05664) pre-trained model (#9406) + +### Bug Fixes + +- Fix CondInst predict error when `batch_size` is greater than 1 in inference (#9400) +- Fix the bug of visualization when the dtype of the pipeline output image is not uint8 in browse dataset (#9401) +- Fix `analyze_logs.py` to plot mAP and calculate train time correctly (#9409) +- Fix backward inplace error with `PAFPN` (#9450) +- Fix config import links in model converters (#9441) +- Fix `DeformableDETRHead` object has no attribute `loss_single` (#9477) +- Fix the logic of pseudo bboxes predicted by teacher model in SemiBaseDetector (#9414) +- Fix demo API in instance segmentation tutorial (#9226) +- Fix `analyze_results` (#9380) +- Fix the error that Readthedocs API cannot be displayed (#9510) + +### Improvements + +- Remove legacy `builder.py` (#9479) +- Make sure the pipeline argument shape is in `(width, height)` order (#9324) +- Add `.pre-commit-config-zh-cn.yaml` file (#9388) +- Refactor dataset metainfo to lowercase (#9469) +- Add PyTorch 1.13 checking in CI (#9478) +- Adjust `FocalLoss` and `QualityFocalLoss` to allow different kinds of targets (#9481) +- Refactor `setup.cfg` (#9370) +- Clip saturation value to valid range `[0, 1]` (#9391) +- Only keep meta and state_dict when publishing model (#9356) +- Add segm evaluator in ms-poly_3x_coco_instance config (#9524) +- Update deployment guide (#9527) +- Update zh_cn `faq.md` (#9396) +- Update `get_started` (#9480) +- Update the zh_cn user_guides of `useful_tools.md` and `useful_hooks.md` (#9453) +- Add type hints for `bfp` and `channel_mapper` (#9410) +- Add type hints of several losses (#9397) +- Add type hints and update docstring for task modules (#9468) + +### New Contributors + +- @lihua199710 made their first contribution in +- @twmht made their first contribution in +- @tianleiSHI made their first contribution in +- @kitecats made their first contribution in +- @QJC123654 made their first contribution in + +### Contributors + +A total of 20 developers contributed to this release. + +Thanks @liuyanyi, @RangeKing, @lihua199710, @MambaWong, @sanbuphy, @Xiangxu-0103, @twmht, @JunyaoHu, @Chan-Sun, @tianleiSHI, @zytx121, @kitecats, @QJC123654, @JosonChan1998, @lvhan028, @Czm369, @BIGWangYuDong, @RangiLyu, @hhaAndroid, @ZwwWayne + ## v3.0.0rc4 (23/11/2022) ### Highlights diff --git a/docs/en/notes/faq.md b/docs/en/notes/faq.md index 0d047cd537b..991da7f6982 100644 --- a/docs/en/notes/faq.md +++ b/docs/en/notes/faq.md @@ -11,6 +11,7 @@ We list some common troubles faced by many users and their corresponding solutio | MMDetection version | MMCV version | MMEngine version | | :-----------------: | :---------------------: | :----------------------: | | 3.x | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 | + | 3.0.0rc5 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 | | 3.0.0rc4 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 | | 3.0.0rc3 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 | | 3.0.0rc2 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.1.0, \<1.0.0 | diff --git a/docs/zh_cn/notes/faq.md b/docs/zh_cn/notes/faq.md index d20bf315955..87a9f10e302 100644 --- a/docs/zh_cn/notes/faq.md +++ b/docs/zh_cn/notes/faq.md @@ -11,6 +11,7 @@ | MMDetection 版本 | MMCV 版本 | MMEngine 版本 | | :--------------: | :---------------------: | :----------------------: | | 3.x | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 | + | 3.0.0rc5 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 | | 3.0.0rc4 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 | | 3.0.0rc3 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 | | 3.0.0rc2 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.1.0, \<1.0.0 | diff --git a/mmdet/version.py b/mmdet/version.py index 27ecb521e48..26b6d6c8b7a 100644 --- a/mmdet/version.py +++ b/mmdet/version.py @@ -1,6 +1,6 @@ # Copyright (c) OpenMMLab. All rights reserved. -__version__ = '3.0.0rc4' +__version__ = '3.0.0rc5' short_version = __version__