From 4da7cc6e4698a10f283b5e2e061c42fc15dabf9c Mon Sep 17 00:00:00 2001 From: Tai-Wang Date: Wed, 1 Sep 2021 01:58:57 +0000 Subject: [PATCH 1/9] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 4d0c0a98e2..c47b65b7c1 100644 --- a/README.md +++ b/README.md @@ -8,7 +8,7 @@ [![license](https://img.shields.io/github/license/open-mmlab/mmdetection3d.svg)](https://github.com/open-mmlab/mmdetection3d/blob/master/LICENSE) -**News**: We released the codebase v0.16.0. +**News**: We released the codebase v0.17.0. In the recent [nuScenes 3D detection challenge](https://www.nuscenes.org/object-detection?externalData=all&mapData=all&modalities=Any) of the 5th AI Driving Olympics in NeurIPS 2020, we obtained the best PKL award and the second runner-up by multi-modality entry, and the best vision-only results. @@ -62,7 +62,7 @@ This project is released under the [Apache 2.0 license](LICENSE). ## Changelog -v0.16.0 was released in 1/8/2021. +v0.17.0 was released in 1/9/2021. Please refer to [changelog.md](docs/changelog.md) for details and release history. ## Benchmark and model zoo From a20ccc08a0c9f79937979f333d2649634a662000 Mon Sep 17 00:00:00 2001 From: Tai-Wang Date: Wed, 1 Sep 2021 01:59:22 +0000 Subject: [PATCH 2/9] Update README_zh-CN.md --- README_zh-CN.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README_zh-CN.md b/README_zh-CN.md index 30c0d4c561..b350c15b0d 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -8,7 +8,7 @@ [![license](https://img.shields.io/github/license/open-mmlab/mmdetection3d.svg)](https://github.com/open-mmlab/mmdetection3d/blob/master/LICENSE) -**新闻**: 我们发布了版本 v0.16.0. +**新闻**: 我们发布了版本 v0.17.0. 在第三届[ nuScenes 3D 检测挑战赛](https://www.nuscenes.org/object-detection?externalData=all&mapData=all&modalities=Any)（第五届 AI Driving Olympics, NeurIPS 2020）中，我们获得了最佳 PKL 奖、第三名和最好的纯视觉的结果，相关的代码和模型将会在不久后发布。 @@ -62,7 +62,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代 ## 更新日志 -最新的版本 v0.16.0 在 2021.08.01发布。 +最新的版本 v0.17.0 在 2021.09.01发布。 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/changelog.md)。 ## 基准测试和模型库 From 37b37ad49c2502382d122cc24f03f3f768ddbfc7 Mon Sep 17 00:00:00 2001 From: Tai-Wang Date: Wed, 1 Sep 2021 02:00:39 +0000 Subject: [PATCH 3/9] Update version.py --- mmdet3d/version.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mmdet3d/version.py b/mmdet3d/version.py index a0c9dcec27..9efec6a926 100644 --- a/mmdet3d/version.py +++ b/mmdet3d/version.py @@ -1,6 +1,6 @@ # Copyright (c) Open-MMLab. All rights reserved. -__version__ = '0.16.0' +__version__ = '0.17.0' short_version = __version__ From 9bf8b18b5c4cf16f4cfb5717ca2b91708e87c765 Mon Sep 17 00:00:00 2001 From: Tai-Wang Date: Wed, 1 Sep 2021 02:01:12 +0000 Subject: [PATCH 4/9] Update getting_started.md --- docs/getting_started.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/getting_started.md b/docs/getting_started.md index 8a825be617..9433622676 100644 --- a/docs/getting_started.md +++ b/docs/getting_started.md @@ -13,6 +13,7 @@ The required versions of MMCV, MMDetection and MMSegmentation for different vers | MMDetection3D version | MMDetection version | MMSegmentation version | MMCV version | |:-------------------:|:-------------------:|:-------------------:|:-------------------:| | master | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4| +| 0.17.0 | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4| | 0.16.0 | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4| | 0.15.0 | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4| | 0.14.0 | mmdet>=2.10.0, <=2.11.0| mmseg==0.14.0 | mmcv-full>=1.3.1, <=1.4| From 67a045e4f3b275813ff22dc7f49314131862e52f Mon Sep 17 00:00:00 2001 From: Tai-Wang Date: Wed, 1 Sep 2021 02:01:34 +0000 Subject: [PATCH 5/9] Update getting_started.md --- docs_zh-CN/getting_started.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs_zh-CN/getting_started.md b/docs_zh-CN/getting_started.md index 317dbaf6a0..0e5239b325 100644 --- a/docs_zh-CN/getting_started.md +++ b/docs_zh-CN/getting_started.md @@ -10,6 +10,7 @@ | MMDetection3D version | MMDetection version | MMSegmentation version | MMCV version | |:-------------------:|:-------------------:|:-------------------:|:-------------------:| | master | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4| +| 0.17.0 | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4| | 0.16.0 | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4| | 0.15.0 | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4| | 0.14.0 | mmdet>=2.10.0, <=2.11.0| mmseg>=0.14.0 | mmcv-full>=1.3.1, <=1.4| From 378a8c9a1616ee3169e710d691c37edd3f7c8ca0 Mon Sep 17 00:00:00 2001 From: Tai-Wang Date: Wed, 1 Sep 2021 02:45:24 +0000 Subject: [PATCH 6/9] Update changelog.md --- docs/changelog.md | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/docs/changelog.md b/docs/changelog.md index c74dea2fa3..ae16ed83ae 100644 --- a/docs/changelog.md +++ b/docs/changelog.md @@ -1,5 +1,52 @@ ## Changelog + +### v0.17.0 (1/9/2021) + +#### Compatibility + +- Unify the camera keys for consistent transformation between coodinate systems on different datasets. The modification change the key names to `lidar2img`, `depth2img`, `cam2img`, etc. for easier understanding. Customized codes using legacy keys may be influenced. +- The next release will begin to move cuda op files to [mmcv](https://github.com/open-mmlab/mmcv). It will influence the way to import related functions. Please stay tuned. + +#### Highlights + +- Support a new task, 3D object detection, on the S3DIS dataset +- Support compilation on windows +- Full benchmark for PAConv on S3DIS +- Further enhancement for documentation, especially on the Chinese documentation + +#### New Features + +- Support 3D object detection on the S3DIS dataset (#835) + +#### Improvements + +- Support point sampling based on distance metric (#667, #840) +- Update PointFusion to support unified camera keys (#791) +- Add Chinese documentation for customized dataset (#792), data pipeline (#827), customized runtime (#829), 3D Detection on ScanNet (#836), nuScenes (#854) and Waymo (#859) +- Unify camera keys used in transformation between different systems (#805) +- Add a script to support benchmark regression (#808) +- Benchmark PAConvCUDA on S3DIS (#847) +- Add a tutorial for 3D detection on the Lyft dataset (#849) +- Support to download pdf and epub documentation (#850) +- Change the `repeat` setting in Group-Free-3D configs to reduce training epochs (#855) + +#### Bug Fixes + +- Fix compiling errors on windows (#766) +- Fix the deprecated nms setting in the ImVoteNet config (#828) +- Use the latest `wrap_fp16_model` import from mmcv (#861) +- Remove 2D annotations generation on Lyft (#867) +- Update index files for the Chinese documentation to be consistent with the English version (#873) +- Fix the nested list transpose in the CenterPoint head (#879) +- Fix deprecated pretrained model loading for RegNet (#889) + +#### Contributors + +A total of 11 developers contributed to this release. + +@THU17cyz, @wHao-Wu, @wangruohui, @Wuziyi616, @filaPro, @ZwwWayne, @Tai-Wang, @DCNSW, @xieenze, @robin-karlsson0, @ZCMax + ### v0.16.0 (1/8/2021) #### Compatibility From 8bb1bc71039c478bc5b204e574e47d62c1960a22 Mon Sep 17 00:00:00 2001 From: Tai-Wang Date: Wed, 1 Sep 2021 02:46:10 +0000 Subject: [PATCH 7/9] Remove "recent" in the news --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index c47b65b7c1..6bf77b04be 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,7 @@ **News**: We released the codebase v0.17.0. -In the recent [nuScenes 3D detection challenge](https://www.nuscenes.org/object-detection?externalData=all&mapData=all&modalities=Any) of the 5th AI Driving Olympics in NeurIPS 2020, we obtained the best PKL award and the second runner-up by multi-modality entry, and the best vision-only results. +In the [nuScenes 3D detection challenge](https://www.nuscenes.org/object-detection?externalData=all&mapData=all&modalities=Any) of the 5th AI Driving Olympics in NeurIPS 2020, we obtained the best PKL award and the second runner-up by multi-modality entry, and the best vision-only results. Code and models for the best vision-only method, [FCOS3D](https://arxiv.org/abs/2104.10956), have been released. Please stay tuned for [MoCa](https://arxiv.org/abs/2012.12741). From 907681d1210a8cc85ef00d3b6c6f9e2784bd2fe0 Mon Sep 17 00:00:00 2001 From: Tai-Wang Date: Wed, 1 Sep 2021 02:47:00 +0000 Subject: [PATCH 8/9] Remove "recent" in the news --- README_zh-CN.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README_zh-CN.md b/README_zh-CN.md index b350c15b0d..eaa67d37c7 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -10,9 +10,9 @@ **新闻**: 我们发布了版本 v0.17.0. -在第三届[ nuScenes 3D 检测挑战赛](https://www.nuscenes.org/object-detection?externalData=all&mapData=all&modalities=Any)（第五届 AI Driving Olympics, NeurIPS 2020）中，我们获得了最佳 PKL 奖、第三名和最好的纯视觉的结果，相关的代码和模型将会在不久后发布。 +在第三届 [nuScenes 3D 检测挑战赛](https://www.nuscenes.org/object-detection?externalData=all&mapData=all&modalities=Any)（第五届 AI Driving Olympics, NeurIPS 2020）中，我们获得了最佳 PKL 奖、第三名和最好的纯视觉的结果，相关的代码和模型将会在不久后发布。 -最好的纯视觉方法[FCOS3D](https://arxiv.org/abs/2104.10956)的代码和模型已经发布。请继续关注我们的多模态检测器[MoCa](https://arxiv.org/abs/2012.12741)。 +最好的纯视觉方法 [FCOS3D](https://arxiv.org/abs/2104.10956) 的代码和模型已经发布。请继续关注我们的多模态检测器 [MoCa](https://arxiv.org/abs/2012.12741)。 文档: https://mmdetection3d.readthedocs.io/ From 7e48902bd1152079b2c32bcc0d29327aa07ecd49 Mon Sep 17 00:00:00 2001 From: Tai-Wang Date: Wed, 1 Sep 2021 12:10:43 +0000 Subject: [PATCH 9/9] Fix comments --- docs/changelog.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/changelog.md b/docs/changelog.md index ae16ed83ae..47a02d8729 100644 --- a/docs/changelog.md +++ b/docs/changelog.md @@ -6,12 +6,12 @@ #### Compatibility - Unify the camera keys for consistent transformation between coodinate systems on different datasets. The modification change the key names to `lidar2img`, `depth2img`, `cam2img`, etc. for easier understanding. Customized codes using legacy keys may be influenced. -- The next release will begin to move cuda op files to [mmcv](https://github.com/open-mmlab/mmcv). It will influence the way to import related functions. Please stay tuned. +- The next release will begin to move files of CUDA ops to [MMCV](https://github.com/open-mmlab/mmcv). It will influence the way to import related functions. We will not break the compatibility but will raise a warning first and please prepare to migrate it. #### Highlights -- Support a new task, 3D object detection, on the S3DIS dataset -- Support compilation on windows +- Support 3D object detection on the S3DIS dataset +- Support compilation on Windows - Full benchmark for PAConv on S3DIS - Further enhancement for documentation, especially on the Chinese documentation @@ -33,7 +33,7 @@ #### Bug Fixes -- Fix compiling errors on windows (#766) +- Fix compiling errors on Windows (#766) - Fix the deprecated nms setting in the ImVoteNet config (#828) - Use the latest `wrap_fp16_model` import from mmcv (#861) - Remove 2D annotations generation on Lyft (#867)