From 7d0011d220b2ea055ec684683c65692343a1267e Mon Sep 17 00:00:00 2001 From: Tai-Wang Date: Tue, 14 Jun 2022 16:40:14 +0800 Subject: [PATCH] Bump to v1.0.0rc3 (#1543) * Release init * v1.0.0rc3 changelog * Update SA-SSD in the model zoo * update SA-SSD model zoo * Update model_zoo.md * Update model_zoo.md * Create README.md * Update README.md * Update changelog.md * Update faq.md * Update pure_point_cloud_dataset.md * Update index.rst --- README.md | 18 ++++----- README_zh-CN.md | 12 +++--- configs/sassd/README.md | 28 ++++++++++++++ docs/en/changelog.md | 38 +++++++++++++++++++ docs/en/faq.md | 6 +-- docs/en/model_zoo.md | 4 ++ docs/en/tutorials/index.rst | 1 + docs/en/tutorials/pure_point_cloud_dataset.md | 2 +- docs/zh_cn/getting_started.md | 1 + docs/zh_cn/model_zoo.md | 4 ++ mmdet3d/version.py | 2 +- 11 files changed, 96 insertions(+), 20 deletions(-) create mode 100644 configs/sassd/README.md diff --git a/README.md b/README.md index 9fc9127476..b3921e742d 100644 --- a/README.md +++ b/README.md @@ -24,7 +24,7 @@ [![codecov](https://codecov.io/gh/open-mmlab/mmdetection3d/branch/master/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmdetection3d) [![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 v1.0.0rc2. +**News**: We released the codebase v1.0.0rc3. Note: We are going through large refactoring to provide simpler and more unified usage of many modules. @@ -84,13 +84,9 @@ This project is released under the [Apache 2.0 license](LICENSE). ## Changelog -v1.0.0rc2 was released in 1/5/2022. +v1.0.0rc3 was released in 8/6/2022. -- Support [spconv 2.0](https://github.com/traveller59/spconv) -- Support [MinkowskiEngine](https://github.com/NVIDIA/MinkowskiEngine) with MinkResNet -- Support training models on custom datasets with only point clouds -- Update Registry to distinguish the scope of built functions -- Replace mmcv.iou3d with a set of bird-eye-view (BEV) operators to unify the operations of rotated boxes +- Support [SA-SSD](https://openaccess.thecvf.com/content_CVPR_2020/papers/He_Structure_Aware_Single-Stage_3D_Object_Detection_From_Point_Cloud_CVPR_2020_paper.pdf) Please refer to [changelog.md](docs/en/changelog.md) for details and release history. @@ -167,6 +163,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
  • PointPillars (CVPR'2019)
  • SSN (ECCV'2020)
  • 3DSSD (CVPR'2020)
    • +
  • SA-SSD (CVPR'2020)
  • PointRCNN (CVPR'2019)
  • Part-A2 (TPAMI'2020)
  • CenterPoint (CVPR'2021)
    • @@ -221,9 +218,9 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md). | VoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | H3DNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | 3DSSD | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | -| Part-A2 | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | -| MVXNet | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | -| CenterPoint | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | +| Part-A2 | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | +| MVXNet | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | +| CenterPoint | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | SSN | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | | ImVoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | FCOS3D | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | @@ -235,6 +232,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md). | SMOKE | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | | PGD | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | MonoFlex | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | +| SA-SSD | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | **Note:** All the about **300+ models, methods of 40+ papers** in 2D detection supported by [MMDetection](https://github.com/open-mmlab/mmdetection/blob/master/docs/en/model_zoo.md) can be trained or used in this codebase. diff --git a/README_zh-CN.md b/README_zh-CN.md index 7fbc95beb8..6d48847c21 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -24,7 +24,7 @@ [![codecov](https://codecov.io/gh/open-mmlab/mmdetection3d/branch/master/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmdetection3d) [![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 v1.0.0rc2. +**新闻**: 我们发布了版本 v1.0.0rc3. 说明：我们正在进行大规模的重构，以提供对许多模块更简单、更统一的使用。 @@ -84,7 +84,7 @@ 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 v1.0.0rc2 在 2022.5.1 发布。 +最新的版本 v1.0.0rc3 在 2022.6.8 发布。 - 支持 [spconv 2.0](https://github.com/traveller59/spconv) - 支持基于 [MinkowskiEngine](https://github.com/NVIDIA/MinkowskiEngine) 的 MinkResNet @@ -167,6 +167,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代
  • PointPillars (CVPR'2019)
  • SSN (ECCV'2020)
  • 3DSSD (CVPR'2020)
    • +
  • SA-SSD (CVPR'2020)
  • PointRCNN (CVPR'2019)
  • Part-A2 (TPAMI'2020)
  • CenterPoint (CVPR'2021)
    • @@ -221,9 +222,9 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代 | VoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | H3DNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | 3DSSD | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | -| Part-A2 | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | -| MVXNet | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | -| CenterPoint | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | +| Part-A2 | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | +| MVXNet | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | +| CenterPoint | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | SSN | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | | ImVoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | FCOS3D | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | @@ -235,6 +236,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代 | SMOKE | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | | PGD | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | MonoFlex | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | +| SA-SSD | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | **注意：** [MMDetection](https://github.com/open-mmlab/mmdetection/blob/master/docs/zh_cn/model_zoo.md) 支持的基于2D检测的**300+个模型 , 40+的论文算法**在 MMDetection3D 中都可以被训练或使用。 diff --git a/configs/sassd/README.md b/configs/sassd/README.md new file mode 100644 index 0000000000..3a4444a0e0 --- /dev/null +++ b/configs/sassd/README.md @@ -0,0 +1,28 @@ +# Structure Aware Single-stage 3D Object Detection from Point Cloud + +> [Structure Aware Single-stage 3D Object Detection from Point Cloud]([https://arxiv.org/abs/2104.02323](https://openaccess.thecvf.com/content_CVPR_2020/papers/He_Structure_Aware_Single-Stage_3D_Object_Detection_From_Point_Cloud_CVPR_2020_paper.pdf)) + + + +## Abstract + +3D object detection from point cloud data plays an essential role in autonomous driving. Current single-stage detectors are efficient by progressively downscaling the 3D point clouds in a fully convolutional manner. However, the downscaled features inevitably lose spatial information and cannot make full use of the structure information of 3D point cloud, degrading their localization precision. In this work, we propose to improve the localization precision of single-stage detectors by explicitly leveraging the structure information of 3D point cloud. Specifically, we design an auxiliary network which converts the convolutional features in the backbone network back to point-level representations. The auxiliary network is jointly optimized, by two point-level supervisions, to guide the convolutional features in the backbone network to be aware of the object structure. The auxiliary network can be detached after training and therefore introduces no extra computation in the inference stage. Besides, considering that single-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient part-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed detector ranks at the top of KITTI 3D/BEV detection leaderboards and runs at 25 FPS for inference. + +
    + +
    + +## Introduction + +We implement SA-SSD and provide the results and checkpoints on KITTI dataset. + +## Citation + +```latex +@InProceedings{he2020sassd, + title={Structure Aware Single-stage 3D Object Detection from Point Cloud}, + author={He, Chenhang and Zeng, Hui and Huang, Jianqiang and Hua, Xian-Sheng and Zhang, Lei}, + booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, + year={2020} +} +``` diff --git a/docs/en/changelog.md b/docs/en/changelog.md index 7f575df6f1..748aa94d44 100644 --- a/docs/en/changelog.md +++ b/docs/en/changelog.md @@ -1,5 +1,43 @@ ## Changelog +### v1.0.0rc3 (8/6/2022) + +#### Highlights + +- Support [SA-SSD](https://openaccess.thecvf.com/content_CVPR_2020/papers/He_Structure_Aware_Single-Stage_3D_Object_Detection_From_Point_Cloud_CVPR_2020_paper.pdf) + +#### New Features + +- Support [SA-SSD](https://openaccess.thecvf.com/content_CVPR_2020/papers/He_Structure_Aware_Single-Stage_3D_Object_Detection_From_Point_Cloud_CVPR_2020_paper.pdf) (#1337) + +#### Improvements + +- Add Chinese documentation for vision-only 3D detection (#1438) +- Update CenterPoint pretrained models that are compatible with refactored coordinate systems (#1450) +- Configure myst-parser to parse anchor tag in the documentation (#1488) +- Replace markdownlint with mdformat for avoiding installing ruby (#1489) +- Add missing `gt_names` when getting annotation info in Custom3DDataset (#1519) +- Support S3DIS full ceph training (#1542) +- Rewrite the installation and FAQ documentation (#1545) + +#### Bug Fixes + +- Fix the incorrect registry name when building RoI extractors (#1460) +- Fix the potential problems caused by the registry scope update when composing pipelines (#1466) and using CocoDataset (#1536) +- Fix the missing selection with `order` in the [box3d_nms](https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/core/post_processing/box3d_nms.py) introduced by [#1403](https://github.com/open-mmlab/mmdetection3d/pull/1403) (#1479) +- Update the [PointPillars config](https://github.com/open-mmlab/mmdetection3d/blob/master/configs/pointpillars/hv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py) to make it consistent with the log (#1486) +- Fix heading anchor in documentation (#1490) +- Fix the compatibility of mmcv in the dockerfile (#1508) +- Make overwrite_spconv packaged when building whl (#1516) +- Fix the requirement of mmcv and mmdet (#1537) +- Update configs of PartA2 and support its compatibility with spconv 2.0 (#1538) + +#### Contributors + +A total of 13 developers contributed to this release. + +@Xiangxu-0103, @ZCMax, @jshilong, @filaPro, @atinfinity, @Tai-Wang, @wenbo-yu, @yi-chen-isuzu, @ZwwWayne, @wchen61, @VVsssssk, @AlexPasqua, @lianqing11 + ### v1.0.0rc2 (1/5/2022) #### Highlights diff --git a/docs/en/faq.md b/docs/en/faq.md index b5376c423a..38b87af9fc 100644 --- a/docs/en/faq.md +++ b/docs/en/faq.md @@ -10,9 +10,9 @@ We list some potential troubles encountered by users and developers, along with | MMDetection3D version | MMDetection version | MMSegmentation version | MMCV version | | :-------------------: | :---------------------: | :--------------------: | :------------------------: | - | master | mmdet>=2.19.0, <=3.0.0 | mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.4.8, <=1.7.0 | - | v1.0.0rc3 | mmdet>=2.19.0, <=3.0.0 | mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.4.8, <=1.7.0 | - | v1.0.0rc2 | mmdet>=2.19.0, <=3.0.0 | mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.4.8, <=1.7.0 | + | master | mmdet>=2.24.0, <=3.0.0 | mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.4.8, <=1.6.0 | + | v1.0.0rc3 | mmdet>=2.24.0, <=3.0.0 | mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.4.8, <=1.6.0 | + | v1.0.0rc2 | mmdet>=2.24.0, <=3.0.0 | mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.4.8, <=1.6.0 | | v1.0.0rc1 | mmdet>=2.19.0, <=3.0.0 | mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.4.8, <=1.5.0 | | v1.0.0rc0 | mmdet>=2.19.0, <=3.0.0 | mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.3.17, <=1.5.0 | | 0.18.1 | mmdet>=2.19.0, <=3.0.0 | mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.3.17, <=1.5.0 | diff --git a/docs/en/model_zoo.md b/docs/en/model_zoo.md index 5bbd081376..1a647ce980 100644 --- a/docs/en/model_zoo.md +++ b/docs/en/model_zoo.md @@ -100,6 +100,10 @@ Please refer to [PointRCNN](https://github.com/open-mmlab/mmdetection3d/tree/v1. Please refer to [MonoFlex](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0/configs/monoflex) for details. We provide MonoFlex baselines on KITTI dataset. +### SA-SSD + +Please refer to [SA-SSD](https://github.com/open-mmlab/mmdetection3d/blob/master/configs/sassd) for details. We provide SA-SSD baselines on the KITTI dataset. + ### Mixed Precision (FP16) Training Please refer to [Mixed Precision (FP16) Training on PointPillars](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0/configs/pointpillars/hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d.py) for details. diff --git a/docs/en/tutorials/index.rst b/docs/en/tutorials/index.rst index 39aa9731bb..866df3fca6 100644 --- a/docs/en/tutorials/index.rst +++ b/docs/en/tutorials/index.rst @@ -8,4 +8,5 @@ customize_runtime.md coord_sys_tutorial.md backends_support.md + model_deployment.md pure_point_cloud_dataset.md diff --git a/docs/en/tutorials/pure_point_cloud_dataset.md b/docs/en/tutorials/pure_point_cloud_dataset.md index fec05501ee..ae7ddaa23b 100644 --- a/docs/en/tutorials/pure_point_cloud_dataset.md +++ b/docs/en/tutorials/pure_point_cloud_dataset.md @@ -1,4 +1,4 @@ -# Tutorial 8: Use Pure Point Cloud Dataset +# Tutorial 9: Use Pure Point Cloud Dataset ## Data Pre-Processing diff --git a/docs/zh_cn/getting_started.md b/docs/zh_cn/getting_started.md index c84444a10b..219e2d5ef8 100644 --- a/docs/zh_cn/getting_started.md +++ b/docs/zh_cn/getting_started.md @@ -10,6 +10,7 @@ | MMDetection3D 版本 | MMDetection 版本 | MMSegmentation 版本 | MMCV 版本 | | :--------------: | :----------------------: | :---------------------: | :-------------------------: | | master | mmdet>=2.24.0, \<=3.0.0 | mmseg>=0.20.0, \<=1.0.0 | mmcv-full>=1.4.8, \<=1.6.0 | +| v1.0.0rc3 | mmdet>=2.24.0, \<=3.0.0 | mmseg>=0.20.0, \<=1.0.0 | mmcv-full>=1.4.8, \<=1.6.0 | | v1.0.0rc2 | mmdet>=2.24.0, \<=3.0.0 | mmseg>=0.20.0, \<=1.0.0 | mmcv-full>=1.4.8, \<=1.6.0 | | v1.0.0rc1 | mmdet>=2.19.0, \<=3.0.0 | mmseg>=0.20.0, \<=1.0.0 | mmcv-full>=1.4.8, \<=1.5.0 | | v1.0.0rc0 | mmdet>=2.19.0, \<=3.0.0 | mmseg>=0.20.0, \<=1.0.0 | mmcv-full>=1.3.17, \<=1.5.0 | diff --git a/docs/zh_cn/model_zoo.md b/docs/zh_cn/model_zoo.md index b2b160e5bf..48cbc98def 100644 --- a/docs/zh_cn/model_zoo.md +++ b/docs/zh_cn/model_zoo.md @@ -100,6 +100,10 @@ 请参考 [MonoFlex](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0/configs/monoflex) 获取更多细节，我们在 KITTI 数据集上给出了相应的结果. +### SA-SSD + +请参考 [SA-SSD](https://github.com/open-mmlab/mmdetection3d/blob/master/configs/sassd) 获取更多的细节，我们在 KITTI 数据集上给出了相应的基准结果。 + ### Mixed Precision (FP16) Training 细节请参考 [Mixed Precision (FP16) Training 在 PointPillars 训练的样例](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0/configs/pointpillars/hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d.py). diff --git a/mmdet3d/version.py b/mmdet3d/version.py index 2d839db402..c95fbedd29 100644 --- a/mmdet3d/version.py +++ b/mmdet3d/version.py @@ -1,6 +1,6 @@ # Copyright (c) Open-MMLab. All rights reserved. -__version__ = '1.0.0rc2' +__version__ = '1.0.0rc3' short_version = __version__