mmdet3d - MMDetection3D v1.4.0 Release

Highlights

Support the training of DSVT in projects (#2738)
Support Nerf-Det in projects (#2732)
Refactor Waymo dataset (#2836)

New Features

Support the training of DSVT in projects (#2738)
Support Nerf-Det in projects (#2732)
Support MV-FCOS3D++ (#2835)
Refactor Waymo dataset (#2836)

Improvements

Support PGD (front-of-view / multi-view) on Waymo dataset (#2835)
Release new Waymo-mini for verify some methods or debug quickly (#2835)

Bug Fixes

Fix MinkUNet and SPVCNN some wrong configs (#2854)
Fix incorrect number of arguments in PETR (#2800)
Delete unused files in mmdet3d/configs (#2773)

Contributors

A total of 5 developers contributed to this release.

@sunjiahao1999, @WendellZ524, @Yanyirong, @JingweiZhang12, @Tai-Wang

New Contributors

@WendellZ524 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2800
@Yanyirong made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2732

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.3.0...v1.4.0

- Python
Published by sunjiahao1999 over 2 years ago

mmdet3d - MMDetection3D v1.3.0 Release

Highlights

Support CENet in projects (#2619)
Enhance demos with new 3D inferencers (#2763)

New Features

Support CENet in projects (#2619)

Improvements

Enhance demos with new 3D inferencers (#2763)
Add BEV-based detection pipeline in nuScenes dataset tutorial (#2672)
Add the new config type of Cylinder3D in mmdet3d/configs (#2681)
Update New Config Type (#2655)
Update the QR code in README.md (#2703)

Bug Fixes

Fix the download script of nuScenes dataset (#2660)
Fix circleCI and GitHub workflow configuration (#2652)
Fix the version of Open3D in requirements (#2633)
Fix unused files in mmdet3d/configs (#2773)
Fix support devices in FreeAnchor3DHead (#2769)
Fix readthedocs building and link (#2739, #2650)
Fix the pitch angle bug in LaserMix (#2710)

Contributors

A total of 7 developers contributed to this release.

@sunjiahao1999, @Xiangxu-0103, @ZhaoCake, @LRJKD, @crazysteeaam, @wep21, @zhiqwang

New Contributors

@wep21 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2660
@zhiqwang made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2650
@1uciusy made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2672
@crazysteeaam made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2703
@ZhaoCake made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2681
@LRJKD made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2769

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.2.0...v1.3.0

- Python
Published by sunjiahao1999 over 2 years ago

mmdet3d - MMDetection3D v1.2.0 Release

Highlights

Support New Config Type in mmdet3d/config (#2608)
Support the inference of DSVT in projects (#2606)
Support downloading datasets from OpenDataLab using mim (#2593)

New Features

Support New Config Type in mmdet3d/config (#2608)
Support the inference of DSVT in projects (#2606)
Support downloading datasets from OpenDataLab using mim (#2593)

Improvements

Enhanced visualization in interactive form (#2611)
Update README.md and Model Zoo (#2599, #2600)
Speed up S3DIS data preparation (#2585)

Bug Fixes

Remove PointRCNN in benchmark training (#2610)
Fix wrong indoor detection visualization (#2625)
Fix MinkUNet download link (#2590)
Fix the formula in the readthedocs (#2580)

Contributors

A total of 5 developers contributed to this release.

@sunjiahao1999, @Xiangxu-0103, @JingweiZhang12, @col14m, @zhulf0804

New Contributors

@col14m made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2585
@zhulf0804 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2600

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.1.1...v1.2.0

- Python
Published by sunjiahao1999 almost 3 years ago

mmdet3d - MMDetection3D v1.1.1 Release

Highlights

Support TPVFormer in projects (#2399, #2517, #2535)
Support the training of BEVFusion in projects (#2546)
Support lidar-based 3D semantic segmentation benchmark (#2530, #2559)

New Features

Support TPVFormer in projects (#2399, #2517, #2535)
Support the training of BEVFusion in projects (#2558)
Support lidar-based 3D Semantic Segmentation Benchmark (#2530, #2559)
Support test-time augmentation for Segmentor (#2382)
Support Minkowski ConvModule and Residual Block (#2528)
Support the visualization of multi-view images in multi-modal methods (#2453)

Improvements

Upload checkpoints and training log of PETR (#2555)
Replace np.float by default float in segmentation evaluation (#2527)
Add docs of converting SemanticKITTI datasets (#2515)
Support different colors for different classes in visualization (#2500)
Support tensor-like operations for BaseInstance3DBoxes and BasePoint(#2501)
Add information of LiDAR Segmentation in NuScenes annotation files
Provide annotation files of datasets generated offline (#2457)
Refactor document structure (#2429)
Complete typehints and docstring (#2396, #2457, #2468, #2464, #2485)

Bug Fixes

Fix the bug of abnormal loss when training SECOND in Automatic mixed precision(AMP) mode (#2452)
Add a warning in function post_process_coords in mmdet3d/dataset/convert_utils.py (#2557)
Fix invalid configs (#2477, #2536)
Fix bugs of unit test (#2466)
Update local-rank argument in test.py for pytorch 2.0 (#2469)
Fix docker file (#2451)
Fix demo and visualization (#2453)
Fix SUN RGB-D data converter (#2440)
Fix readthedocs building (#2459, #2419, #2505, #2396)
Fix CI (#2445,#2424)
Loose the version restriction of numba (#2416)

Contributors

A total of 12 developers contributed to this release.

@sunjiahao1999, @Xiangxu-0103, @JingweiZhang12, @chriscarving, @jaan1729, @pd-michaelstanley, @filaPro, @kabouzeid, @A-new-b, @lbin, @Lum1104, @pd-michaelstanley

New contributors

@A-new-b made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2485
@lbin made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2557
@Lum1104 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2464
@jaan1729 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2451
@pd-michaelstanley made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2442
@chriscarving made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2396

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.1.0...v1.1.1

- Python
Published by JingweiZhang12 about 3 years ago

mmdet3d - MMDetection3D v1.1.0 Release

We are excited to announce the release of MMDetection3D 1.1.0 as a part of the OpenMMLab 2.0 project! Compared with version 1.0.0, MMDetection3D 1.1.0 introduces an updated framework structure for the core package and a new section called Projects. Specifically, we have significantly refactored the core package's code to make it clearer, more comprehensible, and disentangled. The new Projects section serves as an essential addition to MMDetection3D and supports flexible code contribution without strict code requirements, enabling faster integration of state-of-the-art models and features. To help users migrate from version 1.0.0 to 1.1.0 as smoothly as possible, we have prepared a migration guide. Any questions about migration are welcome to be posted on issue。

Highlights

Support several popular LiDAR segmentation methods:
- Cylinder3D (#2291, #2344, #2350)
- MinkUnet (#2294, #2358)
- SPVCNN (#2320，#2372)
- PolarMix augmentation (#2265)
- LaserMix augmentation (#2302)
Support TR3D detector in projects (#2274)
Support DETR3D in projects (#2173)
Support the inference of BEVFusion in projects (#2175)

New Features

Support Cylinder3D (#2291, #2344, #2350)
Support MinkUnet (#2294, #2358)
Support SPVCNN (#2320，#2372)
Support TR3D detector in projects (#2274)
Support the inference of BEVFusion in projects (#2175)
Support DETR3D in projects (#2173)
Support PolarMix and LaserMix augmentations (#2265,#2302)
Support loading annotation of panoptic segmentation (#2223)
Support panoptic segmentation metric (#2230)
Add inferencer for LiDAR-based, monocular and multi-modality 3D detection (#2208, #2190, #2342)
Add inferencer for LiDAR-based segmentation (#2304)

Improvements

Support lazy_init for CBGSDataset (#2271)
Support generating annotation files for test set on Waymo (#2180)
Enhance the support for SemanticKitti (#2253, #2323)
File I/O migration and reconstruction (#2319)
Support format_only option for Lyft, NuScenes and Waymo datasets (#2333, #2151)
Replace np.transpose with torch.permute to speed up (#2277)
Allow setting local-rank for pytorch 2.0 (#2387)

Bug Fixes

Fix the problem of reversal of length and width when drawing heatmap in CenterFormer (#2362)
Deprecate old type alias due to the new version of numpy (#2339)
Lose trimesh version requirements to fix numpy random state (#2340)
Fix the device mismatch error in CenterPoint (#2308)
Fix the bug of visualization when there are no boxes (#2231)
Fix bug of counting ignore index in IOU in segmentation evaluation (#2229)

Contributors

A total of 19 developers contributed to this release. @xizaoqu, @ZLTJohn, @SekiroRong, @yechenzhi, @shufanwu, @chriscarving, @vansin, @triple-Mu, @404Vector, @filaPro, @sunjiahao1999, @Ginray, @Xiangxu-0103, @JingweiZhang12, @DezeZhao, @ZCMax, @roger-lcc, @Tai-Wang, @ZwwWayne

New contributors

@xizaoqu made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2385
@yechenzhi made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2385
@DezeZhao made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2362
@chriscarving made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2396

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.1.0rc3...v1.1.0

- Python
Published by JingweiZhang12 about 3 years ago

mmdet3d - MMDetection3D v1.1.0rc3 Release

Highlights

Support CenterFormer in projects (#2175)
Support PETR in projects (#2173)

New Features

Support CenterFormer in projects (#2175)
Support PETR in projects (#2173)
Refactor ImVoxelNet on SUN RGB-D into mmdet3d v1.1 (#2141)

Improvements

Remove legacy builder.py (#2061)
Update customize_dataset documentation (#2153)
Update tutorial of LiDAR-based detection (#2120)

Bug Fixes

Fix the configs of FCOS3D and PGD (#2191)
Fix numpy's ValueError in updateinfosto_v2.py (#2162)
Fix parameter missing in Det3DVisualizationHook (#2118)
Fix memory overflow in the rotated box IoU calculation (#2134)
Fix lidar2cam error in updateinfosto_v2.py for nus and lyft dataset (#2110)
Fix error of data type in Waymo metrics (#2109)
Update bbox_3d information in cam_instances for mono3d detection task (#2046)
Fix label saving of Waymo dataset (#2096)

Contributors

A total of 10 developers contributed to this release.

@SekiroRong, @ZLTJohn, @vansin, @shanmo, @VVsssssk, @ZCMax, @Xiangxu-0103, @JingweiZhang12, @Tai-Wang, @lianqing11

New Contributors

@shanmo made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2118
@ZLTJohn made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2162
@SekiroRong made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/2175

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.1.0rc2...v1.1.0rc3

- Python
Published by ZwwWayne over 3 years ago

mmdet3d - MMDetection3D V1.0.0rc6 Release

New Features

Add Projects/ folder and the first example project (#2082)

Improvements

Update Waymo converter to save storage space (#1759)
Update model link and performance of CenterPoint (#1916)

Bug Fixes

Fix GPU memory occupancy problem in PointRCNN (#1928)
Fix sampling bug in IoUNegPiecewiseSampler (#2018)

Contributors

A total of 6 developers contributed to this release.

@oyel, @zzj403, @VVsssssk, @Tai-Wang, @tpoisonooo, @JingweiZhang12, @ZCMax, @ZwwWayne

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.0.0rc5...v1.0.0rc6

- Python
Published by ZwwWayne over 3 years ago

mmdet3d - MMDetection3D V1.1.0rc2 Release

Highlights

Support PV-RCNN
Speed up evaluation on Waymo dataset

New Features

Support PV-RCNN (#1597, #2045)
Speed up evaluation on Waymo dataset (#2008)
Refactor FCAF3D into the framework of mmdet3d v1.1 (#1945)
Refactor S3DIS dataset into the framework of mmdet3d v1.1 (#1984)
Add Projects/ folder and the first example project (#2042)

Improvements

Rename CLASSES and PALETTE to classes and palette respectively (#1932)
Update metainfo in pkl files and add categories into metainfo (#1934)
Show instance statistics before and after through the pipeline (#1863)
Add configs of DGCNN for different testing areas (#1967)
Remove testing utils from tests/utils/ to mmdet3d/testing/ (#2012)
Add typehint for code in models/layers/ (#2014)
Refine documentation (#1891, #1994)
Refine voxelization for better speed (#2062)

Bug Fixes

Fix loop visualization error about point cloud (#1914)
Fix image conversion of Waymo to avoid information loss (#1979)
Fix evaluation on KITTI testset (#2005)
Fix sampling bug in IoUNegPiecewiseSampler (#2017)
Fix point cloud range in CenterPoint (#1998)
Fix some loading bugs and support FOV-image-based mode on Waymo dataset (#1942)
Fix dataset conversion utils (#1923, #2040, #1971)
Update metafiles in all the configs (#2006)

Contributors

A total of 12 developers contributed to this release.

@vavanade, @oyel, @thinkthinking, @PeterH0323， @274869388, @cxiang26, @lianqing11, @VVsssssk, @ZCMax, @Xiangxu-0103, @JingweiZhang12, @Tai-Wang

New Contributors

@PeterH0323 made their first contribution in #2065
@cxiang26 made their first contribution in #1965
@vavanade made their first contribution in #2031
@oyel made their first contribution in #2017
@thinkthinking made their first contribution in #2026
@274869388 made their first contribution in #1973

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.1.0rc1...v1.1.0rc2

- Python
Published by ZwwWayne over 3 years ago

mmdet3d - MMDetection3D V1.1.0rc1 Release

Highlights

Support a camera-only 3D detection baseline on Waymo, MV-FCOS3D++

New Features

Support a camera-only 3D detection baseline on Waymo, MV-FCOS3D++, with new evaluation metrics and transformations (#1716)
Refactor PointRCNN in the framework of mmdet3d v1.1 (#1819)

Improvements

Add auto_scale_lr in config to support training with auto-scale learning rates (#1807)
Fix CI (#1813, #1865, #1877)
Update browse_dataset.py script (#1817)
Update SUN RGB-D and Lyft datasets documentation (#1833)
Rename convert_to_datasample to add_pred_to_datasample in detectors (#1843)
Update customized dataset documentation (#1845)
Update Det3DLocalVisualization and visualization documentation (#1857)
Add the code of generating cam_sync_labels for Waymo dataset (#1870)
Update dataset transforms typehints (#1875)

Bug Fixes

Fix missing registration of models in setup_env.py (#1808)
Fix the data base sampler bugs when using the ground plane data (#1812)
Add output directory existing check during visualization (#1828)
Fix bugs of nuScenes dataset for monocular 3D detection (#1837)
Fix visualization hook to support the visualization of different data modalities (#1839)
Fix monocular 3D detection demo (#1864)
Fix the lack of num_pts_feats key in nuscenes dataset and complete docstring (#1882)

Contributors

A total of 10 developers contributed to this release.

@ZwwWayne, @Tai-Wang, @lianqing11, @VVsssssk, @ZCMax, @Xiangxu-0103, @JingweiZhang12, @tpoisonooo, @ice-tong, @jshilong

New Contributors

@ice-tong made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1838

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.1.0rc0...v1.1.0rc1

- Python
Published by Tai-Wang over 3 years ago

mmdet3d - MMDetection3D V1.0.0rc5 Release

New Features

Support ImVoxelNet on SUN RGB-D (#1738)

Improvements

Fix the cross-codebase reference problem in metafile README (#1644)
Update the Chinese documentation about getting started (#1715)
Fix docs link and add docs link checker (#1811)

Bug Fixes

Fix a visualization bug that is potentially triggered by empty prediction labels (#1725)
Fix point cloud segmentation visualization bug due to wrong parameter passing (#1858)
Fix Nan loss bug during PointRCNN training (#1874)

Contributors

A total of 11 developers contributed to this release.

@ZwwWayne, @Tai-Wang, @filaPro, @VVsssssk, @ZCMax, @Xiangxu-0103, @holtvogt, @tpoisonooo, @lianqing01, @TommyZihao, @aditya9710

New Contributors

@tpoisonooo made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1614
@holtvogt made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1725
@TommyZihao made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1778
@aditya9710 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1889

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.0.0rc4...v1.0.0rc5

- Python
Published by Tai-Wang over 3 years ago

mmdet3d - MMDetection3D V1.1.0rc0 Release

Changelog of v1.1

v1.1.0rc0 (1/9/2022)

We are excited to announce the release of MMDetection3D 1.1.0rc0. MMDet3D 1.1.0rc0 is the first version of MMDetection3D 1.1, a part of the OpenMMLab 2.0 projects. Built upon the new training engine and MMDet 3.x, MMDet3D 1.1 unifies the interfaces of dataset, models, evaluation, and visualization with faster training and testing speed. It also provides a standard data protocol for different datasets, modalities, and tasks for 3D perception. We will support more strong baselines in the future release, with our latest exploration on camera-only 3D detection from videos.

Highlights

New engines. MMDet3D 1.1 is based on MMEngine and MMDet 3.x, which provides a universal and powerful runner that allows more flexible customizations and significantly simplifies the entry points of high-level interfaces.
Unified interfaces. As a part of the OpenMMLab 2.0 projects, MMDet3D 1.1 unifies and refactors the interfaces and internal logics of train, testing, datasets, models, evaluation, and visualization. All the OpenMMLab 2.0 projects share the same design in those interfaces and logics to allow the emergence of multi-task/modality algorithms.
Standard data protocol for all the datasets, modalities, and tasks for 3D perception. Based on the unified base datasets inherited from MMEngine, we also design a standard data protocol that defines and unifies the common keys across different datasets, tasks, and modalities. It significantly simplifies the usage of multiple datasets and data modalities for multi-task frameworks and eases dataset customization. Please refer to the documentation of customized datasets for details.
Strong baselines. We will release strong baselines of many popular models to enable fair comparisons among state-of-the-art models.
More documentation and tutorials. We add a bunch of documentation and tutorials to help users get started more smoothly. Read it here.

Breaking Changes

MMDet3D 1.1 has undergone significant changes to have better design, higher efficiency, more flexibility, and more unified interfaces. Besides the changes of API, we briefly list the major breaking changes in this section. We will update the migration guide to provide complete details and migration instructions. Users can also refer to the compatibility documentation and API doc for more details.

Dependencies

MMDet3D 1.1 runs on PyTorch>=1.6. We have deprecated the support of PyTorch 1.5 to embrace the mixed precision training and other new features since PyTorch 1.6. Some models can still run on PyTorch 1.5, but the full functionality of MMDet3D 1.1 is not guaranteed.
MMDet3D 1.1 relies on MMEngine to run. MMEngine is a new foundational library for training deep learning models of OpenMMLab and are widely depended by OpenMMLab 2.0 projects. The dependencies of file IO and training are migrated from MMCV 1.x to MMEngine.
MMDet3D 1.1 relies on MMCV>=2.0.0rc0. Although MMCV no longer maintains the training functionalities since 2.0.0rc0, MMDet3D 1.1 relies on the data transforms, CUDA operators, and image processing interfaces in MMCV. Note that the package mmcv is the version that provides pre-built CUDA operators and mmcv-lite does not since MMCV 2.0.0rc0, while mmcv-full has been deprecated since 2.0.0rc0.
MMDet3D 1.1 is based on MMDet 3.x, which is also a part of OpenMMLab 2.0 projects.

Training and testing

MMDet3D 1.1 uses Runner in MMEngine rather than that in MMCV. The new Runner implements and unifies the building logic of dataset, model, evaluation, and visualizer. Therefore, MMDet3D 1.1 no longer relies on the building logics of those modules in mmdet3d.train.apis and tools/train.py. Those code have been migrated into MMEngine. Please refer to the migration guide of Runner in MMEngine for more details.
The Runner in MMEngine also supports testing and validation. The testing scripts are also simplified, which has similar logic as that in training scripts to build the runner.
The execution points of hooks in the new Runner have been enriched to allow more flexible customization. Please refer to the migration guide of Hook in MMEngine for more details.
Learning rate and momentum scheduling has been migrated from Hook to Parameter Scheduler in MMEngine. Please refer to the migration guide of Parameter Scheduler in MMEngine for more details.

Configs

The Runner in MMEngine uses a different config structure to ease the understanding of the components in runner. Users can read the config example of MMDet3D 1.1 or refer to the migration guide in MMEngine for migration details.
The file names of configs and models are also refactored to follow the new rules unified across OpenMMLab 2.0 projects. The names of checkpoints are not updated for now as there is no BC-breaking of model weights between MMDet3D 1.1 and 1.0.x. We will progressively replace all the model weights by those trained in MMDet3D 1.1. Please refer to the user guides of config for more details.

Dataset

The Dataset classes implemented in MMDet3D 1.1 all inherits from the Det3DDataset and Seg3DDataset, which inherits from the BaseDataset in MMEngine. In addition to the changes of interfaces, there are several changes of Dataset in MMDet3D 1.1.

All the datasets support to serialize the internal data list to reduce the memory when multiple workers are built for data loading.
The internal data structure in the dataset is changed to be self-contained (without losing information like class names in MMDet3D 1.0.x) while keeping simplicity.
Common keys across different datasets and data modalities are defined and all the info files are unified into a standard protocol.
The evaluation functionality of each dataset has been removed from dataset so that some specific evaluation metrics like KITTI AP can be used to evaluate the prediction on other datasets.

Data Transforms

The data transforms in MMDet3D 1.1 all inherits from BaseTransform in MMCV>=2.0.0rc0, which defines a new convention in OpenMMLab 2.0 projects. Besides the interface changes, there are several changes listed as below:

The functionality of some data transforms (e.g., Resize) are decomposed into several transforms to simplify and clarify the usages.
The format of data dict processed by each data transform is changed according to the new data structure of dataset.
Some inefficient data transforms (e.g., normalization and padding) are moved into data preprocessor of model to improve data loading and training speed.
The same data transforms in different OpenMMLab 2.0 libraries have the same augmentation implementation and the logic given the same arguments, i.e., Resize in MMDet 3.x and MMSeg 1.x will resize the image in the exact same manner given the same arguments.

Model

The models in MMDet3D 1.1 all inherits from BaseModel in MMEngine, which defines a new convention of models in OpenMMLeb 2.0 projects. Users can refer to the tutorial of model in MMengine for more details. Accordingly, there are several changes as the following:

The model interfaces, including the input and output formats, are significantly simplified and unified following the new convention in MMDet3D 1.1. Specifically, all the input data in training and testing are packed into inputs and data_samples, where inputs contains model inputs like a dict contain a list of image tensors and the point cloud data, and data_samples contains other information of the current data sample such as ground truths, region proposals, and model predictions. In this way, different tasks in MMDet3D 1.1 can share the same input arguments, which makes the models more general and suitable for multi-task learning and some flexible training paradigms like semi-supervised learning.
The model has a data preprocessor module, which are used to pre-process the input data of model. In MMDet3D 1.1, the data preprocessor usually does necessary steps to form the input images into a batch, such as padding. It can also serve as a place for some special data augmentations or more efficient data transformations like normalization.
The internal logic of model have been changed. In MMDet3D 1.1, model uses forward_train, forward_test, simple_test, and aug_test to deal with different model forward logics. In MMDet3D 1.1 and OpenMMLab 2.0, the forward function has three modes: 'loss', 'predict', and 'tensor' for training, inference, and tracing or other purposes, respectively. The forward function calls self.loss, self.predict, and self._forward given the modes 'loss', 'predict', and 'tensor', respectively.

Evaluation

The evaluation in MMDet3D 1.0.x strictly binds with the dataset. In contrast, MMDet3D 1.1 decomposes the evaluation from dataset, so that all the detection dataset can evaluate with KITTI AP and other metrics implemented in MMDet3D 1.1. MMDet3D 1.1 mainly implements corresponding metrics for each dataset, which are manipulated by Evaluator to complete the evaluation. Users can build evaluator in MMDet3D 1.1 to conduct offline evaluation, i.e., evaluate predictions that may not produced in MMDet3D 1.1 with the dataset as long as the dataset and the prediction follows the dataset conventions. More details can be find in the tutorial in mmengine.

Visualization

The functions of visualization in MMDet3D 1.1 are removed. Instead, in OpenMMLab 2.0 projects, we use Visualizer to visualize data. MMDet3D 1.1 implements Det3DLocalVisualizer to allow visualization of 2D and 3D data, ground truths, model predictions, and feature maps, etc., at any place. It also supports to send the visualization data to any external visualization backends such as Tensorboard.

Planned changes

We list several planned changes of MMDet3D 1.1.0rc0 so that the community could more comprehensively know the progress of MMDet3D 1.1. Feel free to create a PR, issue, or discussion if you are interested, have any suggestions and feedbacks, or want to participate.

Test-time augmentation: which is supported in MMDet3D 1.0.x, is not implemented in this version due to limited time slot. We will support it in the following releases with a new and simplified design.
Inference interfaces: a unified inference interfaces will be supported in the future to ease the use of released models.
Interfaces of useful tools that can be used in notebook: more useful tools that implemented in the tools directory will have their python interfaces so that they can be used through notebook and in downstream libraries.
Documentation: we will add more design docs, tutorials, and migration guidance so that the community can deep dive into our new design, participate the future development, and smoothly migrate downstream libraries to MMDet3D 1.1.
Wandb visualization: MMDet 2.x supports data visualization by WandB since v2.25.0, which has not been migrated to MMDet 3.x for now. Since Wandb provides strong visualization and experiment management capabilities, a DetWandbVisualizer and maybe a hook are planned to fully migrated those functionalities in MMDet 2.x and a Det3DWandbVisualizer will be supported in MMDet3D 1.1 accordingly.
Will support recent new features added in MMDet3D 1.0.x and our recent exploration on camera-only 3D detection from videos: we will refactor these models and support them with benchmarks and models soon.

Contributors

A total of 6 developers contributed to this release. Thanks @ZCMax , @jshilong, @VVsssssk, @Tai-Wang , @lianqing11, @ZwwWayne

- Python
Published by ZwwWayne almost 4 years ago

mmdet3d - MMDetection3D V1.0.0rc4 Release

Highlights

Support FCAF3D

New Features

Support FCAF3D (#1547)
Add the transformation to support multi-camera 3D object detection (#1580)
Support lift-splat-shoot view transformer (#1598)

Improvements

Remove the limitation of the maximum number of points during SUN RGB-D preprocessing (#1555)
Support circle CI (#1647)
Add mim to extras_require in setup.py (#1560, #1574)
Update dockerfile package version (#1697)

Bug Fixes

Flip yaw angle for DepthInstance3DBoxes.overlaps (#1548, #1556)
Fix DGCNN configs (#1587)
Fix bbox head not registered bug (#1625)
Fix missing objects in S3DIS preprocessing (#1665)
Fix spconv2.0 model loading bug (#1699)

Contributors

A total of 9 developers contributed to this release.

@Tai-Wang, @ZwwWayne, @filaPro, @lianqing11, @ZCMax, @HuangJunJie2017, @Xiangxu-0103, @ChonghaoSima, @VVsssssk

New Contributors

@HuangJunJie2017 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1580
@ChonghaoSima made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1614

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.0.0rc3...v1.0.0rc4

- Python
Published by Tai-Wang almost 4 years ago

mmdet3d - MMDetection3D V1.0.0rc3 Release

Highlights

Support SA-SSD

New Features

Support SA-SSD (#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 introduced by #1403 (#1479)
Update the PointPillars config 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

New Contributors

@atinfinity made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1508
@wenbo-yu made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1337
@wchen61 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1516
@AlexPasqua made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1519
@lianqing11 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1545

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.0.0rc2...v1.0.0rc3

- Python
Published by ZwwWayne about 4 years ago

mmdet3d - MMDetection3D V1.0.0rc2 Release

Highlights

Support spconv 2.0
Support 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

New Features

Add loader arguments in the configuration files (#1388)
Support spconv 2.0 when the package is installed. Users can still use spconv 1.x in MMCV with CUDA 9.0 (only cost more memory) without losing the compatibility of model weights between two versions (#1421)
Support MinkowskiEngine with MinkResNet (#1422)

Improvements

Add the documentation for model deployment (#1373, #1436)
Add Chinese documentation of
- Speed benchmark (#1379)
- LiDAR-based 3D detection (#1368)
- LiDAR 3D segmentation (#1420)
- Coordinate system refactoring (#1384)
Support training models on custom datasets with only point clouds (#1393)
Replace mmcv.iou3d with a set of bird-eye-view (BEV) operators to unify the operations of rotated boxes (#1403, #1418)
Update Registry to distinguish the scope of building functions (#1412, #1443)
Replace recommonmark with myst_parser for documentation rendering (#1414)

Bug Fixes

Fix the show pipeline in the browse_dataset.py (#1376)
Fix missing init files after coordinate system refactoring (#1383)
Fix the incorrect yaw in the visualization caused by coordinate system refactoring (#1407)
Fix NaiveSyncBatchNorm1d and NaiveSyncBatchNorm2d to support non-distributed cases and more general inputs (#1435)

Contributors

A total of 11 developers contributed to this release.

@ZCMax, @ZwwWayne, @Tai-Wang, @VVsssssk, @HanaRo, @JoeyforJoy, @ansonlcy, @filaPro, @jshilong, @Xiangxu-0103, @deleomike

New Contributors

@HanaRo made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1379
@JoeyforJoy made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1368
@ansonlcy made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1391
@deleomike made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1383

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.0.0rc1...v1.0.0rc2

- Python
Published by ZwwWayne about 4 years ago

mmdet3d - MMDetection3D V1.0.0rc1 Release

Compatibility

We migrate all
To fix the imprecise
We update some

| | Fully Updated |--------------------|:---- | SECOND | | PointPillars | | FreeAnchor | VoteNet | H3DNet | 3DSSD | | Part-A2 | MVXNet | CenterPoint | | SSN | ImVoteNet | FCOS3D | | PointNet++ | | Group-Free-3D | | ImVoxelNet | PAConv | | DGCNN | | SMOKE | | PGD | | MonoFlex | the mmdet3d ops to mmcv and do not need to compile them when installing mmdet3d. timestamp and optimize its saving method, we reformat the point cloud data during Waymo data conversion. The data conversion time is also optimized significantly by supporting parallel processing. Please re-generate KITTI format Waymo data if necessary. See more details in the compatibility documentation. of the model checkpoints after the refactor of coordinate systems. Please stay tuned for the release of the remaining model checkpoints. | Partially Updated | In Progress | No Influcence | ---------:|:--------:| :-----------: | :-----------: | | ✓ | | | | ✓ | | | | ✓ | | | | | ✓ | | | | | ✓ | | | | | ✓ | | | | ✓ | | | | | ✓ | | | | | |✓ | | | ✓ | | | | | ✓ | | | | | | |✓ | | | |✓ | | | |✓ | | ✓ | | | | | | |✓ | | | |✓ | | | |✓ | | | |✓ | | | |✓ |

Highlights

Migrate all the mmdet3d ops to mmcv
Support parallel waymo data converter
Add ScanNet instance segmentation dataset with metrics
Better compatibility for windows with CI support, op migration and bug fixes
Support loading annotations from Ceph

New Features

Add ScanNet instance segmentation dataset with metrics (#1230)
Support different random seeds for different ranks (#1321)
Support loading annotations from Ceph (#1325)
Support resuming from the latest checkpoint automatically (#1329)
Add windows CI (#1345)

Improvements

Update the table format and OpenMMLab project orders in README.md (#1272, #1283)
Migrate all the mmdet3d ops to mmcv (#1240, #1286, #1290, #1333)
Add with_plane flag in the KITTI data conversion (#1278)
Update instructions and links in the documentation (#1300, 1309, #1319)
Support parallel Waymo dataset converter and ground truth database generator (#1327)
Add quick installation commands to getting_started.md (#1366)

Bug Fixes

Update nuimages configs to use new nms config style (#1258)
Fix the usage of np.long for windows compatibility (#1270)
Fix the incorrect indexing in BasePoints (#1274)
Fix the incorrect indexing in the pillarscatter.forwardsingle (#1280)
Fix unit tests that use GPUs (#1301)
Fix incorrect feature dimensions in DynamicPillarFeatureNet caused by previous upgrading of PillarFeatureNet (#1302)
Remove the CameraPoints constraint in PointSample (#1314)
Fix imprecise timestamps saving of Waymo dataset (#1327)

Contributors

A total of 10 developers contributed to this release.

@ZCMax, @ZwwWayne, @wHao-Wu, @Tai-Wang, @wangruohui, @zjwzcx, @Xiangxu-0103, @EdAyers, @hongye-dev, @zhanggefan

New Contributors

@VVsssssk made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1275
@Xiangxu-0103 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1300
@Subjectivist made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1298
@EdAyers made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1258
@hongye-dev made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1280
@jshilong made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1366

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v1.0.0rc0...v1.0.0rc1

- Python
Published by ZwwWayne about 4 years ago

mmdet3d - MMDetection3D V1.0.0rc0 Release

Compatibility

We refactor our three coordinate systems to make their rotation directions and origins more consistent, and further remove unnecessary hacks in different datasets and models. Therefore, please re-generate data information or convert the old version to the new one with our provided scripts. We will also provide updated checkpoints in the next version. Please refer to the compatibility documentation for more details.
Unify the camera keys for consistent transformation between coordinate systems on different datasets. The modification changes 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 files of CUDA ops to 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 new monocular 3D detectors: PGD, SMOKE, MonoFlex
Support a new LiDAR-based detector: PointRCNN
Support a new backbone: DGCNN
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

New Features

Support 3D object detection on the S3DIS dataset (#835)
Support PointRCNN (#842, #843, #856, #974, #1022, #1109, #1125)
Support DGCNN (#896)
Support PGD (#938, #940, #948, #950, #964, #1014, #1065, #1070, #1157)
Support SMOKE (#939, #955, #959, #975, #988, #999, #1029)
Support MonoFlex (#1026, #1044, #1114, #1115, #1183)
Support CPU Training (#1196)

Improvements

Support point sampling based on distance metric (#667, #840)
Refactor coordinate systems (#677, #774, #803, #899, #906, #912, #968, #1001)
Unify camera keys in PointFusion and transformations between different systems (#791, #805)
Refine documentation (#792, #827, #829, #836, #849, #854, #859, #1111, #1113, #1116, #1121, #1132, #1135, #1185, #1193, #1226)
Add a script to support benchmark regression (#808)
Benchmark PAConvCUDA on S3DIS (#847)
Support to download pdf and epub documentation (#850)
Change the repeat setting in Group-Free-3D configs to reduce training epochs (#855)
Support KITTI AP40 evaluation metric (#927)
Add the mmdet3d2torchserve tool for SECOND (#977)
Add code-spell pre-commit hook and fix typos (#995)
Support the latest numba version (#1043)
Set a default seed to use when the random seed is not specified (#1072)
Distribute mix-precision models to each algorithm folder (#1074)
Add abstract and a representative figure for each algorithm (#1086)
Upgrade pre-commit hook (#1088, #1217)
Support augmented data and ground truth visualization (#1092)
Add local yaw property for CameraInstance3DBoxes (#1130)
Lock the required numba version to 0.53.0 (#1159)
Support the usage of plane information for KITTI dataset (#1162)
Deprecate the support for "python setup.py test" (#1164)
Reduce the number of multi-process threads to accelerate training (#1168)
Support 3D flip augmentation for semantic segmentation (#1181)
Update README format for each model (#1195)

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)
Fix the incorrect dimension indices of rotations and testing config in the CenterPoint test time augmentation (#892)
Fix and improve visualization tools (#956, #1066, #1073)
Fix PointPillars FLOPs calculation error (#1075)
Fix missing dimension information in the SUN RGB-D data generation (#1120)
Fix incorrect anchor range settings in the PointPillars config for KITTI (#1163)
Fix incorrect model information in the RegNet metafile (#1184)
Fix bugs in non-distributed multi-gpu training and testing (#1197)
Fix a potential assertion error when generating corners from an empty box (#1212)
Upgrade bazel version according to the requirement of Waymo Devkit (#1223)

Contributors

A total of 12 developers contributed to this release.

@THU17cyz, @wHao-Wu, @wangruohui, @Wuziyi616, @filaPro, @ZwwWayne, @Tai-Wang, @DCNSW, @xieenze, @robin-karlsson0, @ZCMax, @Otteri

New Contributors

@Otteri made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1070
@zeyu-hello made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1225
@maskjp made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1207

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.18.1...v1.0.0rc0

- Python
Published by ZwwWayne over 4 years ago

mmdet3d - MMDetection3D V0.18.1 Release

Improvements

Support Flip3D augmentation in semantic segmentation task (#1182)
Update regnet metafile (#1184)
Add point cloud annotation tools introduction in FAQ (#1185)
Add missing explanations of cam_intrinsic in the nuScenes dataset doc (#1193)

Bug Fixes

Deprecate the support for "python setup.py test" (#1164)
Fix the rotation matrix while rotation axis=0 (#1182)
Fix the bug in non-distributed multi-gpu training/testing (#1197)
Fix a potential bug when generating corners of empty bounding boxes (#1212)

Contributors

A total of 4 developers contributed to this release.

@ZwwWayne, @ZCMax, @Tai-Wang, @wHao-Wu

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.18.0...v0.18.1

- Python
Published by ZwwWayne over 4 years ago

mmdet3d - MMDetection3D V0.18.0 Release

Highlights

Update the required minimum version of mmdet and mmseg

Improvements

Use the official markdownlint hook and add codespell hook for pre-committing (#1088)
Improve CI operation (#1095, #1102, #1103)
Use shared menu content from OpenMMLab's theme and remove duplicated contents from config (#1111)
Refactor the structure of documentation (#1113, #1121)
Update the required minimum version of mmdet and mmseg (#1147)

Bug Fixes

Fix symlink failure on Windows (#1096)
Fix the upper bound of mmcv version in the mminstall requirements (#1104)
Fix API documentation compilation and mmcv build errors (#1116)
Fix figure links and pdf documentation compilation (#1132, #1135)

Contributors

A total of 4 developers contributed to this release.

@ZwwWayne, @ZCMax, @Tai-Wang, @wHao-Wu

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.17.3...v0.18.0

- Python
Published by ZwwWayne over 4 years ago

mmdet3d - MMDetection3D V0.17.3 Release

What's Changed

[Fix] Update mmcv version in dockerfile by @wHao-Wu in https://github.com/open-mmlab/mmdetection3d/pull/1036
[Fix] Fix the memory-leak problem in init_detector by @Tai-Wang in https://github.com/open-mmlab/mmdetection3d/pull/1045
[Fix] Fix default show value in showresult function and a typo in waymodata_prep by @ZCMax in https://github.com/open-mmlab/mmdetection3d/pull/1034
[Fix] Fix incorrect velo indexing when formatting boxes on nuScenes by @Tai-Wang in https://github.com/open-mmlab/mmdetection3d/pull/1049
[Enhance] Clean unnecessary custom_imports in entrypoints by @ZCMax in https://github.com/open-mmlab/mmdetection3d/pull/1068
[Doc] Add MMFlow into README by @ZCMax in https://github.com/open-mmlab/mmdetection3d/pull/1067
Explicitly setting torch.cuda.device at init_model by @aldakata in https://github.com/open-mmlab/mmdetection3d/pull/1056
[Fix] Fix PointPillars FLOPs calculation error for master branch by @ZCMax in https://github.com/open-mmlab/mmdetection3d/pull/1076
[Enhance] Add mmFewShot in README by @ZCMax in https://github.com/open-mmlab/mmdetection3d/pull/1085
Label visualization by @MilkClouds in https://github.com/open-mmlab/mmdetection3d/pull/1050
[Enhance] add mmhuman3d in readme by @ZCMax in https://github.com/open-mmlab/mmdetection3d/pull/1094
[Enhance] fix mmhuman3d reference by @ZCMax in https://github.com/open-mmlab/mmdetection3d/pull/1100
Bump to v0.17.3 by @Tai-Wang in https://github.com/open-mmlab/mmdetection3d/pull/1083

New Contributors

@aldakata made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1056
@MilkClouds made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/1050

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.17.2...v0.17.3

- Python
Published by ZwwWayne over 4 years ago

mmdet3d - MMDetection3D V0.17.2 Release

Improvements

Update Group-Free-3D and FCOS3D bibtex (#985)
Update the solutions for incompatibility of pycocotools in the FAQ (#993)
Add Chinese documentation for the KITTI (#1003) and Lyft (#1010) dataset tutorial
Add the H3DNet checkpoint converter for incompatible keys (#1007)

Bug Fixes

Update mmdetection and mmsegmentation version in the Dockerfile (#992)
Fix links in the Chinese documentation (#1015)

Contributors

A total of 4 developers contributed to this release.

@Tai-Wang, @wHao-Wu, @ZwwWayne, @ZCMax

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.17.1...v0.17.2

- Python
Published by ZwwWayne over 4 years ago

mmdet3d - MMDetection3D V0.17.1 Release

Highlights

Support a faster but non-deterministic version of hard voxelization
Completion of dataset tutorials and the Chinese documentation
Improved the aesthetics of the documentation format

Improvements

Add Chinese Documentation for training on customized datasets and designing customized models (#729, #820)
Support a faster but non-deterministic version of hard voxelization (#904)
Update paper titles and code details for metafiles (#917)
Add a tutorial for KITTI dataset (#953)
Use Pytorch sphinx theme to improve the format of documentation (#958)
Use the docker to accelerate CI (#971)

Bug Fixes

Fix the sphinx version used in the documentation (#902)
Fix a dynamic scatter bug that discards the first voxel by mistake when all input points are valid (#915)
Fix the inconsistent variable names used in the unit test for voxel generator (#919)
Upgrade to use build_prior_generator to replace the legacy build_anchor_generator (#941)
Fix a minor bug caused by a too-small difference set in the FreeAnchor Head (#944)

Contributors

A total of 8 developers contributed to this release.

@DCNSW, @zhanggefan, @mickeyouyou, @ZCMax, @wHao-Wu, @tojimahammatov, @xiliu8006, @Tai-Wang

New Contributors

@mickeyouyou made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/920
@tojimahammatov made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/944

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.17.0...v0.17.1

- Python
Published by ZwwWayne over 4 years ago

mmdet3d - MMDetection3D V0.17.0 Release

Compatibility

Unify the camera keys for consistent transformation between coordinate systems on different datasets. The modification changes 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 files of CUDA ops to 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 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 the 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

New Contributors

@wangruohui made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/766
@xieenze made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/872
@robin-karlsson0 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/879

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.16.0...v0.17.0

- Python
Published by ZwwWayne almost 5 years ago

mmdet3d - MMDetection3D V0.16.0 Release

Compatibility

Remove the rotation and dimension hack in the monocular 3D detection on nuScenes by applying corresponding transformation in the pre-processing and post-processing. The modification only influences nuScenes coco-style json files. Please re-run the data preparation scripts if necessary. See more details in the PR #744.
Add a new pre-processing module for the ScanNet dataset in order to support multi-view detectors. Please run the updated scripts to extract the RGB data and its annotations. See more details in the PR #696.

Highlights

Support to use MIM with pip installation
Support PAConv models and benchmarks on S3DIS
Enhance the documentation especially on dataset tutorials

New Features

Support RGB images on ScanNet for multi-view detectors (#696)
Support FLOPs and number of parameters calculation (#736)
Support to use MIM with pip installation (#782)
Support PAConv models and benchmarks on the S3DIS dataset (#783, #809)

Improvements

Refactor Group-Free-3D to make it inherit BaseModule from MMCV (#704)
Modify the initialization methods of FCOS3D to be consistent with the refactored approach (#705)
Benchmark the Group-Free-3D models on ScanNet (#710)
Add Chinese Documentation for Getting Started (#725), FAQ (#730), Model Zoo (#735), Demo (#745), Quick Run (#746), Data Preparation (#787) and Configs (#788)
Add documentation for semantic segmentation on ScanNet and S3DIS (#743, #747, #806, #807)
Add a parameter max_keep_ckpts to limit the maximum number of saved Group-Free-3D checkpoints (#765)
Add documentation for 3D detection on SUN RGB-D and nuScenes (#770, #793)
Remove mmpycocotools in the Dockerfile (#785)

Bug Fixes

Fix versions of OpenMMLab dependencies (#708)
Convert rt_mat to torch.Tensor in coordinate transformation for compatibility (#709)
Fix the bev_range initialization in ObjectRangeFilter according to the gt_bboxes_3d type (#717)
Fix Chinese documentation and incorrect doc format due to the incompatible Sphinx version (#718)
Fix a potential bug when setting interval == 1 in analyze_logs.py (#720)
Update the structure of Chinese Documentation (#722)
Fix FCOS3D FPN BC-Breaking caused by the code refactoring in MMDetection (#739)
Fix wrong in_channels when with_distance=True in the Dynamic VFE Layers (#749)
Fix the dimension and yaw hack of FCOS3D on nuScenes (#744, #794, #795, #818)
Fix the missing default bbox_mode in the show_multi_modality_result (#825)

Contributors

A total of 12 developers contributed to this release.

@yinchimaoliang, @gopi231091, @filaPro, @ZwwWayne, @ZCMax, @hjin2902, @wHao-Wu, @Wuziyi616, @xiliu8006, @THU17cyz, @DCNSW, @Tai-Wang

New Contributors

@gopi231091 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/709

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.15.0...v0.16.0

- Python
Published by ZwwWayne almost 5 years ago

mmdet3d - MMDetection3D V0.15.0 Release

Highlights

Support PAConv
Support monocular/multi-view 3D detector ImVoxelNet on KITTI
Support Transformer-based 3D detection method Group-Free-3D on ScanNet
Add documentation for tasks including LiDAR-based 3D detection, vision-only 3D detection and point-based 3D semantic segmentation
Add dataset documents like ScanNet
Upgrade to use MMCV-full v1.3.8

Compatibility

In order to fix the problem that the priority of EvalHook is too low, all hook priorities have been re-adjusted in 1.3.8, so MMDetection 2.14.0 needs to rely on the latest MMCV 1.3.8 version. For related information, please refer to #1120, for related issues, please refer to #5343.

New Features

Support Group-Free-3D on ScanNet (#539)
Support PAConv modules (#598, #599)
Support ImVoxelNet on KITTI (#627, #654)

Improvements

Add unit tests for pipeline functions LoadImageFromFileMono3D, ObjectNameFilter and ObjectRangeFilter (#615)
Enhance IndoorPatchPointSample (#617)
Refactor model initialization methods based MMCV (#622)
Add Chinese docs (#629)
Add documentation for LiDAR-based 3D detection (#642)
Unify intrinsic and extrinsic matrices for all datasets (#653)
Add documentation for point-based 3D semantic segmentation (#663)
Add documentation of ScanNet for 3D detection (#664)
Refine docs for tutorials (#666)
Add documentation for vision-only 3D detection (#669)
Refine docs for Quick Run and Useful Tools (#686)

Bug Fixes

Fix the bug of BackgroundPointsFilter using the bottom center of ground truth (#609)
Fix LoadMultiViewImageFromFiles to unravel stacked multi-view images to list to be consistent with DefaultFormatBundle (#611)
Fix the potential bug in analyze_logs when the training resumes from a checkpoint or is stopped before evaluation (#634)
Fix test commands in docs and make some refinements (#635)
Fix wrong config paths in unit tests (#641)

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.14.0...v0.15.0

- Python
Published by ZwwWayne almost 5 years ago

mmdet3d - MMDetection3D V0.14.0 Release

Highlights

Support the point cloud segmentation method PointNet++

New Features

Support PointNet++ (#479, #528, #532, #541)
Support RandomJitterPoints transform for point cloud segmentation (#584)
Support RandomDropPointsColor transform for point cloud segmentation (#585)

Improvements

Move the point alignment of ScanNet from data pre-processing to pipeline (#439, #470)
Add compatibility document to provide detailed descriptions of BC-breaking changes (#504)
Add MMSegmentation installation requirement (#535)
Support points rotation even without bounding box in GlobalRotScaleTrans for point cloud segmentaiton (#540)
Support visualization of detection results and dataset browse for nuScenes Mono-3D dataset (#542, #582)
Support faster implementation of KNN (#586)
Support RegNetX models on Lyft dataset (#589)
Remove a useless parameter label_weight from segmentation datasets including Custom3DSegDataset, ScanNetSegDataset and S3DISSegDataset (#607)

Bug Fixes

Fix a corrupted lidar data file in Lyft dataset in data_preparation (#546)
Fix evaluation bugs in nuScenes and Lyft dataset (#549)
Fix converting points between coordinates with specific transformation matrix in the coord3dmode.py (#556)
Support PointPillars models on Lyft dataset (#578)
Fix the bug of demo with pre-trained VoteNet model on ScanNet (#600)

New Contributors

@haotian-liu made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/515
@JSchuurmans made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/565

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.13.0...v0.14.0

- Python
Published by ZwwWayne about 5 years ago

mmdet3d - MMDetection3D V0.13.0 Release

Highlights

Support a monocular 3D detection method FCOS3D
Support ScanNet and S3DIS semantic segmentation dataset
Enhancement of visualization tools for dataset browsing and demos, including support of visualization for multi-modality data and point cloud segmentation.

New Features

Support ScanNet semantic segmentation dataset (#390)
Support monocular 3D detection on nuScenes (#392)
Support multi-modality visualization (#405)
Support nuImages visualization (#408)
Support monocular 3D detection on KITTI (#415)
Support online visualization of semantic segmentation results (#416)
Support ScanNet test results submission to online benchmark (#418)
Support S3DIS data pre-processing and dataset class (#433)
Support FCOS3D (#436, #442, #482, #484)
Support dataset browse for multiple types of datasets (#467)
Adding paper-with-code (PWC) metafile for each model in the model zoo (#485)

Improvements

Support dataset browsing for SUNRGBD, ScanNet or KITTI points and detection results (#367)
Add the pipeline to load data using file client (#430)
Support to customize the type of runner (#437)
Make pipeline functions process points and masks simultaneously when sampling points (#444)
Add waymo unit tests (#455)
Split the visualization of projecting points onto image from that for only points (#480)
Efficient implementation of PointSegClassMapping (#489)
Use the new model registry from mmcv (#495)

Bug Fixes

Fix Pytorch 1.8 Compilation issue in the scatterpointscuda.cu (#404)
Fix dynamic_scatter errors triggered by empty point input (#417)
Fix the bug of missing points caused by using break incorrectly in the voxelization (#423)
Fix the missing coord_type in the waymo dataset config (#441)
Fix errors in four unittest functions of configs, test_detectors.py, test_heads.py (#453)
Fix 3DSSD training errors and simplify configs (#462)
Clamp 3D votes projections to image boundaries in ImVoteNet (#463)
Update out-of-date names of pipelines in the config of pointpillars benchmark (#474)
Fix the lack of a placeholder when unpacking RPN targets in the h3dbboxhead.py (#508)
Fix the incorrect value of K when creating pickle files for SUN RGB-D (#511)

New Contributors

@gillbam made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/423
@Divadi made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/463
@virusapex made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/511

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.12.0...v0.13.0

- Python
Published by ZwwWayne about 5 years ago

mmdet3d - MMDetection3D V0.12.0 Release

Highlights

Support a new multi-modality method ImVoteNet.
Support pytorch 1.7 and 1.8
Refactor the structure of tools and train.py/test.py

Bug Fixes

Fix missing keys coord_type in database sampler config (#345)
Rename H3DNet configs (#349)
Fix CI by using ubuntu 18.04 in github workflow (#350)
Add assertions to avoid 4-dim points being input to pointsinboxes (#357)
Fix the SECOND results on Waymo in the corresponding README (#363)
Fix the incorrectly adopted pipeline when adding val to workflow (#370)
Fix a potential bug when indices used in the backwarding in ThreeNN (#377)
Fix a compilation error triggered by scatterpointscuda.cu in pytorch 1.7 (#393)

New Features

Support LiDAR-based semantic segmentation metrics (#332)
Support ImVoteNet (#352, #384)
Support the KNN GPU operation (#360, #371)

Improvements

Add FAQ for common problems in the documentation (#333)
Refactor the structure of tools (#339)
Refactor train.py and test.py (#343)
Support demo on nuScenes (#353)
Add 3DSSD checkpoints (#359)
Update the Bibtex of CenterPoint (#368)
Add citation format and reference to other OpenMMLab projects in the README (#374)
Upgrade the mmcv version requirements (#376)
Add numba and numpy version requirements in FAQ (#379)
Avoid unnecessary for-loop execution of VFE layer creation (#389)
Update SUNRGBD dataset documentation to stress the requirements for training ImVoteNet (#391)
Modify vote head to support 3DSSD (#396)

New Contributors

@tianweiy made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/368
@happynear made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/363
@zehuichen123 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/389

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.11.0...v0.12.0

- Python
Published by ZwwWayne about 5 years ago

mmdet3d - MMDetection3D V0.11.0 Release

Highlights

Support more friendly visualization interfaces based on open3d
Support a faster and more memory-efficient implementation of DynamicScatter
Refactor unit tests and details of configs

Bug Fixes

Fix an unsupported bias setting in the unit test for CenterPoint head (#304)
Fix errors due to typos in the CenterPoint head (#308)
Fix a minor bug in pointsinboxes.py when tensors are not in the same device. (#317)

New Features

Support new visualization methods based on Open3D (#284, #323)

Improvements

Refactor unit tests (#303)
Move the key train_cfg and test_cfg into the model configs (#307)
Update README with Chinese version and instructions for getting started. (#310, #316)
Support a faster and more memory-efficient implementation of DynamicScatter (#318, #326)
Fix warning of deprecated usages of nonzero during training with PyTorch 1.6 (#330)

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.10.0...v0.11.0

- Python
Published by ZwwWayne over 5 years ago

mmdet3d - MMDetection3D V0.10.0 Release

Highlights

Preliminary release of API for SemanticKITTI dataset.
Documentation and demo enhancement for better user experience.
Fix a number of underlying minor bugs and add some corresponding important unit tests.

Bug Fixes

Fixed the issue of unpacking size in furthestpointsample.py (#248)
Fix bugs for 3DSSD triggered by empty ground truths (#258)
Remove models without checkpoints in model zoo statistics of documentation (#259)
Fix some unclear installation instructions in getting_started.md (#269)
Fix relative paths/links in the documentation (#271)
Fix a minor bug in scatterpointscuda.cu when num_features != 4 (#275)
Fix the bug about missing text files when testing on KITTI (#278)
Fix issues caused by inplace modification of tensors in BaseInstance3DBoxes (#283)
Fix log analysis for evaluation and adjust the documentation accordingly (#285)

New Features

Support SemanticKITTI dataset preliminarily (#287)

Improvements

Add tags to README in configurations for specifying different uses (#262)
Update instructions for evaluation metrics in the documentation (#265)
Add nuImages entry in README.md and gif demo (#266, #268)
Add unit test for voxelization (#275)

New Contributors

@congee524 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/259
@wikiwen made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/269
@EricWiener made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/248

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.9.0...v0.10.0

- Python
Published by ZwwWayne over 5 years ago

mmdet3d - MMDetection3D V0.9.0 Release

Highlights

Documentation refactoring with better structure, especially about how to implement new models and customized datasets.
More compatible with refactored point structure by bug fixes in ground truth sampling.

Bug Fixes

Fix point structure related bugs in ground truth sampling (#211)
Fix loading points in ground truth sampling augmentation on nuScenes (#221)
Fix channel setting in the SeparateHead of CenterPoint (#228)
Fix evaluation for indoors 3D detection in case of less classes in prediction (#231)
Remove unreachable lines in nuScenes data converter (#235)
Minor adjustments of numpy implementation for perspective projection and prediction filtering criterion in KITTI evaluation (#241)

Improvements

Documentation refactoring (#242)

New Contributors

@meng-zha made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/211
@zhezhao1989 made their first contribution in https://github.com/open-mmlab/mmdetection3d/pull/228

Full Changelog: https://github.com/open-mmlab/mmdetection3d/compare/v0.8.0...v0.9.0

- Python
Published by ZwwWayne over 5 years ago

mmdet3d - MMDetection3D V0.8.0 Release

v0.8.0 (30/11/2020)

Highlights

Refactor points structure with more constructive and clearer implementation.
Support axis-aligned IoU loss for VoteNet with better performance.
Update and enhance SECOND benchmark on Waymo.

New Features

Support axis-aligned IoU loss for VoteNet. (#194)
Support points structure for consistent processing of all the point related representation. (#196, #204)

Improvements

Enhance SECOND benchmark on Waymo with stronger baselines. (#166)
Add model zoo statistics and polish the documentation. (#201)

- Python
Published by ZwwWayne over 5 years ago

mmdet3d - MMDetection3D V0.7.0 Release

Highlights

Support a new method SSN with benchmarks on nuScenes and Lyft datasets.
Update benchmarks for SECOND on Waymo, CenterPoint with TTA on nuScenes and models with mixed precision training on KITTI and nuScenes.
Support semantic segmentation on nuImages and provide HTC models with configurations and performance for reference.

Bug Fixes

Fix incorrect code weights in anchor3d_head when introducing mixed precision training (#173)
Fix the incorrect label mapping on nuImages dataset (#155)

New Features

Modified primitive head which can support the setting on SUN-RGBD dataset (#136)
Support semantic segmentation and HTC with models for reference on nuImages dataset (#155)
Support SSN on nuScenes and Lyft datasets (#147, #174, #166, #182)
Support double flip for test time augmentation of CenterPoint with updated benchmark (#143)

Improvements

Update SECOND benchmark with configurations for reference on Waymo (#166)
Delete checkpoints on Waymo to comply its specific license agreement (#180)
Update models and instructions with mixed precision training on KITTI and nuScenes (#178)

- Python
Published by ZwwWayne over 5 years ago

mmdet3d - MMDetection3D V0.6.1 Release

Highlights

Support mixed precision training of voxel-based methods
Support docker with PyTorch 1.6.0
Update baseline configs and results (CenterPoint on nuScenes and PointPillars on Waymo with full dataset)
Switch model zoo to download.openmmlab.com

Bug Fixes

Fix a bug of visualization in multi-batch case (#120)
Fix bugs in DCN unit test (#130)
Fix DCN bias bug in CenterPoint (#137)
Fix dataset mapping in the evaluation of nuScenes mini dataset (#140)
Fix origin initialization in CameraInstance3DBoxes (#148, #150)
Correct documentation link in the getting_started.md (#159)
Fix model save path bug in gather_models.py (#153)
Fix image padding shape bug in PointFusion (#162)

New Features

Support dataset pipeline VoxelBasedPointSampler to sample multi-sweep points based on voxelization. (#125)
Support mixed precision training of voxel-based methods (#132)
Support docker with PyTorch 1.6.0 (#160)

Improvements

Reduce requirements for the case exclusive of Waymo (#121)
Switch model zoo to download.openmmlab.com (#126)
Update docs related to Waymo (#128)
Add version assertion in the init file (#129)
Add evaluation interval setting for CenterPoint (#131)
Add unit test for CenterPoint (#133)
Update PointPillars baselines on Waymo with full dataset (#142)
Update CenterPoint results with models and logs (#154)

- Python
Published by ZwwWayne over 5 years ago

mmdet3d - MMDetection3D V0.6.0 Release

Highlights

Support new methods H3DNet, 3DSSD, CenterPoint.
Support new dataset Waymo (with PointPillars baselines) and nuImages (with Mask R-CNN and Cascade Mask R-CNN baselines).
Support Batch Inference
Support Pytorch 1.6
Start to publish mmdet3d package to PyPI since v0.5.0. You can use mmdet3d through pip install mmdet3d.

Backwards Incompatible Changes

Support Batch Inference (#95, #103, #116): MMDetection3D v0.6.0 migrates to support batch inference based on MMDetection >= v2.4.0. This change influences all the test APIs in MMDetection3D and downstream codebases.
Start to use collect environment function from MMCV (#113): MMDetection3D v0.6.0 migrates to use collect_env function in MMCV. get_compiler_version and get_compiling_cuda_version compiled in mmdet3d.ops.utils are removed. Please import these two functions from mmcv.ops.

Bug Fixes

Rename CosineAnealing to CosineAnnealing (#57)
Fix device inconsistant bug in 3D IoU computation (#69)
Fix a minor bug in json2csv of lyft dataset (#78)
Add missed test data for pointnet modules (#85)
Fix use_valid_flag bug in CustomDataset (#106)

New Features

Support nuImages dataset by converting them into coco format and release Mask R-CNN and Cascade Mask R-CNN baseline models (#91, #94)
Support to publish to PyPI in github-action (#17, #19, #25, #39, #40)
Support CBGSDataset and make it generally applicable to all the supported datasets (#75, #94)
Support H3DNet and release models on ScanNet dataset (#53, #58, #105)
Support Fusion Point Sampling used in 3DSSD (#66)
Add BackgroundPointsFilter to filter background points in data pipeline (#84)
Support pointnet2 with multi-scale grouping in backbone and refactor pointnets (#82)
Support dilated ball query used in 3DSSD (#96)
Support 3DSSD and release models on KITTI dataset (#83, #100, #104)
Support CenterPoint and release models on nuScenes dataset (#49, #92)
Support Waymo dataset and release PointPillars baseline models (#118)
Allow LoadPointsFromMultiSweeps to pad empty sweeps and select multiple sweeps randomly (#67)

Improvements

Fix all warnings and bugs in Pytorch 1.6.0 (#70, #72)
Update issue templates (#43)
Update unit tests (#20, #24, #30)
Update documentation for using ply format point cloud data (#41)
Use points loader to load point cloud data in ground truth (GT) samplers (#87)
Unify version file of OpenMMLab projects by using version.py (#112)
Remove unnecessary data preprocessing commands of SUN RGB-D dataset (#110)

- Python
Published by ZwwWayne over 5 years ago

Recent Releases of mmdet3d

mmdet3d - MMDetection3D v1.4.0 Release

Highlights

New Features

Improvements

Bug Fixes

Contributors

New Contributors

mmdet3d - MMDetection3D v1.3.0 Release

Highlights

New Features

Improvements

Bug Fixes

Contributors

New Contributors

mmdet3d - MMDetection3D v1.2.0 Release

Highlights

New Features

Improvements

Bug Fixes

Contributors

New Contributors

mmdet3d - MMDetection3D v1.1.1 Release

Highlights

New Features

Improvements

Bug Fixes

Contributors

New contributors

mmdet3d - MMDetection3D v1.1.0 Release

Highlights

New Features

Improvements

Bug Fixes

Contributors

New contributors

mmdet3d - MMDetection3D v1.1.0rc3 Release

Highlights

New Features

Improvements

Bug Fixes

Contributors

New Contributors

mmdet3d - MMDetection3D V1.0.0rc6 Release

New Features

Improvements

Bug Fixes

Contributors

mmdet3d - MMDetection3D V1.1.0rc2 Release

Highlights

New Features

Improvements

Bug Fixes

Contributors

New Contributors

mmdet3d - MMDetection3D V1.1.0rc1 Release

Highlights

New Features

Improvements

Bug Fixes

Contributors

New Contributors

mmdet3d - MMDetection3D V1.0.0rc5 Release

New Features

Improvements

Bug Fixes

Contributors

New Contributors

mmdet3d - MMDetection3D V1.1.0rc0 Release

Changelog of v1.1

v1.1.0rc0 (1/9/2022)

Highlights

Breaking Changes

Dependencies

Training and testing

Configs

Dataset

Data Transforms

Model

Evaluation