GitLab

* [Feature]: support using nuimages for instance segmentation

* Update performance and start benchmark

* Change default path names

* Update performance

* Update mmcv version

* Update model links

* Update model links and fix unit tests

* rephrase

* add op fps with distance

* add op fps with distance

* modify F-DFS unittest

* modify sa module

* modify sa module

* SA Module support D-FPS and F-FPS

* modify sa module

* update points sa module

* modify point_sa_module

* modify point sa module

* reconstruct FPS

* reconstruct FPS

* modify docstring

* add pointnet2-sa-msg backbone

* modify pointnet2_sa_msg

* fix merge conflicts

* format tests/test_backbones.py

* [Refactor]: Add registry for PointNet2Modules

* modify h3dnet for base pointnet

* fix docstring tweaks

* fix bugs for config unittest
Co-authored-by: ZwwWayne <wayne.zw@outlook.com>

* Fix (torch.nonzero): Fix  warning of torch.nonzero and bug of nms_iou

* Fix contiguous warning of tensor

* Update CI with pt1.6

* update build action

* recover ci

* Add force cuda

* Use mmcv-full==1.0.5

* Fix nonzero warning

* Update CI config

* update links

* fix unit tests

* fix unit tests

* Lock pytorch version in CI

* Lock pytorch version in CI

* Lock pytorch version in CI

* Try specify torchlink

* Try specify torchlink

* Only add 3.7 for CI

* fix synctax error

* Use 1.3.0

* Use 1.3.0 and specify mmcv

* give up 1.3

* fix cublas issue

* fix cublas issue

* add test data

* update fps test data

* update fps test data

* add data_aug BackgroundPointsFilter

* modify BackgroundPointsFilter

* modify BackgroundPointsFilter

* add h3d head

* add h3d roi head

* update docstring of h3d roi head

* reconstruct h3d head

* remove unused code

* modify h3d bbox head

* add h3dnet init files

* modify h3d bbox head

* add depth_box3d unittest

* update h3d head

* add h3dnet benchmark

* update docstring in vote_head

* resovle primitive conflict

* add op fps with distance

* add op fps with distance

* modify F-DFS unittest

* modify sa module

* modify sa module

* SA Module support D-FPS and F-FPS

* modify sa module

* update points sa module

* modify point_sa_module

* modify point sa module

* reconstruct FPS

* reconstruct FPS

* modify docstring

* modify docstring

* Add bottom2gravity and balance_class option.

* Add valid_flag.

* Add use_valid_flag.

* Change balance_class option.

* Add wrapper, remove gravity and balance_class option.

* Change flag, change load_infos to repeat_indices.

* Remove pdb, change docstring.

* Change name, remove unnecessary args.

* Remove _concat_dataset.

* Change name of ClassSampledDataset.

* Change docstring.

* Add get_cat_ids in nus_dataset, add unittest for wrapper.

* Change to len(self.dataset)

* Update nus data.

* add primitive head

* register of primitive head

* modify primitive head

* modify primitive head

* modify primitive head

* modify primitive head

* update primitive head unittest

* modify primitive had

* fix bugs for primitive head

* update primitive head

* Fix a minor bug in json2csv of lyft dataset

* Fix variable names and minor hard code

* Fix minor bugs encountered when computing iou3d with gpu while the specified cuda id is not default 0

* Fix nonstandard formats

* Remove trailing whitespace

* Fix nonstandard format

* Fix ambiguous initialization of cuda tensors

* Add unittest.

* Change to 'defaults to'.

* Add replace=False, remove T op, add num_sweeps=10 unittest.

* Change lyft_infos.pkl.

* Add nus unittest.

* Add nus unittest.

* Change nus_info.pkl.

* Add test_mode.

* add multi backbone

* update multi backbone

* update multi backbone

* update multi backbone

* modify multi backbone

* modify multi_backbone params

* modify docstring

* update multi_backbone unittest

* modify docstring

* Add centerpoint_rpn and scn, change pillar encoder and voxel_encoder

* Move test_voxel_encoders.

* Change names, add docstring.

* Reconstruct centerpoint_rpn.

* Add centerpoint_rpn.

* Change SECONDFPN, delete centerpoint_fpn

* Remove SparseBasicBlock.

* Change SpMiddleResNetFHD to SparseEncoder.

* Finish SparseEncoder unittest.

* Change test_hard_simple_VFE.

* Change option, add legacy.

* Change docstring, change legacy.

* Fix legacy bug.

* Change unittest, change docstring.

* Change docstring.

* Add ply convert

* Change example.

* Change shell to python.

* Add merge_aug_bboxes_3d unittest

* Add voxel_generator unittest

* Change test_merge_augs

* Add clean_data unittest

* Finish eval_class unittest

* Add kitti_eval unittest

* Add do_eval unittest

* Add gpu judgement for do_eval

* Change test_kitti_eval and test_voxel_generator

* Change to isclose

* Add unittests for bbox transform

* Add unittests for bbox transform

* Add unittests for bbox transform

* Add decode

* Add pred_split unittest

* Change allclose to eq

* update issue templates

Change mmdet to mmdet3d

* Update reimplementation_questions.md

Change mmdet to mmdet3d

* Install torch during packaging

* Test deploy

* Fall back to normal

* Finish test_inference

* Finish test_single_gpu_test

* inference supports cpu mode

* Change inference.py

* Add comments

* add test_getitem for kitti

* Change dataset to self

* Fix dbinfo path bug

* Change to 230

* Change bboxes and scores

* Debug, check points shape after dbsample

* Debug, add assert gt_bbox and db bbox

* Debug, add assert sampled and gt_bboxes

* Debug, add assertion for dbinfo and gt_box

* Fix transfom_3d unittest

* Fix kitti dataset unittest

* Add kitti data

* Clean debug

* Change data_augment_utils

* Reduce point file

* Change self to dataset

* Change data_augment_utils to normal

* Change order of CLASSES

* Finish test_random_flip_3d

* Add show unittest for scannet and sunrgbd datasets

* Add show unittest for kitti dataset

* Add test_evaluate for kitti dataset

* Add pytest.skip

* Add format_results unittest

* Add test_show for lyft

* Fix eval

* Add test_time_aug unittest

* Add bbox2result_kitti2d unittest

* Change abs to np.isclose

* add publish workflow

* Add manifest

* Clean files and bump to 0.5.0

* Fix MANIFEST

* Refactor readme

* Add links

* Fix link error

* add table caption

* Refine readme

* Add missing plus

* Be specific of comparison

* Support github action:

* fix docs package

* reduce action items

* Update cuda arch

* Set cuda arch

* Add information

* add cocotools in installation

* skip gpu

* remove duplicated module

* Change points shape from 1177 to 800

* Change 1177 to 800

* Change 1177 to 800

* Add print

* Add other print

* Change gt_labels

* Add seed

* Change to len assert

* Change gt_bboxes_3d

* Change repr
Co-authored-by: ZwwWayne <wayne.zw@outlook.com>
Co-authored-by: liyinhao <liyinhao@sensetime.com>

* update build configs

* Update model links

* Update doc

* Update install

* clean workflow

* Support github action:

* fix docs package

* reduce action items

* Update cuda arch

* Set cuda arch

* Add information

* add cocotools in installation

* skip gpu

* remove duplicated module

* Clean ci

* Update docstring requirements

* Refine docs and license

* Change order of install

* Clean unnecessary requirements

* Install mmdet manually in readthedocs

* delete mmdet install

* reformat docstring in code

* Refine docs

* Reformat

* fix format issue

* Update doc requirements

* Resolve API issue in readthedocs

* Fix package order

* Update requirements

* Update sphinx

* Add mock

* Fix setup missing

* Update docs

Switch ops from mmdet to mmcv

See merge request open-mmlab/mmdet.3d!151