GitLab

* add lidar_seg_inferencer

* fix random caused in slide_infernce

* Update semantickitti.py

* fix

* add BaseSeg3DInferencer

* refactor

* rename BaseDet3DInferencer to Base3DInferencer

* fix import error

* update doc

* fix polarmix UT

* format

* rename SemanticKittiDataset

* add platte & fix data info bug

* fix ut

* fix semantic_kitti ut

* fix ut label_map

* fix ut label_map

* add indication

* add indication

* fix typo

* fix polarmix UT

* add torchsparse block

* fix pytest skip

* add installtion in get_started

* fix name

* fix UT bug

* update doc string

* add omit sudo install

* refactor leio

* update mmengine and mmcv version

* update

* update docs

* update version

* update type alias

* fix UT

* add cylinder decode head

* update

* update

* add lovasz loss

* update

* update

* update

* update

* update

* update

* update

* update

* update

* cylinder3d_head

* update

* update

* update

* update

* fix polarmix UT

* fix bug

* fix img list

* fix polarmix UT

* add location

* fix base_inferencer scope

* fix fail import

* add lasermix

* add prob

* update description

* update

* fix polarmix UT

* add location

* fix base_inferencer scope

* fix_voxel

* update

* support polarmix

* Update __init__.py

* add UT

* use `BasePoints` instead of numpy

* Update transforms_3d.py

* Update transforms_3d.py

* Update test_transforms_3d.py

* update docs

* update polarmix without MultiImageMixDataset

* add comments

* fix UT

* update docstring

* fix yaw calculation

* fix UT

* refactor

* update

* update docs

* fix typo

* Update transforms_3d.py

* update ut

* fix typehint

* add prob argument

* add cylindrical voxelization & voxel feature encoder

* add cylindrical voxelization & voxel feature encoder

* add voxel-wise label & voxelization UT

* fix vfe

* fix vfe UT

* rename voxel encoder & add more test case

* fix type hint

* temporarily refactoring mmcv's voxelize and dynamic in mmdet3d for data_preprocesser

* fix vfe init bug & fix UT

* add grid_size & move voxelization code

* fix import bug

* keep radian to follow origin

* add doc string

* fix type hint

* rename gird shape & add comments

* fix UT

* rename voxelizationofGridshape & fix docstring

* change np.transpose to torch.permute

* add comments

* docstrings and .md fixes

* add minkresnet to readme

* fix cross in zh readme

* fix lint

* fix some vis bug and update doc

* add typehint and fix bug

* Update local_visualizer.py

* update doc

* update docs

* fix doc

* update docs and fix some vis bug

* update

* update docs

* add panoptic loading

* update

* update

* update

* add semantic config

* fix tets

* fix test

* update

* get seg label mapping

* panoptic segmentation metric

* fix

* update

* update

* fix

* fix

* fix

* fix

* rename

* merge

* merge

* fix test

* update

* update

* update

* refactor cbgs

* update cbgs

* add UT

* remove useless line

* Update test_dataset_wrappers.py

* update typehint

* update docs

* Update dataset_wrappers.py

* update

* fix local_visualizer.py: modify add_datasample

 - fix "AttributeError: ‘InstanceData’ object has no attribute ‘bboxes_3d’" error

* Update mmdet3d/visualization/local_visualizer.py
Co-authored-by: Xiang Xu <xuxiang0103@gmail.com>

* fix local_visualizer.py: modify add_datasample

 - add exception handling when there is no instance inside pred_instances_3d

* modify local_visualizer.py: Apply changes from pre-commit

* modify local_visualizer.py: Change exception handling location for empty instance

 - Add exception handling when instances are empty
 - Delete the exception handling previously added to add_datasample

* modify local_visualizer.py: apply pre-commit

---------
Co-authored-by: Xiang Xu <xuxiang0103@gmail.com>

* refactor segmentor

* replace meta info during inference

* Update decode_head.py

* update

* update docs

* Add typehints for models/losses

* Add typehints for models/losses

* Add typehints for models/losses

* Add typehints for models/losses

* support lidar det3d inferencer

* lidar inference normally

* add ut

* add ut

* polish docstring

* resolve comments

* add inferencer registry

* fix ut

* fix docstring

* resolve some comments

* rename varible

* update pointsdata and det3ddatasample

* update eval_ann_info when it is None

* update unittest

* revert

* delete `eval_ann_info`

* remove unittest

* update doc

* Update point_data.py

* Update det3d_data_sample.py

* remove

* update docs

* fix unittest

* update

* Update instance_seg_metric.py

* fix lint

* add mono3d inferencer

* update mono3d inferenceer

* update init file

* update unit test

* fix name

* add base_det3d_inferencer

* fix comments

* fix comments

* fix comments

* renmae pgd-kitti to pgd_kitti

* add parameterized in tests.txt

* add txt file

* update loadimgfromfilemono3d to fit latest mmcv

* add bevfusion models

* refactor

* build successfully

* update ImageAug3D

* support inference

* update the format of final bboxes

* add new loading func

* align test precision

* polish docstring

* refactor transformer decoder

* polish code

* fix table in readme

* fix table in readme

* fix table in readme

* update pre-commit-config

* minor changes

* revert the changes of file_client_args in LoadAnnotation3D

* remove unnucessary functions in BEVFusion

* fix loading bug

* fix docstring

* fix seg_eval

* add test for the bug

* update

* update

* update

* support submit test set on nuscenes and waymo dataset

* Fix typo

* Add typehint for models/utils and others

* fix line too long

* fix format error by pre-commit

* fix format error by pre-commit

* update with review suggestions

* update changelog

* remove links of qq and zhihu

* Support imvoxelnet@sunrgbd on 1.x branch

* Add unit tests

* Update README.md

* Update imvoxelnet_2xb4_sunrgbd-3d-10class.py

* Add typehints

* Fix lint

* Fix BC-breaking caused by updated keys

* Add coord_type in the imvoxelnet kitti config

* init centerformer in projects

* add readme and disable_tf32_switch

* using our iou3d and nms3d, using basicblock in mmdet, simplify code in projects

* remove attention.py and sparse_block.py

* only using single fold

* polish code

* polish code and add dosstring

* add ut for disable_object_sample_hook

* modify data_root

* add ut

* update readme

* polish code

* fix docstring

* resolve comments

* modify project names

* modify project names and add _forward

* fix docstring

* remove disable_tf32

* fix circle ci

* delete model builder

* fix comments