GitLab

* enhance minkunet

* add 2x

* add config

* add flip...

* add bottleneck

* add spvcnn & cylinder3d

* add spvcnn & cylinder3d

* refactor minkunet & spvcnn

* add minkv2

* fix mink34 shared res block

* add mink spconv

* fix spconv int32 max bug

* fix spconv int32 max bug2

* add minkowski backends

* rename config

* fix minkv2 config

* fix max voxel bug

* add checkpointhook mink18

* add backbone docstring

* fix torchsparse uninstall bug

* remove ME

* fix ut

* fix cylinder3d config

* add minkowski block

* fix minkowski residual block

* rename ut

* fix test case

* add doc string

* fix __init__

* enhance

* enhance

* fix __init__

* fix minku backbone

* fix p2v_map when no gt & unit name

* fix gt bug

* fix max_voxels

* add typehint

* fix UT

* update docs

* support TTA for segmentor

* fix UT

* fix UT

* support scale and rotate tta

* update with comments

* add multimodality inferencer

* add multimodality inferencer

* add Loader and Inferencer, fix some mono vis bugs

* add UT for multi_modality_inferencer

* add calib file in UT

* fix type hint

* resolve comments

* small update

* update to Base3DInferencer

* fix docstring

* minor fix

* resolve comments

* resolve comments

* add suffix check

* fix UT

* 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

* _forward

* del checkpoints

* add if tp

* add predict

* 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

* add minkunet voxelization and loss function

* fix data

* init train

* fix sparsetensor typehint

* rename dir

* fix data config

* fix data config

* fix batch_size & replace dynamic_scatter

* fix conflicts 2

* fix conflicts on s_70

* Alignment of the original implementation

* rename config

* add worker_init_fn_hook

* remove test_config & worker hook

* add UT

* fix polarmix UT

* init spcvnn backbone

* add seed for cr0p5

* spvcnn_init

* format

* rename SemanticKittiDataset

* add platte & fix visual bug

* add platte & fix data info bug

* fix ut

* fix ut

* fix semantic_kitti ut

* train init

* fix docstring

* fix config name

* rename layer

* fix doc string

* fix review

* remove filter data

* rename config

* rename backbone

* rename backbone 2

* refactor voxel2point

* fix coors typo

* fix ut

* fix ut

* pred in segmentor

* fix get voxel seg

* resolve comments

* rename p2v and v2p

* rename points and voxels

* mv cylinder blocks from sparse blocks to backbone

* update

* 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

* _forward

* del checkpoints

* add if tp

* add predict

* 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

* add minkunet voxelization and loss function

* fix data

* init train

* fix sparsetensor typehint

* rename dir

* fix data config

* fix data config

* fix batch_size & replace dynamic_scatter

* fix conflicts 2

* fix conflicts on s_70

* Alignment of the original implementation

* rename config

* add worker_init_fn_hook

* remove test_config & worker hook

* add UT

* fix polarmix UT

* add seed for cr0p5

* format

* rename SemanticKittiDataset

* add platte & fix visual bug

* add platte & fix data info bug

* fix ut

* fix semantic_kitti ut

* fix docstring

* fix config name

* rename layer

* fix doc string

* fix review

* remove filter data

* fix coors typo

* fix ut

* pred in segmentor

* fix get voxel seg

* resolve comments

* update

* add cylinder3d_backbone

* add test segmentor

* add cfg

* add test backbone

* rename test cylinder3d backbone

* midway

* update, pass validation

* fix test

* update cfg

* 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

* add lasermix

* add prob

* update description

* 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

* 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 seg_eval

* add test for the bug

* update

* update

* update

* fix test bug

* 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

* fix seg_eval

* add test for the bug

* update

* update

* update

* 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

* fix a bug

* fix a batch inference bug

* fix docs

* add pvrcnn benchmark

* fix

* add link

* add

* fix lint

* update centerpoint, dgcnn, fcos3d and free_anchor metafile

* check all metafile in configs

* update centerpoint, pointpillars and second yml

* rename PartA2 to parta2 in the name of config

* update metafile in nuimages

* update readme in nuimages

* update github action ci

* install torch in ci

* fix ci on win

* add __init__ in tests/utils

* add mmdet3d/testing for modeule importing in UT in win

* fix diff path sep on UT

* reduce RAM in voxel_generator

* reduce RAM in anchor_generator

* remove print in UT

* fix lint

* fix pvrcnn ut

* fix lint

* reduce channels in second_fpn

* support fcaf3d for s3dis dataset

* Update convert_utils.py

* Update seg3d_dataset.py

* Delete compose.py

* fix import error

* use `mmengine.Compose`

* Update s3dis-3d.py

* Update fcaf3d_2xb8_s3dis-3d-5class.py

* Update s3dis_dataset.py

* update unittest for s3dis

* update docs

* use `mmcv.Compose` instead of `mmengine.Compose`

* update docstring

* fix s3dis preprocessing bug

* Add typehint

* Update config and fix s3dis dataset

* update typehit

* Update convert_utils.py

* Update README and metafile
Co-authored-by: Tai-Wang <tab_wang@outlook.com>

fix __all__ keyword

* add pvrcnn module code

* add voxelsa

* fix

* fix comments

* fix comments

* fix comments

* add stack sa

* fix

* fix comments

* fix comments

* fix

* add ut

* fix comments