GitLab

* support 3dssd

* support one-stage method

* for lint

* support two_stage

* Support all methods

* remove init_cfg=[] in configs

* test

* support h3dnet

* fix lint error

* fix isort

* fix code style error

* fix imvotenet bug

* rename init_weight->init_weights

* clean comma

* fix test_apis does not init weights

* support newest mmdet and mmcv

* fix test_heads h3dnet bug

* rm *.swp

* remove the wrong code in build.yml

* fix ssn low map

* modify docs

* modified ssn init_config

* modify params in backbone pointnet2_sa_ssg

* add ssn direction init_cfg

* support segmentor

* add conv a=sqrt(5)

* Convmodule uses kaiming_init

* fix centerpointhead init bug

* add second conv2d init cfg

* add unittest to confirm the input is not be modified

* assert gt_bboxes_3d

* rm .swag

* modify docs mmdet version

* adopt fcosmono3d

* add fcos 3d original init method

* fix mmseg version

* add init cfg in fcos_mono3d.py

* merge newest master

* remove unused code

* modify focs config due to changes of resnet

* support imvoxelnet pointnet2

* modified the dependencies version

* support decode head

* fix inference bug

* modify the useless init_cfg

* fix multi_modality BC-breaking

* fix error blank

* modify docs error

* group-free-3d head

* GroupFree3DNet->VoteNet

* modify docstring

* bugfix: calculate pts_instance_label, decoder self/cross posembed init

* support GroupFree3DNet, modify scannnet train config

* support point cloud input features dim = 0

* add groupfree3dnet test case

* bugfix: softmax in decode boxes

* support multi-stage predictions

* modify GroupFree3DMultiheadAttention input parameters

* refactor: support sunrgbd-based train

* refactor: support sunrgbd-based train

* fix parts of bug

* modify multi-stage prediction

* fixbug: conv_channels

* bugfix: permute

* bugfix: permute

* bugfix: expand

* fix MAX_NUM_OBJ=64

* 4 gpu training, score_thr = 0.0

* modify config, repeattime=1

* bigfix: expand

* modify: GroupFree3DMHA, build_positional_encoding

* modify: GroupFree3DMHA, build_positional_encoding

* bugfix: torch.nn

* bugfix: mean loss

* residual -> identity

* fix name: DropOut -> Dropout

* delete sunrgbd-based congfig

* Fix: trailing whitespace

* suffix -> prefix

* bugfix: groupfree3d config
Co-authored-by: jinhui <PJLAB\jinhui@shai14001019l.pjlab.org>

* Create index.rst

* Create waymo_det.md

* Add waymo doc link

* Delete waymo.md

* Update index.rst

* Update index.rst

* add unittest to confirm the input is not be modified

* assert gt_bboxes_3d

* rm .swag

* modify np.allclose to np.equal

* fix error tap

* fix np.equal() error

* [Fix] Refine tutorials docs

* refine docs

* refine docs

* refactor K and Rt to depth2img for SUN RGB-D

* fix lint

* update 3 tests

* fix extra calib key and comments

* remove calib from browse_dataset

* fix cam to depth; rename return_z

* add seg tutorial

* specify sem seg

* fix typo

* ScanNet-doc: data prepare and train pipeline

* add metric of scannet

* Fix: data prepare link, summary sentence, 'inwhich'

* simplify code script

* simplify code script, add few comments

* Fix typos

* Update sample configs

* Fix typos

* Refine docs

* Add mmseg in the doc config files

* Remove mocked cv2

* Add opencv-python

* Remove mocked imports

* Add mminstall requirements

* Remove mocked imports correspondingly

* Fix mmdet versions

* Fix mmseg version

* Rename 0_demo.md to demo.md

* Move demo to Get Started

* Update Verification correspondingly

* remove mmseg max ver limit

* install mmdet 2.11.0

* mmseg < 0.14.1

* change mmseg to mmsegmentation

* fix mmseg to 0.14.0

* add readme for imvoxelnet

* Update download links in README

* Init with LiDAR-Based 3D Detection Tutorial

* Add supported tasks doc

* Create lidar_det3d.md

* Delete supported_tasks.md

* Create index.rst

* Update lidar_det3d.md

* first try of kitti

* fix python3

* imvoxelnet is ready for open-mmlab/mmdetection3d

* apply pre-commit

* update to ConvModule and AlignedAnchor3DGenerator

* add unit tests

* fix torch.Tensor in docstrings

* revert anchor ranges

* refactor PN SA module code

* refactor PAConv op & add PAConvSAModule

* add unit test

* add PAConvCUDA SA module

* add unit test

* minor fix

* merge master

* move paconv sa modules to a new file

* rename to BasePointSAModule

* rename to PAConvCUDASAModule

* delete typing comment

* refine docs

* rename mlp_spec to mlp_channel

* fix typos in comment

* Add reference in`sample_valid_seeds` function used by ImVoteNet

* add r to docstring

* Fixed wrong config paths and fixed a bug in test

* Fixed metafile

* enhance IndoorPatchPointSample

* modify configs and unit test

* add docs & comment

* fix legacy bug

* minor fix

* keep sample_rate and add warning

* fix when killing before eval

* fix resume log

* add chinese doc

* update

* support knn query in QueryAndGroup

* add cuda implemented assign_scores op

* add unit test for paconv assign_score op

* refactor op

* add non-cuda & cuda version PAConv

* minor fix

* fix cuda-9.0 compatibility

* add weight init of paconv

* fix typos

* refactor paconv

* fix bg_points_filter

* fix 3dssd bg_point_filter bug

* fix bg_filter bug in 3dssd

* update performance

* add model download link

* unit test for LoadImageFromFileMono3D

* fix GlobalRotScaleTrans assertion

* add unit test for ObjectNameFilter

* add unit test for ObjectRangeFilter

* Bump to v0.14.0

* remove the parameter label_weight

* remove useless label_weight args in dataset class

* modify unit tests

* update compatibility docs

* move _get_data to utils

* add comment

* add RandomJitterPoints transform

* add unit test

* add comments

* minor fix

* add tools/dist_train.sh exec permission

* add tools/create_data.sh exec permission

* [Fix] Supplying the model for lyft trained by regnet

* updating readme in regnet

* add knn_heap gpu op support

* add unit test

* remove old knn & rename knn_heap to knn

* interface consistency