GitLab

* support knn gpu op

* made it more robust and fixed comments

* bugfix and add warning in docstring

* support knn gpu op

* made it more robust and fixed comments

* add ini

* add semantickitti_dataset

* add test semantickitti_dataset

* delete last line in test_semmaticdataset

* add test data

* change_names

* load_labels dytype

* change_name

* numpy

* name

* dtype string

* minor issue-string

* seg_3d_dtype

* add_fast hist

* add per_class iou

* add seg_eval

* add unitest

* minor error

* minor error2

* minor error3

* Update README.md

* Update README_zh-CN.md

* Update getting_started.md

* Update version.py

* Update changelog.md

* Update changelog.md

* Update changelog.md

[Fix] fix a bug that may cause compilation failure of dynamic voxelization when using GPUs with compute capability lower than 6.x (#326)

* fix a bug that may cause compilation failure of dynamic voxelization when using gpus with compute capability lower than 6.x
fix imperfection kernel code that may unintentionally discard valid points when input points count is larger than 50000 * 512 (nearly impossible though).

* Modified scatter_points_cuda.cu to ensure backward compatibility with PyTorch1.5 on CUDA9.0

* fix the issue of DynamicScatter gradient check failure by explicit mark non-floating-point tensor as non-differentiable.

* fix nonzero warning with as_tuple

* fix nonzero warning with as_tuple #320

* Reduce the open3d dependency

* Reduce the open3d dependency

* Reduce dependency of open3d if open3d is not used

* remove the warning in show_result

* a faster & more memory-efficient implementation of DynamicScatter

* fix format issues and add pytest skip code for tests on machines without cuda support

* some trivial changes:

decrease the number of kernel threads per block to 512, to enable inference on GPUs with computing capability lower than 2.0

change the backpropagation behavior of max-reduction. when there are multiple points shares the same maximum feature value, only the first point (with lowest row index) among them is chosen to propagate the output gradient back. before this change, all points with the same maximum feature value can propagate the output gradient back. this change makes the max-reduction behaves in consistence with torch.max. this change may cause gradcheck failure in test_dynamic_scatter.py. please do not worry about it because torch.max fails the gradcheck too.

* fix typo
Co-authored-by: zhanggefan <1152009@tongji.edu.cn>

* add h3d backbone

* add h3d backbone

* add h3dnet

* modify scannet config

* fix bugs for proposal refine

* fix bugs for test backbone

* add primitive head test

* modify h3dhead

* modify h3d head

* update loss weight config

* fix bugs for h3d head loss

* modify h3d head get targets function

* update h3dnet base config

* modify weighted loss

* Revert "Merge branch 'h3d_u2' into 'master'"

This reverts merge request !5

* add open3d visual

* modify docstring

* use bbox and coord convert

* modify docstring

* fix bugs for unittest

* fix bugs for unittest

* modify doc

* add visualize script and modify docs

* modify docs

* fix bugs

* fix bug caused by mmcv upgrade; delete pdb breakpoint

* fix typos

* use torch.cuda api

* update unittest for points_in_bbox_gpu and points_in_boxes_batch

* Added comments for explanation

* Move train_cfg/test_cfg to model

* Move train_cfg/test_cfg to model

* Move train_cfg/test_cfg to model

* Move train_cfg/test_cfg to model

* Move train_cfg/test_cfg to model

* Move train_cfg/test_cfg to model

* Move train_cfg/test_cfg to model

* Move train_cfg and test_cfg into model

* modify centerpoint configs

* Modify docs

* modify build_detector

* modify test_config_build_detector

* modify build_detector parameters

* Adopt the same strategy in build_detector

* fix bug caused by mmcv upgrade; delete pdb breakpoint

* fix typos

* Update README.md

* Update getting_started.md

* Update version.py

* Update changelog.md

* Update numpy requirements

* Update runtime.txt

* Merge minor items

* Add support for SemanticKITTI dataset

* add ini

* add semantickitti_dataset

* add test semantickitti_dataset

* delete last line in test_semmaticdataset

* add test data

* change_names

* load_labels dytype

* change_name

* numpy

* name

* dtype string

* minor issue-string

* seg_3d_dtype

* fixed the bug about miss text files on kitti testing

* add bbox2result_kitti unit test

* add bbox2result_kitti unit test

* add exist_submission_file unit test

* deleted debug code and convert{} to dict()

* add _get_kitti_dataset_config()

* delete print

* Fix bug when num_features != 4

* add voxelization unittest

* fixed CI without GPU

* use the numpy version to test the CUDA version
Co-authored-by: Guanghui Ren(任广辉) <sundrops.ren@gmail.com>

The tuple unpacked into three arguments when four were given when
running VoteNet on sunrgbd

* add h3d backbone

* add h3d backbone

* add h3dnet

* modify scannet config

* fix bugs for proposal refine

* fix bugs for test backbone

* add primitive head test

* modify h3dhead

* modify h3d head

* update loss weight config

* fix bugs for h3d head loss

* modify h3d head get targets function

* update h3dnet base config

* modify weighted loss

* Revert "Merge branch 'h3d_u2' into 'master'"

This reverts merge request !5

* fix bugs for empty scene

* modify doc

* modify filter empty scene

* Update README.md

* Update version.py

* Update getting_started.md

* Update __init__.py

* Update changelog.md

* Update README.md

* Update news for nuScenes detection challenge

* Update README to be compatible with refactored doc

* Update an installation subtitle

* rephrase
Co-authored-by: ZwwWayne <wayne.zw@outlook.com>

* Fix an old bug in box_np_ops, not used or influencing results

* Update a minor filter criterion in KITTI evaluation

* Update the fixed criterion, not influencing KITTI results

* fix indoor_eval in case of less classes in prediction

* fix style for formatters

* Update mmdet maximum version

* Update install.md

* Fix bugs for the create_gt_database of kitti

* Fix bugs for '__get_item__' of BasePoints

* Update changelog for v0.8.0

* Update README.md

* Update version.py

* support axis-aligned iou loss for votenet

* added doc for iou loss

* fixed problems in format

* updated docstring

* rename and format fix

* rename and format fix

* rename and format fix

* rename and format fix

* modified config

* abstracted axis_aligned_iou3d

* abstracted a bbox corner decode func

* fix docstring

* add h3d backbone

* add h3d backbone

* add h3dnet

* modify scannet config

* fix bugs for proposal refine

* fix bugs for test backbone

* add primitive head test

* modify h3dhead

* modify h3d head

* update loss weight config

* fix bugs for h3d head loss

* modify h3d head get targets function

* update h3dnet base config

* modify weighted loss

* Revert "Merge branch 'h3d_u2' into 'master'"

This reverts merge request !5

* modify pipeline

* modify kitti pipeline

* fix bugs for points rotation

* modify multi sweeps

* modify multi sweep points

* fix bugs for points slicing

* modify BackgroundPointsFilter

* modify pipeline

* modify unittest

* modify unittest

* modify docstring

* modify config files

* update configs

* modify docstring

* add model stastics

* add model stastics and polish docs

* add model stastics and polish docs

* fix

* chmod +x stat.py

* add h3d backbone

* add h3d backbone

* add h3dnet

* modify scannet config

* fix bugs for proposal refine

* fix bugs for test backbone

* add primitive head test

* modify h3dhead

* modify h3d head

* update loss weight config

* fix bugs for h3d head loss

* modify h3d head get targets function

* update h3dnet base config

* modify weighted loss

* Revert "Merge branch 'h3d_u2' into 'master'"

This reverts merge request !5

* add points structure

* modify points rotation and add coord_3d_mode unittest

* modify docstring

* Update README.md

* Update __init__.py

* Update changelog.md

* Update changelog.md

* Fix a minor typo

* Fix minor typos

* Update changelog.md

* Able to double_flip test.

* Remove nms_post_max_size

* Able to merge then nms for tta.

* Able to merge then nms for tta.

* reproducible performance.

* Add more configs.

* Able to use scale tta.

* Move scale aug to merge_aug_bboxes_3d

* Remove brackets, add comments.

* Delete unnecessary configs, Add instruction in README.

* Add docstring.

* Change readme, add empty line.

* Change name.

* Add tta in unittest.

* Add 'to cpu'

* Add simple test

* Move 'to cpu'

* Add full tta config

* Delete circle_nms tta config, change max_num.

* Update benchmark

* Remove unnecessary code, move position of flip.

* Complete docstring.

* Add comment for double flip change.

* Add shape-aware grouping head

* Reformat docstrings

* Remove rewritten get_anchors in shape_aware_head

* Refactor and simplify shape-aware grouping head

* Fix docstring

* Remove fixed preset shape heads

* Add unittest for AlignedAnchor3DRangeGeneratorPerCls

* Add unittest for get bboxes in shape_aware_head

* Add unittest for loss of shape_aware_head

* Fix unstandard docstrings

* Minor fix for a comment

* Add assertion to make sure not all boxes are filtered

* modify primitive head

* modify primitive head

* rename upper and lower

* modify doc string

* Update v0.6.1 change log

* Update version.py

* Update init file to be compatible with mmdet

* Changelog refinement

* Sync modification in New Features

* Sync modification in Highlights

* Changelog refinement

* Update README.md for v0.6.1

* Update a newest [fix] PR

* Support to train using FP16

* fix type inconsistency error on naive syncBN

* resolve comments

* clean nan check