GitLab

* build BaseSegmentor for point sem seg

* add encoder-decoder segmentor

* update mmseg dependency

* fix linting errors

* warp predicted seg_mask in dict

* add unit test

* use build_model to wrap detector and segmentor

* fix compatibility with mmseg

* faster sliding inference

* merge master

* configs for training on ScanNet

* fix CI errors

* add comments & fix typos

* hard-code class_weight into configs

* fix logger bugs

* update segmentor unit test

* logger use mmdet3d

* use eps to replace hard-coded 1e-3

* add comments

* replace np operation with torch code

* add comments for class_weight

* add comment for BaseSegmentor.simple_test

* rewrite EncoderDecoder3D to avoid inheriting from mmseg

* remove registry.py in datasets/

* remove registry.py in ops/pointnet_modules/

* remove registry.py in models/

* refactor builder using mmcv.MODELS registry

* update mmcv min version requirement

* change min mmcv version requirement in mmdet3d/__init__.py

* min mmcv version to 1.3.2

- fix 'invalid configuration argument' error triggered by empty point input. test cases covering similar situations are added to test_dynamic_scatter.py as well.
trivial changes:
- switch to using torch::unique_dim to generate reduce mapping instead of calculating it from scratch.

* fix pt1.8 issues

* fix pt1.8 issues

* fix compilation error in pytorch 1.7

* add pt1.7 build

* Update build.yml

* Avoid 4 dims points

* add assert prinf

* modify print info

* 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

[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.

* 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>

* 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

* 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 model stastics

* add model stastics and polish docs

* add model stastics and polish docs

* fix

* chmod +x stat.py

* Support to train using FP16

* fix type inconsistency error on naive syncBN

* resolve comments

* clean nan check

* Add gitlab CI back

* clean isort

* Update gitlab CI version

* Update mmcv install

* fix unit test bug

* waymo

* Use new flake8

* Update mmdet3d/core/evaluation/waymo_utils/prediction_kitti_to_waymo.py, tools/data_converter/waymo_converter.py files

* Add baseline configs for waymo

* fix linting

* yapf reformat

* update waymo results

* Update waymo model zoo and docs

* Bump v0.6.0

* Fix a minor bug when converting waymo data

* Fix cmds in the waymo doc

* Fix setup.cfg to pass isort test

* Fix waymo configs

* Update model zoo link & doc

* update version date

* clean ci
Co-authored-by: wangtai <wangtai@sensetime.com>
Co-authored-by: Tai-Wang <tab_wang@outlook.com>

* Add modules.

* Add test_center_head.

* Add docstring.

* Change comments.

* Add dcn_head.

* Add doc_string.

* Add get_targets.

* Can use_get_targets.

* get_targets results aligned.

* Use box_structure.

* Use get_targets_single.

* Add docstring.

* Fix dcn_center_head unittest.

* Delete unnecessary unittest.

* Add docstring.

* Change format.

* Add circle_nms.

* Change structure of mg_head.

* Add bbox coder for centerpoint.

* Add docstrings.

* Add docstrings.

* Add get_bboxes and unittest.

* Change docstring.

* Add img_metas.

* Change bbox coder unittest.

* Add task_detections.

* Change docstring.

* Change circle_nms to cpu.

* Change test_nms.

* Change score_th, chang keep to long type.

* Change docstring and unittest.

* Remove unnecessary things.

* Move gaussian.

* move clip_sigmoid, change dict.

* Change config.

* Change test_heads.

* Move weight initialization to init_weights func.

* Remove loc_loss_element adn==nd num_postive.

* Change bboxes to the right format.

* Change loss and bbox order.

* Update test_heads.

* Change loss.

* Change names in mg_head, change head unittest.

* Remove centerpoint_focal_loss, change docstring.

* Change topK default to 80.

* Change boxes in test_nms. Change task_boxes defaults to None.

* Fix rotate nms bug.

* Change docstring.

* Add docstring for get_task_detection and loss.

* Remove gaussian funcs, change mg_head.

* Change gaussianfocalloss to mean.

* change centerpoint_bbox_coder '/' to torch.div, fix centerhead unittest.

* Change div to '/'

* Change order in centerpoint_coder, change names, change dcn layer.

* Fix import in __init__

* Add gaussian unittest.

* Remove np ops in mg_head.

* Update docstring.

* Fix docstring use config to build head.

* Remove **kwargs

* Remove unnecessary codes, change order of bboxes.

* Remove '\' in args and pdb, change loss_bbox.

* Fix test_heads unittest.

* Remove unnecessary comments

* Change bbox order in rotate nms.

* Remove unnecessary attributes

* Change name, remove float

* add dilated ball query

* fix bugs for group points

* rename max radius

* 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>

* 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

* 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 publish workflow

* Add manifest

* Clean files and bump to 0.5.0

* Fix MANIFEST