GitLab

* Support to train using FP16

* fix type inconsistency error on naive syncBN

* resolve comments

* clean nan check

* support docker

* update installation"

* update mmcv version

* update doc and resolve comment

* Add overall evaluation

* Add config waymo-3d-car.py

* Update README.md

* Create hv_pointpillars_secfpn_sbn_2x16_2x_waymo-3d-3class.py

* Create hv_pointpillars_secfpn_sbn_2x16_2x_waymo-3d-car.py

* Delete waymo-3d-car.py

Instead of using new dataset config, we change the load_interval in the config for specific usage.

* update url links
Co-authored-by: Tai-Wang <tab_wang@outlook.com>
Co-authored-by: twang <30491025+Tai-Wang@users.noreply.github.com>

* add sweep points sampler

* add sweep points sampler

* rebase master

* modify unittest

* modify voxel based point sampler

* modify voxel based point sampler

* fix bugs for voxel based point sampler

* modify voxel based points sampler

* fix bugs

* modify repr string

* fix dcn bias bug in centerpoint

* fix unit tesats bug of empty iou calculation

* Add evaluation interval for centerpoint.

* Add centerpoint unittest.

* Add test unittest for centerpoint

* Add version assert in init file.

* Fix bug in test_dcn_head.

* Reduce requirements if waymo dataset is not used

* Update waymo.md

* Update optional.txt

* Update waymo.md

Add instructions of requirements/optional.txt related to waymo

* Update links in model zoo

* Update links of mmcv

* fall back mmcv url

* Update docs and add hints for waymo

* Change the title of waymo tutorial

* Move waymo into the tutorial part

* Delete original waymo.md

* Update waymo.md

* Update index.rst

* Update get_started in readme.md

* reorganize docs
Co-authored-by: zhangwenwei <wayne.zw@outlook.com>

* Add version assert in init file.

* update mmcv requirement
Co-authored-by: zhangwenwei <wayne.zw@outlook.com>

* 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>

* [Fix]: fix label type bug when using dbsampler

* Unify cat_id for more general usage

* fix CI bugs

* keep astype np.long

* Add pointpillar configs.

* Add 0075 voxel configs.

* Add configs, change to pipeline.

* Add centerpoint.

* Add 01 configs.

* Change sparse shape

* Change model config, change centerpoint detector to inherite from mvx two stage.

* Change names of configs.

* Reduce configs.

* Fix pillar config can't use bug.

* Add readme for centerpoint.

* Streamline the code in configs.

* Change readme, add nus-3d in base config

* Use seperate_head config to build seperate head, remove '[0]' in simple_test_pts

* Remove input_modality

* Change coder weights for configs.

* Change 0075 config, change order of modules in config.

* Change loss_bbox config, remove unnecessary things.

* Add cyclic_20e.py

* Rename centerhead, move centerhead,

* Change cyclic_20e

* 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

[refactor]: migrate to use collect_env in mmcv

* 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 readme.md

* modify readme.md

* Update README.md

* Add experiment details

* Update README

* update readme

* reformat

* Update information in model zoo
Co-authored-by: zhangwenwei <wayne.zw@outlook.com>

* 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 depth box3d

* fix bugs of test box3d

* 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 3dssd config

* add ssd3dhead

* fix bugs for anchorfreebboxcoder

* modify ssd 3d head

* modify ssd 3d head

* reconstruct ssd3dhead and votehead

* add unittest

* modify 3dssd config

* modify 3dssd head

* modify 3dssd head

* rename base conv bbox head

* modify vote module

* modify 3dssd config

* fix bugs for unittest

* modify test_heads.py

* fix bugs for h3d bbox head

* add 3dssd detector

* fix bugs for 3dssd config

* modify base conv bbox head

* modify base conv bbox head

* modify base conv bbox head

* add dilated ball query

* fix bugs for group points

* rename max radius

* update bbox_results to support multi-batches test and fix ci problem in test_part_aggregation_ROI_head

* compress test samples in test_parta2_roi_head

* compress test samples

* fix multi-batch bug

* fix multi-batch bug

* fix multi-batch bug

* fix mvxnet test

* fix mvxnet test

* multi batch test

* multi batch test

* multi batch test

* Change gt_database and dbsampler.

* Add int condition for use_dim.

* Change default sweep_num.

* Change docstring.

* Change to pipeline in db_sampler.

* remove comments.