GitLab

Fix potential undefined variables in PGD when computing loss for cases with none positive predictions (#1157)

* rebase & resubmit

* rename config & model

* fix unittest

* resolve comments & add docstring for class_agnostic_nms

* refine loss calculation & remove find_unused_parameters

* resolve typo & add docstring

* resolve comments

* Support PGD nuscenes benchmark

* Update nuScenes benchmark

* Update metafile.yml

* Update model_zoo.md

* Update model_zoo.md

* Add 2x schedule configs

* Update 2x schedule config links

* Update 2x schedule meta infos

* fix collect3d meta keys

* support inference smoke on nuscenes and fix some bugs

* fix some bugs

* [Refactor] Main code modification for coordinate system refactor (#677)

* [Enhance] Add script for data update (#774)

* Fixed wrong config paths and fixed a bug in test

* Fixed metafile

* Coord sys refactor (main code)

* Update test_waymo_dataset.py

* Manually resolve conflict

* Removed unused lines and fixed imports

* remove coord2box and box2coord

* update dir_limit_offset

* Some minor improvements

* Removed some \s in comments

* Revert a change

* Change Box3DMode to Coord3DMode where points are converted

* Fix points_in_bbox function

* Fix Imvoxelnet config

* Revert adding a line

* Fix rotation bug when batch size is 0

* Keep sign of dir_scores as before

* Fix several comments

* Add a comment

* Fix docstring

* Add data update scripts

* Fix comments

* fix import (#839)

* [Enhance]  refactor  iou_neg_piecewise_sampler.py (#842)

* [Refactor] Main code modification for coordinate system refactor (#677)

* [Enhance] Add script for data update (#774)

* Fixed wrong config paths and fixed a bug in test

* Fixed metafile

* Coord sys refactor (main code)

* Update test_waymo_dataset.py

* Manually resolve conflict

* Removed unused lines and fixed imports

* remove coord2box and box2coord

* update dir_limit_offset

* Some minor improvements

* Removed some \s in comments

* Revert a change

* Change Box3DMode to Coord3DMode where points are converted

* Fix points_in_bbox function

* Fix Imvoxelnet config

* Revert adding a line

* Fix rotation bug when batch size is 0

* Keep sign of dir_scores as before

* Fix several comments

* Add a comment

* Fix docstring

* Add data update scripts

* Fix comments

* fix import

* refactor iou_neg_piecewise_sampler.py

* add docstring

* modify docstring
Co-authored-by: Yezhen Cong <52420115+THU17cyz@users.noreply.github.com>
Co-authored-by: THU17cyz <congyezhen71@hotmail.com>

* [Feature] Add roipooling cuda ops (#843)

* [Refactor] Main code modification for coordinate system refactor (#677)

* [Enhance] Add script for data update (#774)

* Fixed wrong config paths and fixed a bug in test

* Fixed metafile

* Coord sys refactor (main code)

* Update test_waymo_dataset.py

* Manually resolve conflict

* Removed unused lines and fixed imports

* remove coord2box and box2coord

* update dir_limit_offset

* Some minor improvements

* Removed some \s in comments

* Revert a change

* Change Box3DMode to Coord3DMode where points are converted

* Fix points_in_bbox function

* Fix Imvoxelnet config

* Revert adding a line

* Fix rotation bug when batch size is 0

* Keep sign of dir_scores as before

* Fix several comments

* Add a comment

* Fix docstring

* Add data update scripts

* Fix comments

* fix import

* add roipooling cuda ops

* add roi extractor

* add test_roi_extractor unittest

* Modify setup.py to install roipooling ops

* modify docstring

* remove enlarge bbox in roipoint pooling

* add_roipooling_ops

* modify docstring
Co-authored-by: Yezhen Cong <52420115+THU17cyz@users.noreply.github.com>
Co-authored-by: THU17cyz <congyezhen71@hotmail.com>

* [Refactor] Refactor code structure and docstrings (#803)

* refactor points_in_boxes

* Merge same functions of three boxes

* More docstring fixes and unify x/y/z size

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Remove None in function param type

* Fix unittest

* Add comments for NMS functions

* Merge methods of Points

* Add unittest

* Add optional and default value

* Fix box conversion and add unittest

* Fix comments

* Add unit test

* Indent

* Fix CI

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Add unit test for box bev

* More unit tests and refine docstrings in box_np_ops

* Fix comment

* Add deprecation warning

* [Feature] PointXYZWHLRBBoxCoder (#856)

* support PointBasedBoxCoder

* fix unittest bug

* support unittest in gpu

* support unittest in gpu

* modified docstring

* add args

* add args

* [Enhance] Change Groupfree3D config (#855)

* All mods

* PointSample

* PointSample

* [Doc] Add tutorials/data_pipeline Chinese version (#827)

* [Doc] Add tutorials/data_pipeline Chinese version

* refine doc

* Use the absolute link

* Use the absolute link
Co-authored-by: Tai-Wang <tab_wang@outlook.com>

* [Doc] Add Chinese doc for `scannet_det.md` (#836)

* Part

* Complete

* Fix comments

* Fix comments

* [Doc] Add Chinese doc for `waymo_det.md` (#859)

* Add complete translation

* Refinements

* Fix comments

* Fix a minor typo
Co-authored-by: Tai-Wang <tab_wang@outlook.com>

* Remove 2D annotations on Lyft (#867)

* Add header for files (#869)

* Add header for files

* Add header for files

* Add header for files

* Add header for files

* [fix] fix typos (#872)

* Fix 3 unworking configs (#882)

* [Fix] Fix `index.rst` for Chinese docs (#873)

* Fix index.rst for zh docs

* Change switch language

* [Fix] Centerpoint head nested list transpose  (#879)

* FIX Transpose nested lists without Numpy

* Removed unused Numpy import

* [Enhance] Update PointFusion (#791)

* update point fusion

* remove LIDAR hardcode

* move get_proj_mat_by_coord_type to utils

* fix lint

* remove todo

* fix lint

* [Doc] Add nuscenes_det.md Chinese version (#854)

* add nus chinese doc

* add nuScenes Chinese doc

* fix typo

* fix typo

* fix typo

* fix typo

* fix typo

* [Fix] Fix RegNet pretrained weight loading (#889)

* Fix regnet pretrained weight loading

* Remove unused file

* Fix centerpoint tta (#892)

* [Enhance] Add benchmark regression script (#808)

* Initial commit

* [Feature] Support DGCNN (v1.0.0.dev0) (#896)

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* fix typo

* fix typo

* fix typo

* del gf&fa registry (wo reuse pointnet module)

* fix typo

* add benchmark and add copyright header (for DGCNN only)

* fix typo

* fix typo

* fix typo

* fix typo

* fix typo

* support dgcnn

* Change cam rot_3d_in_axis (#906)

* [Doc] Add coord sys tutorial pic and change links to dev branch (#912)

* Modify link branch and add pic

* Fix pic

* [Feature] add kitti AP40 evaluation metric (v1.0.0.dev0) (#927)

* Add citation (#901)

* [Feature] Add python3.9 in CI (#900)

* Add python3.0 in CI

* Add python3.0 in CI

* Bump to v0.17.0 (#898)

* Update README.md

* Update README_zh-CN.md

* Update version.py

* Update getting_started.md

* Update getting_started.md

* Update changelog.md

* Remove "recent" in the news

* Remove "recent" in the news

* Fix comments

* [Docs] Fix the version of sphinx (#902)

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* add AP40

* add unitest

* add unitest

* seperate AP11 and AP40

* fix some typos
Co-authored-by: dingchang <hudingchang.vendor@sensetime.com>
Co-authored-by: Tai-Wang <tab_wang@outlook.com>

* [Feature] add smoke backbone neck (#939)

* add smoke detecotor and it's backbone and neck

* typo fix

* fix typo

* add docstring

* fix typo

* fix comments

* fix comments

* fix comments

* fix typo

* fix typo

* fix

* fix typo

* fix docstring

* refine feature

* fix typo

* use Basemodule in Neck

* [Refactor] Refactor the transformation from image to camera coordinates (#938)

* Refactor points_img2cam

* Refine docstring

* Support array converter and add unit tests

* [Feature] FCOS3D BBox Coder (#940)

* FCOS3D BBox Coder

* Add unit tests

* Change the value from long to float/double

* Rename bbox_out as bbox

* Add comments to forward returns

* Support PGD BBox Coder

* Refine docstring

* Add uncertain l1 loss and its unit tests

* [Feature] PGD BBox Coder (#948)

* Support PGD BBox Coder

* Refine docstring

* PGD Head initialized

* Refactor init methods, fix legacy variable names

* [Feature] Support Uncertain L1 Loss (#950)

* Add uncertain l1 loss and its unit tests

* Remove mmcv.jit and refine docstrings

* [Fix] Fix visualization in KITTI dataset (#956)

* fix bug to support kitti vis

* fix

* Refine variable names and docstrings

* Add unit tests and fix some minor bugs

* Refine assertion messages

* Fix typo in the docs_zh-CN

* Use Pretrain init and remove unused init_cfg in FCOS3D

* Fix the comments for the input_modality in the dataset config

* Fix minor bugs in pgd_bbox_coder and incorrect setting for uncertain loss, use original init

* Add explanations for code_weights

* Adjust the unit test for pgd bbox coder

* Remove unused codes

* Add mono3d metric into the gather_models and fix bugs

* Involve the value assignment of loss_dict into the computing procedure

* Fix incorrect loss_depth
Co-authored-by: Yezhen Cong <52420115+THU17cyz@users.noreply.github.com>
Co-authored-by: Xi Liu <75658786+xiliu8006@users.noreply.github.com>
Co-authored-by: THU17cyz <congyezhen71@hotmail.com>
Co-authored-by: Wenhao Wu <79644370+wHao-Wu@users.noreply.github.com>
Co-authored-by: dingchang <hudingchang.vendor@sensetime.com>
Co-authored-by: 谢恩泽 <Johnny_ez@163.com>
Co-authored-by: Robin Karlsson <34254153+robin-karlsson0@users.noreply.github.com>
Co-authored-by: Danila Rukhovich <danrukh@gmail.com>
Co-authored-by: ChaimZhu <zhuchenming@pjlab.org.cn>

* [Refactor] Main code modification for coordinate system refactor (#677)

* [Enhance] Add script for data update (#774)

* Fixed wrong config paths and fixed a bug in test

* Fixed metafile

* Coord sys refactor (main code)

* Update test_waymo_dataset.py

* Manually resolve conflict

* Removed unused lines and fixed imports

* remove coord2box and box2coord

* update dir_limit_offset

* Some minor improvements

* Removed some \s in comments

* Revert a change

* Change Box3DMode to Coord3DMode where points are converted

* Fix points_in_bbox function

* Fix Imvoxelnet config

* Revert adding a line

* Fix rotation bug when batch size is 0

* Keep sign of dir_scores as before

* Fix several comments

* Add a comment

* Fix docstring

* Add data update scripts

* Fix comments

* fix import (#839)

* [Enhance]  refactor  iou_neg_piecewise_sampler.py (#842)

* [Refactor] Main code modification for coordinate system refactor (#677)

* [Enhance] Add script for data update (#774)

* Fixed wrong config paths and fixed a bug in test

* Fixed metafile

* Coord sys refactor (main code)

* Update test_waymo_dataset.py

* Manually resolve conflict

* Removed unused lines and fixed imports

* remove coord2box and box2coord

* update dir_limit_offset

* Some minor improvements

* Removed some \s in comments

* Revert a change

* Change Box3DMode to Coord3DMode where points are converted

* Fix points_in_bbox function

* Fix Imvoxelnet config

* Revert adding a line

* Fix rotation bug when batch size is 0

* Keep sign of dir_scores as before

* Fix several comments

* Add a comment

* Fix docstring

* Add data update scripts

* Fix comments

* fix import

* refactor iou_neg_piecewise_sampler.py

* add docstring

* modify docstring
Co-authored-by: Yezhen Cong <52420115+THU17cyz@users.noreply.github.com>
Co-authored-by: THU17cyz <congyezhen71@hotmail.com>

* [Feature] Add roipooling cuda ops (#843)

* [Refactor] Main code modification for coordinate system refactor (#677)

* [Enhance] Add script for data update (#774)

* Fixed wrong config paths and fixed a bug in test

* Fixed metafile

* Coord sys refactor (main code)

* Update test_waymo_dataset.py

* Manually resolve conflict

* Removed unused lines and fixed imports

* remove coord2box and box2coord

* update dir_limit_offset

* Some minor improvements

* Removed some \s in comments

* Revert a change

* Change Box3DMode to Coord3DMode where points are converted

* Fix points_in_bbox function

* Fix Imvoxelnet config

* Revert adding a line

* Fix rotation bug when batch size is 0

* Keep sign of dir_scores as before

* Fix several comments

* Add a comment

* Fix docstring

* Add data update scripts

* Fix comments

* fix import

* add roipooling cuda ops

* add roi extractor

* add test_roi_extractor unittest

* Modify setup.py to install roipooling ops

* modify docstring

* remove enlarge bbox in roipoint pooling

* add_roipooling_ops

* modify docstring
Co-authored-by: Yezhen Cong <52420115+THU17cyz@users.noreply.github.com>
Co-authored-by: THU17cyz <congyezhen71@hotmail.com>

* [Refactor] Refactor code structure and docstrings (#803)

* refactor points_in_boxes

* Merge same functions of three boxes

* More docstring fixes and unify x/y/z size

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Remove None in function param type

* Fix unittest

* Add comments for NMS functions

* Merge methods of Points

* Add unittest

* Add optional and default value

* Fix box conversion and add unittest

* Fix comments

* Add unit test

* Indent

* Fix CI

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Add unit test for box bev

* More unit tests and refine docstrings in box_np_ops

* Fix comment

* Add deprecation warning

* support pointrcnn backbone

* add docstring

* modify docstring

* modify docstring

* modify docstring

* Update pointnet2_fp_neck.py

* add code block

* refine docstring & code

* add unittest on fp_neck

* refine unittest

* refine unittest

* refine unittest

* refine unittest

* refine unittest

* fix docstring
Co-authored-by: Yezhen Cong <52420115+THU17cyz@users.noreply.github.com>
Co-authored-by: Xi Liu <75658786+xiliu8006@users.noreply.github.com>
Co-authored-by: THU17cyz <congyezhen71@hotmail.com>
Co-authored-by: xiliu8006 <xiliu8006@gmail.com>

* [Refactor] Main code modification for coordinate system refactor (#677)

* [Enhance] Add script for data update (#774)

* Fixed wrong config paths and fixed a bug in test

* Fixed metafile

* Coord sys refactor (main code)

* Update test_waymo_dataset.py

* Manually resolve conflict

* Removed unused lines and fixed imports

* remove coord2box and box2coord

* update dir_limit_offset

* Some minor improvements

* Removed some \s in comments

* Revert a change

* Change Box3DMode to Coord3DMode where points are converted

* Fix points_in_bbox function

* Fix Imvoxelnet config

* Revert adding a line

* Fix rotation bug when batch size is 0

* Keep sign of dir_scores as before

* Fix several comments

* Add a comment

* Fix docstring

* Add data update scripts

* Fix comments

* fix import (#839)

* [Enhance]  refactor  iou_neg_piecewise_sampler.py (#842)

* [Refactor] Main code modification for coordinate system refactor (#677)

* [Enhance] Add script for data update (#774)

* Fixed wrong config paths and fixed a bug in test

* Fixed metafile

* Coord sys refactor (main code)

* Update test_waymo_dataset.py

* Manually resolve conflict

* Removed unused lines and fixed imports

* remove coord2box and box2coord

* update dir_limit_offset

* Some minor improvements

* Removed some \s in comments

* Revert a change

* Change Box3DMode to Coord3DMode where points are converted

* Fix points_in_bbox function

* Fix Imvoxelnet config

* Revert adding a line

* Fix rotation bug when batch size is 0

* Keep sign of dir_scores as before

* Fix several comments

* Add a comment

* Fix docstring

* Add data update scripts

* Fix comments

* fix import

* refactor iou_neg_piecewise_sampler.py

* add docstring

* modify docstring
Co-authored-by: Yezhen Cong <52420115+THU17cyz@users.noreply.github.com>
Co-authored-by: THU17cyz <congyezhen71@hotmail.com>

* [Feature] Add roipooling cuda ops (#843)

* [Refactor] Main code modification for coordinate system refactor (#677)

* [Enhance] Add script for data update (#774)

* Fixed wrong config paths and fixed a bug in test

* Fixed metafile

* Coord sys refactor (main code)

* Update test_waymo_dataset.py

* Manually resolve conflict

* Removed unused lines and fixed imports

* remove coord2box and box2coord

* update dir_limit_offset

* Some minor improvements

* Removed some \s in comments

* Revert a change

* Change Box3DMode to Coord3DMode where points are converted

* Fix points_in_bbox function

* Fix Imvoxelnet config

* Revert adding a line

* Fix rotation bug when batch size is 0

* Keep sign of dir_scores as before

* Fix several comments

* Add a comment

* Fix docstring

* Add data update scripts

* Fix comments

* fix import

* add roipooling cuda ops

* add roi extractor

* add test_roi_extractor unittest

* Modify setup.py to install roipooling ops

* modify docstring

* remove enlarge bbox in roipoint pooling

* add_roipooling_ops

* modify docstring
Co-authored-by: Yezhen Cong <52420115+THU17cyz@users.noreply.github.com>
Co-authored-by: THU17cyz <congyezhen71@hotmail.com>

* [Refactor] Refactor code structure and docstrings (#803)

* refactor points_in_boxes

* Merge same functions of three boxes

* More docstring fixes and unify x/y/z size

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Remove None in function param type

* Fix unittest

* Add comments for NMS functions

* Merge methods of Points

* Add unittest

* Add optional and default value

* Fix box conversion and add unittest

* Fix comments

* Add unit test

* Indent

* Fix CI

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Add unit test for box bev

* More unit tests and refine docstrings in box_np_ops

* Fix comment

* Add deprecation warning

* [Feature] PointXYZWHLRBBoxCoder (#856)

* support PointBasedBoxCoder

* fix unittest bug

* support unittest in gpu

* support unittest in gpu

* modified docstring

* add args

* add args

* [Enhance] Change Groupfree3D config (#855)

* All mods

* PointSample

* PointSample

* [Doc] Add tutorials/data_pipeline Chinese version (#827)

* [Doc] Add tutorials/data_pipeline Chinese version

* refine doc

* Use the absolute link

* Use the absolute link
Co-authored-by: Tai-Wang <tab_wang@outlook.com>

* [Doc] Add Chinese doc for `scannet_det.md` (#836)

* Part

* Complete

* Fix comments

* Fix comments

* [Doc] Add Chinese doc for `waymo_det.md` (#859)

* Add complete translation

* Refinements

* Fix comments

* Fix a minor typo
Co-authored-by: Tai-Wang <tab_wang@outlook.com>

* Remove 2D annotations on Lyft (#867)

* Add header for files (#869)

* Add header for files

* Add header for files

* Add header for files

* Add header for files

* [fix] fix typos (#872)

* Fix 3 unworking configs (#882)

* [Fix] Fix `index.rst` for Chinese docs (#873)

* Fix index.rst for zh docs

* Change switch language

* [Fix] Centerpoint head nested list transpose  (#879)

* FIX Transpose nested lists without Numpy

* Removed unused Numpy import

* [Enhance] Update PointFusion (#791)

* update point fusion

* remove LIDAR hardcode

* move get_proj_mat_by_coord_type to utils

* fix lint

* remove todo

* fix lint

* [Doc] Add nuscenes_det.md Chinese version (#854)

* add nus chinese doc

* add nuScenes Chinese doc

* fix typo

* fix typo

* fix typo

* fix typo

* fix typo

* [Fix] Fix RegNet pretrained weight loading (#889)

* Fix regnet pretrained weight loading

* Remove unused file

* Fix centerpoint tta (#892)

* [Enhance] Add benchmark regression script (#808)

* Initial commit

* [Feature] Support DGCNN (v1.0.0.dev0) (#896)

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* support dgcnn

* fix typo

* fix typo

* fix typo

* del gf&fa registry (wo reuse pointnet module)

* fix typo

* add benchmark and add copyright header (for DGCNN only)

* fix typo

* fix typo

* fix typo

* fix typo

* fix typo

* support dgcnn

* Change cam rot_3d_in_axis (#906)

* [Doc] Add coord sys tutorial pic and change links to dev branch (#912)

* Modify link branch and add pic

* Fix pic

* [Feature] add kitti AP40 evaluation metric (v1.0.0.dev0) (#927)

* Add citation (#901)

* [Feature] Add python3.9 in CI (#900)

* Add python3.0 in CI

* Add python3.0 in CI

* Bump to v0.17.0 (#898)

* Update README.md

* Update README_zh-CN.md

* Update version.py

* Update getting_started.md

* Update getting_started.md

* Update changelog.md

* Remove "recent" in the news

* Remove "recent" in the news

* Fix comments

* [Docs] Fix the version of sphinx (#902)

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* Fix sphinx version

* add AP40

* add unitest

* add unitest

* seperate AP11 and AP40

* fix some typos
Co-authored-by: dingchang <hudingchang.vendor@sensetime.com>
Co-authored-by: Tai-Wang <tab_wang@outlook.com>

* [Feature] add smoke backbone neck (#939)

* add smoke detecotor and it's backbone and neck

* typo fix

* fix typo

* add docstring

* fix typo

* fix comments

* fix comments

* fix comments

* fix typo

* fix typo

* fix

* fix typo

* fix docstring

* refine feature

* fix typo

* use Basemodule in Neck

* [Refactor] Refactor the transformation from image to camera coordinates (#938)

* Refactor points_img2cam

* Refine docstring

* Support array converter and add unit tests

* [Feature] FCOS3D BBox Coder (#940)

* FCOS3D BBox Coder

* Add unit tests

* Change the value from long to float/double

* Rename bbox_out as bbox

* Add comments to forward returns

* [Feature] PGD BBox Coder (#948)

* Support PGD BBox Coder

* Refine docstring

* [Feature] Support Uncertain L1 Loss (#950)

* Add uncertain l1 loss and its unit tests

* Remove mmcv.jit and refine docstrings

* [Fix] Fix visualization in KITTI dataset (#956)

* fix bug to support kitti vis

* fix

* add smoke head

* fix typo

* fix code

* fix

* fix typo

* add detector

* delete dectector

* fix test_heads

* add coder test

* fix head

* fix bugs in smoke head

* refine kitti_mono3d data config

* remove cuda is available

* fix docstring

* fix unitest

* fix typo

* refine

* add affine aug

* fix rebase typo

* fix docs

* change cam_intrinsics to cam2imgs

* fix typos

* fix lint

* fix bugs

* fix las typos

* fix typos

* add dosctrings for trans_mats
Co-authored-by: Yezhen Cong <52420115+THU17cyz@users.noreply.github.com>
Co-authored-by: Xi Liu <75658786+xiliu8006@users.noreply.github.com>
Co-authored-by: THU17cyz <congyezhen71@hotmail.com>
Co-authored-by: Wenhao Wu <79644370+wHao-Wu@users.noreply.github.com>
Co-authored-by: Tai-Wang <tab_wang@outlook.com>
Co-authored-by: dingchang <hudingchang.vendor@sensetime.com>
Co-authored-by: 谢恩泽 <Johnny_ez@163.com>
Co-authored-by: Robin Karlsson <34254153+robin-karlsson0@users.noreply.github.com>
Co-authored-by: Danila Rukhovich <danrukh@gmail.com>

* FCOS3D BBox Coder

* Add unit tests

* Change the value from long to float/double

* Rename bbox_out as bbox

* Add comments to forward returns

* Refactor points_img2cam

* Refine docstring

* Support array converter and add unit tests

* Add header for files

* Add header for files

* Add header for files

* Add header for files

* refactor points_in_boxes

* Merge same functions of three boxes

* More docstring fixes and unify x/y/z size

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Remove None in function param type

* Fix unittest

* Add comments for NMS functions

* Merge methods of Points

* Add unittest

* Add optional and default value

* Fix box conversion and add unittest

* Fix comments

* Add unit test

* Indent

* Fix CI

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Add unit test for box bev

* More unit tests and refine docstrings in box_np_ops

* Fix comment

* Add deprecation warning

* reduce 1e-12 to make difference between variables

If 1e-12 is used to make a difference between t1 and t2, then later (t2-t1) might become 0 as 1e-12 can't affect to the number (at least true in pytorch, verified in v1.5.0+).

* Revert "reduce 1e-12 to make difference between variables"

This reverts commit 33ec7215d22be59bf0012dea748f5cacc33a0fb8.

* reduce 1e-12 to make difference between variables

If 1e-12 is used to make a difference between t1 and t2, then later (t2-t1) might become 0 as 1e-12 can't affect to the number (at least true in pytorch, verified in v1.5.0+). Not sure whether 1e-7 or 1e-8 worked. But 1e-6 did.

* visuliaztion typos

* fix to visualization

* fixed lint errors by pre-commit

* upgrade to build_anchor_generator

* fixed  isort message

* FIX Transpose nested lists without Numpy

* Removed unused Numpy import

* Add header for files

* Add header for files

* Add header for files

* Add header for files

* fix gf3d cfg name

* fix unit test

* minor fix

* replace all cam_intrinsic

* revert cam_intrinsic in test

* remove rect and fix lint

* Fix rotation and dim hacks between nuscbox and our cambox

* Remove hack in the mono browse, fix cam_intrinsic in the RandomFlip3D

* Apply a more suitable hack transformation (dim & yaw hack)

* Fix incorrect transformation of dim in post-processing

* Remove transformation from global to local yaw in kitti mono dataset

* Add comments for cam_intrinsic modification in the doc and code

* Fix typos and invalid links

* Add compatibility doc for fixing nus hacks

* Update benchmark

* Fix docstring typos and change formats for api-doc to work

* Test on fixing noqa

* Fix noqa

* Fix noqa

* 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

* add init cfg

* add init cfg

* modify fcos3d init_weights

* deleted error merge code

* deleted useless code

* remove useless code

* 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>

* fix bg_points_filter

* fix 3dssd bg_point_filter bug

* fix bg_filter bug in 3dssd

* update performance

* add model download link

* fix error direction

* fix aos bug in get_bboxes

* Support base mono3d dense head and anchor free mono3d head

* Support FCOS3D head

* Support FCOS3D baseline on nuScenes

* Fix an import error caused by update of mmcv/mmdet

* Change img_scale to scale_factor in the MultiScaleFlipAug in the config

* Add pred_bbox2d in the params of anchor_free_mono3d_head

* Add unit test for fcos3d head

* Fix a minor bug when setting img_metas in the unit test

* Add unit test for fcos3d detector

* Simplify the logic of weights initialization

* Add comments to specify the reason of cloning features

* Update head config

* modify vote_head to support 3dssd

* delete .keys()

* add 3dssd unittest

* 3dssd->ssd3d

* Added image loading in SUNRGB-D dataset (#195)

* image loading

* format and docstring fix

* removed irrelevant files

* removed irrelevant files

* load image only if modality is pc+img

* added modality like nuscenes

* Added imvotenet image branch pretrain (#217)

* image loading

* naive commit

* format and docstring fix

* removed irrelevant files

* removed irrelevant files

* load image only if modality is pc+img

* added modality like nuscenes

* pretrain_2d_model

* finetune sunrgbd

* finetune sunrgbd

* deleted unused code

* fixed a bug

* resolve conflict

* update config file

* fix docstring and configs

* integrated vote fusion

* coords transform and unit test

* Update docstring

* refactor and add unit test

* fix bug caused by mmcv upgrade; delete pdb breakpoint

* add point fusion unittest

* remove unused file

* fix typos

* updates

* add assertion info

* update

* add unittest

* add vote fusion unittest

* add vote fusion unittest

* [Refactor] VoteNet refactor (#322)

* votenet refactor

* remove file

* minor update

* docstring

* initial update of imvotenet

* [Feature] Support vote fusion (#297)

* integrated vote fusion

* coords transform and unit test

* Update docstring

* refactor and add unit test

* add point fusion unittest

* remove unused file

* updates

* add assertion info

* update

* add unittest

* add vote fusion unittest

* add vote fusion unittest

* minor update

* docstring

* change np ops to torch

* refactor test

* update

* refactor of image mlp and np random ops to torch

* add docstring

* add config and mod dataset

* fix bugs

* add_comments

* fix bugs

* fix_bug

* fix bug

* fix bug

* fix bug

* fix bug

* final fix

* fix bug

* ?

* add docstring

* move train/test cfg

* change img mlp default param

* rename config

* minor mod

* change config name

* move train/test cfg

* some fixes and 2d utils

* fix config name

* fix config override issue

* config simplify & reformat

* explicitly set eval mode->override train()

* add fix_img_branch to config

* remove set_img_branch_eval_mode

* temporal fix, change calibs to calib

* more docstring and view/reshape, expand/repeat change

* complete imvotenet docstring

* fix docstring

* add config and some minor fix

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

* fix nonzero warning with as_tuple

* fix nonzero warning with as_tuple #320

* fix bug caused by mmcv upgrade; delete pdb breakpoint

* fix typos

* 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

* 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

* 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