1. 03 Dec, 2022 1 commit
    • Jingwei Zhang's avatar
      [Refactor] Refactor FCAF3D (#1945) · 0be27ffb
      Jingwei Zhang authored
      * add fcaf3d config
      
      * support inference of fcaf3d on scannet-3d
      
      * minor changes
      
      * fix config of scannet
      
      * align test precision of facaf3d && support training
      
      * add ut
      
      * fix bugs of dataset conversion and indoor_metric
      
      * support fcaf3d on sunrgbd datasets and add rorate_iou_loss ut
      
      * small fix
      
      * add docstring and typehint
      
      * add typehint for SparseTensor
      
      * remove pdb
      
      * fix fcaf3d ut
      0be27ffb
  2. 20 Jul, 2022 1 commit
  3. 21 Jan, 2022 1 commit
  4. 08 Dec, 2021 1 commit
    • Wenhao Wu's avatar
      [Feature] Support PointRCNN RPN and RCNN module (#1022) · 0f8181f1
      Wenhao Wu authored
      * 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
      0f8181f1
  5. 01 Nov, 2021 1 commit
    • Tai-Wang's avatar
      [Feature] Support PGD Head (#964) · 36aa4cb2
      Tai-Wang authored
      
      
      * [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: default avatarYezhen Cong <52420115+THU17cyz@users.noreply.github.com>
      Co-authored-by: default avatarTHU17cyz <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: default avatarYezhen Cong <52420115+THU17cyz@users.noreply.github.com>
      Co-authored-by: default avatarTHU17cyz <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: default avatarTai-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: default avatarTai-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: default avatardingchang <hudingchang.vendor@sensetime.com>
      Co-authored-by: default avatarTai-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: default avatarYezhen Cong <52420115+THU17cyz@users.noreply.github.com>
      Co-authored-by: default avatarXi Liu <75658786+xiliu8006@users.noreply.github.com>
      Co-authored-by: default avatarTHU17cyz <congyezhen71@hotmail.com>
      Co-authored-by: default avatarWenhao Wu <79644370+wHao-Wu@users.noreply.github.com>
      Co-authored-by: default avatardingchang <hudingchang.vendor@sensetime.com>
      Co-authored-by: default avatar谢恩泽 <Johnny_ez@163.com>
      Co-authored-by: default avatarRobin Karlsson <34254153+robin-karlsson0@users.noreply.github.com>
      Co-authored-by: default avatarDanila Rukhovich <danrukh@gmail.com>
      Co-authored-by: default avatarChaimZhu <zhuchenming@pjlab.org.cn>
      36aa4cb2
  6. 29 Sep, 2021 1 commit
    • ChaimZhu's avatar
      [Feature] Add SMOKE Head and Coder(v1.0.0.dev0) (#959) · f268ba42
      ChaimZhu authored
      
      
      * [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: default avatarYezhen Cong <52420115+THU17cyz@users.noreply.github.com>
      Co-authored-by: default avatarTHU17cyz <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: default avatarYezhen Cong <52420115+THU17cyz@users.noreply.github.com>
      Co-authored-by: default avatarTHU17cyz <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: default avatarTai-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: default avatarTai-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: default avatardingchang <hudingchang.vendor@sensetime.com>
      Co-authored-by: default avatarTai-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: default avatarYezhen Cong <52420115+THU17cyz@users.noreply.github.com>
      Co-authored-by: default avatarXi Liu <75658786+xiliu8006@users.noreply.github.com>
      Co-authored-by: default avatarTHU17cyz <congyezhen71@hotmail.com>
      Co-authored-by: default avatarWenhao Wu <79644370+wHao-Wu@users.noreply.github.com>
      Co-authored-by: default avatarTai-Wang <tab_wang@outlook.com>
      Co-authored-by: default avatardingchang <hudingchang.vendor@sensetime.com>
      Co-authored-by: default avatar谢恩泽 <Johnny_ez@163.com>
      Co-authored-by: default avatarRobin Karlsson <34254153+robin-karlsson0@users.noreply.github.com>
      Co-authored-by: default avatarDanila Rukhovich <danrukh@gmail.com>
      f268ba42
  7. 19 Aug, 2021 1 commit
  8. 01 Jul, 2021 1 commit
    • hjin2902's avatar
      [Feature] Group-Free-3D head (#539) · 318499ac
      hjin2902 authored
      
      
      * 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: default avatarjinhui <PJLAB\jinhui@shai14001019l.pjlab.org>
      318499ac
  9. 23 Apr, 2021 1 commit
    • twang's avatar
      [Feature] Support FCOS3D head (#442) · f7356f4b
      twang authored
      * 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
      f7356f4b
  10. 20 Oct, 2020 1 commit
    • twang's avatar
      [Feature] Add shape-aware grouping head in SSN (#147) · b016d90c
      twang authored
      * 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
      b016d90c
  11. 19 Sep, 2020 1 commit
    • yinchimaoliang's avatar
      [feature]: Add Centerpoint configs (#92) · ee801168
      yinchimaoliang authored
      * 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
      ee801168
  12. 13 Sep, 2020 1 commit
    • encore-zhou's avatar
      [feature]: support ssd_3d_head in 3DSSD (#83) · 460f6b3b
      encore-zhou authored
      * 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
      460f6b3b
  13. 28 Jun, 2020 1 commit
  14. 04 Jun, 2020 1 commit
  15. 18 May, 2020 1 commit