1. 30 Jul, 2021 3 commits
  2. 28 Jul, 2021 5 commits
    • dingchang's avatar
      [Docs] Add 1_exist_data_model.md Chinese Version (#746) · c07e9601
      dingchang authored
      * add 1_exist_data_model.md chinese version
      
      * add 1_exist_data_model.md chinese version
      
      * add 1_exist_data_model.md chinese version
      
      * add 1_exist_data_model.md chinese version
      
      * add 1_exist_data_model.md chinese version & modify 1_exist_data_model.md english version
      
      * add 1_exist_data_model.md chinese version & modify 1_exist_data_model.md english version
      
      * add 1_exist_data_model.md chinese version & modify 1_exist_data_model.md english version
      
      * add 1_exist_data_model.md chinese version & modify 1_exist_data_model.md english version
      c07e9601
    • Wenhao Wu's avatar
      [Enhance] Modify resourse limit (#796) · 5276dfb4
      Wenhao Wu authored
      5276dfb4
    • Tai-Wang's avatar
      [Fix] Fix nuscenes_mono_dataset unit test due to hack fix (#795) · a56185ab
      Tai-Wang authored
      * Fix nuscenes_mono_dataset unit test due to hack fix
      
      * Remove unused codes
      a56185ab
    • Wenhao Wu's avatar
      [Enhance] Support mim (#782) · 77964873
      Wenhao Wu authored
      * support mim
      
      * remove ops
      
      * add ops info into MANIFEST.in
      
      * remove demo in when creating .mim
      
      * refine setup.py
      77964873
    • Ziyi Wu's avatar
      [Feature] Support entire PAConv and PAConvCUDA models (#783) · 3870001a
      Ziyi Wu authored
      * add PAConv decode head
      
      * add config files
      
      * add paconv's correlation loss
      
      * support reg loss in Segmentor class
      
      * minor fix
      
      * add augmentation to configs
      
      * fix ed7 in cfg
      
      * fix bug in corr loss
      
      * enable syncbn in paconv
      
      * rename to loss_regularization
      
      * rename loss_reg to loss_regularize
      
      * use SyncBN
      
      * change weight kernels to kernel weights
      
      * rename corr_loss to reg_loss
      
      * minor fix
      
      * configs fix IndoorPatchPointSample
      
      * fix grouped points minus center error
      
      * update transform_3d & add configs
      
      * merge master
      
      * fix enlarge_size bug
      
      * refine config
      
      * remove cfg files
      
      * minor fix
      
      * add comments on PAConv's ScoreNet
      
      * refine comments
      
      * update compatibility doc
      
      * remove useless lines in transforms_3d
      
      * rename with_loss_regularization to with_regularization_loss
      
      * revert palette change
      
      * remove xavier init from PAConv's ScoreNet
      3870001a
  3. 27 Jul, 2021 1 commit
  4. 25 Jul, 2021 3 commits
  5. 21 Jul, 2021 5 commits
  6. 20 Jul, 2021 4 commits
  7. 14 Jul, 2021 1 commit
  8. 13 Jul, 2021 5 commits
    • xiliu8006's avatar
      fix fcos3d FPN BC-Breaking (#739) · 1db4baed
      xiliu8006 authored
      1db4baed
    • xiliu8006's avatar
      [Enhance] Modify the Fcos3d init_weights methods (#705) · 6a733eb4
      xiliu8006 authored
      * 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
      6a733eb4
    • Ziyi Wu's avatar
      [Fix] Fix potential bug in using `analyze_logs.py` (#720) · 810c44d8
      Ziyi Wu authored
      * fix bug when interval == 1
      
      * minor fix
      810c44d8
    • Ziyi Wu's avatar
      [Feature] Support FLOPs and Params calculation in MMDet3D (#736) · 6cd23071
      Ziyi Wu authored
      * add get_flops.py
      
      * modify SSD to support flops calc
      
      * update docs
      
      * support mono3d models
      6cd23071
    • Wenhao Wu's avatar
      [Docs] Chinese Document of model_zoo (#735) · 0ddbd0ee
      Wenhao Wu authored
      0ddbd0ee
  9. 12 Jul, 2021 3 commits
  10. 09 Jul, 2021 1 commit
  11. 06 Jul, 2021 3 commits
  12. 02 Jul, 2021 3 commits
  13. 01 Jul, 2021 3 commits
    • Ziyi Wu's avatar
      [Fix] Fix `LoadMultiViewImageFromFiles` to be compatible with `DefaultFormatBundle` (#611) · 7fec1d53
      Ziyi Wu authored
      * unravel multi-view img to list
      
      * add unit test
      7fec1d53
    • xiliu8006's avatar
      [Refactor]: Unified parameter initialization (#622) · 07590418
      xiliu8006 authored
      * 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
      07590418
    • 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