dvlab-research/FocalsConv

Issues

• How to get 1/4 nuScenes Dataset？

  #37 opened a month ago by Arno-Tu
  0

• KeyError: 'model_state'

  #35 opened 8 months ago by guoziteng
  2

• how to generate 1/4 nuscenes data on openpcdet

  #24 opened 2 years ago by wenchened
  5

• RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one

  #36 opened 7 months ago by saeid114
  0

• About the instable performance on voxelrcnn-focalsconv-lidar.

  #30 opened 2 years ago by Raiden-cn
  5

• Regarding using the openpcdet version code on the nuscenes dataset.

  #33 opened a year ago by Clangut
  0

• Blogger, I would like to ask how to make this result visualization

  #32 opened 2 years ago by lmn1516
  2

• Can not reproduce the result by loading the provided checkpoint on my machines

  #16 opened 2 years ago by klightz
  6

• How to compute the params and runtime(inference time?)

  #9 opened 2 years ago by Jane-QinJ
  9

• Can you share the following yaml files that detect the three categories

  #31 opened 2 years ago by lmn1516
  0

• Some details about train， especially for train time.

  #29 opened 2 years ago by ZecCheng
  0

• CUDA out of memory

  #20 opened 2 years ago by TimGor1997
  9

• training error ONLY in Focals Conv

  #28 opened 2 years ago by Townjj
  4

• It use too large gpu memory

  #27 opened 2 years ago by blazeCCC
  5

• Performance variance when using nuscenes 1/4

  #26 opened 2 years ago by konyul
  1

• About 2D pretrained model

  #22 opened 2 years ago by yeminglang
  1

• Does FocalsConv supports spconv1.2.1?

  #25 opened 2 years ago by Raiden-cn
  2

• Error when I use demo.py to visulize result. How can I add images as input?

  #23 opened 2 years ago by ChunZheng2022
  1

• OpenPCDet, spconv version issue

  #3 opened 3 years ago by Minwookk
  5

• logger in multi gpu

  #21 opened 2 years ago by konyul
  1

• How long does it takes to train multimodal FocalsConv on nuScenes dataset?

  #5 opened 3 years ago by rkotimi
  3

• why split foreground and background features based importance but then combine them for next submaniford conv?

  #19 opened 2 years ago by FlyingQianMM
  3

• Issues about fusing multimodal features

  #18 opened 2 years ago by Eaton2022
  5

• RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one.

  #17 opened 2 years ago by zijianh4
  1

• Question about the results on nuscenes

  #15 opened 2 years ago by Solacex
  14

• Backward error when training on nuScenes

  #13 opened 2 years ago by klightz
  8

• how did you get performance with flip test??

  #14 opened 2 years ago by Minwookk
  1

• voxel rcnn usage

  #12 opened 2 years ago by vehxianfish
  5

• Occlusion between different classes in multi modal GT-Sampling.

  #11 opened 2 years ago by rkotimi
  1

• lidar-only focal centerpoint config is missing

  #2 opened 3 years ago by konyul
  7

• I can't train the multi-modal accuracy(KITTI val split in AP3D(R11))you mentioned in the paper

  #10 opened 2 years ago by qimingx
  11

• UnboundLocalError: local variable 'mv_height' referenced before assignment

  #8 opened 3 years ago by Jane-QinJ
  3

• add web demo/model to Huggingface

  #1 opened 3 years ago by AK391
  2

• KeyError: 'road_plane' in database_sampler.py

  #7 opened 3 years ago by YangHan-Morningstar
  2

• Error in database_sampler.py

  #6 opened 3 years ago by YangHan-Morningstar
  2

• Data augmentation in Section 3.3.

  #4 opened 3 years ago by CBY-9527
  1