OpenDriveLab/ViDAR

Issues

• About point cloud forecasting in paper table2

  #43 opened 25 days ago by chenshi3
  0

• About the use of the decoder in pts_bbox_head and model outputs in ViDAR training

  #42 opened a month ago by Sora-tabata
  0

• How to reproduce Figure3 in the paper?

  #34 opened 5 months ago by odroidodroid
  5

• Can you provide the visualization code for reproducing Figure3 in the paper?

  #41 opened 2 months ago by jimchenhub
  0

• nuscenes data entry

  #40 opened 3 months ago by naonao-wu
  0

• 修改哪些参数可以保证用较少的GPU达到训练模型的地步

  #39 opened 3 months ago by naonao-wu
  1

• Is an 8x NVIDIA RTX 3090 GPU Setup Sufficient for Training Models in the Predictive World Model 2024 Competition?

  #17 opened 8 months ago by Liury99
  6

• can a single 3090 be used to pretrain ViDAR?

  #29 opened 6 months ago by renyuanzhe
  2

• About custom datasets and num_pred_height in config

  #38 opened 4 months ago by qiuqc1
  2

• 训练时缺少config文件

  #37 opened 4 months ago by liudun226296
  0

• 不存在这个包lyft_converter

  #36 opened 4 months ago by naonao-wu
  1

• About reference points in temporal cross-attention

  #35 opened 5 months ago by artofstate
  3

• About time cost

  #33 opened 6 months ago by artofstate
  1

• About point cloud forecasting in paper table2

  #30 opened 6 months ago by qiuqc1
  3

• About merge_nusc_fullset_pkl.py

  #32 opened 6 months ago by qiuqc1
  2

• Is it reasonable to predict the point cloud from the ego origin?

  #31 opened 6 months ago by SeaBird-Go
  1

• RuntimeError: CUDA error: no kernel image is available for execution on the device 2024-05-15T10:49:54.910116296Z CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. 2024-05-15T10:49:54.910125144Z For debugging consider passing CUDA_LAUNCH_BLOCKING=1

  #28 opened 6 months ago by qiuqc1
  2

• File "/home/uids0529/.local/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1418, in _write_ninja_file_and_build_library verify_ninja_availability() File "/home/uids0529/.local/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1474, in verify_ninja_availability raise RuntimeError("Ninja is required to load C++ extensions") RuntimeError: Ninja is required to load C++ extensions

  #26 opened 6 months ago by yinianwujide
  0

• ModuleNotFoundError: No module named 'DCNv3'

  #25 opened 7 months ago by anilbhatt1
  1

• A simple question of sensor coordinate.

  #24 opened 7 months ago by synsin0
  2

• The performance of ViDAR in private_test_wm dataset

  #23 opened 7 months ago by SeaBird-Go
  2

• MMCV, RuntimeError: modulated_deformable_im2col_impl: implementation for device cuda:0 not found.

  #22 opened 8 months ago by HaoranZhuExplorer
  2

• When will the private test set be released？

  #21 opened 8 months ago by jiangxb98
  1

• About the mini train.pkl and val.pkl

  #20 opened 8 months ago by jiangxb98
  1

• Error with installing scikit_image

  #19 opened 8 months ago by Shin-kyoto
  1

• About the openscene_mini_train.pkl and val.pkl

  #18 opened 8 months ago by jiangxb98
  4

• Regarding Table 1 in the paper

  #15 opened 8 months ago by cdb342
  1

• Align paper results by myself

  #16 opened 8 months ago by LuPaoPao
  4

• About the chamferdist

  #12 opened 8 months ago by jiangxb98
  2

• How to use all the data to fine-tune?

  #14 opened 8 months ago by LuPaoPao
  3

• About ADE, FDE, MR

  #13 opened 8 months ago by Gwan98
  2

• Requesting requirements.txt

  #11 opened 9 months ago by tolgadimli
  3

• What about the GPU usage when finetuning?

  #10 opened 9 months ago by dingli-dean
  2

• Get 'wheel torch'error when run 'pip install torch==1.10.1+cu111 torchvision==0.11.2+cu111 torchaudio==0.10.1 -f https://download.pytorch.org/whl/cu111/torch_stable.html' command

  #9 opened 9 months ago by brodermind
  2

• Why can't I specify a GPU?

  #8 opened 9 months ago by jiangxb98
  0

• Can Vidar produce 4D binary occupancy results during inference?

  #6 opened 9 months ago by synsin0
  1

• Why can't I download the mini-set: openscene_metadata_mini.tgz (509.6 MB)?

  #7 opened 9 months ago by jiangxb98
  2

• `undefined symbol` ImportError with `from chamferdist import _C`

  #5 opened 9 months ago by kminoda
  3

• When will the data processing code be released？

  #4 opened 9 months ago by jiangxb98
  4

• when will code be available?

  #3 opened 10 months ago by HaoranZhuExplorer
  2

• GPU HOURS

  #2 opened 10 months ago by ggosjw
  1

• In Eq5, BEV feature expectation function is 2 dim?? , but conditional probability is 3-dim. how to calculate final Feature for BEV??

  #1 opened 10 months ago by SPA-junghokim
  6