OpenDriveLab / ViDAR

[CVPR 2024 Highlight] Visual Point Cloud Forecasting

https://arxiv.org/abs/2312.17655

OpenDriveLab/ViDAR Issues

About custom datasets and num_pred_height in config
Updated 2 days ago2
训练时缺少config文件
Updated 8 days ago
不存在这个包lyft_converter
Updated 11 days ago1
About reference points in temporal cross-attention
Closed 21 days ago3
How to reproduce Figure3 in the paper?
Closed a month ago4
About time cost
Closed 2 months ago1
About point cloud forecasting in paper table2
Closed 2 months ago3
About merge_nusc_fullset_pkl.py
Closed 2 months ago2
Is it reasonable to predict the point cloud from the ego origin?
Updated 2 months ago1
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
Updated 2 months ago2
can a single 3090 be used to pretrain ViDAR?
Closed 2 months ago1
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
Updated 3 months ago
Is an 8x NVIDIA RTX 3090 GPU Setup Sufficient for Training Models in the Predictive World Model 2024 Competition?
Closed 4 months ago5
ModuleNotFoundError: No module named 'DCNv3'
Closed 3 months ago1
A simple question of sensor coordinate.
Closed 3 months ago2
The performance of ViDAR in private_test_wm dataset
Closed 3 months ago2
MMCV, RuntimeError: modulated_deformable_im2col_impl: implementation for device cuda:0 not found.
Closed 4 months ago2
When will the private test set be released？
Closed 4 months ago1
About the mini train.pkl and val.pkl
Closed 4 months ago1
Error with installing scikit_image
Closed 4 months ago1
About the openscene_mini_train.pkl and val.pkl
Closed 4 months ago4
Regarding Table 1 in the paper
Closed 4 months ago1
Align paper results by myself
Closed 4 months ago4
About the chamferdist
Closed 4 months ago2
How to use all the data to fine-tune?
Closed 4 months ago3
About ADE, FDE, MR
Closed 4 months ago2
Requesting requirements.txt
Closed 5 months ago3
What about the GPU usage when finetuning?
Closed 5 months ago2
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
Closed 5 months ago2
Why can't I specify a GPU?
Closed 5 months ago
Can Vidar produce 4D binary occupancy results during inference?
Closed 5 months ago1
Why can't I download the mini-set: openscene_metadata_mini.tgz (509.6 MB)?
Closed 5 months ago2
`undefined symbol` ImportError with `from chamferdist import _C`
Closed 5 months ago3
When will the data processing code be released？
Closed 5 months ago4
when will code be available?
Closed 6 months ago2
GPU HOURS
Closed 6 months ago1
In Eq5, BEV feature expectation function is 2 dim?? , but conditional probability is 3-dim. how to calculate final Feature for BEV??
Closed 6 months ago6