How to visualize point cloud when running demo.py with pretrain model

[leducnguyen21]

This is my code

%cd /content/OpenPCDet/tools ! python demo.py --cfg_file cfgs/kitti_models/pv_rcnn.yaml
--ckpt /content/OpenPCDet/data/kitti/pv_rcnn_8369.pth
--data_path /content/OpenPCDet/data/kitti/training/velodyne/000000.bin

This is the error, i don't know how to fix /content/OpenPCDet/tools 2022-07-06 13:12:58,075 INFO -----------------Quick Demo of OpenPCDet------------------------- 2022-07-06 13:12:58,075 INFO Total number of samples: 1 2022-07-06 13:13:01,908 INFO ==> Loading parameters from checkpoint /content/OpenPCDet/data/kitti/pv_rcnn_8369.pth to CPU 2022-07-06 13:13:01,978 INFO ==> Done (loaded 367/367) 2022-07-06 13:13:02,311 INFO Visualized sample index: 1 [Exception|implicit_gemm_pair]indices=torch.Size([0, 4]),bs=1,ss=[41, 1600, 1408],algo=ConvAlgo.MaskImplicitGemm,ksize=[3, 3, 3],stride=[1, 1, 1],padding=[1, 1, 1],dilation=[1, 1, 1],subm=True,transpose=False SPCONV_DEBUG_SAVE_PATH not found, you can specify SPCONV_DEBUG_SAVE_PATH as debug data save path to save debug data which can be attached in a issue. Traceback (most recent call last): File "demo.py", line 125, in main() File "demo.py", line 109, in main pred_dicts, _ = model.forward(data_dict) File "../pcdet/models/detectors/pv_rcnn.py", line 11, in forward batch_dict = cur_module(batch_dict) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "../pcdet/models/backbones_3d/spconv_backbone.py", line 148, in forward x = self.conv_input(input_sp_tensor) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.7/dist-packages/spconv/pytorch/modules.py", line 137, in forward input = module(input) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.7/dist-packages/spconv/pytorch/conv.py", line 393, in forward raise e File "/usr/local/lib/python3.7/dist-packages/spconv/pytorch/conv.py", line 384, in forward timer=input._timer) File "/usr/local/lib/python3.7/dist-packages/spconv/pytorch/ops.py", line 340, in get_indice_pairs_implicit_gemm stream_int=stream) RuntimeError: /tmp/pip-build-env-s_j4zkty/overlay/lib/python3.7/site-packages/cumm/include/tensorview/cuda/launch.h(53) N > 0 assert faild. CUDA kernel launch blocks must be positive, but got N= 0

[aldipiroli]

This might be due to a wrong spconv installation. Can you try and run the demo script inside the official docker container?

[OrangeSodahub]

Maybe this is because that your dataset contains empty file (no valid object)

[github-actions[bot]]

This issue is stale because it has been open for 30 days with no activity.

[github-actions[bot]]

This issue was closed because it has been inactive for 14 days since being marked as stale.