A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution, YUV2RGB, cuOSD,).
I converted the sparse convolution backbone of voxel rcnn to onnx by modifying export-scn.py and exptool.py, and the conversion was successful without any errors. But when loaded as an engine, the output for voxels input is always 0. May I ask if there are any possible issues.
ps: without changing other parts, only replace the loaded onnx file with the onnx of bevfusion lidar backbone, and the output is normal.
I converted the sparse convolution backbone of voxel rcnn to onnx by modifying export-scn.py and exptool.py, and the conversion was successful without any errors. But when loaded as an engine, the output for voxels input is always 0. May I ask if there are any possible issues. ps: without changing other parts, only replace the loaded onnx file with the onnx of bevfusion lidar backbone, and the output is normal.