NVIDIA-AI-IOT / Lidar_AI_Solution

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,).
Other
1.33k stars 236 forks source link

spconv onnx #282

Open GEN418 opened 2 months ago

GEN418 commented 2 months ago

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.