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

The number of voxels in Centerpoint and CUDA-CenterPoint did not match. #263

Open mx2013713828 opened 4 months ago

mx2013713828 commented 4 months ago

when I inference the same Bin file, The number of voxels not equal! while I use Centerpoint , I got 87081 voxels after voxel_generator, and 111576 voxels in CUDA-Centerpoint after voxelization. And it is puzzling that there is not much difference in their final results. Can you explain that? I'm very confused! Thank you so much !