Acuno41 comments

Results 5 comments of


                                            Acuno41

Training and evaluation works well when I change MAX_POINTS_PER_VOXEL from 32 to 100, but after converting model to ONNX, TFRT inference results in wrong predictions

Hi, Is there any update on this issue ?

What should I do if I want more labels？

Hello eveyone, I met the same problem. Is there any update on this one ? > @maayanYa I haved met similar problems before. In my case the programme is running...

What should I do if I want more labels？

Hello again, after updating the exporter code with below comment custom model training exported and worked fine for me. https://github.com/NVIDIA-AI-IOT/CUDA-PointPillars/pull/77#issuecomment-1508276016

What should I do if I want more labels？

Hello again everyone, After sometime i was able to train my custom data with 3 classes with OpenPCDet and export it successfully. Both OpenPCDet and c++ side the model worked...

What should I do if I want more labels？

I found out that the "MAX_POINTS_PER_VOXEL" parameter in the pointpillar.yaml file is the problem. When I change the parameter from the default 32 to something different, it causes the problem...