Amadeusz Szymko

Thank you @knzo25 for your review. Let me investigate the kernels first to find mentioned leak. Regarding the NaN output, as you suggested we will: - change the optimization profile,...

@knzo25 Recent fix solves the issue with cuda memory and NaNs. Please check if the issue disappeared on your machine as well.

@scepter914 To keep the consistency we will rename config `v1/lidar_transfusion.param.yaml` -> `v1/transfusion.param.yaml`. Please wait for the deployment.

@knzo25 > While doing other task that was asked of me, I was looking at the whole perception task and saw the preprocessing being done in cpu in centerpoint. I...

cc: @vividf (I think you've working on similar stuff recently)

Hi @zeta-mobility Are there any updates? > We have developed our own integration code for the Ouster Lidar sensor and would like to discuss the possibility of contributing it to...

@badai-nguyen Since #5594 is solved, can we close this issue? Does new feature handle these cases?

Hi @sgNicola Did you fix the issue already? If not, I would like to reproduce it but your link does not have rosbag file, I see only the meta file.

@sgNicola I reproduced your issue and here is brief summary: 1. Apart of fact the cone was detected as pedestrian, indeed `obstacle_pointcloud_based_validator` removes tiny objects. 2. This issue was addressed...

> Thank you for your help! Closing as resolved 👍🏻