OpenPCDet icon indicating copy to clipboard operation
OpenPCDet copied to clipboard

Published 20 hours ago • verified publisher icon open-mmlab

Submit on KITTI website

Open JLIN77 opened this issue 3 years ago • 0 comments

Yes. I did inference the KITTI test set with official PV-RCNN weight, and submit the results to KITTI website. The results show as: Car (3D Detection) | 66.01 % | 64.26 % | 61.65 % Pedestrian (3D Detection) | 35.58 % | 29.18 % | 27.36 % Cyclist (3D Detection) | 51.01 % | 42.79 % | 39.31 % Compared with mmlab-PVRCNN model on KITTI leaderboard, it drops almost 10~20 mAP. Any answer to this question?

JLIN77 avatar Sep 20 '22 09:09 JLIN77