search

qcraftai / pillarnext

PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds (CVPR 2023)
Other
176 stars 13 forks source link

Questions about Waymo val set results #5

Closed StiphyJay closed 11 months ago

StiphyJay commented 11 months ago

Thanks for your great work! I have one question. In your paper, the performance of PillarNeXt-B model in one frame setting on Waymo val set is: 69.8 L2 mAPH in vehicle class

image

However, in your github, this performance is 67.8 L2 mAPH, which one is the right results?

Konstantin5389 commented 11 months ago

Thanks for your question! It's a typo. We have revised README. The paper results are correct.