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