prclibo/kitti_eval

2D AP vs COCO AP

Opened this issue · 0 comments

Hi, I would expect the 2D AP to be somewhat close to the value I get when I evaluate it with COCO evaluation script.
Kitti 2D (iou=0.5) AP: 35.7
COCO AP(iou=0.5) : 56.5

Any idea why there is a disparity?