evaluation code

[kargarisaac]

Hi, I tested the pre-trained model on first 200 sample of kitti dataset but the results are not good: Car [email protected], 0.70, 0.70: bbox AP:0.01, 0.03, 0.04 bev AP:0.02, 0.01, 0.01 3d AP:0.01, 0.01, 0.01 aos AP:0.01, 0.02, 0.02 Car [email protected], 0.50, 0.50: bbox AP:0.01, 0.03, 0.04 bev AP:0.02, 0.01, 0.01 3d AP:0.01, 0.01, 0.01 aos AP:0.01, 0.02, 0.02

Car coco [email protected]:0.05:0.95: bbox AP:0.13, 0.19, 0.22 bev AP:0.01, 0.01, 0.01 3d AP:0.01, 0.00, 0.00 aos AP:0.07, 0.10, 0.11

I saw the get_mAP_v2 code. There is 11 in denominator. What is it? Is there anything that I need to change?

def get_mAP_v2(prec): sums = 0 for i in range(0, prec.shape[-1], 4): sums = sums + prec[..., i] return sums / 11 * 100