KITTI evaluation results don't match with values mentioned in the paper

[Shubhendu-Jena]

trafficstars

Hi,

It seems the using the preprocessed data and KITTI evaluation scripts you included a few days ago, I am not getting the same values as in the paper. Am I doing something wrong? I've tried with models both trained from scratch as well as the pre-trained model given by you and I've used both cases when RGB values are used and when (R,G,B) = (0,0,0). Please let me know what might be the cause of this discrepancy.

Best Regards