different evaluation resullts

[bei181]

Hello, your work is awesome.
But, when I evaluate your model, I get different results from you.

Your results:

Mine:
category | num_preds | num_gts | AP@0.5 | AP@1.0 | AP@1.5 | AP |
ped_crossing | 54856 | 9517 | 0.0585 | 0.3891 | 0.649 | 0.3655 |
divider | 56501 | 23546 | 0.3467 | 0.538 | 0.6338 | 0.5062 |
boundary | 56607 | 14498 | 0.1417 | 0.4599 | 0.6657 | 0.4225 |
+--------------+-----------+---------+--------+--------+--------+--------+
mAP = 0.4314

In addtiton, I evaluate on the validation set.

[yuantianyuan01]

Did you train the baseline model again? Or just using the provided checkpoint?