Open linQian99 opened 4 months ago
Hi @linQian99 , It's just the feature of mAP metric. It doesn't decrease if you predict more objects with very low confidences. It is also correct for 2d detection.
Thank you for your reply, but if the confidence threshold set to 0.01, the visualization result will shows a lot of bounding boxes, is that normal?
Yes, for visualization something like 0.3 should be fine.
I hope this message finds you well. Thank you for your great work. May I ask why changing the score_thr in config file will affect the performance result? Thank you for your time.
This is 0.30 threshold
This is 0.01 threshold