Rank 1, 5, 10 are high, but mAP is low

[InstantWindy]

Hi. I use this code to train my own dataset, and when I train this model many times and then test them separately, some of them have high rank values but low mAP values. What is the reason? Thank.

[huanghoujing]

Hi, mAP is obviously, and sometimes significantly, lower than Rank-1, which is normal. mAP is a harder criterion than Rank-1. mAP measures the overall ranking accuracy of all positive samples in the gallery set, while Rank-1 only considers whether the top-1 returned sample is positive or not.