Possible bug in k reciprocal computation

[bdalal]

Hi,
I think I may have found a bug in the k reciprocal computation.

Based on the implementation from the original author https://github.com/zhunzhong07/person-re-ranking/blob/c11b3514114cbffc70588decda48c958fc965f5a/python-version/re_ranking_feature#L49 the re ranking function expects the actual distance which is then squared to get squared distance.

In your implementation, the _cal_dis function returns the squared distance not the actual distance.

PyRetri/pyretri/index/re_ranker/re_ranker_impl/k_reciprocal.py

Line 51 in 402cb98

return dis

In this case, I don't believe that there's a need to square it again here

PyRetri/pyretri/index/re_ranker/re_ranker_impl/k_reciprocal.py

Line 65 in 402cb98

original_dist = np.power(original_dist, 2).astype(np.float32)

In my own implementation, I removed this line and it improved my performance by 1% pts across all my metrics.

Thank you for the great work!

P.S. Implementing my suggestion in #14 can fix this issue without having to remove the squaring operation

[hby96]

Thanks for you suggestions! I will fix it in the next version.