Request GPU version of re_rank function

[jpainam]

Hi!
When using multi query evaluation in Market1501, this

 original_dist = np.concatenate(
      [np.concatenate([q_q_dist, q_g_dist], axis=1),
       np.concatenate([q_g_dist.T, g_g_dist], axis=1)],
      axis=0)

shows MemoryError even in a 32GB memory window PC. This line of code should run on the GPU
Kindly provide a re_rank_gpu version of this function for very large evaluation
Thank you

[PayneYong]

Hi!
Have you solved it out?
I met the Memory Error too.

[jpainam]

No, i didn't solve. I decided not to include re-ranking at all since the author of the implementation rarely replies

[PayneYong]

OK