honeytidy

I tried it again, and it seemed all right. But it doesn't seem to work well with my test image. I paste the result for Replicate demo: >  >...

I had the same problem.

Yes, I do. infer box first and then run fusion. But I did this on my windows and cpu model. Do it matter. And I as you can see that...

I used the `small_world_rand` method. This is my code: ``` import numpy as np n_neighbors = 10 index_data = np.loadtxt('test_data.txt', delimiter=',') query_data = index_data[:5] import nmslib_vector print "build index" query_time_param...

OK, I got it. Thank you, @searchivarius.