copying files to /scratch...
starting benchmark...
/scratch/knn/venv/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
running only kgraph
order: [Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 2, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 1, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 50, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 20, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 100, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 10, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 40, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 4, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 90, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 3, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 70, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 80, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 5, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 30, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 60, {'reverse': -1}, False])]
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 2, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 2, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0 accuracy: 2.29356 cost: 0.00038 M: 10 delta: 1 time: 54.3312 one-recall: 0 one-ratio: 3.52528
iteration: 2 recall: 0.004 accuracy: 1.20332 cost: 0.000637428 M: 10 delta: 0.856032 time: 92.4778 one-recall: 0 one-ratio: 2.78298
iteration: 3 recall: 0.0276 accuracy: 0.674478 cost: 0.00109521 M: 11.5287 delta: 0.835105 time: 138.686 one-recall: 0.03 one-ratio: 2.30487
iteration: 4 recall: 0.1804 accuracy: 0.313238 cost: 0.00163043 M: 11.8364 delta: 0.783443 time: 184.439 one-recall: 0.21 one-ratio: 1.82894
iteration: 5 recall: 0.4868 accuracy: 0.121046 cost: 0.00223612 M: 12.6038 delta: 0.664615 time: 231.912 one-recall: 0.6 one-ratio: 1.34572
iteration: 6 recall: 0.7564 accuracy: 0.03077 cost: 0.00297993 M: 15.114 delta: 0.432357 time: 285.474 one-recall: 0.9 one-ratio: 1.05903
iteration: 7 recall: 0.8824 accuracy: 0.0110308 cost: 0.00395537 M: 21.1402 delta: 0.196426 time: 346.462 one-recall: 0.96 one-ratio: 1.02932
iteration: 8 recall: 0.938 accuracy: 0.00400482 cost: 0.00497983 M: 27.3045 delta: 0.0885137 time: 403.41 one-recall: 1 one-ratio: 1
iteration: 9 recall: 0.9644 accuracy: 0.00221739 cost: 0.00577293 M: 31.2904 delta: 0.0514019 time: 446.779 one-recall: 1 one-ratio: 1
iteration: 10 recall: 0.9764 accuracy: 0.0012952 cost: 0.00625843 M: 33.3974 delta: 0.0372226 time: 475.935 one-recall: 1 one-ratio: 1
iteration: 11 recall: 0.984 accuracy: 0.000915513 cost: 0.00651572 M: 34.4268 delta: 0.0313604 time: 494.865 one-recall: 1 one-ratio: 1
iteration: 12 recall: 0.9872 accuracy: 0.000651871 cost: 0.00664321 M: 34.9174 delta: 0.028787 time: 507.543 one-recall: 1 one-ratio: 1
iteration: 13 recall: 0.9876 accuracy: 0.000628894 cost: 0.00670536 M: 35.1523 delta: 0.027629 time: 516.706 one-recall: 1 one-ratio: 1
iteration: 14 recall: 0.9876 accuracy: 0.000628894 cost: 0.00673551 M: 35.2647 delta: 0.0270893 time: 523.962 one-recall: 1 one-ratio: 1
iteration: 15 recall: 0.9876 accuracy: 0.000628894 cost: 0.00675029 M: 35.3194 delta: 0.0268326 time: 530.247 one-recall: 1 one-ratio: 1
iteration: 16 recall: 0.9876 accuracy: 0.000628894 cost: 0.00675777 M: 35.3471 delta: 0.0267076 time: 536.044 one-recall: 1 one-ratio: 1
iteration: 17 recall: 0.9876 accuracy: 0.000628894 cost: 0.00676154 M: 35.3608 delta: 0.0266443 time: 541.579 one-recall: 1 one-ratio: 1
iteration: 18 recall: 0.9876 accuracy: 0.000628894 cost: 0.00676338 M: 35.3677 delta: 0.0266122 time: 546.969 one-recall: 1 one-ratio: 1
iteration: 19 recall: 0.9876 accuracy: 0.000628894 cost: 0.00676433 M: 35.3712 delta: 0.0265977 time: 552.287 one-recall: 1 one-ratio: 1
iteration: 20 recall: 0.9876 accuracy: 0.000628894 cost: 0.00676485 M: 35.373 delta: 0.02659 time: 557.564 one-recall: 1 one-ratio: 1
iteration: 21 recall: 0.988 accuracy: 0.0006087 cost: 0.00676515 M: 35.3742 delta: 0.0265857 time: 562.82 one-recall: 1 one-ratio: 1
iteration: 22 recall: 0.988 accuracy: 0.0006087 cost: 0.00676532 M: 35.3749 delta: 0.0265828 time: 568.066 one-recall: 1 one-ratio: 1
iteration: 23 recall: 0.988 accuracy: 0.0006087 cost: 0.00676541 M: 35.3753 delta: 0.0265811 time: 573.3 one-recall: 1 one-ratio: 1
iteration: 24 recall: 0.988 accuracy: 0.0006087 cost: 0.00676547 M: 35.3755 delta: 0.0265798 time: 578.527 one-recall: 1 one-ratio: 1
iteration: 25 recall: 0.988 accuracy: 0.0006087 cost: 0.00676549 M: 35.3756 delta: 0.0265796 time: 583.753 one-recall: 1 one-ratio: 1
iteration: 26 recall: 0.988 accuracy: 0.0006087 cost: 0.00676551 M: 35.3757 delta: 0.0265794 time: 588.977 one-recall: 1 one-ratio: 1
iteration: 27 recall: 0.988 accuracy: 0.0006087 cost: 0.00676552 M: 35.3757 delta: 0.0265791 time: 594.196 one-recall: 1 one-ratio: 1
iteration: 28 recall: 0.988 accuracy: 0.0006087 cost: 0.00676553 M: 35.3757 delta: 0.0265791 time: 599.415 one-recall: 1 one-ratio: 1
iteration: 29 recall: 0.988 accuracy: 0.0006087 cost: 0.00676553 M: 35.3757 delta: 0.026579 time: 604.632 one-recall: 1 one-ratio: 1
iteration: 30 recall: 0.988 accuracy: 0.0006087 cost: 0.00676553 M: 35.3757 delta: 0.026579 time: 609.85 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 624.37
Index size:  1903140.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.1056985000
  Testing...
|S| = 80
|T| = 1152
Reject!
419.166 < 493.978
  -> Decision False in time 0.0200000000, query time of that 0.0051848360, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Reject!
338.12 < 463.103
  -> Decision False in time 0.0000000000, query time of that 0.0001758160, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Reject!
411.272 < 451.876
  -> Decision False in time 0.0000000000, query time of that 0.0004923370, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Reject!
371.934 < 470.431
  -> Decision False in time 0.1100000000, query time of that 0.0037174500, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Reject!
339.759 < 439.057
  -> Decision False in time 0.0400000000, query time of that 0.0015993850, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
471.151 < 488.438
  -> Decision False in time 0.0300000000, query time of that 0.0012802430, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Reject!
441.396 < 455.485
  -> Decision False in time 1.5000000000, query time of that 0.0056921750, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
384.375 < 399.144
  -> Decision False in time 1.7400000000, query time of that 0.0072223960, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
435.38 < 444.073
  -> Decision False in time 0.0900000000, query time of that 0.0006122320, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 1, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 1, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0 accuracy: 2.6766 cost: 0.00038 M: 10 delta: 1 time: 53.8413 one-recall: 0 one-ratio: 3.66072
iteration: 2 recall: 0.0016 accuracy: 1.38091 cost: 0.000637428 M: 10 delta: 0.856032 time: 91.9359 one-recall: 0 one-ratio: 2.8624
iteration: 3 recall: 0.0388 accuracy: 0.711342 cost: 0.00109521 M: 11.5287 delta: 0.835102 time: 138.087 one-recall: 0.04 one-ratio: 2.27853
iteration: 4 recall: 0.2128 accuracy: 0.331692 cost: 0.00163043 M: 11.8362 delta: 0.783466 time: 183.823 one-recall: 0.31 one-ratio: 1.61045
iteration: 5 recall: 0.5252 accuracy: 0.113966 cost: 0.00223606 M: 12.6037 delta: 0.664581 time: 231.319 one-recall: 0.65 one-ratio: 1.31249
iteration: 6 recall: 0.7808 accuracy: 0.0321567 cost: 0.00298004 M: 15.1148 delta: 0.432336 time: 284.945 one-recall: 0.89 one-ratio: 1.10787
iteration: 7 recall: 0.8984 accuracy: 0.00889378 cost: 0.00395541 M: 21.1397 delta: 0.196458 time: 346.014 one-recall: 0.98 one-ratio: 1.00852
iteration: 8 recall: 0.9532 accuracy: 0.00261054 cost: 0.00498005 M: 27.3053 delta: 0.0884561 time: 403.009 one-recall: 1 one-ratio: 1
iteration: 9 recall: 0.97 accuracy: 0.00153751 cost: 0.00577336 M: 31.2902 delta: 0.0513331 time: 446.385 one-recall: 1 one-ratio: 1
iteration: 10 recall: 0.978 accuracy: 0.00108745 cost: 0.00625831 M: 33.3952 delta: 0.0371841 time: 475.517 one-recall: 1 one-ratio: 1
iteration: 11 recall: 0.9816 accuracy: 0.000822769 cost: 0.00651495 M: 34.422 delta: 0.0313218 time: 494.401 one-recall: 1 one-ratio: 1
iteration: 12 recall: 0.9856 accuracy: 0.000634549 cost: 0.00664356 M: 34.9169 delta: 0.0287556 time: 507.12 one-recall: 1 one-ratio: 1
iteration: 13 recall: 0.9868 accuracy: 0.000578651 cost: 0.00670598 M: 35.1529 delta: 0.027595 time: 516.289 one-recall: 1 one-ratio: 1
iteration: 14 recall: 0.9876 accuracy: 0.000568954 cost: 0.00673627 M: 35.2664 delta: 0.0270435 time: 523.564 one-recall: 1 one-ratio: 1
iteration: 15 recall: 0.9876 accuracy: 0.000568954 cost: 0.00675099 M: 35.3217 delta: 0.0267899 time: 529.846 one-recall: 1 one-ratio: 1
iteration: 16 recall: 0.9876 accuracy: 0.000568954 cost: 0.0067584 M: 35.3495 delta: 0.0266568 time: 535.637 one-recall: 1 one-ratio: 1
iteration: 17 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676207 M: 35.3629 delta: 0.0265947 time: 541.161 one-recall: 1 one-ratio: 1
iteration: 18 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676399 M: 35.37 delta: 0.0265678 time: 546.554 one-recall: 1 one-ratio: 1
iteration: 19 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676502 M: 35.3739 delta: 0.0265497 time: 551.874 one-recall: 1 one-ratio: 1
iteration: 20 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676557 M: 35.376 delta: 0.026542 time: 557.152 one-recall: 1 one-ratio: 1
iteration: 21 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676589 M: 35.3772 delta: 0.026538 time: 562.408 one-recall: 1 one-ratio: 1
iteration: 22 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676609 M: 35.378 delta: 0.0265349 time: 567.66 one-recall: 1 one-ratio: 1
iteration: 23 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676619 M: 35.3784 delta: 0.0265336 time: 572.892 one-recall: 1 one-ratio: 1
iteration: 24 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676626 M: 35.3787 delta: 0.0265323 time: 578.122 one-recall: 1 one-ratio: 1
iteration: 25 recall: 0.9876 accuracy: 0.000568954 cost: 0.0067663 M: 35.3789 delta: 0.026532 time: 583.344 one-recall: 1 one-ratio: 1
iteration: 26 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676631 M: 35.3789 delta: 0.0265317 time: 588.561 one-recall: 1 one-ratio: 1
iteration: 27 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676632 M: 35.379 delta: 0.0265314 time: 593.777 one-recall: 1 one-ratio: 1
iteration: 28 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676632 M: 35.379 delta: 0.0265314 time: 598.993 one-recall: 1 one-ratio: 1
iteration: 29 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676633 M: 35.379 delta: 0.0265313 time: 604.207 one-recall: 1 one-ratio: 1
iteration: 30 recall: 0.9876 accuracy: 0.000568954 cost: 0.00676633 M: 35.379 delta: 0.0265314 time: 609.424 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 623.8900000000001
Index size:  260980.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.1023433000
  Testing...
|S| = 80
|T| = 1152
Reject!
339.063 < 464.262
  -> Decision False in time 0.0000000000, query time of that 0.0002024850, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Reject!
440.543 < 445.252
  -> Decision False in time 0.0000000000, query time of that 0.0008893970, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Reject!
495.148 < 497.065
  -> Decision False in time 0.0100000000, query time of that 0.0022321000, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Reject!
377.811 < 406.666
  -> Decision False in time 0.1100000000, query time of that 0.0037644550, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Reject!
387.787 < 443.736
  -> Decision False in time 0.0000000000, query time of that 0.0002435540, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
412.29 < 429.976
  -> Decision False in time 0.0200000000, query time of that 0.0007829820, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Reject!
264.766 < 271.415
  -> Decision False in time 0.8000000000, query time of that 0.0028673900, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
395.264 < 462.5
  -> Decision False in time 0.6700000000, query time of that 0.0027579300, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
358.056 < 429.388
  -> Decision False in time 0.0000000000, query time of that 0.0001692110, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 50, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 50, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0.0008 accuracy: 2.48177 cost: 0.00038 M: 10 delta: 1 time: 53.8724 one-recall: 0 one-ratio: 3.57151
iteration: 2 recall: 0.006 accuracy: 1.20232 cost: 0.000637428 M: 10 delta: 0.856032 time: 91.9802 one-recall: 0.01 one-ratio: 2.71347
iteration: 3 recall: 0.0428 accuracy: 0.621878 cost: 0.00109521 M: 11.5287 delta: 0.835103 time: 138.123 one-recall: 0.06 one-ratio: 2.24598
iteration: 4 recall: 0.2128 accuracy: 0.290189 cost: 0.00163045 M: 11.8363 delta: 0.783464 time: 183.863 one-recall: 0.26 one-ratio: 1.81407
iteration: 5 recall: 0.5444 accuracy: 0.114619 cost: 0.00223604 M: 12.6037 delta: 0.664599 time: 231.335 one-recall: 0.61 one-ratio: 1.37506
iteration: 6 recall: 0.7952 accuracy: 0.0249012 cost: 0.00297982 M: 15.1143 delta: 0.432325 time: 284.925 one-recall: 0.91 one-ratio: 1.08532
iteration: 7 recall: 0.906 accuracy: 0.00733108 cost: 0.00395503 M: 21.1391 delta: 0.196401 time: 345.947 one-recall: 0.98 one-ratio: 1.00751
iteration: 8 recall: 0.9524 accuracy: 0.0028175 cost: 0.00497976 M: 27.3062 delta: 0.0884487 time: 402.925 one-recall: 0.99 one-ratio: 1.00262
iteration: 9 recall: 0.9672 accuracy: 0.00177927 cost: 0.00577206 M: 31.2885 delta: 0.0513769 time: 446.267 one-recall: 0.99 one-ratio: 1.00262
iteration: 10 recall: 0.9756 accuracy: 0.00118986 cost: 0.00625738 M: 33.3953 delta: 0.037235 time: 475.422 one-recall: 0.99 one-ratio: 1.00262
iteration: 11 recall: 0.9776 accuracy: 0.00103341 cost: 0.00651547 M: 34.4285 delta: 0.0313111 time: 494.371 one-recall: 0.99 one-ratio: 1.00262
iteration: 12 recall: 0.98 accuracy: 0.00090889 cost: 0.00664324 M: 34.9202 delta: 0.0287412 time: 507.056 one-recall: 0.99 one-ratio: 1.00262
iteration: 13 recall: 0.9804 accuracy: 0.000905174 cost: 0.00670538 M: 35.1542 delta: 0.0275694 time: 516.21 one-recall: 0.99 one-ratio: 1.00262
iteration: 14 recall: 0.9808 accuracy: 0.00088451 cost: 0.00673527 M: 35.2657 delta: 0.0270449 time: 523.455 one-recall: 0.99 one-ratio: 1.00262
iteration: 15 recall: 0.9812 accuracy: 0.000864632 cost: 0.00674995 M: 35.3209 delta: 0.0267893 time: 529.732 one-recall: 0.99 one-ratio: 1.00262
iteration: 16 recall: 0.9812 accuracy: 0.000864632 cost: 0.0067575 M: 35.3491 delta: 0.0266618 time: 535.532 one-recall: 0.99 one-ratio: 1.00262
iteration: 17 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676138 M: 35.3634 delta: 0.0265954 time: 541.079 one-recall: 0.99 one-ratio: 1.00262
iteration: 18 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676333 M: 35.3707 delta: 0.0265682 time: 546.478 one-recall: 0.99 one-ratio: 1.00262
iteration: 19 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676441 M: 35.3747 delta: 0.0265468 time: 551.804 one-recall: 0.99 one-ratio: 1.00262
iteration: 20 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676491 M: 35.3766 delta: 0.0265395 time: 557.084 one-recall: 0.99 one-ratio: 1.00262
iteration: 21 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676518 M: 35.3777 delta: 0.0265346 time: 562.341 one-recall: 0.99 one-ratio: 1.00262
iteration: 22 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676533 M: 35.3783 delta: 0.0265334 time: 567.584 one-recall: 0.99 one-ratio: 1.00262
iteration: 23 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676543 M: 35.3786 delta: 0.0265323 time: 572.823 one-recall: 0.99 one-ratio: 1.00262
iteration: 24 recall: 0.9812 accuracy: 0.000864632 cost: 0.0067655 M: 35.3789 delta: 0.0265312 time: 578.051 one-recall: 0.99 one-ratio: 1.00262
iteration: 25 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676553 M: 35.379 delta: 0.0265308 time: 583.281 one-recall: 0.99 one-ratio: 1.00262
iteration: 26 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676556 M: 35.3791 delta: 0.0265303 time: 588.508 one-recall: 0.99 one-ratio: 1.00262
iteration: 27 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676557 M: 35.3791 delta: 0.0265304 time: 593.726 one-recall: 0.99 one-ratio: 1.00262
iteration: 28 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676558 M: 35.3792 delta: 0.0265302 time: 598.95 one-recall: 0.99 one-ratio: 1.00262
iteration: 29 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676559 M: 35.3792 delta: 0.02653 time: 604.167 one-recall: 0.99 one-ratio: 1.00262
iteration: 30 recall: 0.9812 accuracy: 0.000864632 cost: 0.00676559 M: 35.3792 delta: 0.02653 time: 609.388 one-recall: 0.99 one-ratio: 1.00262
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 623.8499999999999
Index size:  262916.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0049920000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.0900000000, query time of that 0.0401261910, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Reject!
265.53 < 265.992
  -> Decision False in time 0.0300000000, query time of that 0.0150466670, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Accept!
  -> Decision True in time 8.7100000000, query time of that 4.1403255900, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.5700000000, query time of that 0.0525483590, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Reject!
280.728 < 286.665
  -> Decision False in time 0.6600000000, query time of that 0.0580968800, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
267.696 < 271.192
  -> Decision False in time 9.9600000000, query time of that 0.8960155030, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Reject!
216.799 < 219.789
  -> Decision False in time 2.2700000000, query time of that 0.0205258790, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
265.281 < 271.312
  -> Decision False in time 15.1900000000, query time of that 0.1319222530, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
274.173 < 276.138
  -> Decision False in time 26.6600000000, query time of that 0.2297504530, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 20, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 20, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0.0008 accuracy: 2.75563 cost: 0.00038 M: 10 delta: 1 time: 53.9039 one-recall: 0 one-ratio: 3.20375
iteration: 2 recall: 0.0036 accuracy: 1.28835 cost: 0.000637428 M: 10 delta: 0.856032 time: 92.0189 one-recall: 0.01 one-ratio: 2.58347
iteration: 3 recall: 0.036 accuracy: 0.648029 cost: 0.00109521 M: 11.5287 delta: 0.835107 time: 138.167 one-recall: 0.04 one-ratio: 2.18955
iteration: 4 recall: 0.188 accuracy: 0.300992 cost: 0.00163043 M: 11.8362 delta: 0.783461 time: 183.917 one-recall: 0.15 one-ratio: 1.72886
iteration: 5 recall: 0.4924 accuracy: 0.113896 cost: 0.00223606 M: 12.6036 delta: 0.664592 time: 231.396 one-recall: 0.55 one-ratio: 1.31529
iteration: 6 recall: 0.7456 accuracy: 0.0314581 cost: 0.00297998 M: 15.1149 delta: 0.432378 time: 285.003 one-recall: 0.82 one-ratio: 1.08068
iteration: 7 recall: 0.8684 accuracy: 0.0105535 cost: 0.00395522 M: 21.14 delta: 0.196418 time: 346.02 one-recall: 0.94 one-ratio: 1.01691
iteration: 8 recall: 0.9216 accuracy: 0.00568255 cost: 0.00497947 M: 27.3028 delta: 0.0884904 time: 403.013 one-recall: 0.97 one-ratio: 1.01391
iteration: 9 recall: 0.946399 accuracy: 0.00305373 cost: 0.00577227 M: 31.2875 delta: 0.0513959 time: 446.416 one-recall: 0.99 one-ratio: 1.00022
iteration: 10 recall: 0.9592 accuracy: 0.00227624 cost: 0.00625728 M: 33.3919 delta: 0.037263 time: 475.591 one-recall: 0.99 one-ratio: 1.00022
iteration: 11 recall: 0.9636 accuracy: 0.00198314 cost: 0.0065148 M: 34.4241 delta: 0.0313624 time: 494.556 one-recall: 0.99 one-ratio: 1.00022
iteration: 12 recall: 0.9664 accuracy: 0.00188015 cost: 0.00664244 M: 34.915 delta: 0.0287966 time: 507.276 one-recall: 0.99 one-ratio: 1.00022
iteration: 13 recall: 0.968 accuracy: 0.00180967 cost: 0.00670487 M: 35.1507 delta: 0.0276333 time: 516.493 one-recall: 0.99 one-ratio: 1.00022
iteration: 14 recall: 0.968 accuracy: 0.00180967 cost: 0.0067355 M: 35.265 delta: 0.0270726 time: 523.833 one-recall: 0.99 one-ratio: 1.00022
iteration: 15 recall: 0.9684 accuracy: 0.00179651 cost: 0.00675002 M: 35.3195 delta: 0.0268201 time: 530.149 one-recall: 0.99 one-ratio: 1.00022
iteration: 16 recall: 0.9684 accuracy: 0.00179651 cost: 0.00675759 M: 35.348 delta: 0.0266932 time: 535.993 one-recall: 0.99 one-ratio: 1.00022
iteration: 17 recall: 0.9684 accuracy: 0.00179651 cost: 0.0067614 M: 35.3622 delta: 0.0266311 time: 541.575 one-recall: 0.99 one-ratio: 1.00022
iteration: 18 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676343 M: 35.3695 delta: 0.0265962 time: 547.02 one-recall: 0.99 one-ratio: 1.00022
iteration: 19 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676447 M: 35.3733 delta: 0.026579 time: 552.388 one-recall: 0.99 one-ratio: 1.00022
iteration: 20 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676499 M: 35.3754 delta: 0.02657 time: 557.714 one-recall: 0.99 one-ratio: 1.00022
iteration: 21 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676527 M: 35.3765 delta: 0.0265662 time: 563.012 one-recall: 0.99 one-ratio: 1.00022
iteration: 22 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676542 M: 35.377 delta: 0.0265642 time: 568.301 one-recall: 0.99 one-ratio: 1.00022
iteration: 23 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676549 M: 35.3773 delta: 0.0265634 time: 573.577 one-recall: 0.99 one-ratio: 1.00022
iteration: 24 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676554 M: 35.3776 delta: 0.0265626 time: 578.847 one-recall: 0.99 one-ratio: 1.00022
iteration: 25 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676558 M: 35.3777 delta: 0.0265618 time: 584.116 one-recall: 0.99 one-ratio: 1.00022
iteration: 26 recall: 0.9684 accuracy: 0.00179651 cost: 0.0067656 M: 35.3778 delta: 0.0265612 time: 589.379 one-recall: 0.99 one-ratio: 1.00022
iteration: 27 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676561 M: 35.3778 delta: 0.026561 time: 594.64 one-recall: 0.99 one-ratio: 1.00022
iteration: 28 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676561 M: 35.3778 delta: 0.0265611 time: 599.898 one-recall: 0.99 one-ratio: 1.00022
iteration: 29 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676562 M: 35.3779 delta: 0.0265612 time: 605.16 one-recall: 0.99 one-ratio: 1.00022
iteration: 30 recall: 0.9684 accuracy: 0.00179651 cost: 0.00676562 M: 35.3779 delta: 0.0265612 time: 610.421 one-recall: 0.99 one-ratio: 1.00022
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 624.9299999999998
Index size:  207376.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0091267000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.0800000000, query time of that 0.0267762760, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Accept!
  -> Decision True in time 0.6900000000, query time of that 0.2461572120, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Reject!
389.61 < 401.503
  -> Decision False in time 0.6500000000, query time of that 0.2233606210, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.5300000000, query time of that 0.0284854400, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Accept!
  -> Decision True in time 5.2800000000, query time of that 0.2970828740, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
266.224 < 271.312
  -> Decision False in time 2.3400000000, query time of that 0.1316787630, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Reject!
342.87 < 345.842
  -> Decision False in time 1.0400000000, query time of that 0.0061996710, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
338.495 < 340.212
  -> Decision False in time 7.8000000000, query time of that 0.0422266200, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
244.645 < 245.182
  -> Decision False in time 2.7900000000, query time of that 0.0160117600, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 100, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 100, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0 accuracy: 2.03905 cost: 0.00038 M: 10 delta: 1 time: 53.8726 one-recall: 0 one-ratio: 3.50509
iteration: 2 recall: 0.0016 accuracy: 1.2245 cost: 0.000637428 M: 10 delta: 0.856032 time: 91.9655 one-recall: 0.02 one-ratio: 2.81961
iteration: 3 recall: 0.03 accuracy: 0.698027 cost: 0.00109521 M: 11.5287 delta: 0.835104 time: 138.09 one-recall: 0.08 one-ratio: 2.20535
iteration: 4 recall: 0.1696 accuracy: 0.32534 cost: 0.00163042 M: 11.8363 delta: 0.783447 time: 183.833 one-recall: 0.25 one-ratio: 1.76601
iteration: 5 recall: 0.4944 accuracy: 0.112812 cost: 0.00223605 M: 12.6037 delta: 0.664586 time: 231.296 one-recall: 0.64 one-ratio: 1.28751
iteration: 6 recall: 0.76 accuracy: 0.0301802 cost: 0.00297996 M: 15.1147 delta: 0.432367 time: 284.887 one-recall: 0.9 one-ratio: 1.0583
iteration: 7 recall: 0.8912 accuracy: 0.00948924 cost: 0.00395534 M: 21.1392 delta: 0.196441 time: 345.902 one-recall: 0.98 one-ratio: 1.00825
iteration: 8 recall: 0.9416 accuracy: 0.00397501 cost: 0.0049798 M: 27.3032 delta: 0.0884807 time: 402.905 one-recall: 0.98 one-ratio: 1.00825
iteration: 9 recall: 0.9652 accuracy: 0.00227812 cost: 0.00577239 M: 31.2878 delta: 0.0513368 time: 446.278 one-recall: 0.98 one-ratio: 1.00825
iteration: 10 recall: 0.976 accuracy: 0.00128789 cost: 0.00625729 M: 33.3915 delta: 0.0372015 time: 475.418 one-recall: 0.99 one-ratio: 1.00143
iteration: 11 recall: 0.9784 accuracy: 0.00120828 cost: 0.00651447 M: 34.4227 delta: 0.0312981 time: 494.332 one-recall: 0.99 one-ratio: 1.00143
iteration: 12 recall: 0.9796 accuracy: 0.00117427 cost: 0.00664218 M: 34.9145 delta: 0.0287457 time: 507.016 one-recall: 0.99 one-ratio: 1.00143
iteration: 13 recall: 0.9796 accuracy: 0.00117427 cost: 0.00670446 M: 35.1499 delta: 0.0275821 time: 516.202 one-recall: 0.99 one-ratio: 1.00143
iteration: 14 recall: 0.9808 accuracy: 0.00113585 cost: 0.00673457 M: 35.2627 delta: 0.0270418 time: 523.473 one-recall: 0.99 one-ratio: 1.00143
iteration: 15 recall: 0.9808 accuracy: 0.00113585 cost: 0.00674959 M: 35.3192 delta: 0.0267804 time: 529.779 one-recall: 0.99 one-ratio: 1.00143
iteration: 16 recall: 0.9808 accuracy: 0.00113585 cost: 0.00675751 M: 35.3488 delta: 0.0266439 time: 535.603 one-recall: 0.99 one-ratio: 1.00143
iteration: 17 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676138 M: 35.363 delta: 0.0265777 time: 541.144 one-recall: 0.99 one-ratio: 1.00143
iteration: 18 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676343 M: 35.3706 delta: 0.0265442 time: 546.549 one-recall: 0.99 one-ratio: 1.00143
iteration: 19 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676447 M: 35.3747 delta: 0.0265278 time: 551.873 one-recall: 0.99 one-ratio: 1.00143
iteration: 20 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676507 M: 35.3769 delta: 0.0265189 time: 557.157 one-recall: 0.99 one-ratio: 1.00143
iteration: 21 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676543 M: 35.3784 delta: 0.0265133 time: 562.42 one-recall: 0.99 one-ratio: 1.00143
iteration: 22 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676563 M: 35.3791 delta: 0.0265109 time: 567.665 one-recall: 0.99 one-ratio: 1.00143
iteration: 23 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676574 M: 35.3795 delta: 0.0265096 time: 572.899 one-recall: 0.99 one-ratio: 1.00143
iteration: 24 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676583 M: 35.3798 delta: 0.026508 time: 578.129 one-recall: 0.99 one-ratio: 1.00143
iteration: 25 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676586 M: 35.3799 delta: 0.0265074 time: 583.352 one-recall: 0.99 one-ratio: 1.00143
iteration: 26 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676586 M: 35.3799 delta: 0.0265077 time: 588.575 one-recall: 0.99 one-ratio: 1.00143
iteration: 27 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676587 M: 35.38 delta: 0.0265074 time: 593.796 one-recall: 0.99 one-ratio: 1.00143
iteration: 28 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676588 M: 35.38 delta: 0.0265073 time: 599.011 one-recall: 0.99 one-ratio: 1.00143
iteration: 29 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676588 M: 35.38 delta: 0.0265073 time: 604.233 one-recall: 0.99 one-ratio: 1.00143
iteration: 30 recall: 0.9808 accuracy: 0.00113463 cost: 0.00676589 M: 35.38 delta: 0.0265072 time: 609.448 one-recall: 0.99 one-ratio: 1.00143
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 623.9300000000003
Index size:  207444.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0024532000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.1100000000, query time of that 0.0675824850, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Accept!
  -> Decision True in time 1.1100000000, query time of that 0.6671549560, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Accept!
  -> Decision True in time 11.2900000000, query time of that 6.7048733540, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.6000000000, query time of that 0.0788893210, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Accept!
  -> Decision True in time 5.9000000000, query time of that 0.7730656180, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
298.034 < 335.112
  -> Decision False in time 3.4600000000, query time of that 0.4571829110, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Accept!
  -> Decision True in time 6.6800000000, query time of that 0.0839377150, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
269.793 < 275.131
  -> Decision False in time 24.1400000000, query time of that 0.3330011390, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
278.672 < 281.558
  -> Decision False in time 39.9000000000, query time of that 0.5311671150, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 10, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 10, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0.0008 accuracy: 2.14811 cost: 0.00038 M: 10 delta: 1 time: 53.8782 one-recall: 0 one-ratio: 3.10936
iteration: 2 recall: 0.0052 accuracy: 1.23308 cost: 0.000637428 M: 10 delta: 0.856032 time: 91.9935 one-recall: 0.01 one-ratio: 2.42688
iteration: 3 recall: 0.0292 accuracy: 0.705834 cost: 0.00109521 M: 11.5287 delta: 0.835105 time: 138.12 one-recall: 0.01 one-ratio: 2.00554
iteration: 4 recall: 0.1768 accuracy: 0.334273 cost: 0.00163044 M: 11.8363 delta: 0.783453 time: 183.879 one-recall: 0.17 one-ratio: 1.62459
iteration: 5 recall: 0.5156 accuracy: 0.10198 cost: 0.00223607 M: 12.6036 delta: 0.664584 time: 231.378 one-recall: 0.63 one-ratio: 1.19164
iteration: 6 recall: 0.7772 accuracy: 0.0306228 cost: 0.00297994 M: 15.1142 delta: 0.432359 time: 284.995 one-recall: 0.83 one-ratio: 1.0569
iteration: 7 recall: 0.8956 accuracy: 0.00905348 cost: 0.00395519 M: 21.1395 delta: 0.196402 time: 346.035 one-recall: 0.98 one-ratio: 1.00118
iteration: 8 recall: 0.9404 accuracy: 0.00453322 cost: 0.0049794 M: 27.3024 delta: 0.0884305 time: 403.037 one-recall: 0.98 one-ratio: 1.00118
iteration: 9 recall: 0.9608 accuracy: 0.00270376 cost: 0.0057713 M: 31.2827 delta: 0.0513487 time: 446.376 one-recall: 0.99 one-ratio: 1.00008
iteration: 10 recall: 0.97 accuracy: 0.00214928 cost: 0.00625611 M: 33.3878 delta: 0.0372314 time: 475.528 one-recall: 0.99 one-ratio: 1.00008
iteration: 11 recall: 0.9744 accuracy: 0.00174742 cost: 0.00651375 M: 34.419 delta: 0.0313402 time: 494.475 one-recall: 0.99 one-ratio: 1.00008
iteration: 12 recall: 0.9792 accuracy: 0.00135506 cost: 0.00664167 M: 34.9121 delta: 0.0287548 time: 507.17 one-recall: 0.99 one-ratio: 1.00008
iteration: 13 recall: 0.9804 accuracy: 0.00129821 cost: 0.00670418 M: 35.1482 delta: 0.0276008 time: 516.359 one-recall: 0.99 one-ratio: 1.00008
iteration: 14 recall: 0.9808 accuracy: 0.00128518 cost: 0.00673469 M: 35.2623 delta: 0.0270426 time: 523.667 one-recall: 0.99 one-ratio: 1.00008
iteration: 15 recall: 0.9808 accuracy: 0.00128518 cost: 0.0067496 M: 35.3183 delta: 0.0267806 time: 529.97 one-recall: 0.99 one-ratio: 1.00008
iteration: 16 recall: 0.9808 accuracy: 0.00128518 cost: 0.00675719 M: 35.3463 delta: 0.0266566 time: 535.792 one-recall: 0.99 one-ratio: 1.00008
iteration: 17 recall: 0.9808 accuracy: 0.00128518 cost: 0.0067611 M: 35.3609 delta: 0.0265933 time: 541.367 one-recall: 0.99 one-ratio: 1.00008
iteration: 18 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676306 M: 35.3683 delta: 0.0265598 time: 546.772 one-recall: 0.99 one-ratio: 1.00008
iteration: 19 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676411 M: 35.3721 delta: 0.0265442 time: 552.12 one-recall: 0.99 one-ratio: 1.00008
iteration: 20 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676469 M: 35.3744 delta: 0.0265334 time: 557.412 one-recall: 0.99 one-ratio: 1.00008
iteration: 21 recall: 0.9808 accuracy: 0.00128518 cost: 0.006765 M: 35.3755 delta: 0.0265287 time: 562.701 one-recall: 0.99 one-ratio: 1.00008
iteration: 22 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676518 M: 35.3763 delta: 0.0265254 time: 567.987 one-recall: 0.99 one-ratio: 1.00008
iteration: 23 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676527 M: 35.3766 delta: 0.0265241 time: 573.263 one-recall: 0.99 one-ratio: 1.00008
iteration: 24 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676532 M: 35.3768 delta: 0.0265233 time: 578.533 one-recall: 0.99 one-ratio: 1.00008
iteration: 25 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676534 M: 35.3769 delta: 0.0265231 time: 583.8 one-recall: 0.99 one-ratio: 1.00008
iteration: 26 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676536 M: 35.3771 delta: 0.0265227 time: 589.068 one-recall: 0.99 one-ratio: 1.00008
iteration: 27 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676537 M: 35.3771 delta: 0.0265227 time: 594.33 one-recall: 0.99 one-ratio: 1.00008
iteration: 28 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676537 M: 35.3771 delta: 0.0265225 time: 599.595 one-recall: 0.99 one-ratio: 1.00008
iteration: 29 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676537 M: 35.3771 delta: 0.0265225 time: 604.856 one-recall: 0.99 one-ratio: 1.00008
iteration: 30 recall: 0.9808 accuracy: 0.00128518 cost: 0.00676537 M: 35.3771 delta: 0.0265225 time: 610.119 one-recall: 0.99 one-ratio: 1.00008
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 624.6300000000001
Index size:  207600.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0107911000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.0700000000, query time of that 0.0205835210, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Accept!
  -> Decision True in time 0.6300000000, query time of that 0.1855325310, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Reject!
384.154 < 391.848
  -> Decision False in time 0.0200000000, query time of that 0.0072876590, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.5200000000, query time of that 0.0225377620, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Accept!
  -> Decision True in time 5.1800000000, query time of that 0.2240237590, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
405.646 < 420.617
  -> Decision False in time 3.0400000000, query time of that 0.1347824140, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Reject!
235.754 < 237.619
  -> Decision False in time 4.1500000000, query time of that 0.0175805640, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
239.424 < 244.992
  -> Decision False in time 7.7600000000, query time of that 0.0340861340, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
306.296 < 308.647
  -> Decision False in time 0.1200000000, query time of that 0.0007476200, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 40, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 40, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0 accuracy: 2.11941 cost: 0.00038 M: 10 delta: 1 time: 53.8881 one-recall: 0 one-ratio: 3.37156
iteration: 2 recall: 0.0048 accuracy: 1.0806 cost: 0.000637428 M: 10 delta: 0.856032 time: 91.9793 one-recall: 0 one-ratio: 2.6793
iteration: 3 recall: 0.036 accuracy: 0.612256 cost: 0.00109521 M: 11.5287 delta: 0.835105 time: 138.107 one-recall: 0.04 one-ratio: 2.20943
iteration: 4 recall: 0.1824 accuracy: 0.315975 cost: 0.00163045 M: 11.8363 delta: 0.783468 time: 183.847 one-recall: 0.24 one-ratio: 1.73318
iteration: 5 recall: 0.4848 accuracy: 0.105715 cost: 0.00223604 M: 12.6035 delta: 0.664575 time: 231.301 one-recall: 0.6 one-ratio: 1.27309
iteration: 6 recall: 0.7536 accuracy: 0.0275927 cost: 0.00297994 M: 15.1148 delta: 0.432332 time: 284.879 one-recall: 0.91 one-ratio: 1.0545
iteration: 7 recall: 0.885599 accuracy: 0.00917485 cost: 0.0039555 M: 21.1425 delta: 0.196393 time: 345.891 one-recall: 0.97 one-ratio: 1.01924
iteration: 8 recall: 0.9312 accuracy: 0.00537238 cost: 0.00498001 M: 27.3061 delta: 0.0884293 time: 402.89 one-recall: 0.97 one-ratio: 1.01924
iteration: 9 recall: 0.9548 accuracy: 0.00286568 cost: 0.00577355 M: 31.2905 delta: 0.0513094 time: 446.271 one-recall: 1 one-ratio: 1
iteration: 10 recall: 0.964 accuracy: 0.00181918 cost: 0.00625834 M: 33.392 delta: 0.0371779 time: 475.408 one-recall: 1 one-ratio: 1
iteration: 11 recall: 0.9688 accuracy: 0.0014924 cost: 0.0065157 M: 34.4222 delta: 0.0312949 time: 494.326 one-recall: 1 one-ratio: 1
iteration: 12 recall: 0.972 accuracy: 0.00132756 cost: 0.0066432 M: 34.9136 delta: 0.0287386 time: 506.996 one-recall: 1 one-ratio: 1
iteration: 13 recall: 0.974 accuracy: 0.00124704 cost: 0.00670538 M: 35.1489 delta: 0.0275696 time: 516.154 one-recall: 1 one-ratio: 1
iteration: 14 recall: 0.9748 accuracy: 0.00122424 cost: 0.00673546 M: 35.2614 delta: 0.0270199 time: 523.411 one-recall: 1 one-ratio: 1
iteration: 15 recall: 0.9752 accuracy: 0.00119852 cost: 0.00675018 M: 35.3157 delta: 0.0267629 time: 529.695 one-recall: 1 one-ratio: 1
iteration: 16 recall: 0.9752 accuracy: 0.00119852 cost: 0.00675758 M: 35.3431 delta: 0.026642 time: 535.486 one-recall: 1 one-ratio: 1
iteration: 17 recall: 0.9752 accuracy: 0.00119852 cost: 0.00676127 M: 35.357 delta: 0.0265755 time: 541.017 one-recall: 1 one-ratio: 1
iteration: 18 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676316 M: 35.3641 delta: 0.0265406 time: 546.411 one-recall: 1 one-ratio: 1
iteration: 19 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676416 M: 35.3679 delta: 0.0265241 time: 551.731 one-recall: 1 one-ratio: 1
iteration: 20 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676463 M: 35.3697 delta: 0.026515 time: 557.004 one-recall: 1 one-ratio: 1
iteration: 21 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676486 M: 35.3706 delta: 0.0265107 time: 562.25 one-recall: 1 one-ratio: 1
iteration: 22 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676495 M: 35.3709 delta: 0.0265097 time: 567.482 one-recall: 1 one-ratio: 1
iteration: 23 recall: 0.9756 accuracy: 0.00117784 cost: 0.006765 M: 35.3711 delta: 0.0265089 time: 572.709 one-recall: 1 one-ratio: 1
iteration: 24 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676504 M: 35.3713 delta: 0.0265082 time: 577.932 one-recall: 1 one-ratio: 1
iteration: 25 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676508 M: 35.3715 delta: 0.0265077 time: 583.156 one-recall: 1 one-ratio: 1
iteration: 26 recall: 0.9756 accuracy: 0.00117784 cost: 0.0067651 M: 35.3715 delta: 0.0265076 time: 588.373 one-recall: 1 one-ratio: 1
iteration: 27 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676512 M: 35.3716 delta: 0.0265071 time: 593.593 one-recall: 1 one-ratio: 1
iteration: 28 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676512 M: 35.3716 delta: 0.026507 time: 598.806 one-recall: 1 one-ratio: 1
iteration: 29 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676512 M: 35.3716 delta: 0.026507 time: 604.022 one-recall: 1 one-ratio: 1
iteration: 30 recall: 0.9756 accuracy: 0.00117784 cost: 0.00676512 M: 35.3716 delta: 0.026507 time: 609.239 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 623.6999999999998
Index size:  207636.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0062401000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.0900000000, query time of that 0.0365517570, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Accept!
  -> Decision True in time 0.8000000000, query time of that 0.3586256580, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Accept!
  -> Decision True in time 8.1900000000, query time of that 3.5929015060, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.5600000000, query time of that 0.0432305880, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Accept!
  -> Decision True in time 5.5700000000, query time of that 0.4240213690, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
334.355 < 338.08
  -> Decision False in time 3.0900000000, query time of that 0.2430945720, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Accept!
  -> Decision True in time 6.6600000000, query time of that 0.0520967210, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
286.801 < 288.597
  -> Decision False in time 23.9300000000, query time of that 0.1819823020, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
267.125 < 271.63
  -> Decision False in time 1.2800000000, query time of that 0.0098301590, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 4, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 4, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0.0008 accuracy: 2.05595 cost: 0.00038 M: 10 delta: 1 time: 53.8887 one-recall: 0 one-ratio: 3.5924
iteration: 2 recall: 0.0048 accuracy: 1.12749 cost: 0.000637428 M: 10 delta: 0.856032 time: 91.9825 one-recall: 0 one-ratio: 2.82895
iteration: 3 recall: 0.0316 accuracy: 0.644107 cost: 0.00109521 M: 11.5287 delta: 0.835107 time: 138.107 one-recall: 0.03 one-ratio: 2.24193
iteration: 4 recall: 0.1844 accuracy: 0.320664 cost: 0.00163044 M: 11.8362 delta: 0.783453 time: 183.866 one-recall: 0.24 one-ratio: 1.73051
iteration: 5 recall: 0.5108 accuracy: 0.111532 cost: 0.0022361 M: 12.6038 delta: 0.664588 time: 231.356 one-recall: 0.68 one-ratio: 1.24925
iteration: 6 recall: 0.7744 accuracy: 0.028212 cost: 0.00298008 M: 15.1146 delta: 0.432345 time: 284.971 one-recall: 0.92 one-ratio: 1.04376
iteration: 7 recall: 0.9056 accuracy: 0.00755461 cost: 0.00395546 M: 21.1405 delta: 0.196406 time: 346.009 one-recall: 0.97 one-ratio: 1.00766
iteration: 8 recall: 0.9484 accuracy: 0.00328026 cost: 0.00498012 M: 27.3055 delta: 0.0884283 time: 403.038 one-recall: 0.99 one-ratio: 1.00054
iteration: 9 recall: 0.9656 accuracy: 0.00219985 cost: 0.00577298 M: 31.2898 delta: 0.051311 time: 446.416 one-recall: 0.99 one-ratio: 1.00054
iteration: 10 recall: 0.976 accuracy: 0.00142513 cost: 0.00625784 M: 33.3945 delta: 0.0372011 time: 475.571 one-recall: 0.99 one-ratio: 1.00054
iteration: 11 recall: 0.9808 accuracy: 0.00113796 cost: 0.00651547 M: 34.4262 delta: 0.031332 time: 494.529 one-recall: 0.99 one-ratio: 1.00054
iteration: 12 recall: 0.9828 accuracy: 0.000934415 cost: 0.00664346 M: 34.9186 delta: 0.0287449 time: 507.271 one-recall: 1 one-ratio: 1
iteration: 13 recall: 0.984 accuracy: 0.000859464 cost: 0.00670574 M: 35.1551 delta: 0.0275762 time: 516.479 one-recall: 1 one-ratio: 1
iteration: 14 recall: 0.9856 accuracy: 0.000672632 cost: 0.00673616 M: 35.2686 delta: 0.0270395 time: 523.793 one-recall: 1 one-ratio: 1
iteration: 15 recall: 0.9864 accuracy: 0.000639861 cost: 0.00675099 M: 35.3242 delta: 0.0267772 time: 530.119 one-recall: 1 one-ratio: 1
iteration: 16 recall: 0.9864 accuracy: 0.000639861 cost: 0.00675842 M: 35.3515 delta: 0.0266557 time: 535.955 one-recall: 1 one-ratio: 1
iteration: 17 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676225 M: 35.3658 delta: 0.0265906 time: 541.535 one-recall: 1 one-ratio: 1
iteration: 18 recall: 0.9864 accuracy: 0.000639861 cost: 0.0067642 M: 35.3733 delta: 0.0265594 time: 546.974 one-recall: 1 one-ratio: 1
iteration: 19 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676525 M: 35.3773 delta: 0.0265423 time: 552.329 one-recall: 1 one-ratio: 1
iteration: 20 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676574 M: 35.3792 delta: 0.0265359 time: 557.649 one-recall: 1 one-ratio: 1
iteration: 21 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676604 M: 35.3803 delta: 0.0265314 time: 562.949 one-recall: 1 one-ratio: 1
iteration: 22 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676621 M: 35.381 delta: 0.0265298 time: 568.233 one-recall: 1 one-ratio: 1
iteration: 23 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676632 M: 35.3815 delta: 0.026528 time: 573.51 one-recall: 1 one-ratio: 1
iteration: 24 recall: 0.9864 accuracy: 0.000639861 cost: 0.0067664 M: 35.3818 delta: 0.0265273 time: 578.781 one-recall: 1 one-ratio: 1
iteration: 25 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676646 M: 35.382 delta: 0.0265261 time: 584.048 one-recall: 1 one-ratio: 1
iteration: 26 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676648 M: 35.3821 delta: 0.0265258 time: 589.311 one-recall: 1 one-ratio: 1
iteration: 27 recall: 0.9864 accuracy: 0.000639861 cost: 0.0067665 M: 35.3822 delta: 0.0265254 time: 594.574 one-recall: 1 one-ratio: 1
iteration: 28 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676651 M: 35.3822 delta: 0.0265254 time: 599.836 one-recall: 1 one-ratio: 1
iteration: 29 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676651 M: 35.3822 delta: 0.0265253 time: 605.095 one-recall: 1 one-ratio: 1
iteration: 30 recall: 0.9864 accuracy: 0.000639861 cost: 0.00676651 M: 35.3822 delta: 0.0265253 time: 610.359 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 624.8799999999992
Index size:  207500.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0114753000
  Testing...
|S| = 80
|T| = 1152
Reject!
399.061 < 421.348
  -> Decision False in time 0.0600000000, query time of that 0.0199039800, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Reject!
267.339 < 268.341
  -> Decision False in time 0.1600000000, query time of that 0.0517747570, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Reject!
370.255 < 387.604
  -> Decision False in time 0.0900000000, query time of that 0.0278947500, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.5500000000, query time of that 0.0270745710, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Reject!
358.274 < 370.47
  -> Decision False in time 1.0200000000, query time of that 0.0502716030, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
355.772 < 364.941
  -> Decision False in time 6.8000000000, query time of that 0.3273095800, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Reject!
300.401 < 369.777
  -> Decision False in time 1.6200000000, query time of that 0.0074998090, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
234.092 < 270.488
  -> Decision False in time 16.3100000000, query time of that 0.0710023720, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
277.366 < 279.677
  -> Decision False in time 17.5500000000, query time of that 0.0768243890, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 90, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 90, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0 accuracy: 2.22475 cost: 0.00038 M: 10 delta: 1 time: 63.7177 one-recall: 0 one-ratio: 3.10719
iteration: 2 recall: 0.0044 accuracy: 1.1173 cost: 0.000637428 M: 10 delta: 0.856032 time: 107.885 one-recall: 0 one-ratio: 2.5169
iteration: 3 recall: 0.0336 accuracy: 0.607101 cost: 0.00109521 M: 11.5287 delta: 0.835109 time: 161.332 one-recall: 0.02 one-ratio: 2.10843
iteration: 4 recall: 0.1836 accuracy: 0.291546 cost: 0.00163044 M: 11.8363 delta: 0.783451 time: 214.514 one-recall: 0.28 one-ratio: 1.64962
iteration: 5 recall: 0.4832 accuracy: 0.108682 cost: 0.00223608 M: 12.6037 delta: 0.664593 time: 269.806 one-recall: 0.58 one-ratio: 1.28507
iteration: 6 recall: 0.7408 accuracy: 0.0323214 cost: 0.00297997 M: 15.1143 delta: 0.432345 time: 332.172 one-recall: 0.87 one-ratio: 1.08071
iteration: 7 recall: 0.8756 accuracy: 0.00917624 cost: 0.00395506 M: 21.1383 delta: 0.19643 time: 404.453 one-recall: 0.96 one-ratio: 1.02112
iteration: 8 recall: 0.926 accuracy: 0.00462408 cost: 0.0049795 M: 27.304 delta: 0.0884601 time: 474.139 one-recall: 0.98 one-ratio: 1.00617
iteration: 9 recall: 0.9476 accuracy: 0.00335435 cost: 0.00577242 M: 31.2883 delta: 0.0513482 time: 528.943 one-recall: 0.98 one-ratio: 1.00617
iteration: 10 recall: 0.9604 accuracy: 0.00261199 cost: 0.00625702 M: 33.3932 delta: 0.0371989 time: 566.922 one-recall: 0.98 one-ratio: 1.00617
iteration: 11 recall: 0.9652 accuracy: 0.0022838 cost: 0.00651493 M: 34.425 delta: 0.0313368 time: 592.295 one-recall: 0.98 one-ratio: 1.00617
iteration: 12 recall: 0.9684 accuracy: 0.0021693 cost: 0.00664317 M: 34.9185 delta: 0.028753 time: 609.643 one-recall: 0.98 one-ratio: 1.00617
iteration: 13 recall: 0.97 accuracy: 0.00208717 cost: 0.0067054 M: 35.1544 delta: 0.0275886 time: 622.302 one-recall: 0.98 one-ratio: 1.00617
iteration: 14 recall: 0.97 accuracy: 0.00208717 cost: 0.00673596 M: 35.2687 delta: 0.0270461 time: 632.415 one-recall: 0.98 one-ratio: 1.00617
iteration: 15 recall: 0.9704 accuracy: 0.00201797 cost: 0.0067511 M: 35.3253 delta: 0.0267759 time: 641.19 one-recall: 0.98 one-ratio: 1.00617
iteration: 16 recall: 0.9708 accuracy: 0.00178062 cost: 0.00675861 M: 35.3531 delta: 0.0266475 time: 649.268 one-recall: 0.99 one-ratio: 1.00172
iteration: 17 recall: 0.9708 accuracy: 0.00178062 cost: 0.00676237 M: 35.367 delta: 0.0265857 time: 656.974 one-recall: 0.99 one-ratio: 1.00172
iteration: 18 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676429 M: 35.3743 delta: 0.0265591 time: 664.483 one-recall: 0.99 one-ratio: 1.00172
iteration: 19 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676533 M: 35.3781 delta: 0.0265421 time: 671.892 one-recall: 0.99 one-ratio: 1.00172
iteration: 20 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676589 M: 35.3801 delta: 0.0265329 time: 679.245 one-recall: 0.99 one-ratio: 1.00172
iteration: 21 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676619 M: 35.3812 delta: 0.0265286 time: 686.57 one-recall: 0.99 one-ratio: 1.00172
iteration: 22 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676634 M: 35.3818 delta: 0.0265269 time: 693.875 one-recall: 0.99 one-ratio: 1.00172
iteration: 23 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676641 M: 35.3821 delta: 0.0265257 time: 701.162 one-recall: 0.99 one-ratio: 1.00172
iteration: 24 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676645 M: 35.3822 delta: 0.0265252 time: 708.435 one-recall: 0.99 one-ratio: 1.00172
iteration: 25 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676648 M: 35.3823 delta: 0.0265247 time: 715.706 one-recall: 0.99 one-ratio: 1.00172
iteration: 26 recall: 0.9708 accuracy: 0.00177941 cost: 0.0067665 M: 35.3823 delta: 0.0265248 time: 722.975 one-recall: 0.99 one-ratio: 1.00172
iteration: 27 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676651 M: 35.3824 delta: 0.0265247 time: 730.241 one-recall: 0.99 one-ratio: 1.00172
iteration: 28 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676652 M: 35.3824 delta: 0.0265246 time: 737.506 one-recall: 0.99 one-ratio: 1.00172
iteration: 29 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676653 M: 35.3824 delta: 0.0265246 time: 744.772 one-recall: 0.99 one-ratio: 1.00172
iteration: 30 recall: 0.9708 accuracy: 0.00177941 cost: 0.00676653 M: 35.3824 delta: 0.0265244 time: 752.036 one-recall: 0.99 one-ratio: 1.00172
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 770.8799999999992
Index size:  262880.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0027257000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0889596230, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Accept!
  -> Decision True in time 1.3300000000, query time of that 0.8815932110, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Accept!
  -> Decision True in time 13.3500000000, query time of that 8.7066213060, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.6700000000, query time of that 0.1015482960, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Accept!
  -> Decision True in time 6.6000000000, query time of that 1.0695780850, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
224.798 < 240.539
  -> Decision False in time 5.2800000000, query time of that 0.8430240690, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Accept!
  -> Decision True in time 8.1900000000, query time of that 0.1277884310, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
259.444 < 262.061
  -> Decision False in time 51.2900000000, query time of that 0.7780922270, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
227.249 < 228.48
  -> Decision False in time 4.1400000000, query time of that 0.0641566530, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 3, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 3, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0.0004 accuracy: 2.05149 cost: 0.00038 M: 10 delta: 1 time: 63.6974 one-recall: 0 one-ratio: 3.53429
iteration: 2 recall: 0.002 accuracy: 1.17913 cost: 0.000637428 M: 10 delta: 0.856032 time: 107.853 one-recall: 0 one-ratio: 2.82418
iteration: 3 recall: 0.0328 accuracy: 0.69397 cost: 0.00109521 M: 11.5287 delta: 0.835101 time: 161.27 one-recall: 0.01 one-ratio: 2.34322
iteration: 4 recall: 0.1652 accuracy: 0.38139 cost: 0.00163046 M: 11.8363 delta: 0.783459 time: 214.407 one-recall: 0.14 one-ratio: 1.89492
iteration: 5 recall: 0.4952 accuracy: 0.121634 cost: 0.00223604 M: 12.6035 delta: 0.664597 time: 269.631 one-recall: 0.56 one-ratio: 1.32921
iteration: 6 recall: 0.7632 accuracy: 0.0279259 cost: 0.00297995 M: 15.1142 delta: 0.432349 time: 331.973 one-recall: 0.87 one-ratio: 1.05412
iteration: 7 recall: 0.8816 accuracy: 0.0105962 cost: 0.00395525 M: 21.1394 delta: 0.196408 time: 404.204 one-recall: 0.95 one-ratio: 1.01212
iteration: 8 recall: 0.9328 accuracy: 0.00471739 cost: 0.00497974 M: 27.305 delta: 0.0884532 time: 473.848 one-recall: 0.96 one-ratio: 1.00944
iteration: 9 recall: 0.9596 accuracy: 0.00260654 cost: 0.00577273 M: 31.2891 delta: 0.0513132 time: 528.604 one-recall: 0.98 one-ratio: 1.00633
iteration: 10 recall: 0.9692 accuracy: 0.00188095 cost: 0.00625797 M: 33.3926 delta: 0.0371837 time: 566.601 one-recall: 0.99 one-ratio: 1.00156
iteration: 11 recall: 0.9728 accuracy: 0.00159122 cost: 0.00651474 M: 34.422 delta: 0.0312979 time: 591.921 one-recall: 0.99 one-ratio: 1.00156
iteration: 12 recall: 0.976 accuracy: 0.00139466 cost: 0.00664197 M: 34.9118 delta: 0.0287249 time: 609.215 one-recall: 0.99 one-ratio: 1.00156
iteration: 13 recall: 0.9764 accuracy: 0.00130606 cost: 0.00670445 M: 35.148 delta: 0.0275547 time: 621.897 one-recall: 1 one-ratio: 1
iteration: 14 recall: 0.9768 accuracy: 0.00129865 cost: 0.00673461 M: 35.2607 delta: 0.0270101 time: 631.983 one-recall: 1 one-ratio: 1
iteration: 15 recall: 0.9768 accuracy: 0.00129865 cost: 0.00674943 M: 35.3156 delta: 0.0267547 time: 640.734 one-recall: 1 one-ratio: 1
iteration: 16 recall: 0.9768 accuracy: 0.00129865 cost: 0.00675701 M: 35.3437 delta: 0.0266297 time: 648.809 one-recall: 1 one-ratio: 1
iteration: 17 recall: 0.9768 accuracy: 0.00129865 cost: 0.00676087 M: 35.3581 delta: 0.0265649 time: 656.521 one-recall: 1 one-ratio: 1
iteration: 18 recall: 0.9768 accuracy: 0.00129865 cost: 0.00676292 M: 35.3658 delta: 0.0265348 time: 664.048 one-recall: 1 one-ratio: 1
iteration: 19 recall: 0.9768 accuracy: 0.00129865 cost: 0.006764 M: 35.3699 delta: 0.0265165 time: 671.465 one-recall: 1 one-ratio: 1
iteration: 20 recall: 0.9768 accuracy: 0.00129865 cost: 0.00676455 M: 35.372 delta: 0.0265084 time: 678.82 one-recall: 1 one-ratio: 1
iteration: 21 recall: 0.9768 accuracy: 0.00129865 cost: 0.00676484 M: 35.3732 delta: 0.0265027 time: 686.141 one-recall: 1 one-ratio: 1
iteration: 22 recall: 0.9768 accuracy: 0.00129865 cost: 0.006765 M: 35.3739 delta: 0.0264995 time: 693.439 one-recall: 1 one-ratio: 1
iteration: 23 recall: 0.9768 accuracy: 0.00129865 cost: 0.00676508 M: 35.3742 delta: 0.0264985 time: 700.717 one-recall: 1 one-ratio: 1
iteration: 24 recall: 0.9768 accuracy: 0.00129865 cost: 0.00676513 M: 35.3744 delta: 0.026498 time: 707.994 one-recall: 1 one-ratio: 1
iteration: 25 recall: 0.9768 accuracy: 0.00129865 cost: 0.00676516 M: 35.3745 delta: 0.0264976 time: 715.261 one-recall: 1 one-ratio: 1
iteration: 26 recall: 0.9768 accuracy: 0.00129865 cost: 0.00676518 M: 35.3746 delta: 0.0264972 time: 722.529 one-recall: 1 one-ratio: 1
iteration: 27 recall: 0.9768 accuracy: 0.00129865 cost: 0.00676519 M: 35.3746 delta: 0.0264971 time: 729.794 one-recall: 1 one-ratio: 1
iteration: 28 recall: 0.9768 accuracy: 0.00129865 cost: 0.0067652 M: 35.3746 delta: 0.026497 time: 737.059 one-recall: 1 one-ratio: 1
iteration: 29 recall: 0.9768 accuracy: 0.00129865 cost: 0.0067652 M: 35.3746 delta: 0.026497 time: 744.322 one-recall: 1 one-ratio: 1
iteration: 30 recall: 0.9768 accuracy: 0.00129865 cost: 0.0067652 M: 35.3746 delta: 0.026497 time: 751.582 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 770.4300000000003
Index size:  262916.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0192555000
  Testing...
|S| = 80
|T| = 1152
Reject!
431.687 < 452.135
  -> Decision False in time 0.0200000000, query time of that 0.0099862330, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Reject!
325.08 < 400.204
  -> Decision False in time 0.0100000000, query time of that 0.0009334180, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Reject!
410.873 < 428.492
  -> Decision False in time 0.0300000000, query time of that 0.0116093300, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Reject!
395.425 < 439.877
  -> Decision False in time 0.3600000000, query time of that 0.0176492990, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Reject!
433.19 < 461.067
  -> Decision False in time 0.5700000000, query time of that 0.0266611260, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
360.333 < 385.4
  -> Decision False in time 0.9000000000, query time of that 0.0434638990, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Reject!
396.604 < 410.668
  -> Decision False in time 0.0100000000, query time of that 0.0002061590, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
247.204 < 256.552
  -> Decision False in time 10.4200000000, query time of that 0.0435694850, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
295.215 < 295.227
  -> Decision False in time 4.8600000000, query time of that 0.0217951080, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 70, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 70, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0.0004 accuracy: 2.58764 cost: 0.00038 M: 10 delta: 1 time: 63.7278 one-recall: 0 one-ratio: 3.50935
iteration: 2 recall: 0.0048 accuracy: 1.38285 cost: 0.000637428 M: 10 delta: 0.856032 time: 107.884 one-recall: 0 one-ratio: 2.85683
iteration: 3 recall: 0.0272 accuracy: 0.790267 cost: 0.00109521 M: 11.5287 delta: 0.835106 time: 161.324 one-recall: 0.01 one-ratio: 2.32385
iteration: 4 recall: 0.1916 accuracy: 0.320674 cost: 0.00163043 M: 11.8362 delta: 0.783459 time: 214.493 one-recall: 0.23 one-ratio: 1.69562
iteration: 5 recall: 0.5248 accuracy: 0.116189 cost: 0.00223604 M: 12.6036 delta: 0.664593 time: 269.754 one-recall: 0.57 one-ratio: 1.36147
iteration: 6 recall: 0.7912 accuracy: 0.0254125 cost: 0.00297985 M: 15.1141 delta: 0.432347 time: 332.106 one-recall: 0.87 one-ratio: 1.05923
iteration: 7 recall: 0.9148 accuracy: 0.00877771 cost: 0.00395505 M: 21.1383 delta: 0.196381 time: 404.391 one-recall: 0.91 one-ratio: 1.03881
iteration: 8 recall: 0.9596 accuracy: 0.00322523 cost: 0.00497936 M: 27.3023 delta: 0.08846 time: 474.058 one-recall: 0.98 one-ratio: 1.00179
iteration: 9 recall: 0.9716 accuracy: 0.00226273 cost: 0.0057717 M: 31.2869 delta: 0.0513184 time: 528.855 one-recall: 0.98 one-ratio: 1.00179
iteration: 10 recall: 0.98 accuracy: 0.00157342 cost: 0.00625701 M: 33.3951 delta: 0.0372029 time: 566.871 one-recall: 0.98 one-ratio: 1.00179
iteration: 11 recall: 0.9832 accuracy: 0.00118448 cost: 0.00651462 M: 34.4267 delta: 0.0313074 time: 592.243 one-recall: 0.98 one-ratio: 1.00179
iteration: 12 recall: 0.9852 accuracy: 0.000891051 cost: 0.00664296 M: 34.9185 delta: 0.0287237 time: 609.611 one-recall: 0.98 one-ratio: 1.00179
iteration: 13 recall: 0.9852 accuracy: 0.000891051 cost: 0.00670494 M: 35.1533 delta: 0.0275673 time: 622.26 one-recall: 0.98 one-ratio: 1.00179
iteration: 14 recall: 0.9852 accuracy: 0.000891051 cost: 0.00673507 M: 35.2655 delta: 0.0270331 time: 632.347 one-recall: 0.98 one-ratio: 1.00179
iteration: 15 recall: 0.9852 accuracy: 0.000891051 cost: 0.00675007 M: 35.3215 delta: 0.0267758 time: 641.108 one-recall: 0.98 one-ratio: 1.00179
iteration: 16 recall: 0.9852 accuracy: 0.000891051 cost: 0.00675752 M: 35.3492 delta: 0.0266521 time: 649.172 one-recall: 0.98 one-ratio: 1.00179
iteration: 17 recall: 0.9852 accuracy: 0.000891051 cost: 0.00676136 M: 35.3639 delta: 0.0265853 time: 656.884 one-recall: 0.98 one-ratio: 1.00179
iteration: 18 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676329 M: 35.3711 delta: 0.0265517 time: 664.395 one-recall: 0.98 one-ratio: 1.00179
iteration: 19 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676428 M: 35.3748 delta: 0.0265376 time: 671.802 one-recall: 0.98 one-ratio: 1.00179
iteration: 20 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676486 M: 35.3771 delta: 0.0265278 time: 679.164 one-recall: 0.98 one-ratio: 1.00179
iteration: 21 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676515 M: 35.3782 delta: 0.0265227 time: 686.485 one-recall: 0.98 one-ratio: 1.00179
iteration: 22 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676532 M: 35.3789 delta: 0.0265203 time: 693.784 one-recall: 0.98 one-ratio: 1.00179
iteration: 23 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676542 M: 35.3792 delta: 0.0265191 time: 701.067 one-recall: 0.98 one-ratio: 1.00179
iteration: 24 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676547 M: 35.3794 delta: 0.0265183 time: 708.347 one-recall: 0.98 one-ratio: 1.00179
iteration: 25 recall: 0.9856 accuracy: 0.000847642 cost: 0.0067655 M: 35.3795 delta: 0.0265179 time: 715.616 one-recall: 0.98 one-ratio: 1.00179
iteration: 26 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676552 M: 35.3796 delta: 0.0265175 time: 722.89 one-recall: 0.98 one-ratio: 1.00179
iteration: 27 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676553 M: 35.3796 delta: 0.0265174 time: 730.159 one-recall: 0.98 one-ratio: 1.00179
iteration: 28 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676553 M: 35.3797 delta: 0.0265173 time: 737.434 one-recall: 0.98 one-ratio: 1.00179
iteration: 29 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676553 M: 35.3797 delta: 0.0265172 time: 744.7 one-recall: 0.98 one-ratio: 1.00179
iteration: 30 recall: 0.9856 accuracy: 0.000847642 cost: 0.00676553 M: 35.3797 delta: 0.0265172 time: 751.964 one-recall: 0.98 one-ratio: 1.00179
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 770.7999999999993
Index size:  262768.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0035864000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.1200000000, query time of that 0.0739686950, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Accept!
  -> Decision True in time 1.1900000000, query time of that 0.7309285940, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Reject!
281.233 < 286.065
  -> Decision False in time 2.4000000000, query time of that 1.4615379730, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.6300000000, query time of that 0.0821521710, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Accept!
  -> Decision True in time 6.4000000000, query time of that 0.9033029860, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
324.446 < 335.112
  -> Decision False in time 17.7000000000, query time of that 2.4896025180, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Accept!
  -> Decision True in time 8.1300000000, query time of that 0.1063517750, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Accept!
  -> Decision True in time 81.9800000000, query time of that 1.0467393290, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
199.697 < 218.037
  -> Decision False in time 27.1200000000, query time of that 0.3521846270, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 80, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 80, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0.0012 accuracy: 2.08096 cost: 0.00038 M: 10 delta: 1 time: 63.7279 one-recall: 0 one-ratio: 3.57494
iteration: 2 recall: 0.0024 accuracy: 1.12368 cost: 0.000637428 M: 10 delta: 0.856032 time: 107.878 one-recall: 0 one-ratio: 2.87713
iteration: 3 recall: 0.0388 accuracy: 0.632191 cost: 0.00109521 M: 11.5287 delta: 0.835105 time: 161.306 one-recall: 0.07 one-ratio: 2.20625
iteration: 4 recall: 0.1908 accuracy: 0.325268 cost: 0.00163043 M: 11.8362 delta: 0.78345 time: 214.479 one-recall: 0.26 one-ratio: 1.72095
iteration: 5 recall: 0.5072 accuracy: 0.116272 cost: 0.00223611 M: 12.6039 delta: 0.664605 time: 269.746 one-recall: 0.67 one-ratio: 1.28857
iteration: 6 recall: 0.7796 accuracy: 0.0278297 cost: 0.00297991 M: 15.1136 delta: 0.432359 time: 332.12 one-recall: 0.91 one-ratio: 1.04875
iteration: 7 recall: 0.8992 accuracy: 0.00833896 cost: 0.00395497 M: 21.1383 delta: 0.196405 time: 404.387 one-recall: 0.94 one-ratio: 1.02367
iteration: 8 recall: 0.9464 accuracy: 0.00368615 cost: 0.00497889 M: 27.3003 delta: 0.0884696 time: 474.043 one-recall: 0.97 one-ratio: 1.01773
iteration: 9 recall: 0.9668 accuracy: 0.00239019 cost: 0.00577132 M: 31.2853 delta: 0.0513571 time: 528.831 one-recall: 0.98 one-ratio: 1.01595
iteration: 10 recall: 0.976 accuracy: 0.00132961 cost: 0.00625684 M: 33.392 delta: 0.0372278 time: 566.849 one-recall: 0.99 one-ratio: 1.00311
iteration: 11 recall: 0.98 accuracy: 0.00112352 cost: 0.00651439 M: 34.4227 delta: 0.031312 time: 592.206 one-recall: 0.99 one-ratio: 1.00311
iteration: 12 recall: 0.9808 accuracy: 0.00110398 cost: 0.00664148 M: 34.9121 delta: 0.0287786 time: 609.492 one-recall: 0.99 one-ratio: 1.00311
iteration: 13 recall: 0.9812 accuracy: 0.00108963 cost: 0.00670391 M: 35.1473 delta: 0.027617 time: 622.17 one-recall: 0.99 one-ratio: 1.00311
iteration: 14 recall: 0.9812 accuracy: 0.00108963 cost: 0.00673421 M: 35.2611 delta: 0.0270675 time: 632.271 one-recall: 0.99 one-ratio: 1.00311
iteration: 15 recall: 0.9812 accuracy: 0.00108963 cost: 0.00674927 M: 35.3172 delta: 0.0268048 time: 641.043 one-recall: 0.99 one-ratio: 1.00311
iteration: 16 recall: 0.9812 accuracy: 0.00108963 cost: 0.0067569 M: 35.3458 delta: 0.0266801 time: 649.136 one-recall: 0.99 one-ratio: 1.00311
iteration: 17 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676068 M: 35.3601 delta: 0.0266162 time: 656.841 one-recall: 0.99 one-ratio: 1.00311
iteration: 18 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676271 M: 35.3679 delta: 0.0265851 time: 664.368 one-recall: 0.99 one-ratio: 1.00311
iteration: 19 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676385 M: 35.3722 delta: 0.0265696 time: 671.793 one-recall: 0.99 one-ratio: 1.00311
iteration: 20 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676452 M: 35.3745 delta: 0.0265582 time: 679.164 one-recall: 0.99 one-ratio: 1.00311
iteration: 21 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676483 M: 35.3756 delta: 0.0265534 time: 686.488 one-recall: 0.99 one-ratio: 1.00311
iteration: 22 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676498 M: 35.3762 delta: 0.0265509 time: 693.783 one-recall: 0.99 one-ratio: 1.00311
iteration: 23 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676508 M: 35.3765 delta: 0.0265501 time: 701.081 one-recall: 0.99 one-ratio: 1.00311
iteration: 24 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676515 M: 35.3768 delta: 0.0265494 time: 708.359 one-recall: 0.99 one-ratio: 1.00311
iteration: 25 recall: 0.9812 accuracy: 0.00108963 cost: 0.0067652 M: 35.377 delta: 0.0265482 time: 715.635 one-recall: 0.99 one-ratio: 1.00311
iteration: 26 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676522 M: 35.3771 delta: 0.0265479 time: 722.907 one-recall: 0.99 one-ratio: 1.00311
iteration: 27 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676524 M: 35.3772 delta: 0.0265479 time: 730.172 one-recall: 0.99 one-ratio: 1.00311
iteration: 28 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676525 M: 35.3773 delta: 0.0265478 time: 737.44 one-recall: 0.99 one-ratio: 1.00311
iteration: 29 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676527 M: 35.3773 delta: 0.0265478 time: 744.704 one-recall: 0.99 one-ratio: 1.00311
iteration: 30 recall: 0.9812 accuracy: 0.00108963 cost: 0.00676528 M: 35.3773 delta: 0.0265476 time: 751.971 one-recall: 0.99 one-ratio: 1.00311
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 770.7999999999993
Index size:  262900.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0031654000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0847909780, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Accept!
  -> Decision True in time 1.2400000000, query time of that 0.7907614220, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Accept!
  -> Decision True in time 12.6000000000, query time of that 7.9648553810, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.6500000000, query time of that 0.0950512240, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Reject!
280.403 < 285.107
  -> Decision False in time 1.0900000000, query time of that 0.1618450310, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
301.904 < 350.691
  -> Decision False in time 8.7200000000, query time of that 1.3201476530, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Accept!
  -> Decision True in time 8.1400000000, query time of that 0.1154399760, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
252.816 < 258.681
  -> Decision False in time 52.4700000000, query time of that 0.7390995870, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
262.368 < 267.972
  -> Decision False in time 40.3300000000, query time of that 0.5732771980, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 5, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 5, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0.0004 accuracy: 2.42728 cost: 0.00038 M: 10 delta: 1 time: 63.7289 one-recall: 0 one-ratio: 3.73429
iteration: 2 recall: 0.0044 accuracy: 1.21133 cost: 0.000637428 M: 10 delta: 0.856032 time: 107.878 one-recall: 0 one-ratio: 2.93362
iteration: 3 recall: 0.0412 accuracy: 0.651323 cost: 0.00109521 M: 11.5287 delta: 0.835105 time: 161.313 one-recall: 0.06 one-ratio: 2.33182
iteration: 4 recall: 0.2328 accuracy: 0.312234 cost: 0.00163045 M: 11.8363 delta: 0.783466 time: 214.467 one-recall: 0.27 one-ratio: 1.82535
iteration: 5 recall: 0.5636 accuracy: 0.0997022 cost: 0.00223608 M: 12.6036 delta: 0.664616 time: 269.739 one-recall: 0.69 one-ratio: 1.28661
iteration: 6 recall: 0.7956 accuracy: 0.0282644 cost: 0.00297999 M: 15.1145 delta: 0.432319 time: 332.078 one-recall: 0.94 one-ratio: 1.03763
iteration: 7 recall: 0.9132 accuracy: 0.00634471 cost: 0.00395506 M: 21.1391 delta: 0.196455 time: 404.312 one-recall: 0.99 one-ratio: 1.00004
iteration: 8 recall: 0.9572 accuracy: 0.00214062 cost: 0.00497972 M: 27.3043 delta: 0.0884885 time: 473.938 one-recall: 1 one-ratio: 1
iteration: 9 recall: 0.9728 accuracy: 0.00137518 cost: 0.00577316 M: 31.2894 delta: 0.0513676 time: 528.75 one-recall: 1 one-ratio: 1
iteration: 10 recall: 0.9816 accuracy: 0.000979573 cost: 0.00625798 M: 33.3925 delta: 0.0372502 time: 566.72 one-recall: 1 one-ratio: 1
iteration: 11 recall: 0.984 accuracy: 0.000803076 cost: 0.00651598 M: 34.4272 delta: 0.0313642 time: 592.092 one-recall: 1 one-ratio: 1
iteration: 12 recall: 0.9864 accuracy: 0.000636763 cost: 0.00664449 M: 34.9201 delta: 0.0288044 time: 609.464 one-recall: 1 one-ratio: 1
iteration: 13 recall: 0.9872 accuracy: 0.000609051 cost: 0.00670759 M: 35.1579 delta: 0.0276165 time: 622.191 one-recall: 1 one-ratio: 1
iteration: 14 recall: 0.9876 accuracy: 0.000586353 cost: 0.0067377 M: 35.2709 delta: 0.0270767 time: 632.281 one-recall: 1 one-ratio: 1
iteration: 15 recall: 0.9876 accuracy: 0.000586353 cost: 0.00675259 M: 35.3261 delta: 0.0268118 time: 641.035 one-recall: 1 one-ratio: 1
iteration: 16 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676019 M: 35.3542 delta: 0.0266907 time: 649.116 one-recall: 1 one-ratio: 1
iteration: 17 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676412 M: 35.3685 delta: 0.0266274 time: 656.836 one-recall: 1 one-ratio: 1
iteration: 18 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676612 M: 35.3759 delta: 0.0265959 time: 664.36 one-recall: 1 one-ratio: 1
iteration: 19 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676724 M: 35.3801 delta: 0.0265751 time: 671.785 one-recall: 1 one-ratio: 1
iteration: 20 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676781 M: 35.3822 delta: 0.0265663 time: 679.15 one-recall: 1 one-ratio: 1
iteration: 21 recall: 0.9876 accuracy: 0.000586353 cost: 0.0067681 M: 35.3833 delta: 0.0265625 time: 686.469 one-recall: 1 one-ratio: 1
iteration: 22 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676832 M: 35.3841 delta: 0.0265598 time: 693.779 one-recall: 1 one-ratio: 1
iteration: 23 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676843 M: 35.3846 delta: 0.0265579 time: 701.068 one-recall: 1 one-ratio: 1
iteration: 24 recall: 0.9876 accuracy: 0.000586353 cost: 0.0067685 M: 35.3849 delta: 0.0265569 time: 708.356 one-recall: 1 one-ratio: 1
iteration: 25 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676853 M: 35.385 delta: 0.0265562 time: 715.631 one-recall: 1 one-ratio: 1
iteration: 26 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676856 M: 35.3851 delta: 0.0265554 time: 722.904 one-recall: 1 one-ratio: 1
iteration: 27 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676857 M: 35.3852 delta: 0.026555 time: 730.178 one-recall: 1 one-ratio: 1
iteration: 28 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676858 M: 35.3852 delta: 0.026555 time: 737.448 one-recall: 1 one-ratio: 1
iteration: 29 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676859 M: 35.3852 delta: 0.026555 time: 744.715 one-recall: 1 one-ratio: 1
iteration: 30 recall: 0.9876 accuracy: 0.000586353 cost: 0.00676859 M: 35.3853 delta: 0.0265547 time: 751.977 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 770.8299999999981
Index size:  262860.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0112580000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.0700000000, query time of that 0.0240445690, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Accept!
  -> Decision True in time 0.6700000000, query time of that 0.2193334150, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Reject!
326.158 < 396.836
  -> Decision False in time 0.7500000000, query time of that 0.2382786590, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Reject!
248.171 < 251.026
  -> Decision False in time 0.4000000000, query time of that 0.0199814070, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Reject!
245.155 < 245.967
  -> Decision False in time 3.9500000000, query time of that 0.2029165890, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
241.828 < 247.237
  -> Decision False in time 0.7900000000, query time of that 0.0414418430, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Reject!
256.002 < 269.464
  -> Decision False in time 6.5700000000, query time of that 0.0297456450, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
292.65 < 295.978
  -> Decision False in time 16.3600000000, query time of that 0.0756771900, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
265.402 < 276.454
  -> Decision False in time 27.3500000000, query time of that 0.1241115560, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 30, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 30, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0.0012 accuracy: 2.53268 cost: 0.00038 M: 10 delta: 1 time: 63.6667 one-recall: 0 one-ratio: 3.79169
iteration: 2 recall: 0.0064 accuracy: 1.40482 cost: 0.000637428 M: 10 delta: 0.856032 time: 107.82 one-recall: 0 one-ratio: 2.91995
iteration: 3 recall: 0.0376 accuracy: 0.746772 cost: 0.00109521 M: 11.5287 delta: 0.835104 time: 161.253 one-recall: 0.05 one-ratio: 2.28684
iteration: 4 recall: 0.2128 accuracy: 0.31107 cost: 0.00163044 M: 11.8363 delta: 0.783451 time: 214.439 one-recall: 0.28 one-ratio: 1.72721
iteration: 5 recall: 0.5664 accuracy: 0.0847503 cost: 0.00223613 M: 12.6038 delta: 0.664606 time: 269.711 one-recall: 0.73 one-ratio: 1.19644
iteration: 6 recall: 0.8056 accuracy: 0.0211466 cost: 0.00297998 M: 15.1145 delta: 0.432346 time: 332.057 one-recall: 0.92 one-ratio: 1.06265
iteration: 7 recall: 0.9072 accuracy: 0.00670514 cost: 0.00395527 M: 21.1405 delta: 0.196454 time: 404.315 one-recall: 0.97 one-ratio: 1.00621
iteration: 8 recall: 0.9468 accuracy: 0.00326649 cost: 0.00497963 M: 27.3038 delta: 0.088479 time: 473.947 one-recall: 0.98 one-ratio: 1.0027
iteration: 9 recall: 0.9696 accuracy: 0.00138661 cost: 0.00577178 M: 31.2847 delta: 0.0513595 time: 528.72 one-recall: 0.99 one-ratio: 1.0009
iteration: 10 recall: 0.9764 accuracy: 0.00102328 cost: 0.00625693 M: 33.389 delta: 0.0372442 time: 566.717 one-recall: 0.99 one-ratio: 1.0009
iteration: 11 recall: 0.9772 accuracy: 0.000984872 cost: 0.00651407 M: 34.4196 delta: 0.0313404 time: 592.046 one-recall: 0.99 one-ratio: 1.0009
iteration: 12 recall: 0.9784 accuracy: 0.000946693 cost: 0.0066424 M: 34.9128 delta: 0.0287737 time: 609.414 one-recall: 0.99 one-ratio: 1.0009
iteration: 13 recall: 0.9796 accuracy: 0.00090445 cost: 0.00670427 M: 35.1486 delta: 0.027606 time: 622.055 one-recall: 0.99 one-ratio: 1.0009
iteration: 14 recall: 0.9796 accuracy: 0.00090445 cost: 0.0067345 M: 35.2627 delta: 0.0270532 time: 632.152 one-recall: 0.99 one-ratio: 1.0009
iteration: 15 recall: 0.9796 accuracy: 0.00090445 cost: 0.00674937 M: 35.3177 delta: 0.0267959 time: 640.907 one-recall: 0.99 one-ratio: 1.0009
iteration: 16 recall: 0.9796 accuracy: 0.00090445 cost: 0.00675707 M: 35.3463 delta: 0.0266658 time: 648.991 one-recall: 0.99 one-ratio: 1.0009
iteration: 17 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676091 M: 35.36 delta: 0.0266015 time: 656.697 one-recall: 0.99 one-ratio: 1.0009
iteration: 18 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676277 M: 35.3667 delta: 0.0265711 time: 664.201 one-recall: 0.99 one-ratio: 1.0009
iteration: 19 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676378 M: 35.3705 delta: 0.0265537 time: 671.615 one-recall: 0.99 one-ratio: 1.0009
iteration: 20 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676432 M: 35.3725 delta: 0.0265471 time: 678.97 one-recall: 0.99 one-ratio: 1.0009
iteration: 21 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676458 M: 35.3737 delta: 0.0265426 time: 686.288 one-recall: 0.99 one-ratio: 1.0009
iteration: 22 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676478 M: 35.3745 delta: 0.0265397 time: 693.591 one-recall: 0.99 one-ratio: 1.0009
iteration: 23 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676488 M: 35.3749 delta: 0.0265375 time: 700.883 one-recall: 0.99 one-ratio: 1.0009
iteration: 24 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676495 M: 35.3752 delta: 0.026537 time: 708.163 one-recall: 0.99 one-ratio: 1.0009
iteration: 25 recall: 0.9796 accuracy: 0.00090445 cost: 0.006765 M: 35.3754 delta: 0.0265362 time: 715.446 one-recall: 0.99 one-ratio: 1.0009
iteration: 26 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676501 M: 35.3754 delta: 0.0265359 time: 722.721 one-recall: 0.99 one-ratio: 1.0009
iteration: 27 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676503 M: 35.3755 delta: 0.026536 time: 729.995 one-recall: 0.99 one-ratio: 1.0009
iteration: 28 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676505 M: 35.3756 delta: 0.0265358 time: 737.27 one-recall: 0.99 one-ratio: 1.0009
iteration: 29 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676506 M: 35.3756 delta: 0.0265356 time: 744.537 one-recall: 0.99 one-ratio: 1.0009
iteration: 30 recall: 0.9796 accuracy: 0.00090445 cost: 0.00676506 M: 35.3756 delta: 0.0265355 time: 751.802 one-recall: 0.99 one-ratio: 1.0009
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 770.630000000001
Index size:  262824.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0071860000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.0900000000, query time of that 0.0439988650, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Accept!
  -> Decision True in time 0.8800000000, query time of that 0.4242651460, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Reject!
365.844 < 379.152
  -> Decision False in time 2.1700000000, query time of that 1.0457431120, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.5900000000, query time of that 0.0512957340, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Reject!
279.448 < 286.365
  -> Decision False in time 2.7500000000, query time of that 0.2477283990, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
213.773 < 214.049
  -> Decision False in time 1.9700000000, query time of that 0.1817262880, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Accept!
  -> Decision True in time 8.1100000000, query time of that 0.0659193250, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
218.794 < 240.94
  -> Decision False in time 27.7800000000, query time of that 0.2202150790, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
278.674 < 283.125
  -> Decision False in time 29.9600000000, query time of that 0.2384053380, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 60, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 60, {'reverse': -1}, False])
Got a train set of size (1000000 * 128)
Generating control...
Initializing...
iteration: 1 recall: 0.0004 accuracy: 1.96787 cost: 0.00038 M: 10 delta: 1 time: 63.6633 one-recall: 0 one-ratio: 2.80223
iteration: 2 recall: 0.0036 accuracy: 1.06636 cost: 0.000637428 M: 10 delta: 0.856032 time: 107.788 one-recall: 0.01 one-ratio: 2.2414
iteration: 3 recall: 0.0328 accuracy: 0.578464 cost: 0.00109521 M: 11.5287 delta: 0.835107 time: 161.213 one-recall: 0.02 one-ratio: 1.84001
iteration: 4 recall: 0.1932 accuracy: 0.277843 cost: 0.00163045 M: 11.8363 delta: 0.783472 time: 214.378 one-recall: 0.24 one-ratio: 1.47214
iteration: 5 recall: 0.4824 accuracy: 0.107614 cost: 0.00223606 M: 12.6036 delta: 0.664598 time: 269.632 one-recall: 0.57 one-ratio: 1.19266
iteration: 6 recall: 0.7352 accuracy: 0.0288767 cost: 0.00297997 M: 15.1149 delta: 0.43234 time: 331.971 one-recall: 0.84 one-ratio: 1.05186
iteration: 7 recall: 0.8568 accuracy: 0.0125129 cost: 0.0039554 M: 21.1412 delta: 0.19643 time: 404.257 one-recall: 0.93 one-ratio: 1.03422
iteration: 8 recall: 0.9176 accuracy: 0.00620038 cost: 0.0049799 M: 27.3064 delta: 0.0884472 time: 473.925 one-recall: 0.95 one-ratio: 1.02039
iteration: 9 recall: 0.9488 accuracy: 0.00381299 cost: 0.00577281 M: 31.2932 delta: 0.0512714 time: 528.71 one-recall: 0.96 one-ratio: 1.01904
iteration: 10 recall: 0.96 accuracy: 0.0029532 cost: 0.00625811 M: 33.3958 delta: 0.037179 time: 566.705 one-recall: 0.96 one-ratio: 1.01904
iteration: 11 recall: 0.9696 accuracy: 0.0018502 cost: 0.0065157 M: 34.4247 delta: 0.0312943 time: 592.057 one-recall: 0.97 one-ratio: 1.00733
iteration: 12 recall: 0.9712 accuracy: 0.00166655 cost: 0.00664321 M: 34.9154 delta: 0.0287362 time: 609.371 one-recall: 0.98 one-ratio: 1.00587
iteration: 13 recall: 0.9724 accuracy: 0.00159931 cost: 0.00670498 M: 35.149 delta: 0.0275807 time: 621.997 one-recall: 0.98 one-ratio: 1.00587
iteration: 14 recall: 0.9732 accuracy: 0.0015442 cost: 0.00673515 M: 35.2618 delta: 0.0270395 time: 632.074 one-recall: 0.98 one-ratio: 1.00587
iteration: 15 recall: 0.9732 accuracy: 0.00154402 cost: 0.00675021 M: 35.3181 delta: 0.0267812 time: 640.851 one-recall: 0.98 one-ratio: 1.00587
iteration: 16 recall: 0.9736 accuracy: 0.0015274 cost: 0.00675778 M: 35.3461 delta: 0.026654 time: 648.928 one-recall: 0.98 one-ratio: 1.00587
iteration: 17 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676166 M: 35.3606 delta: 0.026587 time: 656.648 one-recall: 0.98 one-ratio: 1.00587
iteration: 18 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676362 M: 35.3681 delta: 0.0265558 time: 664.165 one-recall: 0.98 one-ratio: 1.00587
iteration: 19 recall: 0.9736 accuracy: 0.0015274 cost: 0.0067647 M: 35.3723 delta: 0.0265386 time: 671.582 one-recall: 0.98 one-ratio: 1.00587
iteration: 20 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676529 M: 35.3745 delta: 0.0265297 time: 678.941 one-recall: 0.98 one-ratio: 1.00587
iteration: 21 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676557 M: 35.3756 delta: 0.0265245 time: 686.264 one-recall: 0.98 one-ratio: 1.00587
iteration: 22 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676572 M: 35.3763 delta: 0.026522 time: 693.571 one-recall: 0.98 one-ratio: 1.00587
iteration: 23 recall: 0.9736 accuracy: 0.0015274 cost: 0.0067658 M: 35.3766 delta: 0.0265208 time: 700.854 one-recall: 0.98 one-ratio: 1.00587
iteration: 24 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676586 M: 35.3768 delta: 0.02652 time: 708.128 one-recall: 0.98 one-ratio: 1.00587
iteration: 25 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676589 M: 35.3769 delta: 0.0265195 time: 715.397 one-recall: 0.98 one-ratio: 1.00587
iteration: 26 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676591 M: 35.377 delta: 0.026519 time: 722.667 one-recall: 0.98 one-ratio: 1.00587
iteration: 27 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676592 M: 35.377 delta: 0.0265189 time: 729.93 one-recall: 0.98 one-ratio: 1.00587
iteration: 28 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676592 M: 35.377 delta: 0.026519 time: 737.208 one-recall: 0.98 one-ratio: 1.00587
iteration: 29 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676592 M: 35.377 delta: 0.026519 time: 744.471 one-recall: 0.98 one-ratio: 1.00587
iteration: 30 recall: 0.9736 accuracy: 0.0015274 cost: 0.00676592 M: 35.377 delta: 0.0265189 time: 751.731 one-recall: 0.98 one-ratio: 1.00587
Graph completion with reverse edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Reranking edges...

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 770.5699999999997
Index size:  263040.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0041183000
  Testing...
|S| = 80
|T| = 1152
Accept!
  -> Decision True in time 0.1100000000, query time of that 0.0678773680, with c1=0.0500000000, c2=0.0010000000
|S| = 800
|T| = 1152
Accept!
  -> Decision True in time 1.1000000000, query time of that 0.6466258320, with c1=0.0500000000, c2=0.0100000000
|S| = 8000
|T| = 1152
Accept!
  -> Decision True in time 11.1300000000, query time of that 6.5019466520, with c1=0.0500000000, c2=0.1000000000
|S| = 80
|T| = 11513
Accept!
  -> Decision True in time 0.6300000000, query time of that 0.0778392880, with c1=0.5000000000, c2=0.0010000000
|S| = 800
|T| = 11513
Accept!
  -> Decision True in time 6.2200000000, query time of that 0.8144024750, with c1=0.5000000000, c2=0.0100000000
|S| = 8000
|T| = 11513
Reject!
253.318 < 257.76
  -> Decision False in time 12.3000000000, query time of that 1.5997879180, with c1=0.5000000000, c2=0.1000000000
|S| = 80
|T| = 115130
Accept!
  -> Decision True in time 8.1200000000, query time of that 0.0963714450, with c1=5.0000000000, c2=0.0010000000
|S| = 800
|T| = 115130
Reject!
264.913 < 265.238
  -> Decision False in time 1.2400000000, query time of that 0.0145128290, with c1=5.0000000000, c2=0.0100000000
|S| = 8000
|T| = 115130
Reject!
301.068 < 307.682
  -> Decision False in time 2.0800000000, query time of that 0.0254833990, with c1=5.0000000000, c2=0.1000000000
