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', 5, {'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', 70, {'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', 100, {'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', 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', 40, {'reverse': -1}, False]), 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', 80, {'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', 1, {'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', 50, {'reverse': -1}, False])]
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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.008 accuracy: 1.6488 cost: 0.00633344 M: 10 delta: 1 time: 0.646815 one-recall: 0 one-ratio: 1.98824
iteration: 2 recall: 0.0748 accuracy: 0.576643 cost: 0.0102207 M: 10 delta: 0.893264 time: 0.887597 one-recall: 0.07 one-ratio: 1.46524
iteration: 3 recall: 0.4584 accuracy: 0.129773 cost: 0.0167282 M: 11.1226 delta: 0.845946 time: 1.21356 one-recall: 0.46 one-ratio: 1.12263
iteration: 4 recall: 0.914 accuracy: 0.00790572 cost: 0.0248723 M: 11.7202 delta: 0.566053 time: 1.58497 one-recall: 0.97 one-ratio: 1.006
iteration: 5 recall: 0.9892 accuracy: 0.000422819 cost: 0.0376552 M: 17.4242 delta: 0.223892 time: 2.13153 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9932 accuracy: 0.000213504 cost: 0.0459954 M: 21.1717 delta: 0.133621 time: 2.52041 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 46.510000000000005
Index size:  97448.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0097650000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0053222010, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0490503320, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2588.98 < 2847.92
  -> Decision False in time 0.1400000000, query time of that 0.0398592770, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0055673280, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2539.26 < 2861.17
  -> Decision False in time 0.1300000000, query time of that 0.0066660350, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1514.02 < 1600.18
  -> Decision False in time 1.0700000000, query time of that 0.0491141340, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0067078450, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1952.74 < 2147.85
  -> Decision False in time 0.9500000000, query time of that 0.0058177850, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1193.95 < 1202.92
  -> Decision False in time 2.5200000000, query time of that 0.0141658760, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0084 accuracy: 1.69509 cost: 0.00633344 M: 10 delta: 1 time: 6.8354 one-recall: 0 one-ratio: 2.00364
iteration: 2 recall: 0.0708 accuracy: 0.558535 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.444 one-recall: 0.05 one-ratio: 1.39372
iteration: 3 recall: 0.4876 accuracy: 0.114564 cost: 0.0167507 M: 11.1153 delta: 0.845791 time: 15.4638 one-recall: 0.52 one-ratio: 1.10757
iteration: 4 recall: 0.9388 accuracy: 0.00658608 cost: 0.0249123 M: 11.7248 delta: 0.566255 time: 21.4056 one-recall: 0.96 one-ratio: 1.0092
iteration: 5 recall: 0.9928 accuracy: 0.000298974 cost: 0.0376862 M: 17.422 delta: 0.224526 time: 30.2538 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 30.539999999999992
Index size:  15988.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0022700000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0065397570, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0538632720, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.7600000000, query time of that 0.5342077420, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0062874340, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2600000000, query time of that 0.0596134700, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1353.15 < 1418.2
  -> Decision False in time 3.0200000000, query time of that 0.1466488630, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0075969820, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1027.79 < 1070.25
  -> Decision False in time 2.8600000000, query time of that 0.0160408740, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1261.38 < 1321.64
  -> Decision False in time 11.0000000000, query time of that 0.0598995600, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0068 accuracy: 1.75848 cost: 0.00633344 M: 10 delta: 1 time: 6.84012 one-recall: 0 one-ratio: 1.96706
iteration: 2 recall: 0.0676 accuracy: 0.577326 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4495 one-recall: 0.08 one-ratio: 1.41426
iteration: 3 recall: 0.4832 accuracy: 0.122289 cost: 0.0167507 M: 11.1153 delta: 0.845789 time: 15.4666 one-recall: 0.55 one-ratio: 1.12198
iteration: 4 recall: 0.913999 accuracy: 0.00919735 cost: 0.0249111 M: 11.7244 delta: 0.566216 time: 21.4083 one-recall: 0.97 one-ratio: 1.01031
iteration: 5 recall: 0.9932 accuracy: 0.000302625 cost: 0.037683 M: 17.4215 delta: 0.224578 time: 30.2528 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 30.54000000000002
Index size:  29624.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0006233333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0091049940, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2007.21 < 2056.29
  -> Decision False in time 0.1200000000, query time of that 0.0539853760, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.1700000000, query time of that 0.9534994150, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0099318640, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3200000000, query time of that 0.1051500080, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1180.64 < 1190.47
  -> Decision False in time 11.0600000000, query time of that 0.8867323120, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0137089800, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4200000000, query time of that 0.1224251170, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Accept!
  -> Decision True in time 136.2400000000, query time of that 1.2121699800, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0056 accuracy: 1.72201 cost: 0.00633344 M: 10 delta: 1 time: 6.83965 one-recall: 0 one-ratio: 1.84478
iteration: 2 recall: 0.0744 accuracy: 0.555636 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4486 one-recall: 0.09 one-ratio: 1.42349
iteration: 3 recall: 0.4872 accuracy: 0.117239 cost: 0.0167507 M: 11.1153 delta: 0.845801 time: 15.4685 one-recall: 0.5 one-ratio: 1.11369
iteration: 4 recall: 0.9164 accuracy: 0.00856392 cost: 0.0249102 M: 11.7246 delta: 0.566197 time: 21.4107 one-recall: 0.95 one-ratio: 1.01557
iteration: 5 recall: 0.9796 accuracy: 0.00135407 cost: 0.0376908 M: 17.4251 delta: 0.224491 time: 30.2637 one-recall: 0.99 one-ratio: 1.00287
iteration: 6 recall: 0.9936 accuracy: 0.000352558 cost: 0.0460229 M: 21.1576 delta: 0.13412 time: 35.9482 one-recall: 0.99 one-ratio: 1.00176
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 36.27000000000004
Index size:  36588.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0026883333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0060159700, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0491948240, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1603.82 < 1944.13
  -> Decision False in time 0.0800000000, query time of that 0.0233887810, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
2187.96 < 2227.86
  -> Decision False in time 0.0400000000, query time of that 0.0017990920, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1303.63 < 1468.31
  -> Decision False in time 0.1000000000, query time of that 0.0043700190, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1963.63 < 2208.28
  -> Decision False in time 3.9600000000, query time of that 0.1788822430, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0063861180, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1772.47 < 1796.65
  -> Decision False in time 6.4600000000, query time of that 0.0342519450, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1766.75 < 1831.59
  -> Decision False in time 44.1500000000, query time of that 0.2239318270, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0092 accuracy: 1.76281 cost: 0.00633344 M: 10 delta: 1 time: 6.84105 one-recall: 0.02 one-ratio: 1.87239
iteration: 2 recall: 0.0708 accuracy: 0.593994 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4506 one-recall: 0.07 one-ratio: 1.43257
iteration: 3 recall: 0.4824 accuracy: 0.135461 cost: 0.0167507 M: 11.1153 delta: 0.84578 time: 15.4701 one-recall: 0.43 one-ratio: 1.1187
iteration: 4 recall: 0.9332 accuracy: 0.00786609 cost: 0.0249112 M: 11.7248 delta: 0.566221 time: 21.4124 one-recall: 0.96 one-ratio: 1.00711
iteration: 5 recall: 0.994 accuracy: 0.000321056 cost: 0.0376795 M: 17.4216 delta: 0.224598 time: 30.2532 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 30.540000000000077
Index size:  29624.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0005266667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0123363860, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2400000000, query time of that 0.1139576820, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.3800000000, query time of that 1.1550350560, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0116352690, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.1360991320, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2299.62 < 2354.4
  -> Decision False in time 1.3600000000, query time of that 0.1323303330, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0144590280, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5100000000, query time of that 0.1435762270, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1598.34 < 1784.58
  -> Decision False in time 39.7700000000, query time of that 0.4246245610, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0088 accuracy: 1.8684 cost: 0.00633344 M: 10 delta: 1 time: 6.84054 one-recall: 0.01 one-ratio: 1.83194
iteration: 2 recall: 0.064 accuracy: 0.603417 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.449 one-recall: 0.08 one-ratio: 1.37361
iteration: 3 recall: 0.4604 accuracy: 0.124649 cost: 0.0167507 M: 11.1153 delta: 0.845799 time: 15.4684 one-recall: 0.53 one-ratio: 1.08071
iteration: 4 recall: 0.9184 accuracy: 0.00802627 cost: 0.0249109 M: 11.7246 delta: 0.566218 time: 21.4116 one-recall: 0.95 one-ratio: 1.00793
iteration: 5 recall: 0.9876 accuracy: 0.00071402 cost: 0.0376883 M: 17.4249 delta: 0.224505 time: 30.262 one-recall: 0.98 one-ratio: 1.00095
iteration: 6 recall: 0.9936 accuracy: 0.000343067 cost: 0.0460286 M: 21.1601 delta: 0.134075 time: 35.9512 one-recall: 0.98 one-ratio: 1.00095
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 36.26999999999998
Index size:  36576.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0010100000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0108922980, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2200000000, query time of that 0.0948105090, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.1600000000, query time of that 0.9458044440, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0099586760, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3100000000, query time of that 0.1078457770, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1877.73 < 2483.42
  -> Decision False in time 9.6800000000, query time of that 0.7707820100, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0117819660, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4000000000, query time of that 0.1201273570, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1463.47 < 1515.23
  -> Decision False in time 73.5600000000, query time of that 0.6613162560, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0032 accuracy: 1.69205 cost: 0.00633344 M: 10 delta: 1 time: 6.84115 one-recall: 0.01 one-ratio: 1.97746
iteration: 2 recall: 0.074 accuracy: 0.550866 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4508 one-recall: 0.08 one-ratio: 1.3574
iteration: 3 recall: 0.4788 accuracy: 0.108826 cost: 0.0167507 M: 11.1153 delta: 0.845787 time: 15.4701 one-recall: 0.61 one-ratio: 1.05502
iteration: 4 recall: 0.9008 accuracy: 0.0086123 cost: 0.0249118 M: 11.725 delta: 0.566215 time: 21.4123 one-recall: 0.97 one-ratio: 1.00088
iteration: 5 recall: 0.9872 accuracy: 0.000744135 cost: 0.03769 M: 17.4242 delta: 0.224487 time: 30.2584 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9944 accuracy: 0.000232242 cost: 0.046021 M: 21.1579 delta: 0.13404 time: 35.9357 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 36.25
Index size:  36576.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004700000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0114517240, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2300000000, query time of that 0.1147991100, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.4000000000, query time of that 1.1780389820, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0135743620, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3500000000, query time of that 0.1326387150, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1369.8 < 1374.62
  -> Decision False in time 1.2300000000, query time of that 0.1187383370, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0147759170, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.3400000000, query time of that 0.1457139080, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Accept!
  -> Decision True in time 135.6400000000, query time of that 1.4762552800, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0064 accuracy: 1.74437 cost: 0.00633344 M: 10 delta: 1 time: 6.83829 one-recall: 0.01 one-ratio: 1.86535
iteration: 2 recall: 0.0708 accuracy: 0.559909 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4465 one-recall: 0.05 one-ratio: 1.37781
iteration: 3 recall: 0.4828 accuracy: 0.11307 cost: 0.0167507 M: 11.1153 delta: 0.84579 time: 15.4654 one-recall: 0.58 one-ratio: 1.08278
iteration: 4 recall: 0.9144 accuracy: 0.00924438 cost: 0.0249123 M: 11.7252 delta: 0.566205 time: 21.4094 one-recall: 0.95 one-ratio: 1.00715
iteration: 5 recall: 0.9888 accuracy: 0.000994754 cost: 0.0376885 M: 17.4242 delta: 0.224531 time: 30.2592 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.996 accuracy: 0.000238412 cost: 0.0460304 M: 21.1594 delta: 0.134062 time: 35.9502 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 36.25999999999999
Index size:  36576.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0096716667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0050874230, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1704.56 < 1714.44
  -> Decision False in time 0.1000000000, query time of that 0.0274764430, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
998.152 < 1148.17
  -> Decision False in time 0.0400000000, query time of that 0.0099019370, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1200000000, query time of that 0.0051592760, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2323.24 < 2433.1
  -> Decision False in time 0.4900000000, query time of that 0.0182237460, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1917.66 < 2099.23
  -> Decision False in time 0.4500000000, query time of that 0.0171009630, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0064175140, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1744.47 < 1770.13
  -> Decision False in time 3.6100000000, query time of that 0.0169040020, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2431.48 < 2624.51
  -> Decision False in time 1.0400000000, query time of that 0.0050654690, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0064 accuracy: 1.65273 cost: 0.00633344 M: 10 delta: 1 time: 6.84147 one-recall: 0.01 one-ratio: 1.97448
iteration: 2 recall: 0.0839999 accuracy: 0.548988 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4503 one-recall: 0.08 one-ratio: 1.36908
iteration: 3 recall: 0.4736 accuracy: 0.123231 cost: 0.0167507 M: 11.1153 delta: 0.845796 time: 15.4702 one-recall: 0.53 one-ratio: 1.10455
iteration: 4 recall: 0.9236 accuracy: 0.00805119 cost: 0.0249129 M: 11.7249 delta: 0.566202 time: 21.4121 one-recall: 0.94 one-ratio: 1.0057
iteration: 5 recall: 0.9892 accuracy: 0.000728446 cost: 0.0376865 M: 17.4235 delta: 0.224552 time: 30.2546 one-recall: 0.99 one-ratio: 1.00138
iteration: 6 recall: 0.9964 accuracy: 0.000319017 cost: 0.0460276 M: 21.1598 delta: 0.134082 time: 35.9379 one-recall: 0.99 one-ratio: 1.00138
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 36.25
Index size:  36584.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0030283333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0081030260, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2000000000, query time of that 0.0756855880, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2635.81 < 2840.24
  -> Decision False in time 0.4500000000, query time of that 0.1777409720, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0086059490, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3000000000, query time of that 0.0876942250, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1776.54 < 1928.2
  -> Decision False in time 0.5600000000, query time of that 0.0384827120, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0103088820, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1188 < 1208.35
  -> Decision False in time 5.0400000000, query time of that 0.0386196270, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1176 < 1182.94
  -> Decision False in time 1.6900000000, query time of that 0.0127426400, with c1=5.0000000000, c2=0.1000000000
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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0068 accuracy: 1.66775 cost: 0.00633344 M: 10 delta: 1 time: 6.84212 one-recall: 0.01 one-ratio: 1.98269
iteration: 2 recall: 0.0772 accuracy: 0.588702 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4512 one-recall: 0.1 one-ratio: 1.39426
iteration: 3 recall: 0.4688 accuracy: 0.120941 cost: 0.0167507 M: 11.1153 delta: 0.84579 time: 15.4711 one-recall: 0.49 one-ratio: 1.10554
iteration: 4 recall: 0.916 accuracy: 0.00789905 cost: 0.0249105 M: 11.7243 delta: 0.566194 time: 21.4125 one-recall: 0.97 one-ratio: 1.00199
iteration: 5 recall: 0.9888 accuracy: 0.000518161 cost: 0.0376852 M: 17.4234 delta: 0.224543 time: 30.2567 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.996 accuracy: 0.000177231 cost: 0.0460146 M: 21.156 delta: 0.134125 time: 35.9326 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 36.25
Index size:  36584.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0151333333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0052015070, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1977.46 < 1997.98
  -> Decision False in time 0.0100000000, query time of that 0.0044486720, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1677.68 < 1976.98
  -> Decision False in time 0.2200000000, query time of that 0.0587870310, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0055514130, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1746.05 < 2118.89
  -> Decision False in time 0.3400000000, query time of that 0.0137816020, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2080.14 < 2116.39
  -> Decision False in time 0.2300000000, query time of that 0.0089559210, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0062693400, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1804.03 < 2184.5
  -> Decision False in time 1.8400000000, query time of that 0.0087832160, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1677.05 < 1724.82
  -> Decision False in time 2.2100000000, query time of that 0.0102887440, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0036 accuracy: 1.64671 cost: 0.00633344 M: 10 delta: 1 time: 6.84282 one-recall: 0 one-ratio: 1.94597
iteration: 2 recall: 0.0672 accuracy: 0.561556 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4518 one-recall: 0.04 one-ratio: 1.42372
iteration: 3 recall: 0.4668 accuracy: 0.127297 cost: 0.0167507 M: 11.1153 delta: 0.845791 time: 15.4733 one-recall: 0.47 one-ratio: 1.11904
iteration: 4 recall: 0.893199 accuracy: 0.0114759 cost: 0.0249119 M: 11.7247 delta: 0.566223 time: 21.4156 one-recall: 0.97 one-ratio: 1.00253
iteration: 5 recall: 0.9788 accuracy: 0.000995 cost: 0.0376838 M: 17.4233 delta: 0.224552 time: 30.261 one-recall: 0.99 one-ratio: 1.00102
iteration: 6 recall: 0.99 accuracy: 0.000345941 cost: 0.046016 M: 21.1564 delta: 0.134144 time: 35.9452 one-recall: 1 one-ratio: 1
iteration: 7 recall: 0.9936 accuracy: 0.000243831 cost: 0.0477883 M: 21.814 delta: 0.126924 time: 37.2978 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 37.62000000000012
Index size:  39580.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004250000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0118588250, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2300000000, query time of that 0.1090231110, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.3300000000, query time of that 1.1097163870, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0130438880, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.1309710610, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1682.07 < 1707.35
  -> Decision False in time 1.5000000000, query time of that 0.1364286180, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0145574330, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1671.29 < 1688.02
  -> Decision False in time 8.2400000000, query time of that 0.0845911360, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1398.24 < 1418.26
  -> Decision False in time 20.0200000000, query time of that 0.2076072440, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0064 accuracy: 1.65455 cost: 0.00633344 M: 10 delta: 1 time: 6.83779 one-recall: 0 one-ratio: 1.89909
iteration: 2 recall: 0.0676 accuracy: 0.573811 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4461 one-recall: 0.06 one-ratio: 1.37762
iteration: 3 recall: 0.4404 accuracy: 0.136303 cost: 0.0167507 M: 11.1153 delta: 0.845806 time: 15.4634 one-recall: 0.44 one-ratio: 1.09953
iteration: 4 recall: 0.914799 accuracy: 0.00863329 cost: 0.0249125 M: 11.7248 delta: 0.566193 time: 21.4037 one-recall: 0.94 one-ratio: 1.00751
iteration: 5 recall: 0.9896 accuracy: 0.000600285 cost: 0.0376841 M: 17.4225 delta: 0.224575 time: 30.2416 one-recall: 0.99 one-ratio: 1.00203
iteration: 6 recall: 0.9964 accuracy: 0.000232471 cost: 0.0460215 M: 21.1567 delta: 0.134174 time: 35.9212 one-recall: 0.99 one-ratio: 1.00203
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 36.24000000000001
Index size:  36580.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0042666667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0054826630, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0456442620, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1889.39 < 1902.85
  -> Decision False in time 1.1500000000, query time of that 0.3133350710, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
2018.46 < 2201.25
  -> Decision False in time 0.0300000000, query time of that 0.0010260400, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2300000000, query time of that 0.0521014430, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2160.26 < 2261.99
  -> Decision False in time 1.3400000000, query time of that 0.0566841190, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0065113970, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.3300000000, query time of that 0.0649472500, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1172.13 < 1175.41
  -> Decision False in time 1.9500000000, query time of that 0.0097240260, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0068 accuracy: 1.94399 cost: 0.00633344 M: 10 delta: 1 time: 6.83887 one-recall: 0.01 one-ratio: 1.95961
iteration: 2 recall: 0.066 accuracy: 0.617438 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4466 one-recall: 0.1 one-ratio: 1.42918
iteration: 3 recall: 0.4932 accuracy: 0.11877 cost: 0.0167507 M: 11.1153 delta: 0.845776 time: 15.4646 one-recall: 0.57 one-ratio: 1.12528
iteration: 4 recall: 0.936 accuracy: 0.0059574 cost: 0.0249123 M: 11.725 delta: 0.566215 time: 21.4062 one-recall: 0.96 one-ratio: 1.01201
iteration: 5 recall: 0.9908 accuracy: 0.000522102 cost: 0.0376834 M: 17.4213 delta: 0.224605 time: 30.2531 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 30.529999999999973
Index size:  29624.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0449200000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0053387620, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2923.11 < 3102.35
  -> Decision False in time 0.0100000000, query time of that 0.0046790990, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1742.28 < 2364.75
  -> Decision False in time 0.0100000000, query time of that 0.0019495140, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
2678.96 < 2701.42
  -> Decision False in time 0.0300000000, query time of that 0.0012662200, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1677.9 < 2741.6
  -> Decision False in time 0.0400000000, query time of that 0.0018620410, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2470.48 < 2701.42
  -> Decision False in time 0.2500000000, query time of that 0.0103361350, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1180.98 < 2644.29
  -> Decision False in time 0.0700000000, query time of that 0.0006436870, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2501.3 < 2670.94
  -> Decision False in time 0.4900000000, query time of that 0.0024670200, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1060.92 < 1061
  -> Decision False in time 1.2500000000, query time of that 0.0060597940, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.006 accuracy: 1.72388 cost: 0.00633344 M: 10 delta: 1 time: 6.84344 one-recall: 0.02 one-ratio: 1.92308
iteration: 2 recall: 0.0764 accuracy: 0.613804 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4512 one-recall: 0.12 one-ratio: 1.40111
iteration: 3 recall: 0.4888 accuracy: 0.132971 cost: 0.0167507 M: 11.1153 delta: 0.845785 time: 15.4709 one-recall: 0.58 one-ratio: 1.0671
iteration: 4 recall: 0.934799 accuracy: 0.00791029 cost: 0.0249122 M: 11.725 delta: 0.566223 time: 21.4157 one-recall: 0.95 one-ratio: 1.00617
iteration: 5 recall: 0.9952 accuracy: 0.000211076 cost: 0.0376851 M: 17.423 delta: 0.22457 time: 30.2624 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 30.559999999999945
Index size:  29628.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0014266667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0064445130, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0602164410, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.8400000000, query time of that 0.6264583860, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0075425490, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2700000000, query time of that 0.0725876280, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1618.47 < 2030.5
  -> Decision False in time 3.1300000000, query time of that 0.1720526180, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0091272080, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1836.65 < 1839.27
  -> Decision False in time 9.3700000000, query time of that 0.0607723830, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1080.69 < 1177.75
  -> Decision False in time 18.7100000000, query time of that 0.1159902080, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0068 accuracy: 1.81509 cost: 0.00633344 M: 10 delta: 1 time: 6.84351 one-recall: 0.01 one-ratio: 2.03483
iteration: 2 recall: 0.0716 accuracy: 0.616837 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4521 one-recall: 0.07 one-ratio: 1.39004
iteration: 3 recall: 0.4652 accuracy: 0.131789 cost: 0.0167507 M: 11.1153 delta: 0.845797 time: 15.4715 one-recall: 0.48 one-ratio: 1.13643
iteration: 4 recall: 0.916799 accuracy: 0.00792093 cost: 0.0249119 M: 11.7249 delta: 0.566236 time: 21.4146 one-recall: 0.98 one-ratio: 1.00297
iteration: 5 recall: 0.9916 accuracy: 0.000544033 cost: 0.0376922 M: 17.4251 delta: 0.224501 time: 30.2652 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 30.549999999999955
Index size:  29624.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0009750000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0082769420, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2100000000, query time of that 0.0827144850, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2065.15 < 2439.74
  -> Decision False in time 0.5200000000, query time of that 0.2090116420, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0088241530, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2900000000, query time of that 0.0921288980, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1640.06 < 1643.73
  -> Decision False in time 1.1600000000, query time of that 0.0788175920, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0106849460, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4300000000, query time of that 0.1064218280, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1809.03 < 1871.82
  -> Decision False in time 0.1700000000, query time of that 0.0019366350, with c1=5.0000000000, c2=0.1000000000
