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', 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', 60, {'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', 40, {'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', 90, {'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', 2, {'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', 20, {'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]), 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', 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: 0.008 accuracy: 1.6488 cost: 0.00633344 M: 10 delta: 1 time: 0.694824 one-recall: 0 one-ratio: 1.98824
iteration: 2 recall: 0.0748 accuracy: 0.576643 cost: 0.0102207 M: 10 delta: 0.893264 time: 0.935889 one-recall: 0.07 one-ratio: 1.46524
iteration: 3 recall: 0.4584 accuracy: 0.129751 cost: 0.0167282 M: 11.1226 delta: 0.845938 time: 1.25823 one-recall: 0.46 one-ratio: 1.12263
iteration: 4 recall: 0.9144 accuracy: 0.00781044 cost: 0.0248719 M: 11.72 delta: 0.566034 time: 1.63043 one-recall: 0.97 one-ratio: 1.006
iteration: 5 recall: 0.9892 accuracy: 0.000422819 cost: 0.0376479 M: 17.421 delta: 0.22398 time: 2.17536 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9932 accuracy: 0.000213504 cost: 0.0459761 M: 21.1646 delta: 0.133757 time: 2.56374 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 46.97
Index size:  97452.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0042766667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0068610500, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0645640950, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1719.01 < 1742.94
  -> Decision False in time 0.1700000000, query time of that 0.0573326920, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0073720610, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2700000000, query time of that 0.0795440490, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2029.29 < 2331.18
  -> Decision False in time 2.7600000000, query time of that 0.1658661660, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3900000000, query time of that 0.0105309350, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.6300000000, query time of that 0.1044270960, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1428.17 < 1438.53
  -> Decision False in time 4.8000000000, query time of that 0.0358065770, 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: 0.0072 accuracy: 1.68312 cost: 0.00633344 M: 10 delta: 1 time: 7.00595 one-recall: 0 one-ratio: 1.87217
iteration: 2 recall: 0.0664 accuracy: 0.581227 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7758 one-recall: 0.06 one-ratio: 1.39745
iteration: 3 recall: 0.46 accuracy: 0.127126 cost: 0.0167507 M: 11.1153 delta: 0.845783 time: 15.9871 one-recall: 0.51 one-ratio: 1.0914
iteration: 4 recall: 0.9052 accuracy: 0.00904859 cost: 0.0249119 M: 11.7249 delta: 0.566223 time: 22.1455 one-recall: 0.96 one-ratio: 1.01044
iteration: 5 recall: 0.9836 accuracy: 0.000898336 cost: 0.0376872 M: 17.4226 delta: 0.224565 time: 31.3189 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.992 accuracy: 0.000340004 cost: 0.0460241 M: 21.1581 delta: 0.134133 time: 37.3167 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 37.63000000000001
Index size:  22944.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0421433333
  Testing...
|S| = 20
|T| = 283
Reject!
2116.73 < 2821.51
  -> Decision False in time 0.0000000000, query time of that 0.0014106190, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2315.75 < 3041.66
  -> Decision False in time 0.0300000000, query time of that 0.0074069320, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2612.45 < 2914.62
  -> Decision False in time 0.0300000000, query time of that 0.0090906200, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0061528620, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2659.11 < 2780.04
  -> Decision False in time 0.0000000000, query time of that 0.0002240700, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2425.69 < 2796.35
  -> Decision False in time 0.2100000000, query time of that 0.0092647580, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1244.79 < 1387.34
  -> Decision False in time 0.2800000000, query time of that 0.0018962860, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1578.41 < 3044.25
  -> Decision False in time 1.4000000000, query time of that 0.0082136970, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2893.15 < 3031.85
  -> Decision False in time 2.7600000000, query time of that 0.0153136220, 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: 0.0028 accuracy: 1.47827 cost: 0.00633344 M: 10 delta: 1 time: 6.98978 one-recall: 0 one-ratio: 1.817
iteration: 2 recall: 0.0724 accuracy: 0.4942 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7355 one-recall: 0.1 one-ratio: 1.35073
iteration: 3 recall: 0.4732 accuracy: 0.101066 cost: 0.0167507 M: 11.1153 delta: 0.845791 time: 15.9198 one-recall: 0.55 one-ratio: 1.08994
iteration: 4 recall: 0.9108 accuracy: 0.00757317 cost: 0.0249115 M: 11.7247 delta: 0.566196 time: 22.0492 one-recall: 0.95 one-ratio: 1.0101
iteration: 5 recall: 0.9908 accuracy: 0.000460796 cost: 0.0376875 M: 17.4237 delta: 0.224514 time: 31.1805 one-recall: 0.99 one-ratio: 1.00062
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 31.47999999999999
Index size:  29612.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0012433333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0094971670, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2100000000, query time of that 0.0892794960, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2000.09 < 2145.43
  -> Decision False in time 0.9300000000, query time of that 0.3909247300, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0097202700, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3200000000, query time of that 0.1024082920, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2124.86 < 2720.46
  -> Decision False in time 8.6300000000, query time of that 0.6524726320, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4100000000, query time of that 0.0119419730, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.8000000000, query time of that 0.1194303190, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2324.98 < 2600.21
  -> Decision False in time 61.3800000000, query time of that 0.5183128300, 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: 0.006 accuracy: 3.14366 cost: 0.00633344 M: 10 delta: 1 time: 6.99108 one-recall: 0.02 one-ratio: 1.87141
iteration: 2 recall: 0.0616 accuracy: 1.05162 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7382 one-recall: 0.1 one-ratio: 1.37955
iteration: 3 recall: 0.5 accuracy: 0.304728 cost: 0.0167507 M: 11.1153 delta: 0.845796 time: 15.9246 one-recall: 0.62 one-ratio: 1.06638
iteration: 4 recall: 0.931999 accuracy: 0.0063439 cost: 0.0249121 M: 11.7249 delta: 0.56622 time: 22.0554 one-recall: 0.97 one-ratio: 1.00927
iteration: 5 recall: 0.9892 accuracy: 0.000541833 cost: 0.0376799 M: 17.4202 delta: 0.22466 time: 31.1818 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9964 accuracy: 0.000129138 cost: 0.0460238 M: 21.1579 delta: 0.134174 time: 37.1498 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 37.47999999999996
Index size:  36552.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004566667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0124106410, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2500000000, query time of that 0.1290559140, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.5000000000, query time of that 1.2752173420, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1500000000, query time of that 0.0149457280, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.1398519670, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 14.0100000000, query time of that 1.4280623210, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4200000000, query time of that 0.0173215370, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.8800000000, query time of that 0.1645424820, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1450.14 < 1537.15
  -> Decision False in time 69.4100000000, query time of that 0.7878926430, 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: 0.008 accuracy: 1.74034 cost: 0.00633344 M: 10 delta: 1 time: 6.99005 one-recall: 0.02 one-ratio: 1.8245
iteration: 2 recall: 0.0672 accuracy: 0.578066 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7361 one-recall: 0.09 one-ratio: 1.37965
iteration: 3 recall: 0.4776 accuracy: 0.117841 cost: 0.0167507 M: 11.1153 delta: 0.845796 time: 15.9227 one-recall: 0.51 one-ratio: 1.08141
iteration: 4 recall: 0.916 accuracy: 0.00719569 cost: 0.0249114 M: 11.7247 delta: 0.566217 time: 22.0498 one-recall: 0.98 one-ratio: 1.00799
iteration: 5 recall: 0.986 accuracy: 0.000622821 cost: 0.0376827 M: 17.421 delta: 0.224556 time: 31.1774 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9964 accuracy: 0.000114371 cost: 0.0460128 M: 21.1545 delta: 0.134196 time: 37.1373 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 37.45999999999992
Index size:  36552.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0030266667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0093278920, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2100000000, query time of that 0.0794719980, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2138.47 < 2729.28
  -> Decision False in time 0.7800000000, query time of that 0.3063380820, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0090208430, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3200000000, query time of that 0.0885659100, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2236.26 < 2354.79
  -> Decision False in time 0.7500000000, query time of that 0.0504431740, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4300000000, query time of that 0.0096976280, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.9600000000, query time of that 0.1077903860, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2425.62 < 2737.11
  -> Decision False in time 4.2700000000, query time of that 0.0313910850, 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: 0.0072 accuracy: 1.77801 cost: 0.00633344 M: 10 delta: 1 time: 6.98888 one-recall: 0.01 one-ratio: 1.89867
iteration: 2 recall: 0.0704 accuracy: 0.598656 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7345 one-recall: 0.09 one-ratio: 1.41057
iteration: 3 recall: 0.466 accuracy: 0.129432 cost: 0.0167507 M: 11.1153 delta: 0.845799 time: 15.9194 one-recall: 0.55 one-ratio: 1.12732
iteration: 4 recall: 0.9152 accuracy: 0.0075282 cost: 0.0249121 M: 11.7246 delta: 0.566214 time: 22.0476 one-recall: 0.99 one-ratio: 1.00607
iteration: 5 recall: 0.9864 accuracy: 0.000644898 cost: 0.0376806 M: 17.421 delta: 0.224612 time: 31.1696 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9936 accuracy: 0.000210821 cost: 0.0460142 M: 21.1554 delta: 0.134128 time: 37.126 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 37.460000000000036
Index size:  36560.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004650000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0116642630, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2300000000, query time of that 0.1116776240, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.3300000000, query time of that 1.0947719190, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0112185790, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.1244705740, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.6700000000, query time of that 1.2121448260, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4200000000, query time of that 0.0133285770, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.8900000000, query time of that 0.1454019690, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1382.24 < 1391.41
  -> Decision False in time 95.8000000000, query time of that 0.9562896720, 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: 0.0044 accuracy: 1.76236 cost: 0.00633344 M: 10 delta: 1 time: 6.99072 one-recall: 0 one-ratio: 2.00162
iteration: 2 recall: 0.08 accuracy: 0.597055 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7369 one-recall: 0.06 one-ratio: 1.40743
iteration: 3 recall: 0.4824 accuracy: 0.121058 cost: 0.0167507 M: 11.1153 delta: 0.845783 time: 15.9198 one-recall: 0.46 one-ratio: 1.10967
iteration: 4 recall: 0.9312 accuracy: 0.00608212 cost: 0.0249113 M: 11.7244 delta: 0.566211 time: 22.0465 one-recall: 0.97 one-ratio: 1.00278
iteration: 5 recall: 0.9856 accuracy: 0.00095679 cost: 0.037684 M: 17.4232 delta: 0.224564 time: 31.1692 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.996 accuracy: 0.000363645 cost: 0.0460182 M: 21.1551 delta: 0.134132 time: 37.1227 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 37.460000000000036
Index size:  36548.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0026900000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0055758980, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0510246540, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1949.59 < 2183.03
  -> Decision False in time 0.1900000000, query time of that 0.0549251770, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0062107180, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2600000000, query time of that 0.0581802680, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1052.33 < 1071.74
  -> Decision False in time 7.9500000000, query time of that 0.3630499690, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4000000000, query time of that 0.0074969950, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.6500000000, query time of that 0.0730829200, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1877.76 < 1971.26
  -> Decision False in time 0.9100000000, query time of that 0.0048942070, 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: 0.0048 accuracy: 1.67392 cost: 0.00633344 M: 10 delta: 1 time: 6.99153 one-recall: 0 one-ratio: 1.93104
iteration: 2 recall: 0.0588 accuracy: 0.596314 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7381 one-recall: 0.05 one-ratio: 1.42417
iteration: 3 recall: 0.4564 accuracy: 0.126241 cost: 0.0167507 M: 11.1153 delta: 0.845786 time: 15.9236 one-recall: 0.51 one-ratio: 1.09444
iteration: 4 recall: 0.9124 accuracy: 0.0092298 cost: 0.0249116 M: 11.7246 delta: 0.566197 time: 22.0551 one-recall: 0.95 one-ratio: 1.00762
iteration: 5 recall: 0.9888 accuracy: 0.00107823 cost: 0.0376863 M: 17.423 delta: 0.224526 time: 31.1866 one-recall: 0.99 one-ratio: 1.00186
iteration: 6 recall: 0.9952 accuracy: 0.000278461 cost: 0.0460185 M: 21.1573 delta: 0.134101 time: 37.1487 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 37.48000000000002
Index size:  36556.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004466667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0127055180, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2400000000, query time of that 0.1176623220, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1916.05 < 1928.2
  -> Decision False in time 0.4100000000, query time of that 0.2005756440, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1500000000, query time of that 0.0141498870, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.4000000000, query time of that 0.1344979600, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1374.22 < 1418.2
  -> Decision False in time 1.3500000000, query time of that 0.1325321150, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4200000000, query time of that 0.0143545610, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.9000000000, query time of that 0.1522065200, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1407.43 < 1414.77
  -> Decision False in time 115.3900000000, query time of that 1.2354038650, 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: 0.006 accuracy: 1.92781 cost: 0.00633344 M: 10 delta: 1 time: 6.98848 one-recall: 0 one-ratio: 2.08539
iteration: 2 recall: 0.0696 accuracy: 0.627939 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7348 one-recall: 0.1 one-ratio: 1.46344
iteration: 3 recall: 0.5028 accuracy: 0.115011 cost: 0.0167507 M: 11.1153 delta: 0.845791 time: 15.9198 one-recall: 0.58 one-ratio: 1.08999
iteration: 4 recall: 0.9424 accuracy: 0.00570959 cost: 0.0249118 M: 11.7249 delta: 0.566221 time: 22.0466 one-recall: 0.96 one-ratio: 1.00454
iteration: 5 recall: 0.9948 accuracy: 0.000434503 cost: 0.0376905 M: 17.4245 delta: 0.224518 time: 31.182 one-recall: 0.99 one-ratio: 1.00307
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 31.47999999999979
Index size:  29604.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0005100000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0112640200, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2300000000, query time of that 0.1061283020, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.2700000000, query time of that 1.0301431860, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0125831190, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.1161185660, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.8400000000, query time of that 1.1806603260, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4200000000, query time of that 0.0131613420, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.9300000000, query time of that 0.1358814910, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1820.45 < 1859.29
  -> Decision False in time 122.2200000000, query time of that 1.1589968010, 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: 0.0056 accuracy: 1.81386 cost: 0.00633344 M: 10 delta: 1 time: 6.99258 one-recall: 0.01 one-ratio: 1.90292
iteration: 2 recall: 0.0716 accuracy: 0.592355 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7394 one-recall: 0.04 one-ratio: 1.40061
iteration: 3 recall: 0.492 accuracy: 0.11629 cost: 0.0167507 M: 11.1153 delta: 0.845796 time: 15.924 one-recall: 0.56 one-ratio: 1.08818
iteration: 4 recall: 0.933999 accuracy: 0.00593177 cost: 0.0249131 M: 11.7248 delta: 0.566235 time: 22.055 one-recall: 0.97 one-ratio: 1.00169
iteration: 5 recall: 0.9884 accuracy: 0.000702298 cost: 0.0376877 M: 17.4234 delta: 0.224503 time: 31.1862 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9948 accuracy: 0.000259232 cost: 0.0460302 M: 21.1593 delta: 0.134086 time: 37.1549 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 37.48000000000002
Index size:  36556.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0151466667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0054148190, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1309.03 < 2075.04
  -> Decision False in time 0.0100000000, query time of that 0.0015329440, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2414.61 < 2789.61
  -> Decision False in time 0.0100000000, query time of that 0.0023072160, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0050187920, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1638.95 < 2138.17
  -> Decision False in time 0.2400000000, query time of that 0.0100394400, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1491.81 < 1779.29
  -> Decision False in time 0.0000000000, query time of that 0.0001969630, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1920.64 < 2069.62
  -> Decision False in time 0.5700000000, query time of that 0.0031848420, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2089.01 < 2649.63
  -> Decision False in time 0.2100000000, query time of that 0.0012276640, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1499.13 < 1534.48
  -> Decision False in time 2.0700000000, query time of that 0.0095945230, 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: 0.0068 accuracy: 2.00854 cost: 0.00633344 M: 10 delta: 1 time: 6.9877 one-recall: 0.01 one-ratio: 1.97905
iteration: 2 recall: 0.0608 accuracy: 0.675183 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7339 one-recall: 0.07 one-ratio: 1.43016
iteration: 3 recall: 0.4652 accuracy: 0.130704 cost: 0.0167507 M: 11.1153 delta: 0.845793 time: 15.9184 one-recall: 0.53 one-ratio: 1.1095
iteration: 4 recall: 0.9344 accuracy: 0.0066031 cost: 0.024912 M: 11.725 delta: 0.566218 time: 22.046 one-recall: 0.98 one-ratio: 1.00176
iteration: 5 recall: 0.992 accuracy: 0.000348773 cost: 0.0376807 M: 17.4211 delta: 0.224584 time: 31.1683 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 31.470000000000027
Index size:  29612.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0014283333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0078754160, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0631108290, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2100.25 < 2252.21
  -> Decision False in time 0.1800000000, query time of that 0.0638379950, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0077315330, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3000000000, query time of that 0.0722019720, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2754.36 < 2785.34
  -> Decision False in time 0.6200000000, query time of that 0.0332523550, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4200000000, query time of that 0.0088685140, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2244.53 < 2259.89
  -> Decision False in time 11.2900000000, query time of that 0.0697768810, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1105.13 < 1106.74
  -> Decision False in time 0.2500000000, query time of that 0.0017659280, 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: 0.004 accuracy: 1.74394 cost: 0.00633344 M: 10 delta: 1 time: 6.99161 one-recall: 0.01 one-ratio: 1.91367
iteration: 2 recall: 0.0756 accuracy: 0.566946 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7381 one-recall: 0.1 one-ratio: 1.37108
iteration: 3 recall: 0.458 accuracy: 0.125027 cost: 0.0167507 M: 11.1153 delta: 0.84579 time: 15.9244 one-recall: 0.5 one-ratio: 1.07539
iteration: 4 recall: 0.926 accuracy: 0.00717235 cost: 0.0249121 M: 11.7249 delta: 0.56621 time: 22.054 one-recall: 0.98 one-ratio: 1.00233
iteration: 5 recall: 0.9884 accuracy: 0.00114296 cost: 0.0376881 M: 17.4236 delta: 0.224514 time: 31.186 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9956 accuracy: 0.00031615 cost: 0.0460171 M: 21.1548 delta: 0.134201 time: 37.1442 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 37.47000000000003
Index size:  36556.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0017116667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0066694250, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0597851590, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1588.33 < 1770.58
  -> Decision False in time 0.8700000000, query time of that 0.2815153520, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0066731140, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2900000000, query time of that 0.0699549820, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.2200000000, query time of that 0.6841835080, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4200000000, query time of that 0.0077352280, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.8400000000, query time of that 0.0848019410, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1063.82 < 1089.81
  -> Decision False in time 10.9800000000, query time of that 0.0654692240, 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: 0.0088 accuracy: 2.09012 cost: 0.00633344 M: 10 delta: 1 time: 6.98956 one-recall: 0 one-ratio: 1.91061
iteration: 2 recall: 0.0728 accuracy: 0.664303 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7363 one-recall: 0.04 one-ratio: 1.38396
iteration: 3 recall: 0.5116 accuracy: 0.128618 cost: 0.0167507 M: 11.1153 delta: 0.845797 time: 15.9217 one-recall: 0.5 one-ratio: 1.08564
iteration: 4 recall: 0.9356 accuracy: 0.00730998 cost: 0.0249101 M: 11.7246 delta: 0.566181 time: 22.0501 one-recall: 0.97 one-ratio: 1.02052
iteration: 5 recall: 0.9928 accuracy: 0.000587918 cost: 0.0376743 M: 17.4193 delta: 0.224676 time: 31.1727 one-recall: 0.99 one-ratio: 1.00525
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 31.480000000000018
Index size:  29596.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0009883333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0084336410, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2000000000, query time of that 0.0833095010, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1627.03 < 1770.75
  -> Decision False in time 0.5100000000, query time of that 0.2053731210, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0102890830, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2218.62 < 2439.74
  -> Decision False in time 0.9200000000, query time of that 0.0680099530, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1860.44 < 1865.56
  -> Decision False in time 6.6800000000, query time of that 0.4578003190, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4000000000, query time of that 0.0114697700, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1263.83 < 1285.4
  -> Decision False in time 8.4600000000, query time of that 0.0691530360, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1215.46 < 1368.58
  -> Decision False in time 31.1400000000, query time of that 0.2466842150, 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 (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.006 accuracy: 1.67995 cost: 0.00633344 M: 10 delta: 1 time: 6.99011 one-recall: 0.02 one-ratio: 1.95318
iteration: 2 recall: 0.0672 accuracy: 0.562928 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.7373 one-recall: 0.09 one-ratio: 1.42844
iteration: 3 recall: 0.4768 accuracy: 0.120351 cost: 0.0167507 M: 11.1153 delta: 0.845802 time: 15.9216 one-recall: 0.5 one-ratio: 1.11906
iteration: 4 recall: 0.9308 accuracy: 0.00697963 cost: 0.0249123 M: 11.7249 delta: 0.566221 time: 22.0496 one-recall: 0.97 one-ratio: 1.0054
iteration: 5 recall: 0.9936 accuracy: 0.000328885 cost: 0.0376816 M: 17.4212 delta: 0.224598 time: 31.1732 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 31.47999999999979
Index size:  29604.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0113616667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0045710580, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2159.65 < 2957.37
  -> Decision False in time 0.0200000000, query time of that 0.0052793720, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1854.79 < 1885.83
  -> Decision False in time 0.0900000000, query time of that 0.0219232440, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
2167.87 < 2855.66
  -> Decision False in time 0.1200000000, query time of that 0.0046931560, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2024.2 < 2371.61
  -> Decision False in time 0.1300000000, query time of that 0.0053314910, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1809.36 < 2179.02
  -> Decision False in time 0.0600000000, query time of that 0.0020355540, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4100000000, query time of that 0.0061592430, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1576.65 < 1616.48
  -> Decision False in time 0.3100000000, query time of that 0.0014490870, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1297.02 < 1326.63
  -> Decision False in time 7.1100000000, query time of that 0.0336968040, 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: 0.006 accuracy: 1.65329 cost: 0.00633344 M: 10 delta: 1 time: 6.98768 one-recall: 0.01 one-ratio: 1.92135
iteration: 2 recall: 0.0708 accuracy: 0.572317 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.733 one-recall: 0.11 one-ratio: 1.42203
iteration: 3 recall: 0.462 accuracy: 0.124217 cost: 0.0167507 M: 11.1153 delta: 0.845782 time: 15.9157 one-recall: 0.56 one-ratio: 1.10079
iteration: 4 recall: 0.9084 accuracy: 0.00952458 cost: 0.024913 M: 11.7252 delta: 0.566246 time: 22.043 one-recall: 0.97 one-ratio: 1.00353
iteration: 5 recall: 0.9904 accuracy: 0.000618106 cost: 0.0376814 M: 17.4202 delta: 0.224601 time: 31.1647 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 31.470000000000027
Index size:  29608.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0124083333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0045227580, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
773.566 < 985.016
  -> Decision False in time 0.0300000000, query time of that 0.0082068530, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1385.85 < 2026.31
  -> Decision False in time 0.0500000000, query time of that 0.0103050480, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
2395.54 < 2491.22
  -> Decision False in time 0.1000000000, query time of that 0.0041438960, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2126.63 < 2134.04
  -> Decision False in time 0.1900000000, query time of that 0.0074494470, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
744.357 < 950.127
  -> Decision False in time 0.1000000000, query time of that 0.0039621410, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4100000000, query time of that 0.0068289110, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2298.77 < 2358.93
  -> Decision False in time 4.7100000000, query time of that 0.0218730640, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1097.5 < 1121.67
  -> Decision False in time 1.5200000000, query time of that 0.0069369300, with c1=5.0000000000, c2=0.1000000000
