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', 70, {'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', 40, {'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', 10, {'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', 60, {'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', 80, {'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', 4, {'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', 90, {'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', 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: 0.008 accuracy: 1.6488 cost: 0.00633344 M: 10 delta: 1 time: 0.721457 one-recall: 0 one-ratio: 1.98824
iteration: 2 recall: 0.0748 accuracy: 0.576643 cost: 0.0102207 M: 10 delta: 0.893264 time: 0.988541 one-recall: 0.07 one-ratio: 1.46524
iteration: 3 recall: 0.4584 accuracy: 0.129751 cost: 0.0167282 M: 11.1226 delta: 0.845941 time: 1.30751 one-recall: 0.46 one-ratio: 1.12263
iteration: 4 recall: 0.9148 accuracy: 0.00780024 cost: 0.0248736 M: 11.7203 delta: 0.56604 time: 1.66275 one-recall: 0.97 one-ratio: 1.006
iteration: 5 recall: 0.9892 accuracy: 0.000422819 cost: 0.0376487 M: 17.421 delta: 0.223956 time: 2.1872 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9932 accuracy: 0.000213504 cost: 0.0459839 M: 21.1684 delta: 0.133646 time: 2.54977 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 46.78
Index size:  97768.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004300000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0088408010, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1900000000, query time of that 0.0893234610, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.8700000000, query time of that 0.9347201580, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1100000000, query time of that 0.0107846150, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.0800000000, query time of that 0.0985434790, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1512.06 < 1657.52
  -> Decision False in time 3.4100000000, query time of that 0.3468794650, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3900000000, query time of that 0.0160230040, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 12.5200000000, query time of that 0.1595085300, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1151.34 < 1187.81
  -> Decision False in time 100.5500000000, query time of that 1.0040055630, 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: 0.006 accuracy: 1.60085 cost: 0.00633344 M: 10 delta: 1 time: 5.40526 one-recall: 0.02 one-ratio: 1.98763
iteration: 2 recall: 0.076 accuracy: 0.551127 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.17885 one-recall: 0.07 one-ratio: 1.46503
iteration: 3 recall: 0.4752 accuracy: 0.120944 cost: 0.0167507 M: 11.1153 delta: 0.84578 time: 12.0337 one-recall: 0.43 one-ratio: 1.14726
iteration: 4 recall: 0.927599 accuracy: 0.00603367 cost: 0.0249116 M: 11.7249 delta: 0.566225 time: 16.5856 one-recall: 0.98 one-ratio: 1.00371
iteration: 5 recall: 0.9924 accuracy: 0.000466727 cost: 0.0376841 M: 17.4223 delta: 0.22457 time: 23.3457 one-recall: 0.99 one-ratio: 1.00316
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 23.589999999999975
Index size:  15928.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0009683333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0067367130, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1600000000, query time of that 0.0634537410, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.5600000000, query time of that 0.6315657060, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1000000000, query time of that 0.0064269880, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.0200000000, query time of that 0.0680695430, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1557.14 < 1917.99
  -> Decision False in time 7.0200000000, query time of that 0.4795191400, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1400000000, query time of that 0.0083287020, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2031.5 < 2364.83
  -> Decision False in time 5.9600000000, query time of that 0.0437702520, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1275.79 < 1276.63
  -> Decision False in time 12.9300000000, query time of that 0.0974060420, 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: 0.006 accuracy: 1.74174 cost: 0.00633344 M: 10 delta: 1 time: 5.4141 one-recall: 0.01 one-ratio: 1.89227
iteration: 2 recall: 0.0812 accuracy: 0.551559 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.18902 one-recall: 0.06 one-ratio: 1.34653
iteration: 3 recall: 0.5124 accuracy: 0.105661 cost: 0.0167507 M: 11.1153 delta: 0.845794 time: 12.039 one-recall: 0.52 one-ratio: 1.10702
iteration: 4 recall: 0.938399 accuracy: 0.00576821 cost: 0.0249107 M: 11.7245 delta: 0.566217 time: 16.5911 one-recall: 0.99 one-ratio: 1.00004
iteration: 5 recall: 0.9872 accuracy: 0.000741897 cost: 0.037684 M: 17.4228 delta: 0.224536 time: 23.362 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9948 accuracy: 0.00023716 cost: 0.0460118 M: 21.1558 delta: 0.134181 time: 27.7078 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 27.970000000000027
Index size:  36520.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0030100000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0063688140, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1500000000, query time of that 0.0610441430, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2089.46 < 2784.54
  -> Decision False in time 0.4700000000, query time of that 0.1873098460, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1100000000, query time of that 0.0067133710, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.0100000000, query time of that 0.0650556240, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2213.47 < 2400.56
  -> Decision False in time 4.5100000000, query time of that 0.2897423620, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1188 < 1208.35
  -> Decision False in time 0.2000000000, query time of that 0.0013085910, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1932.37 < 1934.59
  -> Decision False in time 2.4600000000, query time of that 0.0185071710, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2497.63 < 3005.23
  -> Decision False in time 2.3500000000, query time of that 0.0182511370, 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: 0.0028 accuracy: 1.77297 cost: 0.00633344 M: 10 delta: 1 time: 5.41452 one-recall: 0 one-ratio: 1.91472
iteration: 2 recall: 0.072 accuracy: 0.568537 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.18882 one-recall: 0.08 one-ratio: 1.41035
iteration: 3 recall: 0.472 accuracy: 0.118859 cost: 0.0167507 M: 11.1153 delta: 0.845797 time: 12.0386 one-recall: 0.63 one-ratio: 1.10857
iteration: 4 recall: 0.9104 accuracy: 0.00903534 cost: 0.024912 M: 11.7247 delta: 0.566215 time: 16.5989 one-recall: 0.93 one-ratio: 1.00607
iteration: 5 recall: 0.9872 accuracy: 0.000714421 cost: 0.0376867 M: 17.4226 delta: 0.224543 time: 23.3602 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9968 accuracy: 0.000112569 cost: 0.0460298 M: 21.1598 delta: 0.134075 time: 27.7137 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 27.97999999999996
Index size:  36528.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0421416667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0040750540, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2098.58 < 2113.48
  -> Decision False in time 0.0100000000, query time of that 0.0021931040, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2462.71 < 2922.56
  -> Decision False in time 0.0000000000, query time of that 0.0019402100, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
2526.25 < 2652
  -> Decision False in time 0.0700000000, query time of that 0.0025394350, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2087.39 < 3034.32
  -> Decision False in time 0.1100000000, query time of that 0.0050860980, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2510.08 < 3016.06
  -> Decision False in time 0.1400000000, query time of that 0.0058639550, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1100000000, query time of that 0.0055475360, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1707.49 < 3298.19
  -> Decision False in time 0.2800000000, query time of that 0.0015645050, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2052.57 < 2777.37
  -> Decision False in time 0.8900000000, query time of that 0.0041946240, 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: 0.0048 accuracy: 1.46302 cost: 0.00633344 M: 10 delta: 1 time: 5.41052 one-recall: 0 one-ratio: 1.83749
iteration: 2 recall: 0.0668 accuracy: 0.516428 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.18482 one-recall: 0.07 one-ratio: 1.40187
iteration: 3 recall: 0.4404 accuracy: 0.12659 cost: 0.0167507 M: 11.1153 delta: 0.845806 time: 12.0359 one-recall: 0.46 one-ratio: 1.13902
iteration: 4 recall: 0.902 accuracy: 0.0110902 cost: 0.0249123 M: 11.725 delta: 0.566219 time: 16.5873 one-recall: 0.94 one-ratio: 1.02129
iteration: 5 recall: 0.9848 accuracy: 0.000970118 cost: 0.037689 M: 17.4244 delta: 0.224497 time: 23.3501 one-recall: 0.99 one-ratio: 1.00122
iteration: 6 recall: 0.9936 accuracy: 0.000366028 cost: 0.0460287 M: 21.1607 delta: 0.134048 time: 27.7228 one-recall: 0.99 one-ratio: 1.00122
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 27.980000000000018
Index size:  36540.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0027050000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0051260670, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0382006460, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.3200000000, query time of that 0.3913887210, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1000000000, query time of that 0.0045862750, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 0.9800000000, query time of that 0.0433108690, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
874.802 < 977.806
  -> Decision False in time 1.5000000000, query time of that 0.0667817620, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1100000000, query time of that 0.0055003930, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1778.69 < 1872.73
  -> Decision False in time 9.4300000000, query time of that 0.0476898090, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1252.25 < 1424.35
  -> Decision False in time 1.2800000000, query time of that 0.0060709390, 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: 0.0064 accuracy: 1.68738 cost: 0.00633344 M: 10 delta: 1 time: 5.4199 one-recall: 0 one-ratio: 1.96068
iteration: 2 recall: 0.078 accuracy: 0.583423 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.19317 one-recall: 0.07 one-ratio: 1.39332
iteration: 3 recall: 0.4908 accuracy: 0.122191 cost: 0.0167507 M: 11.1153 delta: 0.845772 time: 12.041 one-recall: 0.55 one-ratio: 1.10604
iteration: 4 recall: 0.9408 accuracy: 0.00601472 cost: 0.0249118 M: 11.7248 delta: 0.566233 time: 16.5913 one-recall: 0.98 one-ratio: 1.01423
iteration: 5 recall: 0.9924 accuracy: 0.000488032 cost: 0.0376892 M: 17.4244 delta: 0.22453 time: 23.3628 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 23.600000000000023
Index size:  29588.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0202066667
  Testing...
|S| = 20
|T| = 283
Reject!
2229.08 < 2285.98
  -> Decision False in time 0.0100000000, query time of that 0.0025450030, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1599.45 < 2038.13
  -> Decision False in time 0.0500000000, query time of that 0.0123807770, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2139 < 2439.45
  -> Decision False in time 0.0800000000, query time of that 0.0214317420, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1000000000, query time of that 0.0036091530, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2741.86 < 2848.18
  -> Decision False in time 0.2500000000, query time of that 0.0091732900, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1683.26 < 1857.74
  -> Decision False in time 0.2500000000, query time of that 0.0093242210, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1100000000, query time of that 0.0049412660, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1617.53 < 1634.61
  -> Decision False in time 1.4000000000, query time of that 0.0065225430, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1629.4 < 1976.98
  -> Decision False in time 2.2300000000, query time of that 0.0101686010, 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: 1.56594 cost: 0.00633344 M: 10 delta: 1 time: 5.41368 one-recall: 0.01 one-ratio: 1.90418
iteration: 2 recall: 0.0712 accuracy: 0.562068 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.56278 one-recall: 0.06 one-ratio: 1.37325
iteration: 3 recall: 0.4568 accuracy: 0.124182 cost: 0.0167507 M: 11.1153 delta: 0.845804 time: 12.8682 one-recall: 0.49 one-ratio: 1.10561
iteration: 4 recall: 0.9156 accuracy: 0.00877574 cost: 0.0249113 M: 11.7249 delta: 0.566226 time: 17.9233 one-recall: 0.95 one-ratio: 1.00848
iteration: 5 recall: 0.9888 accuracy: 0.000560181 cost: 0.0376888 M: 17.4237 delta: 0.224512 time: 25.4111 one-recall: 0.99 one-ratio: 1.00038
iteration: 6 recall: 0.994 accuracy: 0.000285691 cost: 0.046025 M: 21.1581 delta: 0.134136 time: 30.5142 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 30.799999999999955
Index size:  36524.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0010066667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0076928560, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1600000000, query time of that 0.0605431990, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.5500000000, query time of that 0.6232411910, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1000000000, query time of that 0.0075729810, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.0300000000, query time of that 0.0692476300, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2077.9 < 2365.74
  -> Decision False in time 6.3700000000, query time of that 0.4179154080, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1200000000, query time of that 0.0079199710, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1223.64 < 1225.53
  -> Decision False in time 3.8300000000, query time of that 0.0296063320, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1959.64 < 1962.75
  -> Decision False in time 10.8200000000, query time of that 0.0797624310, 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: 0.0044 accuracy: 1.71531 cost: 0.00633344 M: 10 delta: 1 time: 5.42821 one-recall: 0 one-ratio: 1.93294
iteration: 2 recall: 0.0692 accuracy: 0.580635 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.20175 one-recall: 0.06 one-ratio: 1.40698
iteration: 3 recall: 0.4468 accuracy: 0.133806 cost: 0.0167507 M: 11.1153 delta: 0.845795 time: 12.0639 one-recall: 0.5 one-ratio: 1.13236
iteration: 4 recall: 0.9092 accuracy: 0.00933099 cost: 0.0249113 M: 11.7245 delta: 0.566203 time: 16.6149 one-recall: 0.97 one-ratio: 1.01313
iteration: 5 recall: 0.9856 accuracy: 0.00122304 cost: 0.037685 M: 17.4224 delta: 0.224595 time: 23.3761 one-recall: 0.99 one-ratio: 1.00643
iteration: 6 recall: 0.99 accuracy: 0.000756438 cost: 0.0460134 M: 21.1548 delta: 0.134174 time: 27.742 one-recall: 1 one-ratio: 1
iteration: 7 recall: 0.9916 accuracy: 0.000421438 cost: 0.0477836 M: 21.8121 delta: 0.126976 time: 28.7721 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 29.040000000000077
Index size:  39524.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0009883333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0081728730, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0786265210, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2051.89 < 2598.2
  -> Decision False in time 1.4900000000, query time of that 0.6727659590, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1000000000, query time of that 0.0084506520, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1943.06 < 2115.14
  -> Decision False in time 0.5400000000, query time of that 0.0429593660, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 10.5700000000, query time of that 0.8268460130, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1400000000, query time of that 0.0101508540, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 11.0000000000, query time of that 0.1100569010, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2434.39 < 2440.53
  -> Decision False in time 13.1400000000, query time of that 0.1189871920, 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: 0.0076 accuracy: 1.72602 cost: 0.00633344 M: 10 delta: 1 time: 5.41748 one-recall: 0.02 one-ratio: 1.9773
iteration: 2 recall: 0.0728 accuracy: 0.589372 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.19154 one-recall: 0.05 one-ratio: 1.42364
iteration: 3 recall: 0.4644 accuracy: 0.131911 cost: 0.0167507 M: 11.1153 delta: 0.845793 time: 12.0415 one-recall: 0.52 one-ratio: 1.09686
iteration: 4 recall: 0.9296 accuracy: 0.0073455 cost: 0.0249114 M: 11.7248 delta: 0.566196 time: 16.5924 one-recall: 0.99 one-ratio: 1.00125
iteration: 5 recall: 0.9904 accuracy: 0.000377783 cost: 0.0376803 M: 17.4221 delta: 0.224577 time: 23.3652 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 23.6099999999999
Index size:  29568.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0113683333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0038192310, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1900.76 < 1976.54
  -> Decision False in time 0.0400000000, query time of that 0.0111260000, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1826.25 < 1859.66
  -> Decision False in time 0.0100000000, query time of that 0.0009803030, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1000000000, query time of that 0.0034103190, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2533.93 < 2694.24
  -> Decision False in time 0.0600000000, query time of that 0.0023946350, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2285.59 < 2509.2
  -> Decision False in time 0.6400000000, query time of that 0.0237782730, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1100000000, query time of that 0.0045136980, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1150.92 < 1156.12
  -> Decision False in time 4.8500000000, query time of that 0.0214109690, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1866.74 < 2545.18
  -> Decision False in time 1.5000000000, query time of that 0.0069107020, 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: 0.008 accuracy: 1.70605 cost: 0.00633344 M: 10 delta: 1 time: 5.41585 one-recall: 0 one-ratio: 1.97602
iteration: 2 recall: 0.074 accuracy: 0.596272 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.19037 one-recall: 0.04 one-ratio: 1.40257
iteration: 3 recall: 0.484 accuracy: 0.12432 cost: 0.0167507 M: 11.1153 delta: 0.845806 time: 12.0406 one-recall: 0.54 one-ratio: 1.10895
iteration: 4 recall: 0.911199 accuracy: 0.0092498 cost: 0.0249114 M: 11.7247 delta: 0.566207 time: 16.5929 one-recall: 0.96 one-ratio: 1.00956
iteration: 5 recall: 0.9892 accuracy: 0.000694476 cost: 0.0376818 M: 17.4215 delta: 0.224608 time: 23.3528 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.994 accuracy: 0.000271089 cost: 0.0460214 M: 21.1582 delta: 0.13413 time: 27.7037 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 27.960000000000036
Index size:  36520.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004150000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0094588210, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0838675070, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.7800000000, query time of that 0.8567936060, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1100000000, query time of that 0.0099148440, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.0600000000, query time of that 0.0946654110, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2065.35 < 2138.5
  -> Decision False in time 7.1300000000, query time of that 0.6200288010, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1100000000, query time of that 0.0119320910, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 10.9300000000, query time of that 0.1059831560, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1618.48 < 1661.25
  -> Decision False in time 63.8600000000, query time of that 0.6159293750, 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: 0.0056 accuracy: 1.95325 cost: 0.00633344 M: 10 delta: 1 time: 5.41627 one-recall: 0 one-ratio: 1.9421
iteration: 2 recall: 0.0744 accuracy: 0.672926 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.19049 one-recall: 0.07 one-ratio: 1.39446
iteration: 3 recall: 0.476 accuracy: 0.1204 cost: 0.0167507 M: 11.1153 delta: 0.845785 time: 12.0398 one-recall: 0.55 one-ratio: 1.08425
iteration: 4 recall: 0.9264 accuracy: 0.00698597 cost: 0.0249115 M: 11.7245 delta: 0.566219 time: 16.5925 one-recall: 0.96 one-ratio: 1.00541
iteration: 5 recall: 0.992 accuracy: 0.000398293 cost: 0.0376855 M: 17.4231 delta: 0.224562 time: 23.3533 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 23.600000000000023
Index size:  29568.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0022516667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0067345270, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1600000000, query time of that 0.0663592180, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2164.23 < 2346.52
  -> Decision False in time 0.1900000000, query time of that 0.0800668800, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1100000000, query time of that 0.0078831030, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.0600000000, query time of that 0.0749644110, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2160.87 < 2256.91
  -> Decision False in time 1.8500000000, query time of that 0.1263951760, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1500000000, query time of that 0.0087584170, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 11.3200000000, query time of that 0.0920078780, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1654.5 < 1672.99
  -> Decision False in time 0.4900000000, query time of that 0.0038264360, 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: 0.0048 accuracy: 1.64264 cost: 0.00633344 M: 10 delta: 1 time: 5.60425 one-recall: 0.01 one-ratio: 1.84308
iteration: 2 recall: 0.0648 accuracy: 0.556311 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.5646 one-recall: 0.06 one-ratio: 1.34828
iteration: 3 recall: 0.4476 accuracy: 0.125813 cost: 0.0167507 M: 11.1153 delta: 0.845815 time: 12.6082 one-recall: 0.52 one-ratio: 1.07303
iteration: 4 recall: 0.9172 accuracy: 0.00852072 cost: 0.0249111 M: 11.7247 delta: 0.566205 time: 17.3803 one-recall: 0.96 one-ratio: 1.0042
iteration: 5 recall: 0.99 accuracy: 0.000317082 cost: 0.0376837 M: 17.422 delta: 0.22457 time: 24.4746 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9952 accuracy: 8.01514e-05 cost: 0.0460178 M: 21.1564 delta: 0.134137 time: 29.1507 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 29.420000000000073
Index size:  36528.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0042683333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0042909070, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0370549420, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1963.05 < 2249.34
  -> Decision False in time 0.0600000000, query time of that 0.0178479360, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1100000000, query time of that 0.0042082140, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2720.97 < 2732.55
  -> Decision False in time 0.6700000000, query time of that 0.0287316330, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
862.344 < 884.794
  -> Decision False in time 0.6600000000, query time of that 0.0280358460, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1200000000, query time of that 0.0054394310, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 10.8700000000, query time of that 0.0575675680, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1243.42 < 1252.37
  -> Decision False in time 0.6000000000, query time of that 0.0031521990, 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: 0.0068 accuracy: 1.85448 cost: 0.00633344 M: 10 delta: 1 time: 5.40356 one-recall: 0.01 one-ratio: 2.00019
iteration: 2 recall: 0.0724 accuracy: 0.628467 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.17767 one-recall: 0.08 one-ratio: 1.46291
iteration: 3 recall: 0.4528 accuracy: 0.13589 cost: 0.0167507 M: 11.1153 delta: 0.8458 time: 12.0386 one-recall: 0.52 one-ratio: 1.11222
iteration: 4 recall: 0.9216 accuracy: 0.00858423 cost: 0.0249111 M: 11.7246 delta: 0.566216 time: 16.5914 one-recall: 0.96 one-ratio: 1.00682
iteration: 5 recall: 0.9948 accuracy: 0.000354872 cost: 0.0376853 M: 17.4242 delta: 0.224498 time: 23.3519 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 23.570000000000164
Index size:  29568.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0124450000
  Testing...
|S| = 20
|T| = 283
Reject!
583.54 < 1017.18
  -> Decision False in time 0.0100000000, query time of that 0.0005258220, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1675.27 < 1958.73
  -> Decision False in time 0.1000000000, query time of that 0.0269110660, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2035.29 < 2266.46
  -> Decision False in time 0.3000000000, query time of that 0.0776452360, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1100000000, query time of that 0.0039157200, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2006.97 < 2030.5
  -> Decision False in time 0.0700000000, query time of that 0.0029274930, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
844.439 < 1074.62
  -> Decision False in time 0.1000000000, query time of that 0.0035747480, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1100000000, query time of that 0.0057405390, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1217.04 < 1254.78
  -> Decision False in time 5.1900000000, query time of that 0.0233080320, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1375.26 < 1409.46
  -> Decision False in time 0.1900000000, query time of that 0.0009232000, 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: 0.0064 accuracy: 1.70696 cost: 0.00633344 M: 10 delta: 1 time: 5.40529 one-recall: 0.01 one-ratio: 2.03353
iteration: 2 recall: 0.0704 accuracy: 0.587702 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.1801 one-recall: 0.1 one-ratio: 1.46196
iteration: 3 recall: 0.4748 accuracy: 0.133522 cost: 0.0167507 M: 11.1153 delta: 0.845797 time: 12.0427 one-recall: 0.47 one-ratio: 1.12096
iteration: 4 recall: 0.905999 accuracy: 0.0100641 cost: 0.0249118 M: 11.7246 delta: 0.566204 time: 16.5945 one-recall: 0.91 one-ratio: 1.01862
iteration: 5 recall: 0.9832 accuracy: 0.000770234 cost: 0.0376885 M: 17.4241 delta: 0.224573 time: 23.3566 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.994 accuracy: 0.000163836 cost: 0.0460262 M: 21.1578 delta: 0.134112 time: 27.7092 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 27.960000000000036
Index size:  36520.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004483333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0099266710, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1900000000, query time of that 0.0952367860, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1820.45 < 1859.29
  -> Decision False in time 0.2100000000, query time of that 0.1068458260, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1100000000, query time of that 0.0101023850, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.0600000000, query time of that 0.0980740340, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1615.45 < 1630.05
  -> Decision False in time 0.0500000000, query time of that 0.0048930440, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1500000000, query time of that 0.0126315600, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 10.9200000000, query time of that 0.1288974560, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1369.8 < 1374.62
  -> Decision False in time 55.6600000000, query time of that 0.5934595080, 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: 0.0048 accuracy: 1.74122 cost: 0.00633344 M: 10 delta: 1 time: 5.40674 one-recall: 0 one-ratio: 1.96597
iteration: 2 recall: 0.07 accuracy: 0.57113 cost: 0.0102345 M: 10 delta: 0.893354 time: 8.18216 one-recall: 0.07 one-ratio: 1.39308
iteration: 3 recall: 0.4888 accuracy: 0.116427 cost: 0.0167507 M: 11.1153 delta: 0.845793 time: 12.0324 one-recall: 0.58 one-ratio: 1.08461
iteration: 4 recall: 0.938399 accuracy: 0.00520825 cost: 0.0249119 M: 11.7245 delta: 0.56622 time: 16.5828 one-recall: 0.99 one-ratio: 1.00167
iteration: 5 recall: 0.9904 accuracy: 0.000345972 cost: 0.0376841 M: 17.4217 delta: 0.224607 time: 23.3407 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 23.559999999999945
Index size:  29580.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0005316667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0100470160, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1900000000, query time of that 0.0909499160, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2078.29 < 2476.04
  -> Decision False in time 1.0800000000, query time of that 0.5471833870, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1100000000, query time of that 0.0091797660, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.0800000000, query time of that 0.1029186020, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2507.33 < 2742.45
  -> Decision False in time 5.1500000000, query time of that 0.4767537510, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.1200000000, query time of that 0.0119384230, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 10.9400000000, query time of that 0.1163733110, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2231.76 < 2354.4
  -> Decision False in time 35.4100000000, query time of that 0.3909805480, with c1=5.0000000000, c2=0.1000000000
