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', 1, {'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', 40, {'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', 20, {'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', 4, {'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', 3, {'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', 70, {'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', 30, {'reverse': -1}, False])]
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: 0.008 accuracy: 1.6488 cost: 0.00633344 M: 10 delta: 1 time: 0.613749 one-recall: 0 one-ratio: 1.98824
iteration: 2 recall: 0.0748 accuracy: 0.576643 cost: 0.0102207 M: 10 delta: 0.893264 time: 0.854746 one-recall: 0.07 one-ratio: 1.46524
iteration: 3 recall: 0.4584 accuracy: 0.129773 cost: 0.0167282 M: 11.1226 delta: 0.845938 time: 1.17828 one-recall: 0.46 one-ratio: 1.12263
iteration: 4 recall: 0.9152 accuracy: 0.00784512 cost: 0.0248738 M: 11.7204 delta: 0.566022 time: 1.54997 one-recall: 0.97 one-ratio: 1.006
iteration: 5 recall: 0.9892 accuracy: 0.000422819 cost: 0.0376534 M: 17.4219 delta: 0.223903 time: 2.09587 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9932 accuracy: 0.000213504 cost: 0.0459825 M: 21.1657 delta: 0.133639 time: 2.486 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 46.669999999999995
Index size:  97420.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0264416667
  Testing...
|S| = 20
|T| = 283
Reject!
2619.67 < 3047.86
  -> Decision False in time 0.0200000000, query time of that 0.0046687650, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
3396.92 < 3514.28
  -> Decision False in time 0.0400000000, query time of that 0.0141859260, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2891.34 < 2979.66
  -> Decision False in time 0.0400000000, query time of that 0.0149483650, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0081062120, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1795.17 < 2520.03
  -> Decision False in time 0.4000000000, query time of that 0.0256500680, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2852.72 < 2898.43
  -> Decision False in time 0.0800000000, query time of that 0.0053530890, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1423.66 < 1463.51
  -> Decision False in time 0.0800000000, query time of that 0.0011821220, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2766.05 < 3105.31
  -> Decision False in time 0.0700000000, query time of that 0.0008434740, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2961.51 < 3220.78
  -> Decision False in time 0.3500000000, query time of that 0.0032751210, 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: 0.0052 accuracy: 1.75392 cost: 0.00633344 M: 10 delta: 1 time: 6.9111 one-recall: 0 one-ratio: 1.95489
iteration: 2 recall: 0.0684 accuracy: 0.592291 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5496 one-recall: 0.04 one-ratio: 1.37418
iteration: 3 recall: 0.4612 accuracy: 0.127179 cost: 0.0167507 M: 11.1153 delta: 0.845798 time: 15.6019 one-recall: 0.53 one-ratio: 1.084
iteration: 4 recall: 0.931599 accuracy: 0.0069324 cost: 0.0249129 M: 11.7249 delta: 0.566236 time: 21.5833 one-recall: 0.97 one-ratio: 1.0045
iteration: 5 recall: 0.9872 accuracy: 0.000825338 cost: 0.0376833 M: 17.422 delta: 0.22457 time: 30.4874 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9936 accuracy: 0.000551614 cost: 0.0460289 M: 21.1597 delta: 0.13409 time: 36.2337 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

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

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 36.540000000000006
Index size:  92348.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004416667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0116402950, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2300000000, query time of that 0.1134099250, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.3600000000, query time of that 1.1413048460, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0124445060, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.1314818210, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1820.45 < 1859.29
  -> Decision False in time 1.5600000000, query time of that 0.1447224930, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0139594790, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5000000000, query time of that 0.1433574880, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1684.47 < 1732.4
  -> Decision False in time 109.7300000000, query time of that 1.1246779920, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 2, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 2, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0068 accuracy: 1.72968 cost: 0.00633344 M: 10 delta: 1 time: 6.8959 one-recall: 0.01 one-ratio: 1.86268
iteration: 2 recall: 0.072 accuracy: 0.56866 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5289 one-recall: 0.12 one-ratio: 1.34848
iteration: 3 recall: 0.4764 accuracy: 0.122465 cost: 0.0167507 M: 11.1153 delta: 0.845824 time: 15.5767 one-recall: 0.54 one-ratio: 1.07577
iteration: 4 recall: 0.9236 accuracy: 0.00683593 cost: 0.024912 M: 11.7244 delta: 0.566203 time: 21.5521 one-recall: 0.98 one-ratio: 1.00188
iteration: 5 recall: 0.9908 accuracy: 0.000430968 cost: 0.0376834 M: 17.4228 delta: 0.224531 time: 30.4507 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 30.75999999999999
Index size:  85392.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0201183333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0048464420, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2133.6 < 2315.42
  -> Decision False in time 0.1100000000, query time of that 0.0283122400, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2436.99 < 2491.59
  -> Decision False in time 0.0300000000, query time of that 0.0082815030, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0049632300, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1584.1 < 1987.41
  -> Decision False in time 1.1200000000, query time of that 0.0439580410, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2585.41 < 2911.85
  -> Decision False in time 0.1700000000, query time of that 0.0063274120, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1628.65 < 1944.13
  -> Decision False in time 1.2400000000, query time of that 0.0057880660, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1124.38 < 1215.79
  -> Decision False in time 4.3100000000, query time of that 0.0197702400, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
917.283 < 938.15
  -> Decision False in time 1.2100000000, query time of that 0.0053820940, 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: 0.0084 accuracy: 1.65684 cost: 0.00633344 M: 10 delta: 1 time: 6.90999 one-recall: 0 one-ratio: 1.76356
iteration: 2 recall: 0.0688 accuracy: 0.54906 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5427 one-recall: 0.07 one-ratio: 1.36624
iteration: 3 recall: 0.4608 accuracy: 0.122584 cost: 0.0167507 M: 11.1153 delta: 0.845797 time: 15.5913 one-recall: 0.47 one-ratio: 1.14038
iteration: 4 recall: 0.914799 accuracy: 0.00966797 cost: 0.0249127 M: 11.725 delta: 0.566217 time: 21.5667 one-recall: 0.97 one-ratio: 1.01259
iteration: 5 recall: 0.9912 accuracy: 0.000455229 cost: 0.0376867 M: 17.424 delta: 0.224534 time: 30.4634 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 30.77000000000004
Index size:  85392.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0034166667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0084284510, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1900000000, query time of that 0.0709134170, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2080.77 < 2540.45
  -> Decision False in time 0.2900000000, query time of that 0.1082430090, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0089847800, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2321.57 < 2554.54
  -> Decision False in time 0.7000000000, query time of that 0.0453657020, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2783.04 < 2858.95
  -> Decision False in time 1.4000000000, query time of that 0.0900741170, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0103821640, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2267.95 < 2828.25
  -> Decision False in time 6.7800000000, query time of that 0.0497143700, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2101.59 < 2802.03
  -> Decision False in time 2.4300000000, query time of that 0.0164305970, 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: 0.0072 accuracy: 1.74268 cost: 0.00633344 M: 10 delta: 1 time: 6.90607 one-recall: 0.01 one-ratio: 1.99142
iteration: 2 recall: 0.0748 accuracy: 0.57962 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5418 one-recall: 0.09 one-ratio: 1.42784
iteration: 3 recall: 0.4764 accuracy: 0.124208 cost: 0.0167507 M: 11.1153 delta: 0.845792 time: 15.5917 one-recall: 0.56 one-ratio: 1.1146
iteration: 4 recall: 0.9088 accuracy: 0.00997094 cost: 0.0249112 M: 11.7249 delta: 0.566219 time: 21.5662 one-recall: 0.95 one-ratio: 1.01153
iteration: 5 recall: 0.9904 accuracy: 0.000497161 cost: 0.0376852 M: 17.4236 delta: 0.224538 time: 30.4651 one-recall: 0.99 one-ratio: 1.00447
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 30.78000000000003
Index size:  85392.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0039316667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0055445040, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0472379290, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1672.85 < 2055.8
  -> Decision False in time 0.9100000000, query time of that 0.2515252240, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0055714580, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2500000000, query time of that 0.0547735350, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1767.79 < 1953.75
  -> Decision False in time 3.9700000000, query time of that 0.1664258190, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0065682940, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
698.757 < 699.603
  -> Decision False in time 3.0000000000, query time of that 0.0152341060, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
909.279 < 1041.23
  -> Decision False in time 0.8900000000, query time of that 0.0040628160, 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: 0.006 accuracy: 1.68411 cost: 0.00633344 M: 10 delta: 1 time: 6.91591 one-recall: 0.01 one-ratio: 1.84416
iteration: 2 recall: 0.0644 accuracy: 0.541513 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5505 one-recall: 0.07 one-ratio: 1.37951
iteration: 3 recall: 0.4628 accuracy: 0.113854 cost: 0.0167507 M: 11.1153 delta: 0.845797 time: 15.5984 one-recall: 0.52 one-ratio: 1.0888
iteration: 4 recall: 0.910799 accuracy: 0.00832872 cost: 0.0249129 M: 11.7248 delta: 0.566218 time: 21.5747 one-recall: 0.95 one-ratio: 1.00735
iteration: 5 recall: 0.9916 accuracy: 0.000591408 cost: 0.0376866 M: 17.4231 delta: 0.224537 time: 30.4753 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 30.789999999999964
Index size:  85396.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0005633333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0125932180, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2400000000, query time of that 0.1154944290, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.3300000000, query time of that 1.1093867640, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0135229050, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3400000000, query time of that 0.1242906420, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.6900000000, query time of that 1.2601481940, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0127320090, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4800000000, query time of that 0.1375219630, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2369.98 < 2478.03
  -> Decision False in time 75.3700000000, query time of that 0.7670022370, 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: 0.0044 accuracy: 1.70498 cost: 0.00633344 M: 10 delta: 1 time: 6.90485 one-recall: 0 one-ratio: 1.96854
iteration: 2 recall: 0.0612 accuracy: 0.595491 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5377 one-recall: 0.07 one-ratio: 1.42418
iteration: 3 recall: 0.4524 accuracy: 0.126969 cost: 0.0167507 M: 11.1153 delta: 0.845784 time: 15.589 one-recall: 0.55 one-ratio: 1.08402
iteration: 4 recall: 0.9276 accuracy: 0.00783571 cost: 0.0249125 M: 11.7248 delta: 0.566208 time: 21.5649 one-recall: 0.97 one-ratio: 1.02028
iteration: 5 recall: 0.9924 accuracy: 0.000517059 cost: 0.0376901 M: 17.4234 delta: 0.224537 time: 30.4688 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 30.779999999999973
Index size:  85392.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0022566667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0065152350, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0536838070, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2252.18 < 2320.07
  -> Decision False in time 0.0400000000, query time of that 0.0134467300, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0073663020, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2500000000, query time of that 0.0638621840, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1515.55 < 1533.68
  -> Decision False in time 0.1200000000, query time of that 0.0055106300, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0081617070, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1464.58 < 1476.46
  -> Decision False in time 6.0000000000, query time of that 0.0339919650, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1233.76 < 1251.54
  -> Decision False in time 18.2500000000, query time of that 0.1003626030, 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: 0.0052 accuracy: 2.10956 cost: 0.00633344 M: 10 delta: 1 time: 6.88705 one-recall: 0.01 one-ratio: 1.92418
iteration: 2 recall: 0.076 accuracy: 0.740987 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5225 one-recall: 0.08 one-ratio: 1.39
iteration: 3 recall: 0.5028 accuracy: 0.11266 cost: 0.0167507 M: 11.1153 delta: 0.845793 time: 15.5716 one-recall: 0.57 one-ratio: 1.08646
iteration: 4 recall: 0.9356 accuracy: 0.00635528 cost: 0.0249115 M: 11.7249 delta: 0.566229 time: 21.547 one-recall: 0.96 one-ratio: 1.00421
iteration: 5 recall: 0.9924 accuracy: 0.000634582 cost: 0.0376878 M: 17.424 delta: 0.224542 time: 30.4497 one-recall: 0.98 one-ratio: 1.00305
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 30.75999999999999
Index size:  85396.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0012466667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0107922730, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2100000000, query time of that 0.0890300490, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.0900000000, query time of that 0.8771899620, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0099816770, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2900000000, query time of that 0.0967125020, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2400.37 < 2400.56
  -> Decision False in time 3.3500000000, query time of that 0.2577401730, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0125198170, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.3700000000, query time of that 0.1129463390, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1369.95 < 1394.26
  -> Decision False in time 58.9900000000, query time of that 0.4997619650, 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: 0.0068 accuracy: 1.48365 cost: 0.00633344 M: 10 delta: 1 time: 6.89912 one-recall: 0.01 one-ratio: 1.76124
iteration: 2 recall: 0.0712 accuracy: 0.503075 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5322 one-recall: 0.11 one-ratio: 1.3448
iteration: 3 recall: 0.466 accuracy: 0.111243 cost: 0.0167507 M: 11.1153 delta: 0.845791 time: 15.5809 one-recall: 0.52 one-ratio: 1.09056
iteration: 4 recall: 0.9004 accuracy: 0.0100251 cost: 0.0249124 M: 11.7249 delta: 0.566213 time: 21.5574 one-recall: 0.9 one-ratio: 1.02213
iteration: 5 recall: 0.9824 accuracy: 0.000955815 cost: 0.0376825 M: 17.4213 delta: 0.224616 time: 30.4573 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9944 accuracy: 0.00037034 cost: 0.046019 M: 21.1579 delta: 0.134125 time: 36.2007 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

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

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 36.54000000000008
Index size:  92340.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0042633333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0055499620, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2017.37 < 2266.12
  -> Decision False in time 0.0900000000, query time of that 0.0239091830, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1514.5 < 1779.29
  -> Decision False in time 0.0200000000, query time of that 0.0054846630, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
1005.24 < 1053.97
  -> Decision False in time 0.0700000000, query time of that 0.0031471650, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2600000000, query time of that 0.0546515300, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1013.73 < 1148.17
  -> Decision False in time 0.3700000000, query time of that 0.0158586760, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0066616370, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4700000000, query time of that 0.0666495910, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2203.53 < 2335
  -> Decision False in time 0.2900000000, query time of that 0.0016681720, 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: 0.008 accuracy: 1.52592 cost: 0.00633344 M: 10 delta: 1 time: 6.89867 one-recall: 0 one-ratio: 1.92922
iteration: 2 recall: 0.07 accuracy: 0.530052 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5319 one-recall: 0.08 one-ratio: 1.3981
iteration: 3 recall: 0.4488 accuracy: 0.12887 cost: 0.0167507 M: 11.1153 delta: 0.845772 time: 15.5798 one-recall: 0.53 one-ratio: 1.11381
iteration: 4 recall: 0.8952 accuracy: 0.0103386 cost: 0.0249111 M: 11.7248 delta: 0.566215 time: 21.5539 one-recall: 0.94 one-ratio: 1.01123
iteration: 5 recall: 0.984 accuracy: 0.000890878 cost: 0.0376861 M: 17.4227 delta: 0.224583 time: 30.4537 one-recall: 0.99 one-ratio: 1.00164
iteration: 6 recall: 0.992 accuracy: 0.000447563 cost: 0.0460196 M: 21.1558 delta: 0.134156 time: 36.1936 one-recall: 0.99 one-ratio: 1.00164
Graph completion with reverse edges...

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

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 36.539999999999964
Index size:  92332.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0007000000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0106171940, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2100000000, query time of that 0.0887422550, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.0900000000, query time of that 0.8721961780, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0105393810, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3100000000, query time of that 0.1027784970, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1773.05 < 1785.51
  -> Decision False in time 3.4800000000, query time of that 0.2626233370, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0113492710, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4700000000, query time of that 0.1141576570, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2185.94 < 2259.04
  -> Decision False in time 58.1100000000, query time of that 0.4855883300, 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: 0.0084 accuracy: 1.7011 cost: 0.00633344 M: 10 delta: 1 time: 6.90705 one-recall: 0 one-ratio: 1.98177
iteration: 2 recall: 0.0792 accuracy: 0.59027 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5402 one-recall: 0.09 one-ratio: 1.44893
iteration: 3 recall: 0.4496 accuracy: 0.140626 cost: 0.0167507 M: 11.1153 delta: 0.845801 time: 15.5881 one-recall: 0.48 one-ratio: 1.14324
iteration: 4 recall: 0.922 accuracy: 0.00901474 cost: 0.0249113 M: 11.7246 delta: 0.566216 time: 21.5624 one-recall: 0.96 one-ratio: 1.01752
iteration: 5 recall: 0.988 accuracy: 0.0010456 cost: 0.0376864 M: 17.4229 delta: 0.224546 time: 30.4659 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9976 accuracy: 0.00016491 cost: 0.0460159 M: 21.1562 delta: 0.134141 time: 36.2035 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

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

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 36.559999999999945
Index size:  92348.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0095700000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0050922860, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1504.14 < 1958.19
  -> Decision False in time 0.0300000000, query time of that 0.0068355270, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1861.3 < 2155.44
  -> Decision False in time 0.0700000000, query time of that 0.0199036140, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0054144690, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2400000000, query time of that 0.0490998530, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2221.5 < 2380.46
  -> Decision False in time 0.2300000000, query time of that 0.0099272700, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1914.1 < 1919.84
  -> Decision False in time 1.1100000000, query time of that 0.0055718030, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2273.07 < 2397.93
  -> Decision False in time 1.6500000000, query time of that 0.0076384090, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1310.72 < 1410.08
  -> Decision False in time 3.9900000000, query time of that 0.0190982170, 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: 0.0068 accuracy: 1.93526 cost: 0.00633344 M: 10 delta: 1 time: 6.89803 one-recall: 0 one-ratio: 1.98521
iteration: 2 recall: 0.0656 accuracy: 0.631618 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5318 one-recall: 0.07 one-ratio: 1.41958
iteration: 3 recall: 0.4728 accuracy: 0.132866 cost: 0.0167507 M: 11.1153 delta: 0.8458 time: 15.5805 one-recall: 0.43 one-ratio: 1.11072
iteration: 4 recall: 0.9228 accuracy: 0.00827106 cost: 0.0249113 M: 11.7249 delta: 0.566235 time: 21.5552 one-recall: 0.96 one-ratio: 1.00283
iteration: 5 recall: 0.9932 accuracy: 0.000319296 cost: 0.0376779 M: 17.4202 delta: 0.224612 time: 30.4507 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 30.75
Index size:  85392.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0113633333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0048606270, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2392.27 < 2718.21
  -> Decision False in time 0.0300000000, query time of that 0.0082217400, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2069.94 < 2576.86
  -> Decision False in time 0.1900000000, query time of that 0.0485492900, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
1736.45 < 2026.55
  -> Decision False in time 0.0400000000, query time of that 0.0018370790, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2199.18 < 2278.08
  -> Decision False in time 0.4200000000, query time of that 0.0162461870, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2491.25 < 2852.97
  -> Decision False in time 1.3600000000, query time of that 0.0513497990, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1073.48 < 1092.43
  -> Decision False in time 1.1000000000, query time of that 0.0059652160, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1933.49 < 2102.81
  -> Decision False in time 1.6400000000, query time of that 0.0073978760, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2194.78 < 2377.43
  -> Decision False in time 1.6700000000, query time of that 0.0080839660, 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: 0.0064 accuracy: 1.56902 cost: 0.00633344 M: 10 delta: 1 time: 6.91037 one-recall: 0.01 one-ratio: 1.88619
iteration: 2 recall: 0.0708 accuracy: 0.517511 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5428 one-recall: 0.12 one-ratio: 1.36411
iteration: 3 recall: 0.4884 accuracy: 0.106834 cost: 0.0167507 M: 11.1153 delta: 0.845783 time: 15.5915 one-recall: 0.53 one-ratio: 1.09833
iteration: 4 recall: 0.9224 accuracy: 0.00760243 cost: 0.0249115 M: 11.7251 delta: 0.566213 time: 21.5662 one-recall: 1 one-ratio: 1
iteration: 5 recall: 0.9848 accuracy: 0.00125644 cost: 0.0376921 M: 17.4264 delta: 0.224482 time: 30.4684 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9924 accuracy: 0.000556791 cost: 0.0460397 M: 21.1623 delta: 0.134032 time: 36.2129 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

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

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 36.549999999999955
Index size:  92340.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004633333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0119596130, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2200000000, query time of that 0.1039589340, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1710.73 < 1871.77
  -> Decision False in time 1.9200000000, query time of that 0.8737524600, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0109608670, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3400000000, query time of that 0.1158950040, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.5800000000, query time of that 1.1751706740, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3900000000, query time of that 0.0133137400, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5500000000, query time of that 0.1303059500, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1957.89 < 1987.83
  -> Decision False in time 24.9800000000, query time of that 0.2363282880, 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: 0.0032 accuracy: 1.80954 cost: 0.00633344 M: 10 delta: 1 time: 6.90614 one-recall: 0 one-ratio: 2.03538
iteration: 2 recall: 0.066 accuracy: 0.562179 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5391 one-recall: 0.1 one-ratio: 1.38422
iteration: 3 recall: 0.4964 accuracy: 0.104777 cost: 0.0167507 M: 11.1153 delta: 0.845803 time: 15.5865 one-recall: 0.65 one-ratio: 1.08338
iteration: 4 recall: 0.926 accuracy: 0.00672705 cost: 0.0249114 M: 11.7245 delta: 0.566218 time: 21.5609 one-recall: 0.97 one-ratio: 1.00524
iteration: 5 recall: 0.99 accuracy: 0.00037351 cost: 0.0376789 M: 17.4211 delta: 0.224621 time: 30.4561 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9964 accuracy: 9.62179e-05 cost: 0.046001 M: 21.1524 delta: 0.134238 time: 36.1874 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

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

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 36.539999999999964
Index size:  92348.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004550000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0126897810, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2500000000, query time of that 0.1265416080, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.4800000000, query time of that 1.2645509350, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0151127930, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.1367176680, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1771.46 < 2364.83
  -> Decision False in time 5.4200000000, query time of that 0.5661944790, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0168954920, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4300000000, query time of that 0.1618181140, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2264.34 < 2508.22
  -> Decision False in time 10.6300000000, query time of that 0.1271002230, 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: 0.0092 accuracy: 1.75822 cost: 0.00633344 M: 10 delta: 1 time: 6.90617 one-recall: 0.03 one-ratio: 1.85537
iteration: 2 recall: 0.0768 accuracy: 0.566945 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5389 one-recall: 0.11 one-ratio: 1.3409
iteration: 3 recall: 0.506 accuracy: 0.104008 cost: 0.0167507 M: 11.1153 delta: 0.845808 time: 15.5864 one-recall: 0.54 one-ratio: 1.0995
iteration: 4 recall: 0.928 accuracy: 0.00592697 cost: 0.0249124 M: 11.7249 delta: 0.566215 time: 21.5614 one-recall: 0.98 one-ratio: 1.00234
iteration: 5 recall: 0.99 accuracy: 0.000392127 cost: 0.0376832 M: 17.4222 delta: 0.224587 time: 30.457 one-recall: 0.99 one-ratio: 1.00078
iteration: 6 recall: 0.9936 accuracy: 0.000240593 cost: 0.0460222 M: 21.156 delta: 0.134182 time: 36.1963 one-recall: 0.99 one-ratio: 1.00078
Graph completion with reverse edges...

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

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 36.539999999999964
Index size:  92348.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0010066667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0086544680, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0687030580, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.9200000000, query time of that 0.6938340320, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0068691870, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2700000000, query time of that 0.0743537710, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2657 < 2664.74
  -> Decision False in time 2.1600000000, query time of that 0.1301045050, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0090911140, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1352.24 < 1364.05
  -> Decision False in time 2.6700000000, query time of that 0.0175325430, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1427.39 < 1429.88
  -> Decision False in time 8.1300000000, query time of that 0.0540245300, with c1=5.0000000000, c2=0.1000000000
