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', 60, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 90, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 1, {'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', 20, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 50, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 2, {'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', 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', 10, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 100, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 70, {'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', 40, {'reverse': -1}, False])]
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: 0.008 accuracy: 1.6488 cost: 0.00633344 M: 10 delta: 1 time: 0.702419 one-recall: 0 one-ratio: 1.98824
iteration: 2 recall: 0.0748 accuracy: 0.576643 cost: 0.0102207 M: 10 delta: 0.893264 time: 0.943314 one-recall: 0.07 one-ratio: 1.46524
iteration: 3 recall: 0.4584 accuracy: 0.129773 cost: 0.0167282 M: 11.1226 delta: 0.845946 time: 1.26731 one-recall: 0.46 one-ratio: 1.12263
iteration: 4 recall: 0.9144 accuracy: 0.00787512 cost: 0.0248717 M: 11.72 delta: 0.566044 time: 1.63863 one-recall: 0.96 one-ratio: 1.00616
iteration: 5 recall: 0.9892 accuracy: 0.000422819 cost: 0.0376423 M: 17.4202 delta: 0.224004 time: 2.18352 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9932 accuracy: 0.000213504 cost: 0.045977 M: 21.1657 delta: 0.13379 time: 2.57232 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 46.42
Index size:  97424.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0010283333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0114034080, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2200000000, query time of that 0.1051269790, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.2700000000, query time of that 1.0477751950, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0116605880, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3500000000, query time of that 0.1272392720, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2315.96 < 2434.16
  -> Decision False in time 5.2800000000, query time of that 0.4723450090, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0145409490, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4400000000, query time of that 0.1368529130, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1072.92 < 1147.41
  -> Decision False in time 0.3600000000, query time of that 0.0038946670, 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: 0.0076 accuracy: 1.82928 cost: 0.00633344 M: 10 delta: 1 time: 6.84718 one-recall: 0 one-ratio: 2.02741
iteration: 2 recall: 0.0808 accuracy: 0.595872 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4623 one-recall: 0.11 one-ratio: 1.41493
iteration: 3 recall: 0.484 accuracy: 0.125066 cost: 0.0167507 M: 11.1153 delta: 0.845787 time: 15.4897 one-recall: 0.5 one-ratio: 1.10808
iteration: 4 recall: 0.9276 accuracy: 0.00851808 cost: 0.0249125 M: 11.7252 delta: 0.566229 time: 21.4401 one-recall: 0.93 one-ratio: 1.0086
iteration: 5 recall: 0.9912 accuracy: 0.000363161 cost: 0.0376869 M: 17.423 delta: 0.224536 time: 30.294 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 30.58
Index size:  16008.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0005616667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0123889370, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2200000000, query time of that 0.1079193720, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.3300000000, query time of that 1.0982092400, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0114889970, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3500000000, query time of that 0.1224351360, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.6300000000, query time of that 1.2239419330, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0144112220, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5700000000, query time of that 0.1378658280, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1585.2 < 1587.73
  -> Decision False in time 56.7600000000, query time of that 0.5759670800, 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: 0.0048 accuracy: 1.78404 cost: 0.00633344 M: 10 delta: 1 time: 6.85436 one-recall: 0.01 one-ratio: 1.98501
iteration: 2 recall: 0.0612 accuracy: 0.616662 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4682 one-recall: 0.04 one-ratio: 1.43752
iteration: 3 recall: 0.4452 accuracy: 0.143131 cost: 0.0167507 M: 11.1153 delta: 0.845806 time: 15.4936 one-recall: 0.55 one-ratio: 1.11932
iteration: 4 recall: 0.9148 accuracy: 0.00766873 cost: 0.0249114 M: 11.7249 delta: 0.566227 time: 21.4451 one-recall: 0.96 one-ratio: 1.01077
iteration: 5 recall: 0.984 accuracy: 0.00093587 cost: 0.0376826 M: 17.4214 delta: 0.224598 time: 30.2989 one-recall: 0.98 one-ratio: 1.00356
iteration: 6 recall: 0.9936 accuracy: 0.000281674 cost: 0.0460134 M: 21.1556 delta: 0.134211 time: 35.9878 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 36.31
Index size:  36524.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0421416667
  Testing...
|S| = 20
|T| = 283
Reject!
2412.8 < 2632.66
  -> Decision False in time 0.0100000000, query time of that 0.0043226690, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2017.52 < 2109.12
  -> Decision False in time 0.0500000000, query time of that 0.0140734090, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2201.39 < 2801.45
  -> Decision False in time 0.0200000000, query time of that 0.0050029130, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
2557.14 < 2779.51
  -> Decision False in time 0.0900000000, query time of that 0.0040203000, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1778.51 < 2102.2
  -> Decision False in time 0.0400000000, query time of that 0.0018838420, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1410.65 < 2775.79
  -> Decision False in time 0.1900000000, query time of that 0.0080449080, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1690.41 < 1692.2
  -> Decision False in time 0.5100000000, query time of that 0.0029740740, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1972.64 < 3036.05
  -> Decision False in time 8.3900000000, query time of that 0.0425081810, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2343.77 < 2566.44
  -> Decision False in time 0.1400000000, query time of that 0.0009020230, 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: 0.0048 accuracy: 1.55195 cost: 0.00633344 M: 10 delta: 1 time: 6.85493 one-recall: 0 one-ratio: 1.84506
iteration: 2 recall: 0.0624 accuracy: 0.537599 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4683 one-recall: 0.08 one-ratio: 1.38348
iteration: 3 recall: 0.4628 accuracy: 0.120624 cost: 0.0167507 M: 11.1153 delta: 0.845796 time: 15.4956 one-recall: 0.49 one-ratio: 1.09934
iteration: 4 recall: 0.9092 accuracy: 0.00977951 cost: 0.0249113 M: 11.7248 delta: 0.566214 time: 21.4452 one-recall: 0.94 one-ratio: 1.00827
iteration: 5 recall: 0.9868 accuracy: 0.000830136 cost: 0.0376906 M: 17.4248 delta: 0.224477 time: 30.3036 one-recall: 0.99 one-ratio: 1.00043
iteration: 6 recall: 0.9948 accuracy: 0.00018909 cost: 0.0460268 M: 21.159 delta: 0.134076 time: 35.9974 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 36.31999999999999
Index size:  36532.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0095650000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0053717490, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
839.064 < 1277.39
  -> Decision False in time 0.0200000000, query time of that 0.0058654110, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1658.72 < 2097.57
  -> Decision False in time 0.0500000000, query time of that 0.0135067590, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
1364.88 < 1367.35
  -> Decision False in time 0.0400000000, query time of that 0.0018629300, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2115.08 < 2122.74
  -> Decision False in time 0.5000000000, query time of that 0.0192004900, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1600.33 < 1704.05
  -> Decision False in time 1.0600000000, query time of that 0.0418226950, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0061081040, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1519.19 < 1540.72
  -> Decision False in time 1.0200000000, query time of that 0.0050970260, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1165.35 < 1253.61
  -> Decision False in time 0.1400000000, query time of that 0.0009534750, 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: 0.0068 accuracy: 1.84068 cost: 0.00633344 M: 10 delta: 1 time: 6.84841 one-recall: 0 one-ratio: 2.05841
iteration: 2 recall: 0.0704 accuracy: 0.635784 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4623 one-recall: 0.07 one-ratio: 1.47459
iteration: 3 recall: 0.4792 accuracy: 0.131193 cost: 0.0167507 M: 11.1153 delta: 0.845793 time: 15.4888 one-recall: 0.58 one-ratio: 1.09299
iteration: 4 recall: 0.9352 accuracy: 0.00640593 cost: 0.0249127 M: 11.7251 delta: 0.566212 time: 21.4383 one-recall: 0.99 one-ratio: 1.00188
iteration: 5 recall: 0.9932 accuracy: 0.000283443 cost: 0.0376877 M: 17.4237 delta: 0.224536 time: 30.2932 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 30.579999999999984
Index size:  29584.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0022400000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0063651650, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0552416530, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.7400000000, query time of that 0.5361204570, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0067388500, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2682.07 < 2785.34
  -> Decision False in time 0.4800000000, query time of that 0.0230742520, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1930.14 < 2086.24
  -> Decision False in time 3.6500000000, query time of that 0.1755070150, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0074841920, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1628.76 < 1647.28
  -> Decision False in time 7.6900000000, query time of that 0.0408600390, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1598.34 < 1785.51
  -> Decision False in time 14.6400000000, query time of that 0.0796721700, 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: 1.63256 cost: 0.00633344 M: 10 delta: 1 time: 6.85143 one-recall: 0 one-ratio: 1.8822
iteration: 2 recall: 0.07 accuracy: 0.551455 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4688 one-recall: 0.03 one-ratio: 1.41092
iteration: 3 recall: 0.4844 accuracy: 0.120365 cost: 0.0167507 M: 11.1153 delta: 0.845796 time: 15.4938 one-recall: 0.48 one-ratio: 1.11529
iteration: 4 recall: 0.9256 accuracy: 0.00761418 cost: 0.024913 M: 11.7249 delta: 0.566234 time: 21.4436 one-recall: 0.98 one-ratio: 1.00056
iteration: 5 recall: 0.9896 accuracy: 0.00041891 cost: 0.0376928 M: 17.4258 delta: 0.224488 time: 30.302 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9944 accuracy: 0.00018409 cost: 0.0460316 M: 21.1606 delta: 0.133992 time: 35.9948 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 36.309999999999945
Index size:  36532.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0007150000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0101483400, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2100000000, query time of that 0.0870723470, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2441.06 < 2491.79
  -> Decision False in time 1.8000000000, query time of that 0.7512533790, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0095060420, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3000000000, query time of that 0.0969693930, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2298.74 < 2320.07
  -> Decision False in time 10.2100000000, query time of that 0.7622091230, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0118872970, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4400000000, query time of that 0.1111692570, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1977.65 < 2001.06
  -> Decision False in time 2.1100000000, query time of that 0.0170330890, 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: 1.7754 cost: 0.00633344 M: 10 delta: 1 time: 6.85166 one-recall: 0.01 one-ratio: 2.00902
iteration: 2 recall: 0.076 accuracy: 0.571764 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4661 one-recall: 0.11 one-ratio: 1.4054
iteration: 3 recall: 0.4824 accuracy: 0.120375 cost: 0.0167507 M: 11.1153 delta: 0.84579 time: 15.4932 one-recall: 0.58 one-ratio: 1.10082
iteration: 4 recall: 0.9272 accuracy: 0.0095718 cost: 0.0249121 M: 11.725 delta: 0.566226 time: 21.4436 one-recall: 0.91 one-ratio: 1.02821
iteration: 5 recall: 0.992 accuracy: 0.000268816 cost: 0.0376862 M: 17.4237 delta: 0.224548 time: 30.3011 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 30.590000000000032
Index size:  29580.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0201850000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0051330970, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2408.78 < 2426.57
  -> Decision False in time 0.0300000000, query time of that 0.0073768320, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1647.27 < 1676.02
  -> Decision False in time 0.0000000000, query time of that 0.0003247140, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0049970220, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2517.97 < 2542.31
  -> Decision False in time 0.0100000000, query time of that 0.0008831250, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2562.54 < 2590.73
  -> Decision False in time 0.1100000000, query time of that 0.0044295940, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1730.47 < 2032.79
  -> Decision False in time 0.2700000000, query time of that 0.0014138700, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1619.49 < 1644.1
  -> Decision False in time 4.4900000000, query time of that 0.0205168970, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1841.7 < 1874.47
  -> Decision False in time 4.9500000000, query time of that 0.0223056100, 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: 1.66222 cost: 0.00633344 M: 10 delta: 1 time: 6.85493 one-recall: 0 one-ratio: 1.87137
iteration: 2 recall: 0.076 accuracy: 0.559988 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4696 one-recall: 0.06 one-ratio: 1.41333
iteration: 3 recall: 0.4932 accuracy: 0.113527 cost: 0.0167507 M: 11.1153 delta: 0.845793 time: 15.4951 one-recall: 0.59 one-ratio: 1.07821
iteration: 4 recall: 0.9192 accuracy: 0.00844443 cost: 0.0249109 M: 11.7244 delta: 0.566224 time: 21.4434 one-recall: 0.96 one-ratio: 1.00471
iteration: 5 recall: 0.9916 accuracy: 0.000431757 cost: 0.0376846 M: 17.4232 delta: 0.224582 time: 30.2963 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 30.58000000000004
Index size:  29584.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0064900000
  Testing...
|S| = 20
|T| = 283
Reject!
2301.95 < 2525.99
  -> Decision False in time 0.0100000000, query time of that 0.0032128350, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1600000000, query time of that 0.0428947620, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2262.08 < 2756.99
  -> Decision False in time 0.3100000000, query time of that 0.0812294260, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0047789460, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1481.83 < 1819.32
  -> Decision False in time 0.1300000000, query time of that 0.0055970310, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1516.49 < 1875.84
  -> Decision False in time 0.8800000000, query time of that 0.0358096470, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1673.94 < 1727.43
  -> Decision False in time 0.1400000000, query time of that 0.0009089940, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2177.34 < 2197.01
  -> Decision False in time 6.9800000000, query time of that 0.0310836680, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1705.74 < 1816.76
  -> Decision False in time 7.5600000000, query time of that 0.0339745070, 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: 0.0108 accuracy: 1.83797 cost: 0.00633344 M: 10 delta: 1 time: 6.85103 one-recall: 0.01 one-ratio: 1.87505
iteration: 2 recall: 0.068 accuracy: 0.636331 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4651 one-recall: 0.05 one-ratio: 1.41725
iteration: 3 recall: 0.468 accuracy: 0.13715 cost: 0.0167507 M: 11.1153 delta: 0.845792 time: 15.4912 one-recall: 0.49 one-ratio: 1.09941
iteration: 4 recall: 0.9152 accuracy: 0.0112358 cost: 0.024911 M: 11.7246 delta: 0.5662 time: 21.4423 one-recall: 0.95 one-ratio: 1.00622
iteration: 5 recall: 0.9936 accuracy: 0.000413148 cost: 0.0376864 M: 17.4232 delta: 0.224551 time: 30.3 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 30.589999999999918
Index size:  29580.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0113733333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0049118680, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1893.81 < 2118.32
  -> Decision False in time 0.0900000000, query time of that 0.0216494010, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1288.84 < 1683.3
  -> Decision False in time 0.1900000000, query time of that 0.0498661570, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0044272640, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2097.87 < 2155.44
  -> Decision False in time 0.3700000000, query time of that 0.0145969230, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1970.27 < 2957.37
  -> Decision False in time 1.2900000000, query time of that 0.0492455290, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0064964670, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1251.69 < 1401.48
  -> Decision False in time 2.3200000000, query time of that 0.0102946860, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1143.74 < 1215.14
  -> Decision False in time 7.0300000000, query time of that 0.0299322370, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 80, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 80, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.006 accuracy: 1.88242 cost: 0.00633344 M: 10 delta: 1 time: 6.85475 one-recall: 0 one-ratio: 2.05662
iteration: 2 recall: 0.0624 accuracy: 0.670175 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4688 one-recall: 0.03 one-ratio: 1.52781
iteration: 3 recall: 0.47 accuracy: 0.140751 cost: 0.0167507 M: 11.1153 delta: 0.845784 time: 15.4956 one-recall: 0.51 one-ratio: 1.10725
iteration: 4 recall: 0.9364 accuracy: 0.00618021 cost: 0.024913 M: 11.7249 delta: 0.566243 time: 21.4448 one-recall: 0.99 one-ratio: 1.00101
iteration: 5 recall: 0.9908 accuracy: 0.000342327 cost: 0.0376889 M: 17.4243 delta: 0.224542 time: 30.2993 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 30.590000000000032
Index size:  29584.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0005150000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0098107990, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2200000000, query time of that 0.1029058410, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2235.15 < 2259.04
  -> Decision False in time 1.9000000000, query time of that 0.8716130290, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0118986710, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3300000000, query time of that 0.1137139650, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.5000000000, query time of that 1.1713141890, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0134672240, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4400000000, query time of that 0.1296098360, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1877.96 < 1880.75
  -> Decision False in time 5.8700000000, query time of that 0.0558634860, 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: 1.74485 cost: 0.00633344 M: 10 delta: 1 time: 6.84997 one-recall: 0 one-ratio: 1.91287
iteration: 2 recall: 0.0692 accuracy: 0.560072 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4644 one-recall: 0.07 one-ratio: 1.39007
iteration: 3 recall: 0.4672 accuracy: 0.124672 cost: 0.0167507 M: 11.1153 delta: 0.845789 time: 15.4933 one-recall: 0.54 one-ratio: 1.11397
iteration: 4 recall: 0.92 accuracy: 0.00897854 cost: 0.0249117 M: 11.7247 delta: 0.566216 time: 21.4455 one-recall: 0.93 one-ratio: 1.01896
iteration: 5 recall: 0.986 accuracy: 0.00112448 cost: 0.0376905 M: 17.4243 delta: 0.224512 time: 30.3057 one-recall: 0.99 one-ratio: 1.00658
iteration: 6 recall: 0.992 accuracy: 0.000611685 cost: 0.0460198 M: 21.156 delta: 0.134132 time: 36.0006 one-recall: 0.99 one-ratio: 1.00658
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 36.319999999999936
Index size:  36532.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0026950000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0057692580, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0493692170, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
809.62 < 1030.92
  -> Decision False in time 1.0600000000, query time of that 0.3092165300, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0060716760, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2400000000, query time of that 0.0575686920, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2067.64 < 2124.61
  -> Decision False in time 3.2100000000, query time of that 0.1430276050, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0072709350, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.3300000000, query time of that 0.0675911270, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1499.3 < 1549.2
  -> Decision False in time 0.6900000000, query time of that 0.0032009770, 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: 0.0068 accuracy: 1.72221 cost: 0.00633344 M: 10 delta: 1 time: 6.8561 one-recall: 0.01 one-ratio: 1.87987
iteration: 2 recall: 0.072 accuracy: 0.565143 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4692 one-recall: 0.09 one-ratio: 1.36993
iteration: 3 recall: 0.4912 accuracy: 0.112003 cost: 0.0167507 M: 11.1153 delta: 0.845806 time: 15.4947 one-recall: 0.51 one-ratio: 1.08396
iteration: 4 recall: 0.9364 accuracy: 0.00658559 cost: 0.02491 M: 11.7246 delta: 0.566218 time: 21.4439 one-recall: 0.95 one-ratio: 1.01135
iteration: 5 recall: 0.9872 accuracy: 0.000763258 cost: 0.0376866 M: 17.4239 delta: 0.224542 time: 30.301 one-recall: 0.99 one-ratio: 1.00049
iteration: 6 recall: 0.9948 accuracy: 0.000356021 cost: 0.046024 M: 21.1592 delta: 0.134062 time: 35.9951 one-recall: 0.99 one-ratio: 1.00049
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 36.320000000000164
Index size:  36524.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004550000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0138049250, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2400000000, query time of that 0.1251591910, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.4800000000, query time of that 1.2644608750, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1500000000, query time of that 0.0145240920, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.1440677340, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.8700000000, query time of that 1.4142507500, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0157789300, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5000000000, query time of that 0.1556551150, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1279.08 < 1341.27
  -> Decision False in time 14.7900000000, query time of that 0.1705026470, 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: 0.0056 accuracy: 1.62898 cost: 0.00633344 M: 10 delta: 1 time: 6.85434 one-recall: 0.01 one-ratio: 1.86089
iteration: 2 recall: 0.064 accuracy: 0.544939 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4699 one-recall: 0.06 one-ratio: 1.38481
iteration: 3 recall: 0.4708 accuracy: 0.119461 cost: 0.0167507 M: 11.1153 delta: 0.845782 time: 15.4994 one-recall: 0.46 one-ratio: 1.09606
iteration: 4 recall: 0.9348 accuracy: 0.00674044 cost: 0.0249113 M: 11.7246 delta: 0.566193 time: 21.4502 one-recall: 0.98 one-ratio: 1.00665
iteration: 5 recall: 0.9916 accuracy: 0.000329689 cost: 0.037689 M: 17.4256 delta: 0.224508 time: 30.3093 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 30.589999999999918
Index size:  29592.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0006250000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0099318590, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2200000000, query time of that 0.0965502590, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.1800000000, query time of that 0.9554420820, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0109085140, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3300000000, query time of that 0.1108641000, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.4000000000, query time of that 1.0812867690, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0126964870, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1411.47 < 1449.31
  -> Decision False in time 11.0300000000, query time of that 0.0967683810, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1991.19 < 2001.06
  -> Decision False in time 1.2600000000, query time of that 0.0123018780, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 30, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 30, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0068 accuracy: 1.73461 cost: 0.00633344 M: 10 delta: 1 time: 6.854 one-recall: 0.01 one-ratio: 1.9056
iteration: 2 recall: 0.0744 accuracy: 0.565308 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4679 one-recall: 0.15 one-ratio: 1.33964
iteration: 3 recall: 0.4656 accuracy: 0.121619 cost: 0.0167507 M: 11.1153 delta: 0.845798 time: 15.494 one-recall: 0.51 one-ratio: 1.08868
iteration: 4 recall: 0.9316 accuracy: 0.00641637 cost: 0.0249113 M: 11.7248 delta: 0.566206 time: 21.4428 one-recall: 0.98 one-ratio: 1.00191
iteration: 5 recall: 0.9936 accuracy: 0.000369328 cost: 0.0376864 M: 17.4245 delta: 0.22455 time: 30.2967 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 30.579999999999927
Index size:  29584.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0014300000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0065631770, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1900000000, query time of that 0.0629922820, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1942.02 < 1954.53
  -> Decision False in time 1.4900000000, query time of that 0.5051033720, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0080828240, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1989.2 < 2113.48
  -> Decision False in time 0.8500000000, query time of that 0.0454597270, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1382.22 < 2192.89
  -> Decision False in time 7.3800000000, query time of that 0.4021473990, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0090200590, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2249.51 < 2304.75
  -> Decision False in time 9.4700000000, query time of that 0.0574273050, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1450.14 < 1537.15
  -> Decision False in time 3.3900000000, query time of that 0.0210139820, 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: 0.0048 accuracy: 1.66844 cost: 0.00633344 M: 10 delta: 1 time: 6.85634 one-recall: 0.01 one-ratio: 1.89677
iteration: 2 recall: 0.0628 accuracy: 0.580256 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4699 one-recall: 0.07 one-ratio: 1.38482
iteration: 3 recall: 0.4596 accuracy: 0.123364 cost: 0.0167507 M: 11.1153 delta: 0.845774 time: 15.4964 one-recall: 0.43 one-ratio: 1.11369
iteration: 4 recall: 0.9112 accuracy: 0.00936133 cost: 0.0249131 M: 11.7252 delta: 0.566219 time: 21.4464 one-recall: 0.95 one-ratio: 1.0132
iteration: 5 recall: 0.9884 accuracy: 0.000979086 cost: 0.0376877 M: 17.4234 delta: 0.224556 time: 30.3028 one-recall: 0.99 one-ratio: 1.00151
iteration: 6 recall: 0.9944 accuracy: 0.000551672 cost: 0.0460288 M: 21.1589 delta: 0.134116 time: 35.9991 one-recall: 0.99 one-ratio: 1.00151
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 36.31000000000017
Index size:  36528.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0030233333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0095937570, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2000000000, query time of that 0.0793131440, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2220.07 < 2478.03
  -> Decision False in time 0.7000000000, query time of that 0.2746393400, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0079569180, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2113.13 < 2929.14
  -> Decision False in time 0.3000000000, query time of that 0.0212186150, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2203.09 < 2328.64
  -> Decision False in time 6.0900000000, query time of that 0.4139888710, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0102112330, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2157.38 < 2170.27
  -> Decision False in time 2.5600000000, query time of that 0.0185821100, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2248.62 < 2615.41
  -> Decision False in time 8.9200000000, query time of that 0.0651561840, with c1=5.0000000000, c2=0.1000000000
