copying files to /scratch...
starting benchmark...
/scratch/knn/venv/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
running only kgraph
order: [Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 70, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 40, {'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', 80, {'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]), 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', 10, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 100, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 60, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 20, {'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', 5, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 3, {'reverse': -1}, False])]
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 70, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 70, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.008 accuracy: 1.6488 cost: 0.00633344 M: 10 delta: 1 time: 0.662558 one-recall: 0 one-ratio: 1.98824
iteration: 2 recall: 0.0748 accuracy: 0.576643 cost: 0.0102207 M: 10 delta: 0.893264 time: 0.903342 one-recall: 0.07 one-ratio: 1.46524
iteration: 3 recall: 0.4584 accuracy: 0.129751 cost: 0.0167282 M: 11.1226 delta: 0.845945 time: 1.2263 one-recall: 0.46 one-ratio: 1.12263
iteration: 4 recall: 0.9148 accuracy: 0.0078007 cost: 0.0248721 M: 11.7203 delta: 0.566045 time: 1.59875 one-recall: 0.97 one-ratio: 1.006
iteration: 5 recall: 0.9892 accuracy: 0.000422819 cost: 0.0376471 M: 17.421 delta: 0.223972 time: 2.14618 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9932 accuracy: 0.000213504 cost: 0.0459966 M: 21.1716 delta: 0.1336 time: 2.53542 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 46.54
Index size:  97732.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004216667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0116506220, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2400000000, query time of that 0.1143934390, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.3400000000, query time of that 1.1273802920, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0128593360, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.1309075650, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.7000000000, query time of that 1.3016471030, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0160423080, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5600000000, query time of that 0.1414329710, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2030.6 < 2042.72
  -> Decision False in time 44.4600000000, query time of that 0.4895963420, 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: 0.0096 accuracy: 1.84315 cost: 0.00633344 M: 10 delta: 1 time: 6.88875 one-recall: 0.02 one-ratio: 1.89745
iteration: 2 recall: 0.0716 accuracy: 0.611339 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4987 one-recall: 0.06 one-ratio: 1.39342
iteration: 3 recall: 0.4564 accuracy: 0.135365 cost: 0.0167507 M: 11.1153 delta: 0.845784 time: 15.522 one-recall: 0.58 one-ratio: 1.07855
iteration: 4 recall: 0.9184 accuracy: 0.00923209 cost: 0.0249109 M: 11.7246 delta: 0.566211 time: 21.4675 one-recall: 0.96 one-ratio: 1.00679
iteration: 5 recall: 0.9888 accuracy: 0.000656903 cost: 0.037689 M: 17.4241 delta: 0.224504 time: 30.3221 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9952 accuracy: 0.000239886 cost: 0.0460239 M: 21.159 delta: 0.134062 time: 36.0097 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 36.33000000000001
Index size:  100212.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0030250000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0090965730, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1339.94 < 2892.74
  -> Decision False in time 0.1000000000, query time of that 0.0387746010, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2313.79 < 2387.33
  -> Decision False in time 0.2100000000, query time of that 0.0818947980, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0089035970, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3000000000, query time of that 0.0896053810, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2566.61 < 2955.1
  -> Decision False in time 2.7300000000, query time of that 0.1847357490, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0117038010, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2277 < 2641.11
  -> Decision False in time 2.9400000000, query time of that 0.0311031270, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1418.22 < 1488.72
  -> Decision False in time 21.1900000000, query time of that 0.2111268890, 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: 0.0084 accuracy: 1.52767 cost: 0.00633344 M: 10 delta: 1 time: 6.90357 one-recall: 0.01 one-ratio: 1.74858
iteration: 2 recall: 0.0764 accuracy: 0.510227 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5267 one-recall: 0.09 one-ratio: 1.35065
iteration: 3 recall: 0.488 accuracy: 0.107708 cost: 0.0167507 M: 11.1153 delta: 0.845791 time: 15.5667 one-recall: 0.52 one-ratio: 1.08025
iteration: 4 recall: 0.9252 accuracy: 0.00648685 cost: 0.0249113 M: 11.7248 delta: 0.566209 time: 21.5311 one-recall: 0.98 one-ratio: 1.0071
iteration: 5 recall: 0.9888 accuracy: 0.000415394 cost: 0.0376803 M: 17.4212 delta: 0.224599 time: 30.4099 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9928 accuracy: 0.00029957 cost: 0.0460126 M: 21.1558 delta: 0.134144 time: 36.1285 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 36.44
Index size:  100220.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0006966667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0097224760, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2100000000, query time of that 0.0877310140, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.1300000000, query time of that 0.8859780870, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0094428110, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3300000000, query time of that 0.0997736200, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.4700000000, query time of that 1.0052147460, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3900000000, query time of that 0.0110464020, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5600000000, query time of that 0.1121348640, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Accept!
  -> Decision True in time 138.1900000000, query time of that 1.1379917910, 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: 0.0084 accuracy: 1.70355 cost: 0.00633344 M: 10 delta: 1 time: 6.90412 one-recall: 0 one-ratio: 1.86535
iteration: 2 recall: 0.0724 accuracy: 0.55923 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5289 one-recall: 0.1 one-ratio: 1.33599
iteration: 3 recall: 0.4808 accuracy: 0.114087 cost: 0.0167507 M: 11.1153 delta: 0.845808 time: 15.5678 one-recall: 0.55 one-ratio: 1.07519
iteration: 4 recall: 0.9124 accuracy: 0.00776997 cost: 0.0249114 M: 11.7246 delta: 0.566225 time: 21.5316 one-recall: 0.96 one-ratio: 1.00328
iteration: 5 recall: 0.9844 accuracy: 0.00110734 cost: 0.0376897 M: 17.4242 delta: 0.22453 time: 30.4135 one-recall: 0.98 one-ratio: 1.00134
iteration: 6 recall: 0.9924 accuracy: 0.000518765 cost: 0.0460223 M: 21.158 delta: 0.134073 time: 36.1309 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 36.47000000000003
Index size:  100220.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0151366667
  Testing...
|S| = 20
|T| = 283
Reject!
2158.67 < 2453.29
  -> Decision False in time 0.0200000000, query time of that 0.0043092550, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2537.78 < 2652.23
  -> Decision False in time 0.0000000000, query time of that 0.0007225980, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1839.68 < 1919.43
  -> Decision False in time 0.0200000000, query time of that 0.0062672760, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
1682.76 < 1955.19
  -> Decision False in time 0.0100000000, query time of that 0.0004768960, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2143.93 < 2282.5
  -> Decision False in time 0.4900000000, query time of that 0.0209739460, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1142.57 < 1156.32
  -> Decision False in time 0.1600000000, query time of that 0.0068293820, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0066375260, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1784.76 < 1837.03
  -> Decision False in time 6.7900000000, query time of that 0.0349669420, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1370.23 < 1373.13
  -> Decision False in time 0.6600000000, query time of that 0.0033100560, 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: 0.0064 accuracy: 1.91747 cost: 0.00633344 M: 10 delta: 1 time: 6.9013 one-recall: 0 one-ratio: 1.93882
iteration: 2 recall: 0.0736 accuracy: 0.600535 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5245 one-recall: 0.06 one-ratio: 1.37756
iteration: 3 recall: 0.4688 accuracy: 0.122181 cost: 0.0167507 M: 11.1153 delta: 0.845803 time: 15.562 one-recall: 0.5 one-ratio: 1.13736
iteration: 4 recall: 0.922 accuracy: 0.0110962 cost: 0.0249117 M: 11.7247 delta: 0.566216 time: 21.525 one-recall: 0.94 one-ratio: 1.03964
iteration: 5 recall: 0.982 accuracy: 0.00150165 cost: 0.0376874 M: 17.4238 delta: 0.22454 time: 30.4045 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9916 accuracy: 0.000298874 cost: 0.0460245 M: 21.1573 delta: 0.134119 time: 36.1234 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 36.44999999999993
Index size:  91180.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004366667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0123026890, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2400000000, query time of that 0.1112650660, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.3100000000, query time of that 1.0929228090, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0126384350, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3500000000, query time of that 0.1275584530, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.7200000000, query time of that 1.2535426140, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0146092230, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5200000000, query time of that 0.1398709030, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2403.64 < 2514.71
  -> Decision False in time 10.4300000000, query time of that 0.1068915330, 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: 1.87602 cost: 0.00633344 M: 10 delta: 1 time: 6.89726 one-recall: 0.01 one-ratio: 1.96935
iteration: 2 recall: 0.0756 accuracy: 0.624821 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5212 one-recall: 0.09 one-ratio: 1.36464
iteration: 3 recall: 0.4884 accuracy: 0.123855 cost: 0.0167507 M: 11.1153 delta: 0.845797 time: 15.5605 one-recall: 0.55 one-ratio: 1.0834
iteration: 4 recall: 0.9228 accuracy: 0.00754544 cost: 0.0249121 M: 11.7249 delta: 0.566226 time: 21.5241 one-recall: 0.96 one-ratio: 1.00339
iteration: 5 recall: 0.9924 accuracy: 0.000437594 cost: 0.0376812 M: 17.4214 delta: 0.224561 time: 30.4028 one-recall: 0.99 one-ratio: 1.00191
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 30.699999999999932
Index size:  84224.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0014283333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0075070590, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0610918860, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2526.56 < 2785.34
  -> Decision False in time 1.1900000000, query time of that 0.4044675790, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0065918050, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2900000000, query time of that 0.0739223050, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2430.23 < 2439.74
  -> Decision False in time 7.6500000000, query time of that 0.4280580260, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0089469520, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1232.07 < 1249.13
  -> Decision False in time 4.6900000000, query time of that 0.0298110790, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1277.56 < 1298.08
  -> Decision False in time 27.1500000000, query time of that 0.1683830420, 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: 0.0092 accuracy: 1.85276 cost: 0.00633344 M: 10 delta: 1 time: 6.90132 one-recall: 0 one-ratio: 1.95736
iteration: 2 recall: 0.0724 accuracy: 0.589663 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5255 one-recall: 0.06 one-ratio: 1.44141
iteration: 3 recall: 0.4892 accuracy: 0.121825 cost: 0.0167507 M: 11.1153 delta: 0.845787 time: 15.563 one-recall: 0.54 one-ratio: 1.12927
iteration: 4 recall: 0.9264 accuracy: 0.00814322 cost: 0.0249129 M: 11.7249 delta: 0.566207 time: 21.5257 one-recall: 0.94 one-ratio: 1.01917
iteration: 5 recall: 0.9868 accuracy: 0.0010586 cost: 0.0376822 M: 17.4217 delta: 0.224592 time: 30.3997 one-recall: 0.99 one-ratio: 1.00514
iteration: 6 recall: 0.994 accuracy: 0.000356315 cost: 0.0460125 M: 21.155 delta: 0.134213 time: 36.1131 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 36.43999999999994
Index size:  91172.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0421333333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0054062870, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2599.51 < 2797.64
  -> Decision False in time 0.0000000000, query time of that 0.0006746550, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2555.84 < 2891.31
  -> Decision False in time 0.0200000000, query time of that 0.0053340750, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
2836.89 < 3183.09
  -> Decision False in time 0.0900000000, query time of that 0.0040650240, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2570.84 < 3020.12
  -> Decision False in time 0.0000000000, query time of that 0.0002253050, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2045.42 < 3115.68
  -> Decision False in time 0.2800000000, query time of that 0.0125265630, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0066190870, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2757.39 < 2905.61
  -> Decision False in time 0.8200000000, query time of that 0.0047575510, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1897.19 < 2898.34
  -> Decision False in time 0.0700000000, query time of that 0.0005181790, 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: 0.0024 accuracy: 1.71205 cost: 0.00633344 M: 10 delta: 1 time: 6.89337 one-recall: 0 one-ratio: 1.99075
iteration: 2 recall: 0.0612 accuracy: 0.557073 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5159 one-recall: 0.09 one-ratio: 1.45109
iteration: 3 recall: 0.4692 accuracy: 0.121282 cost: 0.0167507 M: 11.1153 delta: 0.845782 time: 15.5544 one-recall: 0.53 one-ratio: 1.12034
iteration: 4 recall: 0.9132 accuracy: 0.00931623 cost: 0.0249114 M: 11.7246 delta: 0.566223 time: 21.5193 one-recall: 0.96 one-ratio: 1.01061
iteration: 5 recall: 0.99 accuracy: 0.000661625 cost: 0.0376833 M: 17.422 delta: 0.224547 time: 30.4026 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.996 accuracy: 0.000193941 cost: 0.0460126 M: 21.155 delta: 0.134127 time: 36.1209 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 36.440000000000055
Index size:  91168.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0042633333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0052316020, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
974.553 < 1105.72
  -> Decision False in time 0.1500000000, query time of that 0.0429408130, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2178.27 < 2266.46
  -> Decision False in time 0.1900000000, query time of that 0.0502847000, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0056063180, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2500000000, query time of that 0.0543436010, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1727.68 < 2184.61
  -> Decision False in time 2.7300000000, query time of that 0.1174498840, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0069598500, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1602.96 < 1628
  -> Decision False in time 5.9300000000, query time of that 0.0290825640, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1699.14 < 1849.66
  -> Decision False in time 8.5000000000, query time of that 0.0438453390, 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: 0.0052 accuracy: 1.67282 cost: 0.00633344 M: 10 delta: 1 time: 6.89763 one-recall: 0 one-ratio: 1.8781
iteration: 2 recall: 0.0692 accuracy: 0.5838 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5209 one-recall: 0.05 one-ratio: 1.39907
iteration: 3 recall: 0.484 accuracy: 0.115001 cost: 0.0167507 M: 11.1153 delta: 0.845784 time: 15.558 one-recall: 0.5 one-ratio: 1.10923
iteration: 4 recall: 0.913999 accuracy: 0.00822927 cost: 0.0249124 M: 11.7249 delta: 0.566205 time: 21.5218 one-recall: 0.99 one-ratio: 1.00011
iteration: 5 recall: 0.9888 accuracy: 0.000790005 cost: 0.0376909 M: 17.4234 delta: 0.224564 time: 30.4034 one-recall: 0.99 one-ratio: 1.00011
iteration: 6 recall: 0.9936 accuracy: 0.000531377 cost: 0.046032 M: 21.1606 delta: 0.13406 time: 36.1277 one-recall: 0.99 one-ratio: 1.00011
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 36.450000000000045
Index size:  91164.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0026900000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0061763610, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0497280070, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2098.91 < 2219.78
  -> Decision False in time 0.7000000000, query time of that 0.2042844430, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0054943130, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2500000000, query time of that 0.0588575390, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2363.76 < 2387.89
  -> Decision False in time 6.5200000000, query time of that 0.2990315350, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0069243200, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4100000000, query time of that 0.0721188380, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1113.72 < 1123.27
  -> Decision False in time 9.1200000000, query time of that 0.0488733900, 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: 0.0064 accuracy: 1.66326 cost: 0.00633344 M: 10 delta: 1 time: 6.90169 one-recall: 0.01 one-ratio: 1.88613
iteration: 2 recall: 0.0672 accuracy: 0.586805 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5274 one-recall: 0.08 one-ratio: 1.38871
iteration: 3 recall: 0.456 accuracy: 0.136141 cost: 0.0167507 M: 11.1153 delta: 0.845782 time: 15.5675 one-recall: 0.42 one-ratio: 1.1118
iteration: 4 recall: 0.9072 accuracy: 0.0103664 cost: 0.0249109 M: 11.7246 delta: 0.566207 time: 21.5297 one-recall: 0.91 one-ratio: 1.02027
iteration: 5 recall: 0.99 accuracy: 0.000506568 cost: 0.0376862 M: 17.4237 delta: 0.22457 time: 30.4104 one-recall: 0.99 one-ratio: 1.00035
iteration: 6 recall: 0.9948 accuracy: 0.000226203 cost: 0.0460284 M: 21.1604 delta: 0.134077 time: 36.1288 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 36.460000000000036
Index size:  91180.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004550000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0142365160, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2500000000, query time of that 0.1287687820, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.5000000000, query time of that 1.2689787370, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0143810330, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.1480134030, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.8600000000, query time of that 1.4303336030, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0164162930, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4800000000, query time of that 0.1624881460, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2274.42 < 2440.53
  -> Decision False in time 66.9000000000, query time of that 0.7856509290, 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: 0.0036 accuracy: 1.87531 cost: 0.00633344 M: 10 delta: 1 time: 6.89047 one-recall: 0 one-ratio: 2.04211
iteration: 2 recall: 0.0716 accuracy: 0.609387 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5135 one-recall: 0.08 one-ratio: 1.41655
iteration: 3 recall: 0.5144 accuracy: 0.117958 cost: 0.0167507 M: 11.1153 delta: 0.845806 time: 15.5516 one-recall: 0.59 one-ratio: 1.07285
iteration: 4 recall: 0.944799 accuracy: 0.0058672 cost: 0.0249116 M: 11.7249 delta: 0.566227 time: 21.5158 one-recall: 0.95 one-ratio: 1.01016
iteration: 5 recall: 0.996 accuracy: 0.000255683 cost: 0.0376918 M: 17.4252 delta: 0.224496 time: 30.4002 one-recall: 0.99 one-ratio: 1.00208
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 30.689999999999827
Index size:  84228.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0012466667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0094607960, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2418.31 < 2439.74
  -> Decision False in time 0.1900000000, query time of that 0.0829996200, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2291.95 < 2295.73
  -> Decision False in time 1.2300000000, query time of that 0.5183885690, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0102070400, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2061.87 < 2510.77
  -> Decision False in time 0.3300000000, query time of that 0.0255044080, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1915.55 < 1940.16
  -> Decision False in time 0.6000000000, query time of that 0.0477278200, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0125193130, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1682.07 < 1709.86
  -> Decision False in time 2.3500000000, query time of that 0.0197501990, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2371.98 < 2476.04
  -> Decision False in time 19.8700000000, query time of that 0.1699334780, 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: 0.0064 accuracy: 1.66998 cost: 0.00633344 M: 10 delta: 1 time: 6.89711 one-recall: 0.01 one-ratio: 1.89285
iteration: 2 recall: 0.064 accuracy: 0.545931 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5208 one-recall: 0.08 one-ratio: 1.3851
iteration: 3 recall: 0.4784 accuracy: 0.112738 cost: 0.0167507 M: 11.1153 delta: 0.845796 time: 15.558 one-recall: 0.5 one-ratio: 1.12044
iteration: 4 recall: 0.9092 accuracy: 0.00857387 cost: 0.0249116 M: 11.7247 delta: 0.566231 time: 21.5225 one-recall: 0.93 one-ratio: 1.01243
iteration: 5 recall: 0.9872 accuracy: 0.000807137 cost: 0.037683 M: 17.4213 delta: 0.224592 time: 30.4044 one-recall: 0.99 one-ratio: 1.00678
iteration: 6 recall: 0.9936 accuracy: 0.000491249 cost: 0.0460181 M: 21.1558 delta: 0.13416 time: 36.1274 one-recall: 0.99 one-ratio: 1.00678
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 36.450000000000045
Index size:  91188.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0016966667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0067123180, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0568232400, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.8100000000, query time of that 0.5942762990, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0071216650, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2600000000, query time of that 0.0657153960, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1138.32 < 1144.17
  -> Decision False in time 0.0500000000, query time of that 0.0029709220, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0075158070, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1368.18 < 1397.99
  -> Decision False in time 7.6400000000, query time of that 0.0473497140, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1851.7 < 1892.25
  -> Decision False in time 8.6100000000, query time of that 0.0518581200, 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: 0.0088 accuracy: 1.79373 cost: 0.00633344 M: 10 delta: 1 time: 6.90428 one-recall: 0 one-ratio: 1.91599
iteration: 2 recall: 0.0828 accuracy: 0.575596 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5286 one-recall: 0.05 one-ratio: 1.41346
iteration: 3 recall: 0.504 accuracy: 0.110552 cost: 0.0167507 M: 11.1153 delta: 0.845801 time: 15.567 one-recall: 0.53 one-ratio: 1.09538
iteration: 4 recall: 0.9416 accuracy: 0.00698636 cost: 0.0249117 M: 11.7247 delta: 0.566193 time: 21.5299 one-recall: 1 one-ratio: 1
iteration: 5 recall: 0.9932 accuracy: 0.000488208 cost: 0.0376821 M: 17.4215 delta: 0.224584 time: 30.4077 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 30.700000000000045
Index size:  84224.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0005633333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0122436590, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2200000000, query time of that 0.1083574190, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2203.52 < 2264.34
  -> Decision False in time 1.9800000000, query time of that 0.9347272820, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0124474550, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2350.86 < 2354.4
  -> Decision False in time 0.0700000000, query time of that 0.0084625700, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1885.41 < 2437.73
  -> Decision False in time 3.5100000000, query time of that 0.3201761220, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0141694640, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5000000000, query time of that 0.1363167220, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1636.07 < 1693.03
  -> Decision False in time 15.6800000000, query time of that 0.1576792760, 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: 0.0048 accuracy: 1.7057 cost: 0.00633344 M: 10 delta: 1 time: 6.90529 one-recall: 0.02 one-ratio: 1.92508
iteration: 2 recall: 0.0664 accuracy: 0.574516 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.53 one-recall: 0.08 one-ratio: 1.41761
iteration: 3 recall: 0.486 accuracy: 0.113541 cost: 0.0167507 M: 11.1153 delta: 0.845779 time: 15.5687 one-recall: 0.59 one-ratio: 1.07368
iteration: 4 recall: 0.926 accuracy: 0.00658049 cost: 0.0249124 M: 11.725 delta: 0.566233 time: 21.5322 one-recall: 0.95 one-ratio: 1.00413
iteration: 5 recall: 0.9884 accuracy: 0.000509258 cost: 0.0376854 M: 17.4221 delta: 0.224562 time: 30.4116 one-recall: 0.99 one-ratio: 1.00027
iteration: 6 recall: 0.996 accuracy: 0.000207182 cost: 0.0460209 M: 21.1584 delta: 0.134095 time: 36.1274 one-recall: 0.99 one-ratio: 1.00027
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 36.44999999999982
Index size:  91180.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0093350000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0050281400, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2089.87 < 2615.41
  -> Decision False in time 0.1000000000, query time of that 0.0244983300, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2045.59 < 2902.03
  -> Decision False in time 0.0100000000, query time of that 0.0031409270, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0052675100, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2114.23 < 2132.23
  -> Decision False in time 0.0300000000, query time of that 0.0014580810, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2119.09 < 2340.08
  -> Decision False in time 2.1600000000, query time of that 0.0882069240, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.4000000000, query time of that 0.0073092140, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.7000000000, query time of that 0.0660301240, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1453.42 < 1464.09
  -> Decision False in time 1.3600000000, query time of that 0.0072000010, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 3, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 3, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0064 accuracy: 1.53566 cost: 0.00633344 M: 10 delta: 1 time: 6.90235 one-recall: 0 one-ratio: 1.92501
iteration: 2 recall: 0.0636 accuracy: 0.546242 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5268 one-recall: 0.08 one-ratio: 1.41033
iteration: 3 recall: 0.4604 accuracy: 0.118479 cost: 0.0167507 M: 11.1153 delta: 0.845784 time: 15.5667 one-recall: 0.66 one-ratio: 1.10185
iteration: 4 recall: 0.9092 accuracy: 0.00983886 cost: 0.0249113 M: 11.7246 delta: 0.566224 time: 21.5307 one-recall: 0.97 one-ratio: 1.00871
iteration: 5 recall: 0.988 accuracy: 0.000527357 cost: 0.0376816 M: 17.4217 delta: 0.224594 time: 30.4082 one-recall: 0.99 one-ratio: 1.00004
iteration: 6 recall: 0.9984 accuracy: 0.000100661 cost: 0.046013 M: 21.1545 delta: 0.134182 time: 36.123 one-recall: 0.99 one-ratio: 1.00004
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 36.440000000000055
Index size:  91172.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0096350000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0046489640, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1329.65 < 1376.71
  -> Decision False in time 0.0500000000, query time of that 0.0148424030, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
993.645 < 1340.49
  -> Decision False in time 0.1200000000, query time of that 0.0301171100, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0047437880, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1179.58 < 2279.06
  -> Decision False in time 0.0500000000, query time of that 0.0021649560, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2057.64 < 2214.08
  -> Decision False in time 1.9700000000, query time of that 0.0781830030, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0066918770, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1247.15 < 1258.05
  -> Decision False in time 0.2500000000, query time of that 0.0015325560, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1953.41 < 2122.74
  -> Decision False in time 4.9000000000, query time of that 0.0238126040, with c1=5.0000000000, c2=0.1000000000
