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', 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', 40, {'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', 80, {'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', 3, {'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', 2, {'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', 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', 50, {'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]) ...
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: 0.008 accuracy: 1.6488 cost: 0.00633344 M: 10 delta: 1 time: 0.713892 one-recall: 0 one-ratio: 1.98824
iteration: 2 recall: 0.0748 accuracy: 0.576643 cost: 0.0102207 M: 10 delta: 0.893264 time: 0.954487 one-recall: 0.07 one-ratio: 1.46524
iteration: 3 recall: 0.4588 accuracy: 0.129708 cost: 0.0167282 M: 11.1226 delta: 0.845954 time: 1.27889 one-recall: 0.46 one-ratio: 1.12263
iteration: 4 recall: 0.914 accuracy: 0.00790804 cost: 0.0248711 M: 11.72 delta: 0.566023 time: 1.65069 one-recall: 0.97 one-ratio: 1.006
iteration: 5 recall: 0.9892 accuracy: 0.000422819 cost: 0.0376436 M: 17.4204 delta: 0.224002 time: 2.19671 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9932 accuracy: 0.000213504 cost: 0.0459821 M: 21.1672 delta: 0.133641 time: 2.58628 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 46.52
Index size:  97528.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004450000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0135866010, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2500000000, query time of that 0.1306167020, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.5300000000, query time of that 1.3217928130, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0147261440, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.1490947450, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2101.08 < 2286.56
  -> Decision False in time 11.7500000000, query time of that 1.2545496900, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0157001640, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5400000000, query time of that 0.1627440880, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1226.19 < 1244.35
  -> Decision False in time 6.7900000000, query time of that 0.0813335000, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 5, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 5, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0068 accuracy: 1.75086 cost: 0.00633344 M: 10 delta: 1 time: 6.88699 one-recall: 0 one-ratio: 1.91066
iteration: 2 recall: 0.0744 accuracy: 0.555351 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5044 one-recall: 0.06 one-ratio: 1.38887
iteration: 3 recall: 0.48 accuracy: 0.117901 cost: 0.0167507 M: 11.1153 delta: 0.845804 time: 15.5354 one-recall: 0.53 one-ratio: 1.10986
iteration: 4 recall: 0.9176 accuracy: 0.00866458 cost: 0.0249111 M: 11.7246 delta: 0.566225 time: 21.4889 one-recall: 0.96 one-ratio: 1.00843
iteration: 5 recall: 0.9888 accuracy: 0.000642636 cost: 0.0376826 M: 17.4227 delta: 0.224567 time: 30.3521 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9964 accuracy: 0.000110865 cost: 0.0460113 M: 21.1542 delta: 0.134176 time: 36.0513 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 36.370000000000005
Index size:  88524.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0093550000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0048596490, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0439548010, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2203.02 < 2600.21
  -> Decision False in time 0.0500000000, query time of that 0.0130128280, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1200000000, query time of that 0.0048416170, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2666.07 < 2682.73
  -> Decision False in time 1.1900000000, query time of that 0.0482661240, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1963.58 < 2590.44
  -> Decision False in time 0.6400000000, query time of that 0.0267966870, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0061761490, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4300000000, query time of that 0.0614726620, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1974.49 < 2202.95
  -> Decision False in time 6.6000000000, query time of that 0.0306262720, 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: 0.0044 accuracy: 1.58305 cost: 0.00633344 M: 10 delta: 1 time: 6.89269 one-recall: 0 one-ratio: 1.95961
iteration: 2 recall: 0.066 accuracy: 0.562959 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5089 one-recall: 0.08 one-ratio: 1.43242
iteration: 3 recall: 0.4604 accuracy: 0.128762 cost: 0.0167507 M: 11.1153 delta: 0.845812 time: 15.5393 one-recall: 0.52 one-ratio: 1.11387
iteration: 4 recall: 0.9112 accuracy: 0.0100281 cost: 0.0249112 M: 11.7245 delta: 0.566208 time: 21.4924 one-recall: 0.97 one-ratio: 1.00434
iteration: 5 recall: 0.9892 accuracy: 0.000546928 cost: 0.0376878 M: 17.4231 delta: 0.224546 time: 30.3532 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9968 accuracy: 0.000159794 cost: 0.0460036 M: 21.1505 delta: 0.134228 time: 36.0402 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 36.359999999999985
Index size:  88540.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0030250000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0087704050, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2000000000, query time of that 0.0762247300, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2265.36 < 2902.03
  -> Decision False in time 0.0000000000, query time of that 0.0020203840, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0094891800, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2244.01 < 2252.21
  -> Decision False in time 0.1500000000, query time of that 0.0103472580, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2194.65 < 2405.75
  -> Decision False in time 1.2500000000, query time of that 0.0828720260, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0115607850, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4400000000, query time of that 0.1002605370, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1504.06 < 1533.62
  -> Decision False in time 77.2700000000, query time of that 0.5752955200, 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: 0.0076 accuracy: 1.78362 cost: 0.00633344 M: 10 delta: 1 time: 6.88636 one-recall: 0 one-ratio: 1.8945
iteration: 2 recall: 0.0744 accuracy: 0.598286 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5013 one-recall: 0.05 one-ratio: 1.39783
iteration: 3 recall: 0.4392 accuracy: 0.134486 cost: 0.0167507 M: 11.1153 delta: 0.845788 time: 15.5312 one-recall: 0.45 one-ratio: 1.11536
iteration: 4 recall: 0.902 accuracy: 0.00906337 cost: 0.024912 M: 11.7249 delta: 0.566212 time: 21.4842 one-recall: 0.94 one-ratio: 1.00691
iteration: 5 recall: 0.984 accuracy: 0.000842545 cost: 0.037688 M: 17.4226 delta: 0.224568 time: 30.3419 one-recall: 0.99 one-ratio: 1.00154
iteration: 6 recall: 0.9908 accuracy: 0.00045147 cost: 0.0460216 M: 21.1563 delta: 0.134198 time: 36.039 one-recall: 0.99 one-ratio: 1.00154
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 36.370000000000005
Index size:  88536.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004550000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0133948900, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2500000000, query time of that 0.1274045240, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.4600000000, query time of that 1.2410329940, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0133763110, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.1399666590, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1628.76 < 1647.28
  -> Decision False in time 8.1600000000, query time of that 0.8279545760, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3900000000, query time of that 0.0174856620, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5500000000, query time of that 0.1531959020, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2459.42 < 2508.22
  -> Decision False in time 11.2700000000, query time of that 0.1255963580, 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: 1.73208 cost: 0.00633344 M: 10 delta: 1 time: 6.89651 one-recall: 0.01 one-ratio: 2.05001
iteration: 2 recall: 0.0636 accuracy: 0.603671 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5126 one-recall: 0.16 one-ratio: 1.44153
iteration: 3 recall: 0.4656 accuracy: 0.139735 cost: 0.0167507 M: 11.1153 delta: 0.845786 time: 15.5416 one-recall: 0.57 one-ratio: 1.11814
iteration: 4 recall: 0.9136 accuracy: 0.0134168 cost: 0.0249129 M: 11.7249 delta: 0.566224 time: 21.4962 one-recall: 0.96 one-ratio: 1.00285
iteration: 5 recall: 0.9876 accuracy: 0.000675953 cost: 0.0376821 M: 17.422 delta: 0.224545 time: 30.3559 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.994 accuracy: 0.000210125 cost: 0.0460197 M: 21.1557 delta: 0.134159 time: 36.0596 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 36.379999999999995
Index size:  88544.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004383333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0123103940, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2300000000, query time of that 0.1094217170, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.3300000000, query time of that 1.1123063320, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0108408700, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3400000000, query time of that 0.1204227380, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.6300000000, query time of that 1.2650122500, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0139321280, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4900000000, query time of that 0.1330147660, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2065.35 < 2138.5
  -> Decision False in time 65.0400000000, query time of that 0.6484456760, 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: 0.0084 accuracy: 1.80364 cost: 0.00633344 M: 10 delta: 1 time: 6.89556 one-recall: 0 one-ratio: 2.04142
iteration: 2 recall: 0.0744 accuracy: 0.609784 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5124 one-recall: 0.03 one-ratio: 1.42342
iteration: 3 recall: 0.4636 accuracy: 0.12899 cost: 0.0167507 M: 11.1153 delta: 0.845798 time: 15.5429 one-recall: 0.56 one-ratio: 1.11147
iteration: 4 recall: 0.93 accuracy: 0.00696569 cost: 0.0249116 M: 11.7252 delta: 0.566222 time: 21.4931 one-recall: 0.99 one-ratio: 1.00489
iteration: 5 recall: 0.9908 accuracy: 0.000407132 cost: 0.0376871 M: 17.4235 delta: 0.22457 time: 30.3518 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 30.639999999999986
Index size:  81592.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0012483333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0102761870, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2100000000, query time of that 0.0869358620, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2300.91 < 2405.75
  -> Decision False in time 0.9200000000, query time of that 0.3889624660, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0110627200, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3000000000, query time of that 0.0995870540, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1598.03 < 1889.67
  -> Decision False in time 1.2600000000, query time of that 0.0929972680, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0115935680, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4300000000, query time of that 0.1100208750, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1762.49 < 2022.94
  -> Decision False in time 12.6100000000, query time of that 0.1030246510, 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: 0.0072 accuracy: 1.78803 cost: 0.00633344 M: 10 delta: 1 time: 6.88726 one-recall: 0 one-ratio: 1.91264
iteration: 2 recall: 0.0812 accuracy: 0.584313 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5042 one-recall: 0.07 one-ratio: 1.34834
iteration: 3 recall: 0.4876 accuracy: 0.122677 cost: 0.0167507 M: 11.1153 delta: 0.845786 time: 15.5333 one-recall: 0.52 one-ratio: 1.08135
iteration: 4 recall: 0.9288 accuracy: 0.00872793 cost: 0.0249109 M: 11.7243 delta: 0.566231 time: 21.4903 one-recall: 0.93 one-ratio: 1.01323
iteration: 5 recall: 0.9916 accuracy: 0.000458998 cost: 0.0376844 M: 17.4236 delta: 0.22457 time: 30.3517 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 30.639999999999986
Index size:  81600.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0123950000
  Testing...
|S| = 20
|T| = 283
Reject!
1294.48 < 1562.99
  -> Decision False in time 0.0100000000, query time of that 0.0035379120, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1796.24 < 2248.49
  -> Decision False in time 0.1200000000, query time of that 0.0300532580, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1881.22 < 2139.8
  -> Decision False in time 0.0100000000, query time of that 0.0001712260, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0049255220, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
763.508 < 950.127
  -> Decision False in time 0.5500000000, query time of that 0.0210594020, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2632.51 < 2660.65
  -> Decision False in time 0.0000000000, query time of that 0.0001841820, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0057489670, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2657.88 < 2961.41
  -> Decision False in time 7.7500000000, query time of that 0.0317687860, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1496.35 < 1553.83
  -> Decision False in time 1.1200000000, query time of that 0.0047180670, 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: 0.0056 accuracy: 1.75535 cost: 0.00633344 M: 10 delta: 1 time: 6.89348 one-recall: 0 one-ratio: 1.92916
iteration: 2 recall: 0.0704 accuracy: 0.595666 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5091 one-recall: 0.1 one-ratio: 1.38236
iteration: 3 recall: 0.46 accuracy: 0.130551 cost: 0.0167507 M: 11.1153 delta: 0.845786 time: 15.5369 one-recall: 0.57 one-ratio: 1.08661
iteration: 4 recall: 0.9208 accuracy: 0.00693231 cost: 0.0249115 M: 11.7248 delta: 0.566206 time: 21.4888 one-recall: 0.97 one-ratio: 1.00382
iteration: 5 recall: 0.99 accuracy: 0.000249799 cost: 0.0376884 M: 17.4238 delta: 0.224522 time: 30.3537 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9948 accuracy: 0.000157345 cost: 0.046019 M: 21.1573 delta: 0.134108 time: 36.0543 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 36.379999999999995
Index size:  88544.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0421633333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0051760290, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1874.96 < 3052.34
  -> Decision False in time 0.0000000000, query time of that 0.0001795790, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2691.7 < 2909.75
  -> Decision False in time 0.0000000000, query time of that 0.0020200690, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
2770.31 < 3000.8
  -> Decision False in time 0.0000000000, query time of that 0.0001358890, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2176.51 < 2302.13
  -> Decision False in time 0.2100000000, query time of that 0.0089891850, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1888.57 < 2959.7
  -> Decision False in time 0.0400000000, query time of that 0.0019028450, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0069394220, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
3089.19 < 3104.91
  -> Decision False in time 0.3400000000, query time of that 0.0020203730, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1356.46 < 1384.72
  -> Decision False in time 0.4000000000, query time of that 0.0017764080, 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: 0.0056 accuracy: 1.68546 cost: 0.00633344 M: 10 delta: 1 time: 6.89943 one-recall: 0 one-ratio: 1.95835
iteration: 2 recall: 0.0612 accuracy: 0.575445 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5166 one-recall: 0.02 one-ratio: 1.45367
iteration: 3 recall: 0.4536 accuracy: 0.124386 cost: 0.0167507 M: 11.1153 delta: 0.845795 time: 15.5469 one-recall: 0.52 one-ratio: 1.10006
iteration: 4 recall: 0.9064 accuracy: 0.00943448 cost: 0.024912 M: 11.725 delta: 0.566196 time: 21.5005 one-recall: 0.96 one-ratio: 1.0129
iteration: 5 recall: 0.9856 accuracy: 0.00123664 cost: 0.0376847 M: 17.4223 delta: 0.224553 time: 30.3632 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9936 accuracy: 0.00027868 cost: 0.0460215 M: 21.1581 delta: 0.13413 time: 36.0669 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 36.379999999999995
Index size:  88532.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0042500000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0056707050, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1600000000, query time of that 0.0458000490, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2126.36 < 2178.88
  -> Decision False in time 0.2700000000, query time of that 0.0732563580, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0057241790, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2300000000, query time of that 0.0520390830, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1838.04 < 2006.93
  -> Decision False in time 5.8800000000, query time of that 0.2484826080, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.0070712150, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.3100000000, query time of that 0.0628478200, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1799.46 < 1832.24
  -> Decision False in time 7.0300000000, query time of that 0.0343345350, 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: 0.0076 accuracy: 1.71511 cost: 0.00633344 M: 10 delta: 1 time: 6.89376 one-recall: 0.02 one-ratio: 1.87876
iteration: 2 recall: 0.0736 accuracy: 0.56647 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5101 one-recall: 0.06 one-ratio: 1.42239
iteration: 3 recall: 0.4764 accuracy: 0.121412 cost: 0.0167507 M: 11.1153 delta: 0.845782 time: 15.5399 one-recall: 0.41 one-ratio: 1.11425
iteration: 4 recall: 0.9324 accuracy: 0.00644118 cost: 0.0249126 M: 11.725 delta: 0.566235 time: 21.4938 one-recall: 0.98 one-ratio: 1.00429
iteration: 5 recall: 0.9928 accuracy: 0.000466268 cost: 0.037692 M: 17.4251 delta: 0.224502 time: 30.3582 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 30.639999999999873
Index size:  81592.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0201550000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0048471180, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1714.44 < 1920.38
  -> Decision False in time 0.0900000000, query time of that 0.0222266020, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1481.73 < 2151.74
  -> Decision False in time 0.0400000000, query time of that 0.0101597300, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0048317580, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1770.39 < 2107.21
  -> Decision False in time 0.4000000000, query time of that 0.0159565430, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1306.57 < 1616.03
  -> Decision False in time 0.5100000000, query time of that 0.0187828020, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1767.41 < 2212.96
  -> Decision False in time 0.0000000000, query time of that 0.0002124300, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1946.41 < 2006.01
  -> Decision False in time 7.0900000000, query time of that 0.0303588000, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1828.28 < 2020.46
  -> Decision False in time 0.2800000000, query time of that 0.0014901290, 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: 0.0092 accuracy: 1.63519 cost: 0.00633344 M: 10 delta: 1 time: 6.88848 one-recall: 0 one-ratio: 1.92315
iteration: 2 recall: 0.0791999 accuracy: 0.537224 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5031 one-recall: 0.09 one-ratio: 1.40638
iteration: 3 recall: 0.4824 accuracy: 0.114129 cost: 0.0167507 M: 11.1153 delta: 0.845782 time: 15.5308 one-recall: 0.64 one-ratio: 1.1007
iteration: 4 recall: 0.923599 accuracy: 0.00661407 cost: 0.0249115 M: 11.7251 delta: 0.566229 time: 21.4828 one-recall: 0.97 one-ratio: 1.00126
iteration: 5 recall: 0.9936 accuracy: 0.000457487 cost: 0.0376836 M: 17.4215 delta: 0.224568 time: 30.3402 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 30.61999999999989
Index size:  81592.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0039666667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0052637950, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0467332520, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1014.02 < 1259.9
  -> Decision False in time 0.9900000000, query time of that 0.2691521250, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0054317190, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2500000000, query time of that 0.0554563830, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1548.79 < 1722.98
  -> Decision False in time 6.2000000000, query time of that 0.2600857940, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0064096500, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4400000000, query time of that 0.0629506530, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1384.14 < 1461.88
  -> Decision False in time 3.8300000000, query time of that 0.0183975330, 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: 0.0088 accuracy: 1.74773 cost: 0.00633344 M: 10 delta: 1 time: 6.88029 one-recall: 0 one-ratio: 1.9628
iteration: 2 recall: 0.082 accuracy: 0.559456 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.495 one-recall: 0.08 one-ratio: 1.38101
iteration: 3 recall: 0.5096 accuracy: 0.10936 cost: 0.0167507 M: 11.1153 delta: 0.845794 time: 15.5225 one-recall: 0.54 one-ratio: 1.09404
iteration: 4 recall: 0.9316 accuracy: 0.00661878 cost: 0.0249115 M: 11.7248 delta: 0.566231 time: 21.4723 one-recall: 1 one-ratio: 1
iteration: 5 recall: 0.9956 accuracy: 0.000275389 cost: 0.0376812 M: 17.421 delta: 0.224594 time: 30.3253 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 30.6099999999999
Index size:  81596.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0006250000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0099585100, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2200000000, query time of that 0.0980281700, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.2000000000, query time of that 0.9582571010, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0112985180, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3400000000, query time of that 0.1099179640, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1504.06 < 1533.62
  -> Decision False in time 3.6100000000, query time of that 0.2844534320, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3900000000, query time of that 0.0141430060, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5200000000, query time of that 0.1217462560, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1625.61 < 1627.94
  -> Decision False in time 8.4100000000, query time of that 0.0758510830, 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: 0.0084 accuracy: 1.58667 cost: 0.00633344 M: 10 delta: 1 time: 6.88588 one-recall: 0 one-ratio: 1.86814
iteration: 2 recall: 0.0792 accuracy: 0.53653 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4999 one-recall: 0.11 one-ratio: 1.34928
iteration: 3 recall: 0.4748 accuracy: 0.118562 cost: 0.0167507 M: 11.1153 delta: 0.845793 time: 15.5277 one-recall: 0.52 one-ratio: 1.0665
iteration: 4 recall: 0.9204 accuracy: 0.00692212 cost: 0.0249126 M: 11.725 delta: 0.56623 time: 21.479 one-recall: 0.99 one-ratio: 1.00251
iteration: 5 recall: 0.9848 accuracy: 0.000662152 cost: 0.0376855 M: 17.4229 delta: 0.224554 time: 30.3349 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9924 accuracy: 0.000279089 cost: 0.0460236 M: 21.1584 delta: 0.134117 time: 36.0344 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 36.3599999999999
Index size:  88540.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0010066667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0077400410, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1900000000, query time of that 0.0688140310, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2398.49 < 2509.2
  -> Decision False in time 0.5800000000, query time of that 0.2050763810, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0079530530, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3100000000, query time of that 0.0775893810, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1182.7 < 1204.86
  -> Decision False in time 1.7200000000, query time of that 0.1016772030, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3900000000, query time of that 0.0085041680, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.6400000000, query time of that 0.0886375060, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1983.59 < 1991.19
  -> Decision False in time 35.1200000000, query time of that 0.2252457200, 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: 0.004 accuracy: 1.58336 cost: 0.00633344 M: 10 delta: 1 time: 6.89538 one-recall: 0 one-ratio: 1.95991
iteration: 2 recall: 0.0696 accuracy: 0.520346 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5124 one-recall: 0.05 one-ratio: 1.45764
iteration: 3 recall: 0.5 accuracy: 0.107367 cost: 0.0167507 M: 11.1153 delta: 0.845786 time: 15.5398 one-recall: 0.54 one-ratio: 1.12102
iteration: 4 recall: 0.9196 accuracy: 0.00784209 cost: 0.0249124 M: 11.725 delta: 0.566229 time: 21.4933 one-recall: 0.95 one-ratio: 1.00824
iteration: 5 recall: 0.9908 accuracy: 0.000389749 cost: 0.037689 M: 17.4237 delta: 0.224536 time: 30.3575 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 30.639999999999873
Index size:  81592.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0009866667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0098875450, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2000000000, query time of that 0.0811148700, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.0100000000, query time of that 0.7918796050, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0091880050, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2800000000, query time of that 0.0867628100, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2251.99 < 2320.07
  -> Decision False in time 7.4400000000, query time of that 0.5085067200, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
2106.12 < 2123.28
  -> Decision False in time 0.3300000000, query time of that 0.0025076250, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4200000000, query time of that 0.1037827520, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1959.96 < 2010.77
  -> Decision False in time 17.2900000000, query time of that 0.1328513420, 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: 0.008 accuracy: 1.81902 cost: 0.00633344 M: 10 delta: 1 time: 6.88804 one-recall: 0.02 one-ratio: 1.99811
iteration: 2 recall: 0.074 accuracy: 0.602206 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.503 one-recall: 0.13 one-ratio: 1.43481
iteration: 3 recall: 0.4816 accuracy: 0.126501 cost: 0.0167507 M: 11.1153 delta: 0.845806 time: 15.5326 one-recall: 0.59 one-ratio: 1.13637
iteration: 4 recall: 0.926 accuracy: 0.00998416 cost: 0.0249128 M: 11.7252 delta: 0.566202 time: 21.4849 one-recall: 0.93 one-ratio: 1.02163
iteration: 5 recall: 0.986 accuracy: 0.00104732 cost: 0.0376856 M: 17.4222 delta: 0.224581 time: 30.3419 one-recall: 0.99 one-ratio: 1.00074
iteration: 6 recall: 0.992 accuracy: 0.000557559 cost: 0.0460195 M: 21.1563 delta: 0.134176 time: 36.0416 one-recall: 0.99 one-ratio: 1.00074
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 36.36000000000013
Index size:  88532.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0016966667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0066653320, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0582927370, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.8000000000, query time of that 0.5853316500, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0063535430, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2600000000, query time of that 0.0664749710, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1870.05 < 1882.06
  -> Decision False in time 5.0700000000, query time of that 0.2647381060, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0084651600, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1602.96 < 1621.73
  -> Decision False in time 7.7500000000, query time of that 0.0443457290, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1369.93 < 1453.49
  -> Decision False in time 70.8800000000, query time of that 0.3964889020, with c1=5.0000000000, c2=0.1000000000
