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', 80, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 20, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 1, {'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', 2, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 3, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 90, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 60, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 4, {'reverse': -1}, False]), Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 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', 5, {'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', 50, {'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]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 80, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.008 accuracy: 1.6488 cost: 0.00633344 M: 10 delta: 1 time: 0.615672 one-recall: 0 one-ratio: 1.98824
iteration: 2 recall: 0.0748 accuracy: 0.576643 cost: 0.0102207 M: 10 delta: 0.893264 time: 0.856529 one-recall: 0.07 one-ratio: 1.46524
iteration: 3 recall: 0.4588 accuracy: 0.129708 cost: 0.0167282 M: 11.1226 delta: 0.845934 time: 1.17992 one-recall: 0.46 one-ratio: 1.12263
iteration: 4 recall: 0.9152 accuracy: 0.00779198 cost: 0.024872 M: 11.7202 delta: 0.566056 time: 1.55164 one-recall: 0.97 one-ratio: 1.006
iteration: 5 recall: 0.9892 accuracy: 0.000422819 cost: 0.0376498 M: 17.4235 delta: 0.223942 time: 2.09606 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9932 accuracy: 0.000213504 cost: 0.0459846 M: 21.1695 delta: 0.133636 time: 2.48503 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 46.46
Index size:  97364.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004266667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0132548680, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2400000000, query time of that 0.1195462850, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.4400000000, query time of that 1.2232468630, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0134803000, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3600000000, query time of that 0.1366546200, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.7900000000, query time of that 1.4078728330, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0150438150, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.4400000000, query time of that 0.1601259870, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1791.27 < 1850.43
  -> Decision False in time 1.2000000000, query time of that 0.0134895780, 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: 1.76368 cost: 0.00633344 M: 10 delta: 1 time: 6.89142 one-recall: 0 one-ratio: 1.88135
iteration: 2 recall: 0.0764 accuracy: 0.534729 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5099 one-recall: 0.05 one-ratio: 1.3723
iteration: 3 recall: 0.4924 accuracy: 0.111887 cost: 0.0167507 M: 11.1153 delta: 0.845805 time: 15.5386 one-recall: 0.54 one-ratio: 1.08356
iteration: 4 recall: 0.9256 accuracy: 0.00671844 cost: 0.0249106 M: 11.7246 delta: 0.566205 time: 21.4918 one-recall: 0.97 one-ratio: 1.00312
iteration: 5 recall: 0.9912 accuracy: 0.000339863 cost: 0.0376879 M: 17.4242 delta: 0.224499 time: 30.3488 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 30.629999999999995
Index size:  76104.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0022450000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0100000000, query time of that 0.0064944570, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1800000000, query time of that 0.0515111990, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.7600000000, query time of that 0.5362592550, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0071450500, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
1387.4 < 1404.72
  -> Decision False in time 0.4300000000, query time of that 0.0201579450, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2496 < 2509.2
  -> Decision False in time 5.8200000000, query time of that 0.2811379590, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0072960610, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1502.44 < 1582.74
  -> Decision False in time 7.0600000000, query time of that 0.0392013890, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1048.77 < 1055.49
  -> Decision False in time 2.8400000000, query time of that 0.0152468680, 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: 0.0068 accuracy: 1.77345 cost: 0.00633344 M: 10 delta: 1 time: 6.87904 one-recall: 0.01 one-ratio: 1.91211
iteration: 2 recall: 0.0752 accuracy: 0.579188 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4933 one-recall: 0.09 one-ratio: 1.36172
iteration: 3 recall: 0.474 accuracy: 0.115259 cost: 0.0167507 M: 11.1153 delta: 0.845809 time: 15.5188 one-recall: 0.49 one-ratio: 1.09592
iteration: 4 recall: 0.9164 accuracy: 0.00738214 cost: 0.0249117 M: 11.7249 delta: 0.566194 time: 21.468 one-recall: 0.95 one-ratio: 1.00405
iteration: 5 recall: 0.986 accuracy: 0.000729652 cost: 0.0376866 M: 17.4235 delta: 0.224519 time: 30.3215 one-recall: 0.99 one-ratio: 1.00002
iteration: 6 recall: 0.9936 accuracy: 0.000335099 cost: 0.0460219 M: 21.1578 delta: 0.134136 time: 36.0109 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:  83052.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0421550000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0052104560, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1943.35 < 3004.11
  -> Decision False in time 0.0300000000, query time of that 0.0088484690, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2511.61 < 2780.13
  -> Decision False in time 0.0000000000, query time of that 0.0018453860, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
2168.59 < 2800.43
  -> Decision False in time 0.1100000000, query time of that 0.0044082970, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
3126.42 < 3183.09
  -> Decision False in time 0.0800000000, query time of that 0.0038365890, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1963.92 < 3134.91
  -> Decision False in time 0.2200000000, query time of that 0.0100052210, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
2800.55 < 3170.86
  -> Decision False in time 0.6900000000, query time of that 0.0037065340, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2396.32 < 2416.83
  -> Decision False in time 0.3400000000, query time of that 0.0018455490, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2472.61 < 3048.79
  -> Decision False in time 1.8900000000, query time of that 0.0093614950, 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: 0.0056 accuracy: 1.64271 cost: 0.00633344 M: 10 delta: 1 time: 6.8821 one-recall: 0.02 one-ratio: 1.93112
iteration: 2 recall: 0.064 accuracy: 0.543687 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4967 one-recall: 0.08 one-ratio: 1.4484
iteration: 3 recall: 0.4588 accuracy: 0.121585 cost: 0.0167507 M: 11.1153 delta: 0.845782 time: 15.5235 one-recall: 0.55 one-ratio: 1.10526
iteration: 4 recall: 0.9148 accuracy: 0.00863754 cost: 0.0249117 M: 11.7247 delta: 0.566211 time: 21.4743 one-recall: 0.94 one-ratio: 1.00542
iteration: 5 recall: 0.9868 accuracy: 0.000819067 cost: 0.037685 M: 17.4222 delta: 0.224607 time: 30.3321 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9948 accuracy: 0.000285032 cost: 0.0460246 M: 21.1601 delta: 0.134132 time: 36.0269 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 36.339999999999975
Index size:  83052.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0010050000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0067143440, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1900000000, query time of that 0.0670867290, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 1.9100000000, query time of that 0.6861259650, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0079786320, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3000000000, query time of that 0.0788258510, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1888.52 < 1929.11
  -> Decision False in time 3.4000000000, query time of that 0.2020121580, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0089801630, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.5500000000, query time of that 0.0909032470, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1762.15 < 1763.94
  -> Decision False in time 115.8200000000, query time of that 0.7723776420, 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: 0.0052 accuracy: 1.58765 cost: 0.00633344 M: 10 delta: 1 time: 6.87939 one-recall: 0 one-ratio: 1.98889
iteration: 2 recall: 0.064 accuracy: 0.561333 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4959 one-recall: 0.07 one-ratio: 1.42638
iteration: 3 recall: 0.4492 accuracy: 0.128674 cost: 0.0167507 M: 11.1153 delta: 0.845798 time: 15.5254 one-recall: 0.53 one-ratio: 1.12163
iteration: 4 recall: 0.904 accuracy: 0.0116468 cost: 0.024912 M: 11.7249 delta: 0.566196 time: 21.4781 one-recall: 0.93 one-ratio: 1.03866
iteration: 5 recall: 0.9872 accuracy: 0.000695168 cost: 0.0376791 M: 17.4199 delta: 0.224597 time: 30.3334 one-recall: 0.99 one-ratio: 1.00234
iteration: 6 recall: 0.9952 accuracy: 0.000199818 cost: 0.0460186 M: 21.1581 delta: 0.13414 time: 36.0318 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 36.35000000000002
Index size:  83044.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0151533333
  Testing...
|S| = 20
|T| = 283
Reject!
2132 < 2375.88
  -> Decision False in time 0.0000000000, query time of that 0.0015064570, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1940.52 < 1964.25
  -> Decision False in time 0.0100000000, query time of that 0.0006797830, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1969.7 < 2615.41
  -> Decision False in time 0.0400000000, query time of that 0.0114126370, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0055583260, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2500000000, query time of that 0.0529029580, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1791.48 < 1917.47
  -> Decision False in time 0.4100000000, query time of that 0.0172170480, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1894.22 < 1907.99
  -> Decision False in time 0.1500000000, query time of that 0.0009241060, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1580.82 < 1596.08
  -> Decision False in time 0.6800000000, query time of that 0.0034072350, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1751.61 < 1942.29
  -> Decision False in time 0.9000000000, query time of that 0.0052870460, 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: 0.0076 accuracy: 1.75525 cost: 0.00633344 M: 10 delta: 1 time: 6.87814 one-recall: 0.02 one-ratio: 1.87816
iteration: 2 recall: 0.0708 accuracy: 0.580282 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4943 one-recall: 0.11 one-ratio: 1.36447
iteration: 3 recall: 0.482 accuracy: 0.115098 cost: 0.0167507 M: 11.1153 delta: 0.845806 time: 15.5209 one-recall: 0.6 one-ratio: 1.08143
iteration: 4 recall: 0.9332 accuracy: 0.00532544 cost: 0.0249109 M: 11.7247 delta: 0.566201 time: 21.4691 one-recall: 0.96 one-ratio: 1.00332
iteration: 5 recall: 0.99 accuracy: 0.000555619 cost: 0.037678 M: 17.4199 delta: 0.2246 time: 30.3176 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.996 accuracy: 0.000172385 cost: 0.0460061 M: 21.153 delta: 0.134208 time: 36.0031 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 36.319999999999936
Index size:  83040.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0097750000
  Testing...
|S| = 20
|T| = 283
Reject!
2002.2 < 2091.89
  -> Decision False in time 0.0000000000, query time of that 0.0008241350, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
2045.06 < 2070.34
  -> Decision False in time 0.0200000000, query time of that 0.0063060790, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1650.85 < 1660.42
  -> Decision False in time 0.0100000000, query time of that 0.0040964030, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0040272470, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2500000000, query time of that 0.0490562240, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2179.26 < 2203.07
  -> Decision False in time 0.4500000000, query time of that 0.0173998930, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0063674490, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1692.34 < 1769.38
  -> Decision False in time 1.9700000000, query time of that 0.0096413420, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1726.86 < 2004.88
  -> Decision False in time 1.1900000000, query time of that 0.0064205500, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 90, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 90, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.006 accuracy: 1.68366 cost: 0.00633344 M: 10 delta: 1 time: 6.88242 one-recall: 0.02 one-ratio: 1.93106
iteration: 2 recall: 0.07 accuracy: 0.606136 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.499 one-recall: 0.05 one-ratio: 1.38836
iteration: 3 recall: 0.4384 accuracy: 0.135769 cost: 0.0167507 M: 11.1153 delta: 0.845802 time: 15.5252 one-recall: 0.48 one-ratio: 1.09753
iteration: 4 recall: 0.9056 accuracy: 0.0106537 cost: 0.0249115 M: 11.7248 delta: 0.566215 time: 21.4754 one-recall: 0.9 one-ratio: 1.00875
iteration: 5 recall: 0.9868 accuracy: 0.000691725 cost: 0.0376841 M: 17.4213 delta: 0.224584 time: 30.329 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9936 accuracy: 0.000401852 cost: 0.0460149 M: 21.1547 delta: 0.134193 time: 36.0148 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 36.33000000000004
Index size:  83056.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0004700000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0141777700, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2400000000, query time of that 0.1197241160, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.4100000000, query time of that 1.1837913670, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0112768660, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.1335251610, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.7700000000, query time of that 1.3161688950, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3900000000, query time of that 0.0167213180, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
2242.92 < 2440.53
  -> Decision False in time 5.4100000000, query time of that 0.0569693950, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2136.76 < 2142.06
  -> Decision False in time 16.9900000000, query time of that 0.1816988200, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 60, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 60, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0044 accuracy: 1.75705 cost: 0.00633344 M: 10 delta: 1 time: 6.8693 one-recall: 0.01 one-ratio: 1.9049
iteration: 2 recall: 0.062 accuracy: 0.582415 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4847 one-recall: 0.07 one-ratio: 1.41307
iteration: 3 recall: 0.454 accuracy: 0.125154 cost: 0.0167507 M: 11.1153 delta: 0.845787 time: 15.5112 one-recall: 0.47 one-ratio: 1.10511
iteration: 4 recall: 0.9164 accuracy: 0.00715329 cost: 0.0249126 M: 11.7247 delta: 0.566223 time: 21.4616 one-recall: 0.96 one-ratio: 1.00538
iteration: 5 recall: 0.9896 accuracy: 0.000478161 cost: 0.0376814 M: 17.4204 delta: 0.224633 time: 30.3125 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9964 accuracy: 0.000112123 cost: 0.0460084 M: 21.1514 delta: 0.134276 time: 35.9971 one-recall: 1 one-ratio: 1
Graph completion with reverse edges...

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

0%   10   20   30   40   50   60   70   80   90   100%
|----|----|----|----|----|----|----|----|----|----|
***************************************************
Built index in 36.309999999999945
Index size:  83056.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0010133333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0105548950, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2200000000, query time of that 0.0964702220, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.1600000000, query time of that 0.9391252280, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Reject!
1249.44 < 1252.13
  -> Decision False in time 0.0500000000, query time of that 0.0038912590, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3200000000, query time of that 0.1109117500, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
2154.65 < 2309.68
  -> Decision False in time 7.3700000000, query time of that 0.5865595490, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0117928050, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1962.12 < 1970.41
  -> Decision False in time 9.6100000000, query time of that 0.0870404000, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2098.36 < 2130.78
  -> Decision False in time 26.8400000000, query time of that 0.2377046630, 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: 0.006 accuracy: 1.67668 cost: 0.00633344 M: 10 delta: 1 time: 6.88276 one-recall: 0.01 one-ratio: 1.97778
iteration: 2 recall: 0.0664 accuracy: 0.622811 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4982 one-recall: 0.08 one-ratio: 1.45532
iteration: 3 recall: 0.4468 accuracy: 0.127754 cost: 0.0167507 M: 11.1153 delta: 0.845791 time: 15.5255 one-recall: 0.49 one-ratio: 1.11738
iteration: 4 recall: 0.9144 accuracy: 0.00762947 cost: 0.0249111 M: 11.7249 delta: 0.566194 time: 21.4767 one-recall: 0.96 one-ratio: 1.00478
iteration: 5 recall: 0.9868 accuracy: 0.000653944 cost: 0.0376889 M: 17.4242 delta: 0.224517 time: 30.3361 one-recall: 0.99 one-ratio: 1.00002
iteration: 6 recall: 0.9948 accuracy: 0.000270195 cost: 0.0460198 M: 21.1562 delta: 0.134117 time: 36.0264 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 36.32999999999993
Index size:  83060.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0042700000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0050173480, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1700000000, query time of that 0.0483727290, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2365.95 < 2649.36
  -> Decision False in time 0.2600000000, query time of that 0.0710236990, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0052190140, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
755.862 < 958.478
  -> Decision False in time 0.2900000000, query time of that 0.0125053510, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1788.52 < 1828.86
  -> Decision False in time 0.8700000000, query time of that 0.0365344770, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1518.56 < 1525.12
  -> Decision False in time 0.8500000000, query time of that 0.0044569380, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1540.84 < 1589.65
  -> Decision False in time 12.8000000000, query time of that 0.0635237760, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1297.58 < 1307.89
  -> Decision False in time 20.7500000000, query time of that 0.0997752260, 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: 0.0036 accuracy: 1.7992 cost: 0.00633344 M: 10 delta: 1 time: 6.88023 one-recall: 0 one-ratio: 1.97582
iteration: 2 recall: 0.068 accuracy: 0.611524 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.496 one-recall: 0.11 one-ratio: 1.35477
iteration: 3 recall: 0.462 accuracy: 0.131333 cost: 0.0167507 M: 11.1153 delta: 0.845812 time: 15.5231 one-recall: 0.45 one-ratio: 1.10528
iteration: 4 recall: 0.9284 accuracy: 0.00690635 cost: 0.0249113 M: 11.7246 delta: 0.566212 time: 21.4725 one-recall: 0.97 one-ratio: 1.0031
iteration: 5 recall: 0.9936 accuracy: 0.000338083 cost: 0.0376824 M: 17.4207 delta: 0.224564 time: 30.323 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 30.610000000000014
Index size:  76100.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0006233333
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0098493060, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2100000000, query time of that 0.0938580710, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.1700000000, query time of that 0.9519698000, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0107459380, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3300000000, query time of that 0.1097492110, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.3400000000, query time of that 1.0715239070, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0124882060, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1654.91 < 1751.13
  -> Decision False in time 3.7200000000, query time of that 0.0348331310, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1536.32 < 1657.52
  -> Decision False in time 30.8100000000, query time of that 0.2792304800, 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: 0.0056 accuracy: 1.7334 cost: 0.00633344 M: 10 delta: 1 time: 6.88168 one-recall: 0 one-ratio: 2.08606
iteration: 2 recall: 0.0736 accuracy: 0.571746 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4984 one-recall: 0.05 one-ratio: 1.4126
iteration: 3 recall: 0.4964 accuracy: 0.117597 cost: 0.0167507 M: 11.1153 delta: 0.845801 time: 15.5253 one-recall: 0.49 one-ratio: 1.08035
iteration: 4 recall: 0.9252 accuracy: 0.00736696 cost: 0.0249118 M: 11.7246 delta: 0.566224 time: 21.475 one-recall: 0.94 one-ratio: 1.01194
iteration: 5 recall: 0.9912 accuracy: 0.000362893 cost: 0.0376778 M: 17.4202 delta: 0.224634 time: 30.3247 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:  76100.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0034166667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0074374470, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.1900000000, query time of that 0.0682819990, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2537.74 < 2641.11
  -> Decision False in time 0.4400000000, query time of that 0.1605290280, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0080364260, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2163.67 < 2852.97
  -> Decision False in time 0.5200000000, query time of that 0.0316797470, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1751.54 < 2902.03
  -> Decision False in time 3.8600000000, query time of that 0.2424151620, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0099203310, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1765.6 < 1776.47
  -> Decision False in time 3.8700000000, query time of that 0.0282121280, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1877.75 < 1970.41
  -> Decision False in time 1.9900000000, query time of that 0.0147913830, 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: 1.69722 cost: 0.00633344 M: 10 delta: 1 time: 6.88177 one-recall: 0 one-ratio: 1.88927
iteration: 2 recall: 0.0776 accuracy: 0.593001 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.497 one-recall: 0.04 one-ratio: 1.31782
iteration: 3 recall: 0.4548 accuracy: 0.125754 cost: 0.0167507 M: 11.1153 delta: 0.845793 time: 15.5237 one-recall: 0.44 one-ratio: 1.11188
iteration: 4 recall: 0.9144 accuracy: 0.00781433 cost: 0.0249117 M: 11.7249 delta: 0.566215 time: 21.4739 one-recall: 0.92 one-ratio: 1.01136
iteration: 5 recall: 0.984 accuracy: 0.000812515 cost: 0.0376849 M: 17.4223 delta: 0.22454 time: 30.3274 one-recall: 0.99 one-ratio: 1.00036
iteration: 6 recall: 0.992 accuracy: 0.000277698 cost: 0.0460231 M: 21.157 delta: 0.134138 time: 36.0191 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 36.32999999999993
Index size:  83044.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0093300000
  Testing...
|S| = 20
|T| = 283
Reject!
2248.19 < 2903.78
  -> Decision False in time 0.0200000000, query time of that 0.0038375560, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1787.46 < 2299.12
  -> Decision False in time 0.1400000000, query time of that 0.0400066270, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2402.35 < 2542.06
  -> Decision False in time 0.1900000000, query time of that 0.0502764440, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0052514230, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Reject!
2208.99 < 2354.09
  -> Decision False in time 0.8500000000, query time of that 0.0369761800, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
973.805 < 1107.34
  -> Decision False in time 0.9100000000, query time of that 0.0366301810, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Reject!
1143.32 < 1172.35
  -> Decision False in time 0.2200000000, query time of that 0.0015046330, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1883.07 < 2194.87
  -> Decision False in time 3.0200000000, query time of that 0.0142901070, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2008.75 < 2092.65
  -> Decision False in time 7.9900000000, query time of that 0.0376640000, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 10, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 10, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.0048 accuracy: 1.76907 cost: 0.00633344 M: 10 delta: 1 time: 6.88444 one-recall: 0 one-ratio: 2.09584
iteration: 2 recall: 0.0748 accuracy: 0.592974 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.5004 one-recall: 0.1 one-ratio: 1.45074
iteration: 3 recall: 0.4908 accuracy: 0.123473 cost: 0.0167507 M: 11.1153 delta: 0.845805 time: 15.5297 one-recall: 0.53 one-ratio: 1.11973
iteration: 4 recall: 0.927199 accuracy: 0.00692747 cost: 0.0249127 M: 11.7248 delta: 0.566215 time: 21.4831 one-recall: 0.98 one-ratio: 1.00497
iteration: 5 recall: 0.988 accuracy: 0.000885643 cost: 0.0376934 M: 17.4258 delta: 0.224465 time: 30.3471 one-recall: 1 one-ratio: 1
iteration: 6 recall: 0.9964 accuracy: 0.000150505 cost: 0.0460251 M: 21.1583 delta: 0.134092 time: 36.0412 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 36.34999999999991
Index size:  83048.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0026916667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0058350810, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Reject!
1555.15 < 1684.75
  -> Decision False in time 0.0600000000, query time of that 0.0183296200, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
1130.75 < 1700.79
  -> Decision False in time 0.7800000000, query time of that 0.2272522600, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0060282440, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.2700000000, query time of that 0.0591777090, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1235.97 < 1511.88
  -> Decision False in time 3.0500000000, query time of that 0.1358659450, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.0065031350, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1037.47 < 1061.87
  -> Decision False in time 0.6200000000, query time of that 0.0035574120, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1791.4 < 1802.4
  -> Decision False in time 7.6500000000, query time of that 0.0391331970, with c1=5.0000000000, c2=0.1000000000
Definition(algorithm='kgraph', constructor='KGraph', module='ann_benchmarks.algorithms.kgraph', docker_tag='ann-benchmarks-kgraph', arguments=['euclidean', 50, {'reverse': -1}, False]) ...
Trying to instantiate ann_benchmarks.algorithms.kgraph.KGraph(['euclidean', 50, {'reverse': -1}, False])
Got a train set of size (60000 * 784)
Generating control...
Initializing...
iteration: 1 recall: 0.006 accuracy: 1.67277 cost: 0.00633344 M: 10 delta: 1 time: 6.87613 one-recall: 0.03 one-ratio: 1.95552
iteration: 2 recall: 0.0712 accuracy: 0.560809 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4925 one-recall: 0.1 one-ratio: 1.42126
iteration: 3 recall: 0.4904 accuracy: 0.116449 cost: 0.0167507 M: 11.1153 delta: 0.845789 time: 15.5195 one-recall: 0.51 one-ratio: 1.10274
iteration: 4 recall: 0.923999 accuracy: 0.00721491 cost: 0.0249111 M: 11.7247 delta: 0.566207 time: 21.471 one-recall: 0.97 one-ratio: 1.00266
iteration: 5 recall: 0.9932 accuracy: 0.000189861 cost: 0.0376863 M: 17.4233 delta: 0.22456 time: 30.3282 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 30.610000000000127
Index size:  76100.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0009666667
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0200000000, query time of that 0.0083725120, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2000000000, query time of that 0.0799212640, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Reject!
2212.69 < 2284.28
  -> Decision False in time 1.0900000000, query time of that 0.4310392910, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1400000000, query time of that 0.0090252410, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3100000000, query time of that 0.0955939080, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Accept!
  -> Decision True in time 13.2000000000, query time of that 0.9103578550, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0112447600, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Accept!
  -> Decision True in time 13.6000000000, query time of that 0.1077261610, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
1636.07 < 1695.89
  -> Decision False in time 56.5300000000, query time of that 0.4346607440, 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: 0.006 accuracy: 1.88124 cost: 0.00633344 M: 10 delta: 1 time: 6.87734 one-recall: 0 one-ratio: 1.93478
iteration: 2 recall: 0.0756 accuracy: 0.619587 cost: 0.0102345 M: 10 delta: 0.893354 time: 10.4923 one-recall: 0.1 one-ratio: 1.36471
iteration: 3 recall: 0.4692 accuracy: 0.138741 cost: 0.0167507 M: 11.1153 delta: 0.845798 time: 15.5202 one-recall: 0.56 one-ratio: 1.09014
iteration: 4 recall: 0.9208 accuracy: 0.00880953 cost: 0.0249124 M: 11.7248 delta: 0.566209 time: 21.4734 one-recall: 0.97 one-ratio: 1.00355
iteration: 5 recall: 0.9912 accuracy: 0.00039718 cost: 0.0376895 M: 17.4246 delta: 0.224522 time: 30.3344 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:  76104.0
Run 1/1...
  Calculating distance...
  -> Distance: 0.0005250000
  Testing...
|S| = 20
|T| = 283
Accept!
  -> Decision True in time 0.0300000000, query time of that 0.0130820270, with c1=0.0500000000, c2=0.0010000000
|S| = 196
|T| = 283
Accept!
  -> Decision True in time 0.2300000000, query time of that 0.1139939080, with c1=0.0500000000, c2=0.0100000000
|S| = 1960
|T| = 283
Accept!
  -> Decision True in time 2.4100000000, query time of that 1.1695308180, with c1=0.0500000000, c2=0.1000000000
|S| = 20
|T| = 2821
Accept!
  -> Decision True in time 0.1300000000, query time of that 0.0130958990, with c1=0.5000000000, c2=0.0010000000
|S| = 196
|T| = 2821
Accept!
  -> Decision True in time 1.3700000000, query time of that 0.1313872250, with c1=0.5000000000, c2=0.0100000000
|S| = 1960
|T| = 2821
Reject!
1537.91 < 1542.61
  -> Decision False in time 12.6000000000, query time of that 1.1920246230, with c1=0.5000000000, c2=0.1000000000
|S| = 20
|T| = 28201
Accept!
  -> Decision True in time 1.3800000000, query time of that 0.0127651750, with c1=5.0000000000, c2=0.0010000000
|S| = 196
|T| = 28201
Reject!
1828.61 < 1937.87
  -> Decision False in time 12.8200000000, query time of that 0.1426277850, with c1=5.0000000000, c2=0.0100000000
|S| = 1960
|T| = 28201
Reject!
2030.6 < 2042.72
  -> Decision False in time 98.8700000000, query time of that 1.0496615270, with c1=5.0000000000, c2=0.1000000000
