Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 7042971012352089088
In this apply, we use a network to learn this target input, given it's pre-evaluated output:
TrainingTester.java:332 executed in 0.02 seconds (0.000 gc):
return RefArrays.stream(RefUtil.addRef(input_target)).flatMap(RefArrays::stream).map(x -> {
try {
return x.prettyPrint();
} finally {
x.freeRef();
}
}).reduce((a, b) -> a + "\n" + b).orElse("");
Returns
[
[ [ -1.228 ], [ 0.048 ], [ 1.368 ], [ -1.476 ], [ -1.028 ], [ 0.7 ], [ -0.464 ], [ -0.384 ] ],
[ [ 1.652 ], [ 1.612 ], [ -0.636 ], [ -0.384 ], [ -1.424 ], [ 1.048 ], [ -0.068 ], [ -1.492 ] ],
[ [ 0.3 ], [ -0.876 ], [ -1.572 ], [ 0.092 ], [ 0.028 ], [ -0.712 ], [ -0.608 ], [ 1.764 ] ],
[ [ 1.208 ], [ 1.356 ], [ -0.176 ], [ -0.892 ], [ 0.788 ], [ -0.852 ], [ 1.64 ], [ 0.392 ] ],
[ [ 0.148 ], [ -1.54 ], [ 0.048 ], [ 1.704 ], [ -1.516 ], [ 1.552 ], [ 1.876 ], [ -0.804 ] ],
[ [ -1.832 ], [ 0.636 ], [ -0.768 ], [ 0.496 ], [ -0.556 ], [ 1.62 ], [ 0.996 ], [ -1.616 ] ],
[ [ 1.512 ], [ 1.556 ], [ 1.556 ], [ 1.032 ], [ -0.804 ], [ 1.108 ], [ -0.128 ], [ -0.012 ] ],
[ [ 0.08 ], [ -0.408 ], [ 1.524 ], [ -1.856 ], [ -1.688 ], [ 1.912 ], [ -1.72 ], [ -0.032 ] ]
]
[
[ [ 0.636 ], [ -1.72 ], [ -0.892 ], [ 0.148 ], [ 1.556 ], [ 1.108 ], [ -0.608 ], [ -1.028 ] ],
[ [ -0.712 ], [ 1.512 ], [ 1.62 ], [ -1.688 ], [ -1.856 ], [ 1.764 ], [ 1.652 ], [ 0.092 ] ],
[ [ 1.876 ], [ -0.128 ], [ -1.228 ], [ -0.768 ], [ 1.552 ], [ -0.068 ], [ 0.7 ], [ 0.028 ] ],
[ [ 0.392 ], [ -0.032 ], [ 1.64 ], [ 0.996 ], [ -0.384 ], [ -0.876 ], [ 1.704 ], [ -0.804 ] ],
[ [ -0.804 ], [ 1.524 ], [ 0.496 ], [ -1.424 ], [ 1.048 ], [ 1.032 ], [ 0.048 ], [ 1.208 ] ],
[ [ 0.788 ], [ 1.356 ], [ -1.516 ], [ 1.612 ], [ 1.368 ], [ -0.464 ], [ -0.176 ], [ -1.476 ] ],
[ [ -0.556 ], [ 0.08 ], [ -0.852 ], [ -1.616 ], [ -1.492 ], [ -1.54 ], [ -1.572 ], [ 1.556 ] ],
[ [ -0.012 ], [ 0.048 ], [ 1.912 ], [ -0.384 ], [ -0.636 ], [ -0.408 ], [ 0.3 ], [ -1.832 ] ]
]
[
[ [ 0.996 ], [ -0.768 ], [ 1.612 ], [ 0.496 ], [ -0.128 ], [ -0.876 ], [ 0.028 ], [ -1.516 ] ],
[ [ -0.852 ], [ 1.876 ], [ 1.512 ], [ 0.7 ], [ 1.368 ], [ -0.892 ], [ -1.72 ], [ 1.652 ] ],
[ [ 1.64 ], [ -1.688 ], [ 0.392 ], [ -1.54 ], [ -1.572 ], [ -1.476 ], [ 1.356 ], [ -1.228 ] ],
[ [ -1.424 ], [ -0.012 ], [ 0.08 ], [ 1.556 ], [ -1.616 ], [ 1.208 ], [ -0.384 ], [ -0.712 ] ],
[ [ -0.608 ], [ 1.764 ], [ -0.032 ], [ -0.068 ], [ -0.464 ], [ 1.032 ], [ 1.552 ], [ -1.492 ] ],
[ [ 0.788 ], [ 0.3 ], [ 0.048 ], [ -1.856 ], [ 0.048 ], [ 1.556 ], [ -1.832 ], [ -0.636 ] ],
[ [ 1.048 ], [ -0.176 ], [ -0.384 ], [ -0.556 ], [ -0.804 ], [ -1.028 ], [ 1.108 ], [ 0.092 ] ],
[ [ 1.62 ], [ -0.804 ], [ 1.524 ], [ 0.148 ], [ -0.408 ], [ 1.912 ], [ 1.704 ], [ 0.636 ] ]
]
[
[ [ -0.712 ], [ 0.788 ], [ -1.856 ], [ 0.028 ], [ -0.892 ], [ -1.028 ], [ 1.556 ], [ -1.72 ] ],
[ [ -0.556 ], [ -1.424 ], [ -0.852 ], [ -0.608 ], [ -0.032 ], [ 0.08 ], [ 1.368 ], [ -1.228 ] ],
[ [ -0.636 ], [ 1.512 ], [ 1.556 ], [ -0.804 ], [ -0.804 ], [ -0.012 ], [ 1.652 ], [ -0.128 ] ],
[ [ -1.476 ], [ 1.912 ], [ -1.688 ], [ 1.048 ], [ 1.612 ], [ -0.176 ], [ 0.092 ], [ -0.768 ] ],
[ [ -1.832 ], [ 1.64 ], [ 0.7 ], [ 0.392 ], [ 1.356 ], [ 1.704 ], [ 1.552 ], [ -0.384 ] ],
[ [ 1.764 ], [ 0.048 ], [ -1.492 ], [ 1.62 ], [ 0.496 ], [ 0.636 ], [ -0.464 ], [ 0.048 ] ],
[ [ 0.148 ], [ 1.108 ], [ -0.408 ], [ 1.208 ], [ 0.996 ], [ 1.524 ], [ 0.3 ], [ -0.384 ] ],
[ [ 1.032 ], [ -0.068 ], [ -0.876 ], [ -1.54 ], [ -1.516 ], [ -1.616 ], [ 1.876 ], [ -1.572 ] ]
]
[
[ [ 1.108 ], [ -0.876 ], [ -1.476 ], [ -1.832 ], [ -1.856 ], [ -0.852 ], [ -0.176 ], [ 1.912 ] ],
[ [ 1.048 ], [ 1.524 ], [ -0.768 ], [ -0.384 ], [ 1.556 ], [ -1.688 ], [ -1.54 ], [ -0.068 ] ],
[ [ 1.368 ], [ -1.72 ], [ -0.636 ], [ 1.876 ], [ -0.408 ], [ -1.516 ], [ -0.556 ], [ 1.556 ] ],
[ [ -0.892 ], [ -0.012 ], [ 0.148 ], [ -1.572 ], [ -1.616 ], [ 0.636 ], [ 1.612 ], [ -1.424 ] ],
[ [ 1.704 ], [ -0.804 ], [ 1.512 ], [ 1.652 ], [ -0.712 ], [ -1.228 ], [ -0.804 ], [ -1.028 ] ],
[ [ -0.464 ], [ 0.996 ], [ 1.552 ], [ 0.392 ], [ 0.788 ], [ 0.048 ], [ 1.64 ], [ 1.764 ] ],
[ [ 1.208 ], [ -0.608 ], [ 0.092 ], [ -0.384 ], [ -1.492 ], [ 0.496 ], [ -0.128 ], [ 0.048 ] ],
[ [ 0.08 ], [ -0.032 ], [ 0.028 ], [ 0.3 ], [ 1.62 ], [ 1.032 ], [ 0.7 ], [ 1.356 ] ]
]
First, we train using basic gradient descent method apply weak line search conditions.
TrainingTester.java:480 executed in 0.57 seconds (0.000 gc):
IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
try {
iterativeTrainer.setLineSearchFactory(label -> new ArmijoWolfeSearch());
iterativeTrainer.setOrientation(new GradientDescent());
iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
iterativeTrainer.setMaxIterations(250);
iterativeTrainer.setTerminateThreshold(0);
return iterativeTrainer.run();
} finally {
iterativeTrainer.freeRef();
}
Reset training subject: 4137473001716
BACKPROP_AGG_SIZE = 3
THREADS = 64
SINGLE_THREADED = false
Initialized CoreSettings = {
"backpropAggregationSize" : 3,
"jvmThreads" : 64,
"singleThreaded" : false
}
Reset training subject: 4137531497119
Constructing line search parameters: GD
th(0)=6.266746592923697;dx=-4.393216000000002E22
New Minimum: 6.266746592923697 > 0.0
Armijo: th(2.154434690031884)=0.0; dx=-4.393216000052817E10 evalInputDelta=6.266746592923697
Armijo: th(1.077217345015942)=0.0; dx=-4.393216000052817E10 evalInputDelta=6.266746592923697
Armijo: th(0.3590724483386473)=0.027862413162153765; dx=-4.393216000059292E10 evalInputDelta=6.238884179761543
Armijo: th(0.08976811208466183)=0.24909549780718013; dx=-4.3932160001603004E10 evalInputDelta=6.017651095116517
Armijo: th(0.017953622416932366)=0.4050780018365069; dx=-4.3932160003392494E10 evalInputDelta=5.861668591087191
Armijo: th(0.002992270402822061)=0.4617282308225164; dx=-4.3932160004476585E10 evalInputDelta=5.805018362101181
Armijo: th(4.2746720040315154E-4)=0.4732905433119317; dx=-4.393216000473833E10 evalInputDelta=5.793456049611765
Armijo: th(5.343340005039394E-5)=0.4750342197364944; dx=-4.393216000477913E10 evalInputDelta=5.7917123731872024
Armijo: th(5.9370444500437714E-6)=0.4752567351174597; dx=-4.393216000478436E10 evalInputDelta=5.791489857806237
Armijo: th(5.937044450043771E-7)=0.47528178365931667; dx=-4.393216000478495E10 evalInputDelta=5.79146480926438
Armijo: th(5.397313136403428E-8)=0.47528431399021526; dx=-4.393216000478502E10 evalInputDelta=5.791462278933482
Armijo: th(4.4977609470028565E-9)=0.4752845459388224; dx=-4.393216000478502E10 evalInputDelta=5.791462046984875
Armijo: th(3.4598161130791205E-10)=0.4752845654030535; dx=-4.393216000478502E10 evalInputDelta=5.791462027520644
Armijo: th(2.4712972236279432E-11)=0.47528456690921433; dx=-4.393216000478502E10 evalInputDelta=5.791462026014483
Armijo: th(1.6475314824186289E-12)=6.266746592915974; dx=-4.393216000000002E22 evalInputDelta=7.723599537712289E-12
Armijo: th(1.029707176511643E-13)=6.266746592923214; dx=-4.393216000000002E22 evalInputDelta=4.831690603168681E-13
Armijo: th(6.057101038303783E-15)=6.266746592923669; dx=-4.393216000000002E22 evalInputDelta=2.8421709430404007E-14
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.0
Fitness changed from 6.266746592923697 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.2764; Orientation: 0.0045; Line Search: 0.1769
th(0)=0.0;dx=-0.18045824000000002
Armijo: th(2.154434690031884E-15)=0.0; dx=-0.18045824000000002 evalInputDelta=0.0
Armijo: th(1.077217345015942E-15)=0.0; dx=-0.18045824000000002 evalInputDelta=0.0
MIN ALPHA (3.5907244833864734E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.2825; Orientation: 0.1671; Line Search: 0.1109
Iteration 2 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 2
Final threshold in iteration 2: 0.0 (> 0.0) after 0.560s (< 30.000s)
Returns
0.0
First, we use a conjugate gradient descent method, which converges the fastest for purely linear functions.
TrainingTester.java:452 executed in 0.54 seconds (0.000 gc):
IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
try {
iterativeTrainer.setLineSearchFactory(label -> new QuadraticSearch());
iterativeTrainer.setOrientation(new GradientDescent());
iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
iterativeTrainer.setMaxIterations(250);
iterativeTrainer.setTerminateThreshold(0);
return iterativeTrainer.run();
} finally {
iterativeTrainer.freeRef();
}
Reset training subject: 4138037740635
Reset training subject: 4138040669850
Constructing line search parameters: GD
F(0.0) = LineSearchPoint{point=PointSample{avg=6.266746592923697}, derivative=-4.393216000000002E22}
New Minimum: 6.266746592923697 > 0.4752845665562562
F(1.0E-10) = LineSearchPoint{point=PointSample{avg=0.4752845665562562}, derivative=-4.393216000478502E10}, evalInputDelta = -5.791462026367441
New Minimum: 0.4752845665562562 > 0.4752845637433564
F(7.000000000000001E-10) = LineSearchPoint{point=PointSample{avg=0.4752845637433564}, derivative=-4.393216000478502E10}, evalInputDelta = -5.791462029180341
New Minimum: 0.4752845637433564 > 0.47528454405305914
F(4.900000000000001E-9) = LineSearchPoint{point=PointSample{avg=0.47528454405305914}, derivative=-4.393216000478502E10}, evalInputDelta = -5.791462048870638
New Minimum: 0.47528454405305914 > 0.4752844062210319
F(3.430000000000001E-8) = LineSearchPoint{point=PointSample{avg=0.4752844062210319}, derivative=-4.393216000478502E10}, evalInputDelta = -5.791462186702665
New Minimum: 0.4752844062210319 > 0.4752834413995122
F(2.4010000000000004E-7) = LineSearchPoint{point=PointSample{avg=0.4752834413995122}, derivative=-4.3932160004784996E10}, evalInputDelta = -5.7914631515241854
New Minimum: 0.4752834413995122 > 0.4752766877797174
F(1.6807000000000003E-6) = LineSearchPoint{point=PointSample{avg=0.4752766877797174}, derivative=-4.3932160004784836E10}, evalInputDelta = -5.7914699051439795
New Minimum: 0.4752766877797174 > 0.47522941885130543
F(1.1764900000000001E-5) = LineSearchPoint{point=PointSample{avg=0.47522941885130543}, derivative=-4.393216000478372E10}, evalInputDelta = -5.791517174072392
New Minimum: 0.47522941885130543 > 0.47489885004577354
F(8.235430000000001E-5) = LineSearchPoint{point=PointSample{avg=0.47489885004577354}, derivative=-4.3932160004775955E10}, evalInputDelta = -5.791847742877923
New Minimum: 0.47489885004577354 > 0.47260010217780585
F(5.764801000000001E-4) = LineSearchPoint{point=PointSample{avg=0.47260010217780585}, derivative=-4.393216000472227E10}, evalInputDelta = -5.7941464907458915
New Minimum: 0.47260010217780585 > 0.45721137349712704
F(0.004035360700000001) = LineSearchPoint{point=PointSample{avg=0.45721137349712704}, derivative=-4.3932160004378395E10}, evalInputDelta = -5.80953521942657
New Minimum: 0.45721137349712704 > 0.3737507697223422
F(0.028247524900000005) = LineSearchPoint{point=PointSample{avg=0.3737507697223422}, derivative=-4.39321600029129E10}, evalInputDelta = -5.892995823201355
New Minimum: 0.3737507697223422 > 0.13021074035687855
F(0.19773267430000002) = LineSearchPoint{point=PointSample{avg=0.13021074035687855}, derivative=-4.393216000092609E10}, evalInputDelta = -6.136535852566818
New Minimum: 0.13021074035687855 > 0.0
F(1.3841287201) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(9.688901040700001) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(67.8223072849) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(474.7561509943) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(3323.2930569601003) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(23263.0513987207) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(162841.3597910449) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(1139889.5185373144) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(7979226.6297612) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(5.58545864083284E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(3.909821048582988E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(2.7368747340080914E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
F(1.915812313805664E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
0.0 <= 6.266746592923697
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.393216000052817E10}, evalInputDelta = -6.266746592923697
Right bracket at 1.0E10
Converged to right
Fitness changed from 6.266746592923697 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.1951; Orientation: 0.0011; Line Search: 0.1851
F(0.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
0.0 <= 0.0
F(5.0E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 5.0E9
F(2.5E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 2.5E9
F(1.25E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 1.25E9
F(6.25E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 6.25E8
F(3.125E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 3.125E8
F(1.5625E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 1.5625E8
F(7.8125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 7.8125E7
F(3.90625E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 3.90625E7
F(1.953125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 1.953125E7
F(9765625.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 9765625.0
F(4882812.5) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Right bracket at 4882812.5
F(2441406.25) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.18045824000000002}, evalInputDelta = 0.0
Loops = 12
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.3480; Orientation: 0.0009; Line Search: 0.3450
Iteration 2 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 2
Final threshold in iteration 2: 0.0 (> 0.0) after 0.543s (< 30.000s)
Returns
0.0
Next, we apply the same optimization using L-BFGS, which is nearly ideal for purely second-order or quadratic functions.
TrainingTester.java:509 executed in 0.28 seconds (0.000 gc):
IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
try {
iterativeTrainer.setLineSearchFactory(label -> new ArmijoWolfeSearch());
iterativeTrainer.setOrientation(new LBFGS());
iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
iterativeTrainer.setIterationsPerSample(100);
iterativeTrainer.setMaxIterations(250);
iterativeTrainer.setTerminateThreshold(0);
return iterativeTrainer.run();
} finally {
iterativeTrainer.freeRef();
}
Reset training subject: 4138584787529
Reset training subject: 4138587950879
Adding measurement 18b1e73b to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD
Non-optimal measurement 6.266746592923697 < 6.266746592923697. Total: 1
th(0)=6.266746592923697;dx=-4.393216000000002E22
Adding measurement 73dea026 to history. Total: 1
New Minimum: 6.266746592923697 > 0.0
Armijo: th(2.154434690031884)=0.0; dx=-4.393216000052817E10 evalInputDelta=6.266746592923697
Non-optimal measurement 0.0 < 0.0. Total: 2
Armijo: th(1.077217345015942)=0.0; dx=-4.393216000052817E10 evalInputDelta=6.266746592923697
Non-optimal measurement 0.027862413162153765 < 0.0. Total: 2
Armijo: th(0.3590724483386473)=0.027862413162153765; dx=-4.393216000059292E10 evalInputDelta=6.238884179761543
Non-optimal measurement 0.24909549780718013 < 0.0. Total: 2
Armijo: th(0.08976811208466183)=0.24909549780718013; dx=-4.3932160001603E10 evalInputDelta=6.017651095116517
Non-optimal measurement 0.4050780018365069 < 0.0. Total: 2
Armijo: th(0.017953622416932366)=0.4050780018365069; dx=-4.393216000339249E10 evalInputDelta=5.861668591087191
Non-optimal measurement 0.4617282308225164 < 0.0. Total: 2
Armijo: th(0.002992270402822061)=0.4617282308225164; dx=-4.3932160004476585E10 evalInputDelta=5.805018362101181
Non-optimal measurement 0.4732905433119317 < 0.0. Total: 2
Armijo: th(4.2746720040315154E-4)=0.4732905433119317; dx=-4.393216000473833E10 evalInputDelta=5.793456049611765
Non-optimal measurement 0.4750342197364944 < 0.0. Total: 2
Armijo: th(5.343340005039394E-5)=0.4750342197364944; dx=-4.393216000477913E10 evalInputDelta=5.7917123731872024
Non-optimal measurement 0.4752567351174597 < 0.0. Total: 2
Armijo: th(5.9370444500437714E-6)=0.4752567351174597; dx=-4.393216000478436E10 evalInputDelta=5.791489857806237
Non-optimal measurement 0.47528178365931667 < 0.0. Total: 2
Armijo: th(5.937044450043771E-7)=0.47528178365931667; dx=-4.393216000478496E10 evalInputDelta=5.79146480926438
Non-optimal measurement 0.47528431399021526 < 0.0. Total: 2
Armijo: th(5.397313136403428E-8)=0.47528431399021526; dx=-4.393216000478501E10 evalInputDelta=5.791462278933482
Non-optimal measurement 0.4752845459388224 < 0.0. Total: 2
Armijo: th(4.4977609470028565E-9)=0.4752845459388224; dx=-4.393216000478502E10 evalInputDelta=5.791462046984875
Non-optimal measurement 0.4752845654030535 < 0.0. Total: 2
Armijo: th(3.4598161130791205E-10)=0.4752845654030535; dx=-4.393216000478502E10 evalInputDelta=5.791462027520644
Non-optimal measurement 0.47528456690921433 < 0.0. Total: 2
Armijo: th(2.4712972236279432E-11)=0.47528456690921433; dx=-4.393216000478502E10 evalInputDelta=5.791462026014483
Non-optimal measurement 6.266746592915974 < 0.0. Total: 2
Armijo: th(1.6475314824186289E-12)=6.266746592915974; dx=-4.393216000000002E22 evalInputDelta=7.723599537712289E-12
Non-optimal measurement 6.266746592923214 < 0.0. Total: 2
Armijo: th(1.029707176511643E-13)=6.266746592923214; dx=-4.393216000000002E22 evalInputDelta=4.831690603168681E-13
Non-optimal measurement 6.266746592923669 < 0.0. Total: 2
Armijo: th(6.057101038303783E-15)=6.266746592923669; dx=-4.393216000000002E22 evalInputDelta=2.8421709430404007E-14
Non-optimal measurement 0.0 < 0.0. Total: 2
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.0
Fitness changed from 6.266746592923697 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.1177; Orientation: 0.0057; Line Search: 0.1016
Non-optimal measurement 0.0 < 0.0. Total: 2
LBFGS Accumulation History: 2 points
Non-optimal measurement 0.0 < 0.0. Total: 2
th(0)=0.0;dx=-0.18045824000000002
Non-optimal measurement 0.0 < 0.0. Total: 2
Armijo: th(2.154434690031884E-15)=0.0; dx=-0.18045824000000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 2
Armijo: th(1.077217345015942E-15)=0.0; dx=-0.18045824000000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 2
MIN ALPHA (3.5907244833864734E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.1608; Orientation: 0.0020; Line Search: 0.1564
Iteration 2 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 2
Final threshold in iteration 2: 0.0 (> 0.0) after 0.279s (< 30.000s)
Returns
0.0
TrainingTester.java:432 executed in 0.10 seconds (0.000 gc):
return TestUtil.compare(title + " vs Iteration", runs);
Plotting range=[0.0, 0.0], [2.0, 1.0]; valueStats=DoubleSummaryStatistics{count=0, sum=0.000000, min=Infinity, average=0.000000, max=-Infinity}
Only 0 points for GD
Only 0 points for CjGD
Only 0 points for LBFGS
Returns
TrainingTester.java:435 executed in 0.00 seconds (0.000 gc):
return TestUtil.compareTime(title + " vs Time", runs);
No Data
TrainingTester.java:255 executed in 0.00 seconds (0.000 gc):
return grid(inputLearning, modelLearning, completeLearning);
Returns
TrainingTester.java:258 executed in 0.00 seconds (0.000 gc):
return new ComponentResult(null == inputLearning ? null : inputLearning.value,
null == modelLearning ? null : modelLearning.value, null == completeLearning ? null : completeLearning.value);
Returns
{"input":{ "LBFGS": { "type": "Converged", "value": 0.0 }, "CjGD": { "type": "Converged", "value": 0.0 }, "GD": { "type": "Converged", "value": 0.0 } }, "model":null, "complete":null}
LayerTests.java:425 executed in 0.00 seconds (0.000 gc):
throwException(exceptions.addRef());
| details | result |
|---|---|
| {"input":{ "LBFGS": { "type": "Converged", "value": 0.0 }, "CjGD": { "type": "Converged", "value": 0.0 }, "GD": { "type": "Converged", "value": 0.0 } }, "model":null, "complete":null} | OK |
{
"result": "OK",
"performance": {
"execution_time": "1.933",
"gc_time": "0.213"
},
"created_on": 1586738725257,
"file_name": "trainingTest",
"report": {
"simpleName": "Basic",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ImgCropLayerTest.Basic",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/ImgCropLayerTest.java",
"javaDoc": ""
},
"training_analysis": {
"input": {
"LBFGS": {
"type": "Converged",
"value": 0.0
},
"CjGD": {
"type": "Converged",
"value": 0.0
},
"GD": {
"type": "Converged",
"value": 0.0
}
}
},
"archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/ImgCropLayer/Basic/trainingTest/202004134525",
"id": "f38ad54d-7a0d-4c30-afef-9541dc2a998b",
"report_type": "Components",
"display_name": "Comparative Training",
"target": {
"simpleName": "ImgCropLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ImgCropLayer",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/ImgCropLayer.java",
"javaDoc": ""
}
}