Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 6023951248040130560
In this apply, we use a network to learn this target input, given it's pre-evaluated output:
TrainingTester.java:332 executed in 0.01 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
[
[ [ -0.712 ], [ -0.384 ], [ -1.424 ], [ -0.608 ], [ 1.208 ], [ -0.892 ], [ 0.08 ], [ -1.516 ] ],
[ [ 1.356 ], [ 1.612 ], [ -1.54 ], [ 1.524 ], [ 1.704 ], [ 1.652 ], [ 1.552 ], [ -0.852 ] ],
[ [ 1.108 ], [ 1.368 ], [ -0.636 ], [ -1.856 ], [ 0.788 ], [ 0.048 ], [ 1.64 ], [ 0.996 ] ],
[ [ -1.72 ], [ 1.512 ], [ -1.832 ], [ -1.476 ], [ -1.688 ], [ 0.496 ], [ -0.384 ], [ -0.012 ] ],
[ [ 0.092 ], [ -1.572 ], [ 1.556 ], [ -1.228 ], [ 1.764 ], [ -1.028 ], [ 1.912 ], [ -0.876 ] ],
[ [ 1.048 ], [ -0.768 ], [ -0.032 ], [ -0.804 ], [ 1.62 ], [ -0.804 ], [ 1.876 ], [ -1.492 ] ],
[ [ 0.148 ], [ 0.636 ], [ -0.408 ], [ -1.616 ], [ 0.7 ], [ 0.392 ], [ 0.028 ], [ 1.556 ] ],
[ [ 0.048 ], [ -0.176 ], [ -0.128 ], [ 1.032 ], [ -0.068 ], [ -0.556 ], [ 0.3 ], [ -0.464 ] ]
]
[
[ [ 1.776 ], [ -0.472 ], [ 0.56 ], [ -0.856 ], [ -1.808 ], [ -1.156 ], [ -1.76 ], [ -1.34 ] ],
[ [ 0.52 ], [ 0.184 ], [ 0.012 ], [ -1.1 ], [ -0.124 ], [ -0.968 ], [ -1.58 ], [ -0.808 ] ],
[ [ -1.484 ], [ -0.312 ], [ -1.764 ], [ 1.916 ], [ 0.016 ], [ -0.968 ], [ 0.344 ], [ -1.16 ] ],
[ [ 1.98 ], [ 1.352 ], [ 0.688 ], [ 1.444 ], [ 1.288 ], [ -1.456 ], [ -1.176 ], [ -1.656 ] ],
[ [ 0.812 ], [ 1.42 ], [ -0.892 ], [ -0.628 ], [ 0.82 ], [ 0.66 ], [ -1.16 ], [ -1.724 ] ],
[ [ 1.628 ], [ 0.52 ], [ 0.972 ], [ -2.0 ], [ 1.156 ], [ -1.564 ], [ -1.256 ], [ -1.248 ] ],
[ [ 0.644 ], [ -0.888 ], [ -0.316 ], [ -0.368 ], [ -1.256 ], [ -0.784 ], [ -0.504 ], [ 1.628 ] ],
[ [ -1.552 ], [ 1.24 ], [ 1.324 ], [ -1.664 ], [ 0.692 ], [ 0.82 ], [ 1.956 ], [ -1.116 ] ]
]
[
[ [ 1.524 ], [ 1.048 ], [ 0.092 ], [ -1.616 ], [ 1.876 ], [ -1.516 ], [ 0.636 ], [ -0.804 ] ],
[ [ 1.356 ], [ -1.688 ], [ -0.384 ], [ -0.068 ], [ -1.028 ], [ -1.832 ], [ 1.556 ], [ -1.228 ] ],
[ [ 1.368 ], [ -0.876 ], [ 1.764 ], [ -0.032 ], [ 0.788 ], [ 0.148 ], [ -0.636 ], [ -0.892 ] ],
[ [ 1.108 ], [ 1.512 ], [ 1.64 ], [ -0.768 ], [ -0.804 ], [ -1.54 ], [ 1.032 ], [ 0.7 ] ],
[ [ 1.912 ], [ -0.012 ], [ -0.408 ], [ 1.556 ], [ -0.852 ], [ -0.556 ], [ -1.572 ], [ -0.176 ] ],
[ [ 1.208 ], [ 0.3 ], [ -0.712 ], [ -1.476 ], [ -0.128 ], [ 0.496 ], [ 1.62 ], [ 1.704 ] ],
[ [ 0.08 ], [ -0.384 ], [ 0.048 ], [ 1.652 ], [ 1.552 ], [ 0.028 ], [ -0.464 ], [ 0.996 ] ],
[ [ -1.492 ], [ 0.048 ], [ 1.612 ], [ 0.392 ], [ -1.856 ], [ -1.72 ], [ -1.424 ], [ -0.608 ] ]
]
[
[ [ -1.58 ], [ 1.444 ], [ -1.176 ], [ 0.82 ], [ 1.98 ], [ -1.724 ], [ -0.504 ], [ -1.484 ] ],
[ [ 1.24 ], [ -0.892 ], [ 1.288 ], [ -0.312 ], [ 0.66 ], [ -1.34 ], [ -0.888 ], [ -1.16 ] ],
[ [ 0.184 ], [ -0.316 ], [ 1.42 ], [ -1.76 ], [ 0.56 ], [ 0.016 ], [ -0.124 ], [ -1.1 ] ],
[ [ -0.368 ], [ -1.256 ], [ -1.156 ], [ 0.688 ], [ -1.764 ], [ 1.156 ], [ 1.628 ], [ -1.656 ] ],
[ [ 0.692 ], [ 0.644 ], [ 0.012 ], [ -1.456 ], [ -0.472 ], [ -1.116 ], [ -0.856 ], [ -0.968 ] ],
[ [ 0.82 ], [ 1.352 ], [ 0.52 ], [ -0.968 ], [ 0.812 ], [ -0.784 ], [ -1.256 ], [ 1.628 ] ],
[ [ -1.564 ], [ -2.0 ], [ -1.664 ], [ 0.344 ], [ 0.52 ], [ -0.628 ], [ -1.16 ], [ 1.776 ] ],
[ [ -1.552 ], [ 1.956 ], [ 1.916 ], [ -1.248 ], [ -0.808 ], [ 1.324 ], [ 0.972 ], [ -1.808 ] ]
]
[
[ [ 1.356 ], [ 0.148 ], [ 0.636 ], [ 1.512 ], [ -1.424 ], [ 1.64 ], [ -0.384 ], [ 1.764 ] ],
[ [ 1.612 ], [ -0.556 ], [ -0.408 ], [ 1.552 ], [ 0.3 ], [ 0.7 ], [ 0.788 ], [ 1.556 ] ],
[ [ -1.572 ], [ -1.54 ], [ 1.912 ], [ 1.876 ], [ -1.856 ], [ 0.392 ], [ -0.636 ], [ 1.032 ] ],
[ [ -0.712 ], [ -0.804 ], [ -0.852 ], [ -0.128 ], [ -1.228 ], [ -1.516 ], [ 0.048 ], [ 0.08 ] ],
[ [ -0.176 ], [ -0.608 ], [ 1.368 ], [ -0.768 ], [ -0.892 ], [ -1.688 ], [ -0.804 ], [ 1.652 ] ],
[ [ -0.012 ], [ -1.492 ], [ -0.068 ], [ 1.208 ], [ -0.876 ], [ 1.62 ], [ 0.996 ], [ 1.704 ] ],
[ [ 1.048 ], [ 0.028 ], [ 0.496 ], [ 1.556 ], [ 0.092 ], [ -0.464 ], [ 1.524 ], [ 0.048 ] ],
[ [ -1.476 ], [ 1.108 ], [ -0.384 ], [ -1.028 ], [ -1.832 ], [ -0.032 ], [ -1.616 ], [ -1.72 ] ]
]
[
[ [ -1.456 ], [ 0.82 ], [ 1.628 ], [ 1.24 ], [ -0.892 ], [ -1.552 ], [ 0.688 ], [ -1.256 ] ],
[ [ 0.52 ], [ -0.504 ], [ -0.888 ], [ -0.968 ], [ 0.56 ], [ -1.656 ], [ -1.16 ], [ 1.628 ] ],
[ [ 0.52 ], [ -0.628 ], [ -0.316 ], [ -1.664 ], [ -1.76 ], [ -1.16 ], [ -1.764 ], [ -1.808 ] ],
[ [ 1.42 ], [ -0.784 ], [ -0.312 ], [ -1.248 ], [ 0.184 ], [ 1.444 ], [ -1.564 ], [ -2.0 ] ],
[ [ 1.288 ], [ 1.324 ], [ 0.812 ], [ -1.484 ], [ 1.98 ], [ 0.012 ], [ -0.968 ], [ 0.82 ] ],
[ [ -0.856 ], [ -1.156 ], [ 1.352 ], [ -1.34 ], [ 1.156 ], [ -1.256 ], [ -1.116 ], [ -0.472 ] ],
[ [ 1.776 ], [ 0.016 ], [ 0.644 ], [ -1.176 ], [ 0.972 ], [ -1.724 ], [ -0.368 ], [ -0.124 ] ],
[ [ 1.916 ], [ -1.58 ], [ 0.66 ], [ 1.956 ], [ 0.692 ], [ 0.344 ], [ -0.808 ], [ -1.1 ] ]
]
[
[ [ -0.556 ], [ 1.876 ], [ -0.464 ], [ -0.408 ], [ -0.712 ], [ 1.912 ], [ -0.012 ], [ -0.384 ] ],
[ [ -1.516 ], [ -0.608 ], [ -0.068 ], [ 1.108 ], [ 1.524 ], [ -0.892 ], [ 0.496 ], [ -1.832 ] ],
[ [ 1.764 ], [ -1.424 ], [ -0.032 ], [ -1.572 ], [ 1.64 ], [ 1.208 ], [ -1.54 ], [ 1.556 ] ],
[ [ -0.804 ], [ 1.652 ], [ -0.768 ], [ 0.392 ], [ -1.228 ], [ 1.556 ], [ -0.384 ], [ -0.636 ] ],
[ [ 1.552 ], [ -0.852 ], [ -1.856 ], [ 1.368 ], [ -1.028 ], [ -1.492 ], [ 1.62 ], [ 0.636 ] ],
[ [ 0.048 ], [ 1.356 ], [ 0.028 ], [ 1.704 ], [ 1.048 ], [ -0.804 ], [ -0.876 ], [ 0.048 ] ],
[ [ 0.092 ], [ 0.148 ], [ -1.72 ], [ -1.476 ], [ -0.176 ], [ -1.616 ], [ 1.612 ], [ -0.128 ] ],
[ [ 0.3 ], [ 0.996 ], [ 0.08 ], [ 1.032 ], [ 1.512 ], [ 0.788 ], [ 0.7 ], [ -1.688 ] ]
]
[
[ [ -0.316 ], [ -1.484 ], [ -1.552 ], [ -1.456 ], [ 0.56 ], [ -0.312 ], [ -1.256 ], [ -1.76 ] ],
[ [ -0.368 ], [ -1.764 ], [ 1.628 ], [ 0.82 ], [ -0.504 ], [ -1.16 ], [ 0.644 ], [ -0.784 ] ],
[ [ 0.016 ], [ -1.16 ], [ -0.628 ], [ -0.472 ], [ 0.82 ], [ 1.916 ], [ -1.34 ], [ 1.444 ] ],
[ [ 1.628 ], [ 1.24 ], [ 0.52 ], [ -1.1 ], [ -0.968 ], [ 0.972 ], [ 0.812 ], [ -1.116 ] ],
[ [ -1.656 ], [ -0.808 ], [ 0.012 ], [ -1.564 ], [ -1.248 ], [ -0.892 ], [ -1.58 ], [ 1.956 ] ],
[ [ 0.184 ], [ -0.856 ], [ 1.352 ], [ -0.968 ], [ -1.176 ], [ 0.692 ], [ -1.156 ], [ -0.124 ] ],
[ [ 1.42 ], [ 0.688 ], [ -1.808 ], [ 1.156 ], [ 0.344 ], [ -0.888 ], [ 1.288 ], [ 0.52 ] ],
[ [ -1.724 ], [ -1.664 ], [ -2.0 ], [ 1.98 ], [ 1.776 ], [ 0.66 ], [ -1.256 ], [ 1.324 ] ]
]
[
[ [ 0.496 ], [ 1.032 ], [ -0.768 ], [ -0.128 ], [ 0.392 ], [ -0.892 ], [ 1.368 ], [ 1.912 ] ],
[ [ 1.512 ], [ 0.3 ], [ -1.516 ], [ 1.556 ], [ 0.08 ], [ 1.704 ], [ -0.384 ], [ -0.068 ] ],
[ [ 1.048 ], [ 1.208 ], [ 1.552 ], [ 1.524 ], [ -1.72 ], [ 1.62 ], [ 0.028 ], [ -1.616 ] ],
[ [ -1.832 ], [ -0.712 ], [ 0.048 ], [ 1.764 ], [ -1.54 ], [ 0.148 ], [ -1.856 ], [ -0.012 ] ],
[ [ 0.996 ], [ 0.092 ], [ 0.788 ], [ 1.64 ], [ -0.176 ], [ -0.852 ], [ -0.556 ], [ 1.612 ] ],
[ [ 0.636 ], [ -0.608 ], [ -1.572 ], [ -0.408 ], [ -0.384 ], [ -0.636 ], [ 1.108 ], [ 1.556 ] ],
[ [ 1.356 ], [ 0.7 ], [ 0.048 ], [ -1.476 ], [ 1.652 ], [ -0.464 ], [ -1.424 ], [ -1.688 ] ],
[ [ -0.804 ], [ -1.028 ], [ -0.804 ], [ -1.492 ], [ -0.032 ], [ -1.228 ], [ -0.876 ], [ 1.876 ] ]
]
[
[ [ 0.344 ], [ 0.012 ], [ -1.664 ], [ 0.972 ], [ 1.288 ], [ 1.916 ], [ -0.316 ], [ -0.856 ] ],
[ [ 0.66 ], [ -1.248 ], [ -1.58 ], [ -1.16 ], [ -2.0 ], [ 1.42 ], [ 1.956 ], [ 1.444 ] ],
[ [ -1.764 ], [ 1.156 ], [ 0.184 ], [ -1.76 ], [ -0.368 ], [ -1.16 ], [ -1.484 ], [ -0.892 ] ],
[ [ -1.176 ], [ 0.82 ], [ -0.472 ], [ 0.016 ], [ 1.628 ], [ 1.324 ], [ -1.1 ], [ -0.968 ] ],
[ [ 1.352 ], [ -1.256 ], [ -1.564 ], [ 0.56 ], [ -0.888 ], [ -0.312 ], [ 0.688 ], [ 1.98 ] ],
[ [ 0.52 ], [ -0.968 ], [ -1.656 ], [ -1.808 ], [ -1.256 ], [ 1.776 ], [ -0.784 ], [ 0.692 ] ],
[ [ -1.34 ], [ -1.456 ], [ 0.82 ], [ 1.24 ], [ -0.628 ], [ -1.552 ], [ -0.808 ], [ -1.116 ] ],
[ [ -0.504 ], [ 1.628 ], [ -1.724 ], [ -1.156 ], [ -0.124 ], [ 0.644 ], [ 0.52 ], [ 0.812 ] ]
]
First, we train using basic gradient descent method apply weak line search conditions.
TrainingTester.java:480 executed in 0.05 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: 937151519995
BACKPROP_AGG_SIZE = 3
THREADS = 64
SINGLE_THREADED = false
Initialized CoreSettings = {
"backpropAggregationSize" : 3,
"jvmThreads" : 64,
"singleThreaded" : false
}
Final threshold in iteration 0: 0.0 (> 0.0) after 0.045s (< 30.000s)
Returns
0.0
This training apply resulted in the following configuration:
TrainingTester.java:610 executed in 0.00 seconds (0.000 gc):
RefList<double[]> state = network.state();
assert state != null;
String description = state.stream().map(RefArrays::toString).reduce((a, b) -> a + "\n" + b)
.orElse("");
state.freeRef();
return description;
Returns
TrainingTester.java:622 executed in 0.00 seconds (0.000 gc):
return RefArrays.stream(RefUtil.addRef(data)).flatMap(x -> {
return RefArrays.stream(x);
}).limit(1).map(x -> {
String temp_18_0015 = x.prettyPrint();
x.freeRef();
return temp_18_0015;
}).reduce((a, b) -> a + "\n" + b).orElse("");
Returns
[
[ [ -1.856 ], [ 0.392 ], [ -1.832 ], [ 0.636 ], [ 0.092 ], [ 1.652 ], [ -0.556 ], [ 1.108 ] ],
[ [ 1.764 ], [ -1.688 ], [ 0.996 ], [ 0.028 ], [ -0.128 ], [ 0.048 ], [ 1.552 ], [ -0.892 ] ],
[ [ -1.228 ], [ -1.572 ], [ 1.032 ], [ -1.028 ], [ -0.804 ], [ 1.512 ], [ 0.496 ], [ -0.176 ] ],
[ [ -0.384 ], [ -1.476 ], [ -0.068 ], [ 1.048 ], [ 1.556 ], [ 0.08 ], [ 1.62 ], [ 0.7 ] ],
[ [ -0.012 ], [ -0.804 ], [ 0.3 ], [ -0.852 ], [ -0.032 ], [ 1.704 ], [ -0.608 ], [ -1.616 ] ],
[ [ -1.492 ], [ -0.464 ], [ 0.788 ], [ -0.408 ], [ 1.912 ], [ -1.424 ], [ -0.768 ], [ -0.712 ] ],
[ [ -1.516 ], [ -1.54 ], [ -0.636 ], [ 0.048 ], [ 1.612 ], [ 1.556 ], [ 0.148 ], [ 1.356 ] ],
[ [ 1.208 ], [ -0.384 ], [ 1.368 ], [ 1.876 ], [ 1.524 ], [ -0.876 ], [ -1.72 ], [ 1.64 ] ]
]
To produce the following output:
TrainingTester.java:633 executed in 0.00 seconds (0.000 gc):
Result[] array = ConstantResult.batchResultArray(pop(RefUtil.addRef(data)));
@Nullable
Result eval = layer.eval(array);
assert eval != null;
TensorList tensorList = Result.getData(eval);
String temp_18_0016 = tensorList.stream().limit(1).map(x -> {
String temp_18_0017 = x.prettyPrint();
x.freeRef();
return temp_18_0017;
}).reduce((a, b) -> a + "\n" + b).orElse("");
tensorList.freeRef();
return temp_18_0016;
Returns
[ 2.8158015 ]
First, we use a conjugate gradient descent method, which converges the fastest for purely linear functions.
TrainingTester.java:452 executed in 0.01 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: 937214357728
Final threshold in iteration 0: 0.0 (> 0.0) after 0.010s (< 30.000s)
Returns
0.0
This training apply resulted in the following configuration:
TrainingTester.java:610 executed in 0.00 seconds (0.000 gc):
RefList<double[]> state = network.state();
assert state != null;
String description = state.stream().map(RefArrays::toString).reduce((a, b) -> a + "\n" + b)
.orElse("");
state.freeRef();
return description;
Returns
TrainingTester.java:622 executed in 0.00 seconds (0.000 gc):
return RefArrays.stream(RefUtil.addRef(data)).flatMap(x -> {
return RefArrays.stream(x);
}).limit(1).map(x -> {
String temp_18_0015 = x.prettyPrint();
x.freeRef();
return temp_18_0015;
}).reduce((a, b) -> a + "\n" + b).orElse("");
Returns
[
[ [ -1.856 ], [ 0.392 ], [ -1.832 ], [ 0.636 ], [ 0.092 ], [ 1.652 ], [ -0.556 ], [ 1.108 ] ],
[ [ 1.764 ], [ -1.688 ], [ 0.996 ], [ 0.028 ], [ -0.128 ], [ 0.048 ], [ 1.552 ], [ -0.892 ] ],
[ [ -1.228 ], [ -1.572 ], [ 1.032 ], [ -1.028 ], [ -0.804 ], [ 1.512 ], [ 0.496 ], [ -0.176 ] ],
[ [ -0.384 ], [ -1.476 ], [ -0.068 ], [ 1.048 ], [ 1.556 ], [ 0.08 ], [ 1.62 ], [ 0.7 ] ],
[ [ -0.012 ], [ -0.804 ], [ 0.3 ], [ -0.852 ], [ -0.032 ], [ 1.704 ], [ -0.608 ], [ -1.616 ] ],
[ [ -1.492 ], [ -0.464 ], [ 0.788 ], [ -0.408 ], [ 1.912 ], [ -1.424 ], [ -0.768 ], [ -0.712 ] ],
[ [ -1.516 ], [ -1.54 ], [ -0.636 ], [ 0.048 ], [ 1.612 ], [ 1.556 ], [ 0.148 ], [ 1.356 ] ],
[ [ 1.208 ], [ -0.384 ], [ 1.368 ], [ 1.876 ], [ 1.524 ], [ -0.876 ], [ -1.72 ], [ 1.64 ] ]
]
To produce the following output:
TrainingTester.java:633 executed in 0.00 seconds (0.000 gc):
Result[] array = ConstantResult.batchResultArray(pop(RefUtil.addRef(data)));
@Nullable
Result eval = layer.eval(array);
assert eval != null;
TensorList tensorList = Result.getData(eval);
String temp_18_0016 = tensorList.stream().limit(1).map(x -> {
String temp_18_0017 = x.prettyPrint();
x.freeRef();
return temp_18_0017;
}).reduce((a, b) -> a + "\n" + b).orElse("");
tensorList.freeRef();
return temp_18_0016;
Returns
[ 2.8158015 ]
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 0.02 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: 937237129153
Final threshold in iteration 0: 0.0 (> 0.0) after 0.015s (< 30.000s)
Returns
0.0
This training apply resulted in the following configuration:
TrainingTester.java:610 executed in 0.00 seconds (0.000 gc):
RefList<double[]> state = network.state();
assert state != null;
String description = state.stream().map(RefArrays::toString).reduce((a, b) -> a + "\n" + b)
.orElse("");
state.freeRef();
return description;
Returns
TrainingTester.java:622 executed in 0.00 seconds (0.000 gc):
return RefArrays.stream(RefUtil.addRef(data)).flatMap(x -> {
return RefArrays.stream(x);
}).limit(1).map(x -> {
String temp_18_0015 = x.prettyPrint();
x.freeRef();
return temp_18_0015;
}).reduce((a, b) -> a + "\n" + b).orElse("");
Returns
[
[ [ -1.856 ], [ 0.392 ], [ -1.832 ], [ 0.636 ], [ 0.092 ], [ 1.652 ], [ -0.556 ], [ 1.108 ] ],
[ [ 1.764 ], [ -1.688 ], [ 0.996 ], [ 0.028 ], [ -0.128 ], [ 0.048 ], [ 1.552 ], [ -0.892 ] ],
[ [ -1.228 ], [ -1.572 ], [ 1.032 ], [ -1.028 ], [ -0.804 ], [ 1.512 ], [ 0.496 ], [ -0.176 ] ],
[ [ -0.384 ], [ -1.476 ], [ -0.068 ], [ 1.048 ], [ 1.556 ], [ 0.08 ], [ 1.62 ], [ 0.7 ] ],
[ [ -0.012 ], [ -0.804 ], [ 0.3 ], [ -0.852 ], [ -0.032 ], [ 1.704 ], [ -0.608 ], [ -1.616 ] ],
[ [ -1.492 ], [ -0.464 ], [ 0.788 ], [ -0.408 ], [ 1.912 ], [ -1.424 ], [ -0.768 ], [ -0.712 ] ],
[ [ -1.516 ], [ -1.54 ], [ -0.636 ], [ 0.048 ], [ 1.612 ], [ 1.556 ], [ 0.148 ], [ 1.356 ] ],
[ [ 1.208 ], [ -0.384 ], [ 1.368 ], [ 1.876 ], [ 1.524 ], [ -0.876 ], [ -1.72 ], [ 1.64 ] ]
]
To produce the following output:
TrainingTester.java:633 executed in 0.00 seconds (0.000 gc):
Result[] array = ConstantResult.batchResultArray(pop(RefUtil.addRef(data)));
@Nullable
Result eval = layer.eval(array);
assert eval != null;
TensorList tensorList = Result.getData(eval);
String temp_18_0016 = tensorList.stream().limit(1).map(x -> {
String temp_18_0017 = x.prettyPrint();
x.freeRef();
return temp_18_0017;
}).reduce((a, b) -> a + "\n" + b).orElse("");
tensorList.freeRef();
return temp_18_0016;
Returns
[ 2.8158015 ]
TrainingTester.java:432 executed in 0.01 seconds (0.000 gc):
return TestUtil.compare(title + " vs Iteration", runs);
No Data
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 0.03 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": "NonConverged", "value": NaN }, "CjGD": { "type": "NonConverged", "value": NaN }, "GD": { "type": "NonConverged", "value": NaN } }, "model":null, "complete":null}
LayerTests.java:425 executed in 0.00 seconds (0.000 gc):
throwException(exceptions.addRef());
| details | result |
|---|---|
| {"input":{ "LBFGS": { "type": "NonConverged", "value": NaN }, "CjGD": { "type": "NonConverged", "value": NaN }, "GD": { "type": "NonConverged", "value": NaN } }, "model":null, "complete":null} | OK |
{
"result": "OK",
"performance": {
"execution_time": "0.450",
"gc_time": "0.155"
},
"created_on": 1586735524948,
"file_name": "trainingTest",
"report": {
"simpleName": "Basic",
"canonicalName": "com.simiacryptus.mindseye.layers.java.MeanSqLossLayerTest.Basic",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/MeanSqLossLayerTest.java",
"javaDoc": ""
},
"training_analysis": {
"input": {
"LBFGS": {
"type": "NonConverged",
"value": "NaN"
},
"CjGD": {
"type": "NonConverged",
"value": "NaN"
},
"GD": {
"type": "NonConverged",
"value": "NaN"
}
}
},
"archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/MeanSqLossLayer/Basic/trainingTest/202004125204",
"id": "e3067a5d-f343-4afd-af71-9955c405750e",
"report_type": "Components",
"display_name": "Comparative Training",
"target": {
"simpleName": "MeanSqLossLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.java.MeanSqLossLayer",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/MeanSqLossLayer.java",
"javaDoc": ""
}
}