Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 9203828650370176000
SingleDerivativeTester.java:101 executed in 0.00 seconds (0.000 gc):
log.info(RefString.format("Inputs: %s", prettyPrint(inputPrototype)));
log.info(RefString.format("Inputs Statistics: %s", printStats(inputPrototype)));
log.info(RefString.format("Output: %s", outputPrototype.prettyPrint()));
assert outputPrototype != null;
log.info(RefString.format("Outputs Statistics: %s", outputPrototype.getScalarStatistics()));
},
outputPrototype.addRef(),
RefUtil.addRef(inputPrototype)));
Inputs: [ 8.0, 70.0, -12.8, 49.6 ]
Inputs Statistics: {meanExponent=1.3877199182860667, negative=1, min=-12.8, max=70.0, mean=28.700000000000003, count=4, sum=114.80000000000001, positive=3, stdDev=32.761410226057116, zeros=0}
Output: [ 0.06968641114982578, 0.6097560975609756, -0.11149825783972125, 0.43205574912891986 ]
Outputs Statistics: {meanExponent=-0.6722219697758881, negative=1, min=-0.11149825783972125, max=0.6097560975609756, mean=0.25, count=4, sum=1.0, positive=3, stdDev=0.28537813785764043, zeros=0}
We validate the agreement between the implemented derivative of the inputs apply finite difference estimations:
SingleDerivativeTester.java:117 executed in 0.02 seconds (0.000 gc):
return testFeedback(
statistics,
component.addRef(),
RefUtil.addRef(inputPrototype),
outputPrototype.addRef());
},
outputPrototype.addRef(),
RefUtil.addRef(inputPrototype),
component.addRef()));
Feedback for input 0
Inputs Values: [ 8.0, 70.0, -12.8, 49.6 ]
Value Statistics: {meanExponent=1.3877199182860667, negative=1, min=-12.8, max=70.0, mean=28.700000000000003, count=4, sum=114.80000000000001, positive=3, stdDev=32.761410226057116, zeros=0}
Implemented Feedback: [ [ 0.008103776906360403, -0.005311464264468429, 9.712391797885128E-4, -0.0037635518216804866 ], [ -6.070244873678204E-4, 0.0033993371292597944, 9.712391797885128E-4, -0.0037635518216804866 ], [ -6.070244873678204E-4, -0.005311464264468429, 0.009682040573516735, -0.0037635518216804866 ], [ -6.070244873678204E-4, -0.005311464264468429, 9.712391797885128E-4, 0.004947249572047736 ] ]
Implemented Statistics: {meanExponent=-2.604097116358875, negative=9, min=-0.005311464264468429, max=0.009682040573516735, mean=-1.0842021724855044E-19, count=16, sum=-1.734723475976807E-18, positive=7, stdDev=0.004517377272276163, zeros=0}
Measured Feedback: [ [ 0.008103769847250808, -0.0053114596376691026, 9.712383337856512E-4, -0.0037635485433673566 ], [ -6.070239585986847E-4, 0.0033993341685967238, 9.712383337856512E-4, -0.0037635485433673566 ], [ -6.070239584599069E-4, -0.0053114596365588795, 0.009682032139496366, -0.003763548542812245 ], [ -6.070239585986847E-4, -0.0053114596376691026, 9.712383337856512E-4, 0.00494724526289847 ] ]
Measured Statistics: {meanExponent=-2.6040974946745723, negative=9, min=-0.0053114596376691026, max=0.009682032139496366, mean=1.5612511283791264E-13, count=16, sum=2.4980018054066022E-12, positive=7, stdDev=0.004517373337162912, zeros=0}
Feedback Error: [ [ -7.059109595475288E-9, 4.626799326480635E-9, -8.460028616237916E-10, 3.2783131300763435E-9 ], [ 5.287691356818669E-10, -2.9606630706086046E-9, -8.460028616237916E-10, 3.2783131300763435E-9 ], [ 5.28907913559945E-10, 4.62790954950526E-9, -8.434020369249562E-9, 3.278868241588656E-9 ], [ 5.287691356818669E-10, 4.626799326480635E-9, -8.460028616237916E-10, -4.309149266579215E-9 ] ]
Error Statistics: {meanExponent=-8.664027258005207, negative=7, min=-8.434020369249562E-9, max=4.62790954950526E-9, mean=1.5612514671923053E-13, count=16, sum=2.4980023475076885E-12, positive=9, stdDev=3.935113261714419E-9, zeros=0}
Returns
{
"absoluteTol" : {
"count" : 16,
"sum" : 5.06043997759156E-8,
"min" : 5.287691356818669E-10,
"max" : 8.434020369249562E-9,
"sumOfSquare" : 2.477618625103322E-16,
"standardDeviation" : 2.34136088522505E-9,
"average" : 3.162774985994725E-9
},
"relativeTol" : {
"count" : 16,
"sum" : 6.968832673971972E-6,
"min" : 4.3547671903803336E-7,
"max" : 4.3565634911656297E-7,
"sumOfSquare" : 3.035289336748485E-12,
"standardDeviation" : 4.635783080739171E-11,
"average" : 4.3555204212324827E-7
}
}
We validate the agreement between the implemented derivative of the internal weights apply finite difference estimations:
SingleDerivativeTester.java:133 executed in 0.00 seconds (0.000 gc):
return testLearning(
statistics,
component.addRef(),
RefUtil.addRef(inputPrototype),
outputPrototype.addRef());
},
outputPrototype.addRef(),
RefUtil.addRef(inputPrototype),
component.addRef()));
Returns
{
"absoluteTol" : {
"count" : 16,
"sum" : 5.06043997759156E-8,
"min" : 5.287691356818669E-10,
"max" : 8.434020369249562E-9,
"sumOfSquare" : 2.477618625103322E-16,
"standardDeviation" : 2.34136088522505E-9,
"average" : 3.162774985994725E-9
},
"relativeTol" : {
"count" : 16,
"sum" : 6.968832673971972E-6,
"min" : 4.3547671903803336E-7,
"max" : 4.3565634911656297E-7,
"sumOfSquare" : 3.035289336748485E-12,
"standardDeviation" : 4.635783080739171E-11,
"average" : 4.3555204212324827E-7
}
}
The overall agreement accuracy between the implemented derivative and the finite difference estimations:
SingleDerivativeTester.java:148 executed in 0.00 seconds (0.000 gc):
//log.info(String.format("Component: %s\nInputs: %s\noutput=%s", component, Arrays.toStream(inputPrototype), outputPrototype));
log.info(RefString.format("Finite-Difference Derivative Accuracy:"));
log.info(RefString.format("absoluteTol: %s", statistics.absoluteTol));
log.info(RefString.format("relativeTol: %s", statistics.relativeTol));
Finite-Difference Derivative Accuracy:
absoluteTol: 3.1628e-09 +- 2.3414e-09 [5.2877e-10 - 8.4340e-09] (16#)
relativeTol: 4.3555e-07 +- 4.6358e-11 [4.3548e-07 - 4.3566e-07] (16#)
SingleDerivativeTester.java:156 executed in 0.01 seconds (0.000 gc):
testFrozen(component.addRef(), RefUtil.addRef(inputPrototype));
testUnFrozen(component.addRef(), RefUtil.addRef(inputPrototype));
LayerTests.java:425 executed in 0.00 seconds (0.000 gc):
throwException(exceptions.addRef());
class | details | result |
---|---|---|
com.simiacryptus.mindseye.test.unit.SingleDerivativeTester | ToleranceStatistics{absoluteTol=3.1628e-09 +- 2.3414e-09 [5.2877e-10 - 8.4340e-09] (16#), relativeTol=4.3555e-07 +- 4.6358e-11 [4.3548e-07 - 4.3566e-07] (16#)} | OK |
{
"result": "OK",
"performance": {
"execution_time": "0.167",
"gc_time": "0.110"
},
"created_on": 1586738552534,
"file_name": "derivativeTest",
"report": {
"simpleName": "Basic",
"canonicalName": "com.simiacryptus.mindseye.layers.java.L1NormalizationLayerTest.Basic",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/L1NormalizationLayerTest.java",
"javaDoc": ""
},
"archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/L1NormalizationLayer/Basic/derivativeTest/202004134232",
"id": "d76d1e75-c79e-4073-a240-91e4c891b3be",
"report_type": "Components",
"display_name": "Derivative Validation",
"target": {
"simpleName": "L1NormalizationLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.java.L1NormalizationLayer",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/L1NormalizationLayer.java",
"javaDoc": ""
}
}