Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 8148076380569302016
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: [ 0.08, 0.7, -0.128 ],
[ 0.496 ]
Inputs Statistics: {meanExponent=-0.7148673344486438, negative=1, min=-0.128, max=0.7, mean=0.2173333333333333, count=3, sum=0.6519999999999999, positive=2, stdDev=0.3517018939701949, zeros=0},
{meanExponent=-0.30451832350980257, negative=0, min=0.496, max=0.496, mean=0.496, count=1, sum=0.496, positive=1, stdDev=0.0, zeros=0}
Output: [ 0.03968, 0.34719999999999995, -0.063488 ]
Outputs Statistics: {meanExponent=-1.0193856579584464, negative=1, min=-0.063488, max=0.34719999999999995, mean=0.10779733333333331, count=3, sum=0.32339199999999996, positive=2, stdDev=0.17444413940921666, 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: [ 0.08, 0.7, -0.128 ]
Value Statistics: {meanExponent=-0.7148673344486438, negative=1, min=-0.128, max=0.7, mean=0.2173333333333333, count=3, sum=0.6519999999999999, positive=2, stdDev=0.3517018939701949, zeros=0}
Implemented Feedback: [ [ 0.496, 0.0, 0.0 ], [ 0.0, 0.496, 0.0 ], [ 0.0, 0.0, 0.496 ] ]
Implemented Statistics: {meanExponent=-0.30451832350980257, negative=0, min=0.0, max=0.496, mean=0.16533333333333333, count=9, sum=1.488, positive=3, stdDev=0.23381664231235166, zeros=6}
Measured Feedback: [ [ 0.4960000000000381, 0.0, 0.0 ], [ 0.0, 0.496000000000385, 0.0 ], [ 0.0, 0.0, 0.4959999999999687 ] ]
Measured Statistics: {meanExponent=-0.30451832350968816, negative=0, min=0.0, max=0.496000000000385, mean=0.16533333333337685, count=9, sum=1.4880000000003917, positive=3, stdDev=0.23381664231241328, zeros=6}
Feedback Error: [ [ 3.808064974464287E-14, 0.0, 0.0 ], [ 0.0, 3.850253449400043E-13, 0.0 ], [ 0.0, 0.0, -3.1308289294429414E-14 ] ]
Error Statistics: {meanExponent=-13.112715664468903, negative=1, min=-3.1308289294429414E-14, max=3.850253449400043E-13, mean=4.353307837669086E-14, count=9, sum=3.9179770539021774E-13, positive=2, stdDev=1.2184630614613877E-13, zeros=6}
Feedback for input 1
Inputs Values: [ 0.496 ]
Value Statistics: {meanExponent=-0.30451832350980257, negative=0, min=0.496, max=0.496, mean=0.496, count=1, sum=0.496, positive=1, stdDev=0.0, zeros=0}
Implemented Feedback: [ [ 0.08, 0.7, -0.128 ] ]
Implemented Statistics: {meanExponent=-0.7148673344486438, negative=1, min=-0.128, max=0.7, mean=0.2173333333333333, count=3, sum=0.6519999999999999, positive=2, stdDev=0.3517018939701949, zeros=0}
Measured Feedback: [ [ 0.08000000000001062, 0.700000000000145, -0.12799999999993372 ] ]
Measured Statistics: {meanExponent=-0.7148673344486695, negative=1, min=-0.12799999999993372, max=0.700000000000145, mean=0.2173333333334073, count=3, sum=0.6520000000002218, positive=2, stdDev=0.35170189397023816, zeros=0}
Feedback Error: [ [ 1.061650767297806E-14, 1.4499512701604544E-13, 6.628031457012185E-14 ] ]
Error Statistics: {meanExponent=-13.330426784780968, negative=0, min=1.061650767297806E-14, max=1.4499512701604544E-13, mean=7.396398308638179E-14, count=3, sum=2.2189194925914535E-13, positive=3, stdDev=5.5128228737118425E-14, zeros=0}
Returns
{
"absoluteTol" : {
"count" : 12,
"sum" : 6.763062332382219E-13,
"min" : 0.0,
"max" : 3.850253449400043E-13,
"sumOfSquare" : 1.76204238302771E-25,
"standardDeviation" : 1.072723927191758E-13,
"average" : 5.635885276985183E-14
},
"relativeTol" : {
"count" : 6,
"sum" : 8.869075149156445E-13,
"min" : 3.156077549841774E-14,
"max" : 3.881303880442085E-13,
"sumOfSquare" : 2.3527704611874274E-25,
"standardDeviation" : 1.317676128537801E-13,
"average" : 1.4781791915260742E-13
}
}
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" : 12,
"sum" : 6.763062332382219E-13,
"min" : 0.0,
"max" : 3.850253449400043E-13,
"sumOfSquare" : 1.76204238302771E-25,
"standardDeviation" : 1.072723927191758E-13,
"average" : 5.635885276985183E-14
},
"relativeTol" : {
"count" : 6,
"sum" : 8.869075149156445E-13,
"min" : 3.156077549841774E-14,
"max" : 3.881303880442085E-13,
"sumOfSquare" : 2.3527704611874274E-25,
"standardDeviation" : 1.317676128537801E-13,
"average" : 1.4781791915260742E-13
}
}
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: 5.6359e-14 +- 1.0727e-13 [0.0000e+00 - 3.8503e-13] (12#)
relativeTol: 1.4782e-13 +- 1.3177e-13 [3.1561e-14 - 3.8813e-13] (6#)
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=5.6359e-14 +- 1.0727e-13 [0.0000e+00 - 3.8503e-13] (12#), relativeTol=1.4782e-13 +- 1.3177e-13 [3.1561e-14 - 3.8813e-13] (6#)} | OK |
{
"result": "OK",
"performance": {
"execution_time": "0.171",
"gc_time": "0.113"
},
"created_on": 1586738595643,
"file_name": "derivativeTest",
"report": {
"simpleName": "N1Test",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ProductInputsLayerTest.N1Test",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/ProductInputsLayerTest.java",
"javaDoc": ""
},
"archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/ProductInputsLayer/N1Test/derivativeTest/202004134315",
"id": "6bb19317-bb31-4f61-b3e8-f15ae65baea7",
"report_type": "Components",
"display_name": "Derivative Validation",
"target": {
"simpleName": "ProductInputsLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ProductInputsLayer",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/ProductInputsLayer.java",
"javaDoc": ""
}
}