Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 7073826765672087552
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, -0.608, 1.764 ]
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=-0.09137205448042225, negative=1, min=-0.608, max=1.764, mean=0.5506666666666667, count=3, sum=1.6520000000000001, positive=2, stdDev=0.9691361560115735, zeros=0}
Output: [ 0.0038131319439359992 ]
Outputs Statistics: {meanExponent=-2.418718166787198, negative=0, min=0.0038131319439359992, max=0.0038131319439359992, mean=0.0038131319439359992, count=1, sum=0.0038131319439359992, positive=1, stdDev=0.0, 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: [ [ 0.04766414929919999 ], [ 0.005447331348479999 ], [ -0.029790093311999992 ] ]
Implemented Statistics: {meanExponent=-1.7038508323385544, negative=1, min=-0.029790093311999992, max=0.04766414929919999, mean=0.007773795778559999, count=3, sum=0.023321387335679997, positive=2, stdDev=0.03166332528522526, zeros=0}
Measured Feedback: [ [ 0.04766414929920949 ], [ 0.00544733134848728 ], [ -0.02979009331199184 ] ]
Measured Statistics: {meanExponent=-1.7038508323383716, negative=1, min=-0.02979009331199184, max=0.04766414929920949, mean=0.007773795778568311, count=3, sum=0.023321387335704935, positive=2, stdDev=0.03166332528522584, zeros=0}
Feedback Error: [ [ 9.506284648352903E-15 ], [ 7.281501790412648E-15 ], [ 8.153200337090993E-15 ] ]
Error Statistics: {meanExponent=-14.0828133704315, negative=0, min=7.281501790412648E-15, max=9.506284648352903E-15, mean=8.313662258618848E-15, count=3, sum=2.4940986775856544E-14, positive=3, stdDev=9.153235174667337E-16, zeros=0}
Feedback for input 1
Inputs Values: [ 0.496, -0.608, 1.764 ]
Value Statistics: {meanExponent=-0.09137205448042225, negative=1, min=-0.608, max=1.764, mean=0.5506666666666667, count=3, sum=1.6520000000000001, positive=2, stdDev=0.9691361560115735, zeros=0}
Implemented Feedback: [ [ 0.007687766015999999 ], [ -0.006271598591999999 ], [ 0.0021616394239999995 ] ]
Implemented Statistics: {meanExponent=-2.327346112306776, negative=1, min=-0.006271598591999999, max=0.007687766015999999, mean=0.0011926022826666664, count=3, sum=0.003577806847999999, positive=2, stdDev=0.005739932624501984, zeros=0}
Measured Feedback: [ [ 0.0076877660160025105 ], [ -0.006271598592001021 ], [ 0.002161639423999516 ] ]
Measured Statistics: {meanExponent=-2.327346112306737, negative=1, min=-0.006271598592001021, max=0.0076877660160025105, mean=0.0011926022826670019, count=3, sum=0.0035778068480010056, positive=2, stdDev=0.005739932624503347, zeros=0}
Feedback Error: [ [ 2.5118795932144167E-15 ], [ -1.0217521273503394E-15 ], [ -4.83554168928535E-16 ] ]
Error Statistics: {meanExponent=-14.96873683327341, negative=2, min=-1.0217521273503394E-15, max=2.5118795932144167E-15, mean=3.355244323118474E-16, count=3, sum=1.0065732969355423E-15, positive=1, stdDev=1.554521491306952E-15, zeros=0}
Returns
{
"absoluteTol" : {
"count" : 6,
"sum" : 2.8958172665349835E-14,
"min" : 4.83554168928535E-16,
"max" : 9.506284648352903E-15,
"sumOfSquare" : 2.174517330108735E-28,
"standardDeviation" : 3.59835855305747E-15,
"average" : 4.8263621108916394E-15
},
"relativeTol" : {
"count" : 6,
"sum" : 1.2615968887799932E-12,
"min" : 8.145866738454809E-14,
"max" : 6.683549544346684E-13,
"sumOfSquare" : 5.21204062983884E-25,
"standardDeviation" : 2.0653205751461616E-13,
"average" : 2.1026614812999886E-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" : 6,
"sum" : 2.8958172665349835E-14,
"min" : 4.83554168928535E-16,
"max" : 9.506284648352903E-15,
"sumOfSquare" : 2.174517330108735E-28,
"standardDeviation" : 3.59835855305747E-15,
"average" : 4.8263621108916394E-15
},
"relativeTol" : {
"count" : 6,
"sum" : 1.2615968887799932E-12,
"min" : 8.145866738454809E-14,
"max" : 6.683549544346684E-13,
"sumOfSquare" : 5.21204062983884E-25,
"standardDeviation" : 2.0653205751461616E-13,
"average" : 2.1026614812999886E-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: 4.8264e-15 +- 3.5984e-15 [4.8355e-16 - 9.5063e-15] (6#)
relativeTol: 2.1027e-13 +- 2.0653e-13 [8.1459e-14 - 6.6835e-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=4.8264e-15 +- 3.5984e-15 [4.8355e-16 - 9.5063e-15] (6#), relativeTol=2.1027e-13 +- 2.0653e-13 [8.1459e-14 - 6.6835e-13] (6#)} | OK |
{
"result": "OK",
"performance": {
"execution_time": "0.145",
"gc_time": "0.095"
},
"created_on": 1586739082273,
"file_name": "derivativeTest",
"report": {
"simpleName": "Basic",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ProductLayerTest.Basic",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/ProductLayerTest.java",
"javaDoc": ""
},
"archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/ProductLayer/Basic/derivativeTest/202004135122",
"id": "42c14ecc-1cc7-46a2-ad75-637b4b3722fa",
"report_type": "Components",
"display_name": "Derivative Validation",
"target": {
"simpleName": "ProductLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ProductLayer",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/ProductLayer.java",
"javaDoc": ""
}
}