Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 6386650402948461568
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 ], [ -0.128 ] ],
[ [ 0.7 ], [ 0.496 ] ]
]
Inputs Statistics: {meanExponent=-0.6122800817139336, negative=1, min=-0.128, max=0.7, mean=0.287, count=4, sum=1.148, positive=3, stdDev=0.3276141022605712, zeros=0}
Output: [
[ [ -3.5 ] ]
]
Outputs Statistics: {meanExponent=0.5440680443502757, negative=1, min=-3.5, max=-3.5, mean=-3.5, count=1, sum=-3.5, positive=0, 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 0.04 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 ], [ -0.128 ] ],
[ [ 0.7 ], [ 0.496 ] ]
]
Value Statistics: {meanExponent=-0.6122800817139336, negative=1, min=-0.128, max=0.7, mean=0.287, count=4, sum=1.148, positive=3, stdDev=0.3276141022605712, zeros=0}
Implemented Feedback: [ [ 0.0 ], [ -5.0 ], [ 0.0 ], [ 0.0 ] ]
Implemented Statistics: {meanExponent=0.6989700043360189, negative=1, min=-5.0, max=0.0, mean=-1.25, count=4, sum=-5.0, positive=0, stdDev=2.165063509461097, zeros=3}
Measured Feedback: [ [ 0.0 ], [ -4.999999999997229 ], [ 0.0 ], [ 0.0 ] ]
Measured Statistics: {meanExponent=0.6989700043357782, negative=1, min=-4.999999999997229, max=0.0, mean=-1.2499999999993072, count=4, sum=-4.999999999997229, positive=0, stdDev=2.165063509459897, zeros=3}
Feedback Error: [ [ 0.0 ], [ 2.7711166694643907E-12 ], [ 0.0 ], [ 0.0 ] ]
Error Statistics: {meanExponent=-11.557345189180618, negative=0, min=0.0, max=2.7711166694643907E-12, mean=6.927791673660977E-13, count=4, sum=2.7711166694643907E-12, positive=1, stdDev=1.199928716303344E-12, zeros=3}
Returns
{
"absoluteTol" : {
"count" : 4,
"sum" : 2.7711166694643907E-12,
"min" : 0.0,
"max" : 2.7711166694643907E-12,
"sumOfSquare" : 7.679087595783417E-24,
"standardDeviation" : 1.199928716303344E-12,
"average" : 6.927791673660977E-13
},
"relativeTol" : {
"count" : 1,
"sum" : 2.7711166694651586E-13,
"min" : 2.7711166694651586E-13,
"max" : 2.7711166694651586E-13,
"sumOfSquare" : 7.679087595787673E-26,
"standardDeviation" : 0.0,
"average" : 2.7711166694651586E-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" : 4,
"sum" : 2.7711166694643907E-12,
"min" : 0.0,
"max" : 2.7711166694643907E-12,
"sumOfSquare" : 7.679087595783417E-24,
"standardDeviation" : 1.199928716303344E-12,
"average" : 6.927791673660977E-13
},
"relativeTol" : {
"count" : 1,
"sum" : 2.7711166694651586E-13,
"min" : 2.7711166694651586E-13,
"max" : 2.7711166694651586E-13,
"sumOfSquare" : 7.679087595787673E-26,
"standardDeviation" : 0.0,
"average" : 2.7711166694651586E-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: 6.9278e-13 +- 1.1999e-12 [0.0000e+00 - 2.7711e-12] (4#)
relativeTol: 2.7711e-13 +- 0.0000e+00 [2.7711e-13 - 2.7711e-13] (1#)
SingleDerivativeTester.java:156 executed in 0.02 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=6.9278e-13 +- 1.1999e-12 [0.0000e+00 - 2.7711e-12] (4#), relativeTol=2.7711e-13 +- 0.0000e+00 [2.7711e-13 - 2.7711e-13] (1#)} | OK |
{
"result": "OK",
"performance": {
"execution_time": "0.291",
"gc_time": "0.172"
},
"created_on": 1586736841429,
"file_name": "derivativeTest",
"report": {
"simpleName": "Negative",
"canonicalName": "com.simiacryptus.mindseye.layers.cudnn.BandReducerLayerTest.Negative",
"link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/test/java/com/simiacryptus/mindseye/layers/cudnn/BandReducerLayerTest.java",
"javaDoc": ""
},
"archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/cudnn/BandReducerLayer/Negative/derivativeTest/202004131401",
"id": "a23b342c-be0c-4145-a041-57fb66195104",
"report_type": "Components",
"display_name": "Derivative Validation",
"target": {
"simpleName": "BandReducerLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.cudnn.BandReducerLayer",
"link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/main/java/com/simiacryptus/mindseye/layers/cudnn/BandReducerLayer.java",
"javaDoc": ""
}
}