Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 3942457384392102912
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 ] ]
]
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}
Output: [
[ [ 0.08, 0.7 ] ]
]
Outputs Statistics: {meanExponent=-0.6259059864968999, negative=0, min=0.08, max=0.7, mean=0.38999999999999996, count=2, sum=0.7799999999999999, positive=2, stdDev=0.31000000000000005, zeros=0}
We validate the agreement between the implemented derivative of the inputs apply finite difference estimations:
SingleDerivativeTester.java:117 executed in 0.06 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: [ [ 1.0, 0.0 ], [ 0.0, 1.0 ], [ 0.0, 0.0 ] ]
Implemented Statistics: {meanExponent=0.0, negative=0, min=0.0, max=1.0, mean=0.3333333333333333, count=6, sum=2.0, positive=2, stdDev=0.4714045207910317, zeros=4}
Measured Feedback: [ [ 1.0000000000000286, 0.0 ], [ 0.0, 0.9999999999998899 ], [ 0.0, 0.0 ] ]
Measured Statistics: {meanExponent=-1.7695409011254224E-14, negative=0, min=0.0, max=1.0000000000000286, mean=0.33333333333331977, count=6, sum=1.9999999999999185, positive=2, stdDev=0.47140452079101247, zeros=4}
Feedback Error: [ [ 2.864375403532904E-14, 0.0 ], [ 0.0, -1.1013412404281553E-13 ], [ 0.0, 0.0 ] ]
Error Statistics: {meanExponent=-13.2505240811323, negative=1, min=-1.1013412404281553E-13, max=2.864375403532904E-14, mean=-1.3581728334581081E-14, count=6, sum=-8.149037000748649E-14, positive=1, stdDev=4.442823774843452E-14, zeros=4}
Returns
{
"absoluteTol" : {
"count" : 6,
"sum" : 1.3877787807814457E-13,
"min" : 0.0,
"max" : 1.1013412404281553E-13,
"sumOfSquare" : 1.2949989923914706E-26,
"standardDeviation" : 4.029083163547532E-14,
"average" : 2.312964634635743E-14
},
"relativeTol" : {
"count" : 2,
"sum" : 6.938893903907511E-14,
"min" : 1.4321877017664317E-14,
"max" : 5.50670620214108E-14,
"sumOfSquare" : 3.237497480979005E-27,
"standardDeviation" : 2.0372592501873248E-14,
"average" : 3.4694469519537556E-14
}
}
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" : 1.3877787807814457E-13,
"min" : 0.0,
"max" : 1.1013412404281553E-13,
"sumOfSquare" : 1.2949989923914706E-26,
"standardDeviation" : 4.029083163547532E-14,
"average" : 2.312964634635743E-14
},
"relativeTol" : {
"count" : 2,
"sum" : 6.938893903907511E-14,
"min" : 1.4321877017664317E-14,
"max" : 5.50670620214108E-14,
"sumOfSquare" : 3.237497480979005E-27,
"standardDeviation" : 2.0372592501873248E-14,
"average" : 3.4694469519537556E-14
}
}
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: 2.3130e-14 +- 4.0291e-14 [0.0000e+00 - 1.1013e-13] (6#)
relativeTol: 3.4694e-14 +- 2.0373e-14 [1.4322e-14 - 5.5067e-14] (2#)
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=2.3130e-14 +- 4.0291e-14 [0.0000e+00 - 1.1013e-13] (6#), relativeTol=3.4694e-14 +- 2.0373e-14 [1.4322e-14 - 5.5067e-14] (2#)} | OK |
{
"result": "OK",
"performance": {
"execution_time": "0.267",
"gc_time": "0.145"
},
"created_on": 1586739136076,
"file_name": "derivativeTest",
"report": {
"simpleName": "BandLimitTest",
"canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ImgConcatLayerTest.BandLimitTest",
"link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/test/java/com/simiacryptus/mindseye/layers/cudnn/ImgConcatLayerTest.java",
"javaDoc": ""
},
"archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/cudnn/ImgConcatLayer/BandLimitTest/derivativeTest/202004135216",
"id": "a9fb9344-a833-4f3b-8b8c-c1661ee01f36",
"report_type": "Components",
"display_name": "Derivative Validation",
"target": {
"simpleName": "ImgConcatLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ImgConcatLayer",
"link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/main/java/com/simiacryptus/mindseye/layers/cudnn/ImgConcatLayer.java",
"javaDoc": ""
}
}