Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 6691407812718682112
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: [
[ [ 0.699999988079071 ] ]
]
Outputs Statistics: {meanExponent=-0.15490196738173417, negative=0, min=0.699999988079071, max=0.699999988079071, mean=0.699999988079071, count=1, sum=0.699999988079071, 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 0.04 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 ], [ 1.0 ], [ 0.0 ], [ 0.0 ] ]
Implemented Statistics: {meanExponent=0.0, negative=0, min=0.0, max=1.0, mean=0.25, count=4, sum=1.0, positive=1, stdDev=0.4330127018922193, zeros=3}
Measured Feedback: [ [ 0.0 ], [ 0.9999871253967285 ], [ 0.0 ], [ 0.0 ] ]
Measured Statistics: {meanExponent=-5.5914051511379775E-6, negative=0, min=0.0, max=0.9999871253967285, mean=0.24999678134918213, count=4, sum=0.9999871253967285, positive=1, stdDev=0.43300712702547095, zeros=3}
Feedback Error: [ [ 0.0 ], [ -1.2874603271484375E-5 ], [ 0.0 ], [ 0.0 ] ]
Error Statistics: {meanExponent=-4.890266144784618, negative=1, min=-1.2874603271484375E-5, max=0.0, mean=-3.2186508178710938E-6, count=4, sum=-1.2874603271484375E-5, positive=0, stdDev=5.5748667483758555E-6, zeros=3}
Returns
{
"absoluteTol" : {
"count" : 4,
"sum" : 1.2874603271484375E-5,
"min" : 0.0,
"max" : 1.2874603271484375E-5,
"sumOfSquare" : 1.6575540939811617E-10,
"standardDeviation" : 5.5748667483758555E-6,
"average" : 3.2186508178710938E-6
},
"relativeTol" : {
"count" : 1,
"sum" : 6.437343074861293E-6,
"min" : 6.437343074861293E-6,
"max" : 6.437343074861293E-6,
"sumOfSquare" : 4.1439385863464646E-11,
"standardDeviation" : 0.0,
"average" : 6.437343074861293E-6
}
}
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" : 1.2874603271484375E-5,
"min" : 0.0,
"max" : 1.2874603271484375E-5,
"sumOfSquare" : 1.6575540939811617E-10,
"standardDeviation" : 5.5748667483758555E-6,
"average" : 3.2186508178710938E-6
},
"relativeTol" : {
"count" : 1,
"sum" : 6.437343074861293E-6,
"min" : 6.437343074861293E-6,
"max" : 6.437343074861293E-6,
"sumOfSquare" : 4.1439385863464646E-11,
"standardDeviation" : 0.0,
"average" : 6.437343074861293E-6
}
}
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: 3.2187e-06 +- 5.5749e-06 [0.0000e+00 - 1.2875e-05] (4#)
relativeTol: 6.4373e-06 +- 0.0000e+00 [6.4373e-06 - 6.4373e-06] (1#)
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=3.2187e-06 +- 5.5749e-06 [0.0000e+00 - 1.2875e-05] (4#), relativeTol=6.4373e-06 +- 0.0000e+00 [6.4373e-06 - 6.4373e-06] (1#)} | OK |
{
"result": "OK",
"performance": {
"execution_time": "0.210",
"gc_time": "0.116"
},
"created_on": 1586736778439,
"file_name": "derivativeTest",
"report": {
"simpleName": "Float",
"canonicalName": "com.simiacryptus.mindseye.layers.cudnn.BandReducerLayerTest.Float",
"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/Float/derivativeTest/202004131258",
"id": "97f6021f-df1f-4847-a21b-cb063ca8f022",
"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": ""
}
}