1. Test Modules
  2. Differential Validation
    1. Feedback Validation
    2. Learning Validation
    3. Total Accuracy
    4. Frozen and Alive Status
  3. Results

Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase

Test Modules

Using Seed 4775558086222059520

Differential Validation

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)));
Logging
Inputs: [
[ [ 0.08 ], [ 0.496 ] ],
[ [ 0.7 ], [ -0.608 ] ],
[ [ -0.128 ], [ 1.764 ] ]
]
Inputs Statistics: {meanExponent=-0.403119694464533, negative=2, min=-0.608, max=1.764, mean=0.38399999999999995, count=6, sum=2.304, positive=4, stdDev=0.747821725636086, zeros=0}
Output: [
[ [ 1.764 ] ]
]
Outputs Statistics: {meanExponent=0.24649858079580092, negative=0, min=1.764, max=1.764, mean=1.764, count=1, sum=1.764, positive=1, stdDev=0.0, zeros=0}

Feedback Validation

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()));
Logging
Feedback for input 0
Inputs Values: [
[ [ 0.08 ], [ 0.496 ] ],
[ [ 0.7 ], [ -0.608 ] ],
[ [ -0.128 ], [ 1.764 ] ]
]
Value Statistics: {meanExponent=-0.403119694464533, negative=2, min=-0.608, max=1.764, mean=0.38399999999999995, count=6, sum=2.304, positive=4, stdDev=0.747821725636086, zeros=0}
Implemented Feedback: [ [ 0.0 ], [ 0.0 ], [ 0.0 ], [ 0.0 ], [ 0.0 ], [ 1.0 ] ]
Implemented Statistics: {meanExponent=0.0, negative=0, min=0.0, max=1.0, mean=0.16666666666666666, count=6, sum=1.0, positive=1, stdDev=0.37267799624996495, zeros=5}
Measured Feedback: [ [ 0.0 ], [ 0.0 ], [ 0.0 ], [ 0.0 ], [ 0.0 ], [ 0.9999999999998899 ] ]
Measured Statistics: {meanExponent=-4.7830642341045674E-14, negative=0, min=0.0, max=0.9999999999998899, mean=0.1666666666666483, count=6, sum=0.9999999999998899, positive=1, stdDev=0.3726779962499239, zeros=5}
Feedback Error: [ [ 0.0 ], [ 0.0 ], [ 0.0 ], [ 0.0 ], [ 0.0 ], [ -1.1013412404281553E-13 ] ]
Error Statistics: {meanExponent=-12.958078098036825, negative=1, min=-1.1013412404281553E-13, max=0.0, mean=-1.8355687340469256E-14, count=6, sum=-1.1013412404281553E-13, positive=0, stdDev=4.104456466702158E-14, zeros=5}

Returns

    {
      "absoluteTol" : {
        "count" : 6,
        "sum" : 1.1013412404281553E-13,
        "min" : 0.0,
        "max" : 1.1013412404281553E-13,
        "sumOfSquare" : 1.2129525278678278E-26,
        "standardDeviation" : 4.104456466702158E-14,
        "average" : 1.8355687340469256E-14
      },
      "relativeTol" : {
        "count" : 1,
        "sum" : 5.50670620214108E-14,
        "min" : 5.50670620214108E-14,
        "max" : 5.50670620214108E-14,
        "sumOfSquare" : 3.0323813196699037E-27,
        "standardDeviation" : 0.0,
        "average" : 5.50670620214108E-14
      }
    }

Learning Validation

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" : 1.1013412404281553E-13,
        "min" : 0.0,
        "max" : 1.1013412404281553E-13,
        "sumOfSquare" : 1.2129525278678278E-26,
        "standardDeviation" : 4.104456466702158E-14,
        "average" : 1.8355687340469256E-14
      },
      "relativeTol" : {
        "count" : 1,
        "sum" : 5.50670620214108E-14,
        "min" : 5.50670620214108E-14,
        "max" : 5.50670620214108E-14,
        "sumOfSquare" : 3.0323813196699037E-27,
        "standardDeviation" : 0.0,
        "average" : 5.50670620214108E-14
      }
    }

Total Accuracy

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));
Logging
Finite-Difference Derivative Accuracy:
absoluteTol: 1.8356e-14 +- 4.1045e-14 [0.0000e+00 - 1.1013e-13] (6#)
relativeTol: 5.5067e-14 +- 0.0000e+00 [5.5067e-14 - 5.5067e-14] (1#)

Frozen and Alive Status

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());

Results

classdetailsresult
com.simiacryptus.mindseye.test.unit.SingleDerivativeTesterToleranceStatistics{absoluteTol=1.8356e-14 +- 4.1045e-14 [0.0000e+00 - 1.1013e-13] (6#), relativeTol=5.5067e-14 +- 0.0000e+00 [5.5067e-14 - 5.5067e-14] (1#)}OK
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.231",
      "gc_time": "0.131"
    },
    "created_on": 1586736416257,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "Repro",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.PoolingLayerTest.Repro",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/test/java/com/simiacryptus/mindseye/layers/cudnn/PoolingLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/cudnn/PoolingLayer/Repro/derivativeTest/202004130656",
    "id": "cb0568ae-efd7-4764-a100-a1c21e9f9a8f",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "PoolingLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.PoolingLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/main/java/com/simiacryptus/mindseye/layers/cudnn/PoolingLayer.java",
      "javaDoc": ""
    }
  }