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 2274674339757922304

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, -0.608, 1.208, -0.852, 1.108 ], [ -0.128, 0.048, -1.028, -1.688, -0.712 ] ],
[ [ 0.7, 1.764, -1.72, 1.912, 0.028 ], [ 0.496, 1.524, -0.384, -0.804, 1.048 ] ]
]
Inputs Statistics: {meanExponent=-0.2465738600212258, negative=9, min=-1.72, max=1.912, mean=0.09960000000000001, count=20, sum=1.9920000000000002, positive=11, stdDev=1.06535545241952, zeros=0}
Output: [
[ [ 1.208, -0.852 ], [ -1.028, -1.688 ] ],
[ [ -1.72, 1.912 ], [ -0.384, -0.804 ] ]
]
Outputs Statistics: {meanExponent=0.032309461745539815, negative=6, min=-1.72, max=1.912, mean=-0.4195, count=8, sum=-3.356, positive=2, stdDev=1.2294038189301348, zeros=0}

Feedback Validation

We validate the agreement between the implemented derivative of the inputs apply finite difference estimations:

SingleDerivativeTester.java:117 executed in 0.24 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, -0.608, 1.208, -0.852, 1.108 ], [ -0.128, 0.048, -1.028, -1.688, -0.712 ] ],
[ [ 0.7, 1.764, -1.72, 1.912, 0.028 ], [ 0.496, 1.524, -0.384, -0.804, 1.048 ] ]
]
Value Statistics: {meanExponent=-0.2465738600212258, negative=9, min=-1.72, max=1.912, mean=0.09960000000000001, count=20, sum=1.9920000000000002, positive=11, stdDev=1.06535545241952, zeros=0}
Implemented Feedback: [ [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], ... ]
Implemented Statistics: {meanExponent=0.0, negative=0, min=0.0, max=1.0, mean=0.05, count=160, sum=8.0, positive=8, stdDev=0.21794494717703367, zeros=152}
Measured Feedback: [ [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], ... ]
Measured Statistics: {meanExponent=-4.7830642341045674E-14, negative=0, min=0.0, max=0.9999999999998899, mean=0.04999999999999449, count=160, sum=7.999999999999119, positive=8, stdDev=0.21794494717700968, zeros=152}
Feedback Error: [ [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], ... ]
Error Statistics: {meanExponent=-12.958078098036824, negative=8, min=-1.1013412404281553E-13, max=0.0, mean=-5.5067062021407766E-15, count=160, sum=-8.810729923425242E-13, positive=0, stdDev=2.4003175846900303E-14, zeros=152}

Returns

    {
      "absoluteTol" : {
        "count" : 160,
        "sum" : 8.810729923425242E-13,
        "min" : 0.0,
        "max" : 1.1013412404281553E-13,
        "sumOfSquare" : 9.703620222942622E-26,
        "standardDeviation" : 2.4003175846900303E-14,
        "average" : 5.5067062021407766E-15
      },
      "relativeTol" : {
        "count" : 8,
        "sum" : 4.405364961712864E-13,
        "min" : 5.50670620214108E-14,
        "max" : 5.50670620214108E-14,
        "sumOfSquare" : 2.425905055735923E-26,
        "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" : 160,
        "sum" : 8.810729923425242E-13,
        "min" : 0.0,
        "max" : 1.1013412404281553E-13,
        "sumOfSquare" : 9.703620222942622E-26,
        "standardDeviation" : 2.4003175846900303E-14,
        "average" : 5.5067062021407766E-15
      },
      "relativeTol" : {
        "count" : 8,
        "sum" : 4.405364961712864E-13,
        "min" : 5.50670620214108E-14,
        "max" : 5.50670620214108E-14,
        "sumOfSquare" : 2.425905055735923E-26,
        "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: 5.5067e-15 +- 2.4003e-14 [0.0000e+00 - 1.1013e-13] (160#)
relativeTol: 5.5067e-14 +- 0.0000e+00 [5.5067e-14 - 5.5067e-14] (8#)

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=5.5067e-15 +- 2.4003e-14 [0.0000e+00 - 1.1013e-13] (160#), relativeTol=5.5067e-14 +- 0.0000e+00 [5.5067e-14 - 5.5067e-14] (8#)}OK
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.455",
      "gc_time": "0.153"
    },
    "created_on": 1586745781889,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "Double",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ImgBandSelectLayerTest.Double",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/test/java/com/simiacryptus/mindseye/layers/cudnn/ImgBandSelectLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/cudnn/ImgBandSelectLayer/Double/derivativeTest/202004134301",
    "id": "4639a2f4-4a09-4735-8e9f-a1819797e560",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "ImgBandSelectLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ImgBandSelectLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/main/java/com/simiacryptus/mindseye/layers/cudnn/ImgBandSelectLayer.java",
      "javaDoc": ""
    }
  }