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 357471034474150912

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 ], [ -0.128 ] ],
[ [ 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: [
[ [ 0.5199893401555818 ], [ 0.46804361920235915 ] ],
[ [ 0.6681877721681662 ], [ 0.621518856927611 ] ]
]
Outputs Statistics: {meanExponent=-0.24884159923755497, negative=0, min=0.46804361920235915, max=0.6681877721681662, mean=0.5694348971134295, count=4, sum=2.277739588453718, positive=4, stdDev=0.07935666881367515, zeros=0}

Feedback Validation

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

SingleDerivativeTester.java:117 executed in 0.06 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 ], [ -0.128 ] ],
[ [ 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: [ [ 0.24960042628014445, 0.0, 0.0, 0.0 ], [ 0.0, 0.22171287329310904, 0.0, 0.0 ], [ 0.0, 0.0, 0.24897878972631618, 0.0 ], [ 0.0, 0.0, 0.0, 0.2352331674110068 ] ]
Implemented Statistics: {meanExponent=-0.6223257147813432, negative=0, min=0.0, max=0.24960042628014445, mean=0.05972032854441103, count=16, sum=0.9555252567105765, positive=4, stdDev=0.10359710707341013, zeros=12}
Measured Feedback: [ [ 0.24959992713680101, 0.0, 0.0, 0.0 ], [ 0.0, 0.22170914423025323, 0.0, 0.0 ], [ 0.0, 0.0, 0.24897958516845176, 0.0 ], [ 0.0, 0.0, 0.0, 0.23523030872385498 ] ]
Measured Statistics: {meanExponent=-0.6223287306389902, negative=0, min=0.0, max=0.24959992713680101, mean=0.05971993532871006, count=16, sum=0.955518965259361, positive=4, stdDev=0.10359647358390664, zeros=12}
Feedback Error: [ [ -4.991433434353709E-7, 0.0, 0.0, 0.0 ], [ 0.0, -3.72906285581176E-6, 0.0, 0.0 ], [ 0.0, 0.0, 7.954421355760299E-7, 0.0 ], [ 0.0, 0.0, 0.0, -2.8586871518299084E-6 ] ]
Error Statistics: {meanExponent=-5.843349947589542, negative=3, min=-3.72906285581176E-6, max=7.954421355760299E-7, mean=-3.932157009688131E-7, count=16, sum=-6.291451215501009E-6, positive=1, stdDev=1.1315359274887063E-6, zeros=12}

Returns

    {
      "absoluteTol" : {
        "count" : 16,
        "sum" : 7.88233548665307E-6,
        "min" : 0.0,
        "max" : 3.72906285581176E-6,
        "sumOfSquare" : 2.2959874282977947E-11,
        "standardDeviation" : 1.0919212851586005E-6,
        "average" : 4.926459679158168E-7
      },
      "relativeTol" : {
        "count" : 4,
        "sum" : 1.708335148676086E-5,
        "min" : 9.998857973934025E-7,
        "max" : 8.409737695569637E-6,
        "sumOfSquare" : 1.1119684670620836E-10,
        "standardDeviation" : 3.0917884064548608E-6,
        "average" : 4.270837871690215E-6
      }
    }

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" : 16,
        "sum" : 7.88233548665307E-6,
        "min" : 0.0,
        "max" : 3.72906285581176E-6,
        "sumOfSquare" : 2.2959874282977947E-11,
        "standardDeviation" : 1.0919212851586005E-6,
        "average" : 4.926459679158168E-7
      },
      "relativeTol" : {
        "count" : 4,
        "sum" : 1.708335148676086E-5,
        "min" : 9.998857973934025E-7,
        "max" : 8.409737695569637E-6,
        "sumOfSquare" : 1.1119684670620836E-10,
        "standardDeviation" : 3.0917884064548608E-6,
        "average" : 4.270837871690215E-6
      }
    }

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: 4.9265e-07 +- 1.0919e-06 [0.0000e+00 - 3.7291e-06] (16#)
relativeTol: 4.2708e-06 +- 3.0918e-06 [9.9989e-07 - 8.4097e-06] (4#)

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=4.9265e-07 +- 1.0919e-06 [0.0000e+00 - 3.7291e-06] (16#), relativeTol=4.2708e-06 +- 3.0918e-06 [9.9989e-07 - 8.4097e-06] (4#)}OK
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.238",
      "gc_time": "0.127"
    },
    "created_on": 1586740493441,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "Sigmoid_Double",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ActivationLayerTest.Sigmoid_Double",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/test/java/com/simiacryptus/mindseye/layers/cudnn/ActivationLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/cudnn/ActivationLayer/Sigmoid_Double/derivativeTest/202004131453",
    "id": "08d4516c-c031-474b-8ffe-ec346d06337c",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "ActivationLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ActivationLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/main/java/com/simiacryptus/mindseye/layers/cudnn/ActivationLayer.java",
      "javaDoc": ""
    }
  }