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 5203318880050255872

Differential Validation

SingleDerivativeTester.java:101 executed in 0.01 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 ], [ 1.208 ], [ 1.108 ], [ 1.032 ], [ 1.612 ], [ 1.552 ], [ -0.804 ], [ -1.832 ] ],
[ [ 0.7 ], [ -1.72 ], [ 0.028 ], [ 0.3 ], [ 1.64 ], [ 1.876 ], [ 0.148 ], [ 1.368 ] ],
[ [ -0.128 ], [ -1.028 ], [ -0.712 ], [ 0.636 ], [ 0.392 ], [ -0.408 ], [ -0.032 ], [ -1.54 ] ],
[ [ 0.496 ], [ -0.384 ], [ 1.048 ], [ -0.176 ], [ 0.092 ], [ -0.384 ], [ -0.892 ], [ -0.876 ] ],
[ [ -0.608 ], [ -0.852 ], [ -1.616 ], [ 1.556 ], [ -0.556 ], [ -1.572 ], [ 1.62 ], [ 1.652 ] ],
[ [ 1.764 ], [ 1.912 ], [ 1.356 ], [ 0.788 ], [ -1.476 ], [ -1.516 ], [ -1.856 ], [ -1.424 ] ],
[ [ 0.048 ], [ -1.688 ], [ 1.512 ], [ -0.768 ], [ 1.704 ], [ -0.636 ], [ 0.996 ], [ -0.464 ] ],
[ [ 1.524 ], [ -0.804 ], [ 1.556 ], [ -0.068 ], [ -1.228 ], [ -1.492 ], [ 0.048 ], [ -0.012 ] ]
]
Inputs Statistics: {meanExponent=-0.1923523558471011, negative=32, min=-1.856, max=1.912, mean=0.059375000000000025, count=64, sum=3.8000000000000016, positive=32, stdDev=1.1518728703181615, zeros=0}
Output: [
[ [ -0.556 ], [ -1.572 ], [ 1.62 ], [ 1.652 ], [ -0.608 ], [ -0.852 ], [ -1.616 ], [ 1.556 ] ],
[ [ -1.476 ], [ -1.516 ], [ -1.856 ], [ -1.424 ], [ 1.764 ], [ 1.912 ], [ 1.356 ], [ 0.788 ] ],
[ [ 1.704 ], [ -0.636 ], [ 0.996 ], [ -0.464 ], [ 0.048 ], [ -1.688 ], [ 1.512 ], [ -0.768 ] ],
[ [ -1.228 ], [ -1.492 ], [ 0.048 ], [ -0.012 ], [ 1.524 ], [ -0.804 ], [ 1.556 ], [ -0.068 ] ],
[ [ 1.612 ], [ 1.552 ], [ -0.804 ], [ -1.832 ], [ 0.08 ], [ 1.208 ], [ 1.108 ], [ 1.032 ] ],
[ [ 1.64 ], [ 1.876 ], [ 0.148 ], [ 1.368 ], [ 0.7 ], [ -1.72 ], [ 0.028 ], [ 0.3 ] ],
[ [ 0.392 ], [ -0.408 ], [ -0.032 ], [ -1.54 ], [ -0.128 ], [ -1.028 ], [ -0.712 ], [ 0.636 ] ],
[ [ 0.092 ], [ -0.384 ], [ -0.892 ], [ -0.876 ], [ 0.496 ], [ -0.384 ], [ 1.048 ], [ -0.176 ] ]
]
Outputs Statistics: {meanExponent=-0.19235235584710103, negative=32, min=-1.856, max=1.912, mean=0.05937499999999999, count=64, sum=3.7999999999999994, positive=32, stdDev=1.1518728703181615, zeros=0}

Feedback Validation

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

SingleDerivativeTester.java:117 executed in 1.56 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 ], [ 1.208 ], [ 1.108 ], [ 1.032 ], [ 1.612 ], [ 1.552 ], [ -0.804 ], [ -1.832 ] ],
[ [ 0.7 ], [ -1.72 ], [ 0.028 ], [ 0.3 ], [ 1.64 ], [ 1.876 ], [ 0.148 ], [ 1.368 ] ],
[ [ -0.128 ], [ -1.028 ], [ -0.712 ], [ 0.636 ], [ 0.392 ], [ -0.408 ], [ -0.032 ], [ -1.54 ] ],
[ [ 0.496 ], [ -0.384 ], [ 1.048 ], [ -0.176 ], [ 0.092 ], [ -0.384 ], [ -0.892 ], [ -0.876 ] ],
[ [ -0.608 ], [ -0.852 ], [ -1.616 ], [ 1.556 ], [ -0.556 ], [ -1.572 ], [ 1.62 ], [ 1.652 ] ],
[ [ 1.764 ], [ 1.912 ], [ 1.356 ], [ 0.788 ], [ -1.476 ], [ -1.516 ], [ -1.856 ], [ -1.424 ] ],
[ [ 0.048 ], [ -1.688 ], [ 1.512 ], [ -0.768 ], [ 1.704 ], [ -0.636 ], [ 0.996 ], [ -0.464 ] ],
[ [ 1.524 ], [ -0.804 ], [ 1.556 ], [ -0.068 ], [ -1.228 ], [ -1.492 ], [ 0.048 ], [ -0.012 ] ]
]
Value Statistics: {meanExponent=-0.1923523558471011, negative=32, min=-1.856, max=1.912, mean=0.059375000000000025, count=64, sum=3.8000000000000016, positive=32, stdDev=1.1518728703181615, 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=0.015625, count=4096, sum=64.0, positive=64, stdDev=0.12401959270615269, zeros=4032}
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=-4.0766943648542506E-14, negative=0, min=0.0, max=1.0000000000000286, mean=0.015624999999998512, count=4096, sum=63.9999999999939, positive=64, stdDev=0.12401959270614105, zeros=4032}
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=-13.052415404627576, negative=58, min=-1.1013412404281553E-13, max=2.864375403532904E-14, mean=-1.4667086989383904E-15, count=4096, sum=-6.007638830851647E-12, positive=6, stdDev=1.2841398738306384E-14, zeros=4032}

Returns

    {
      "absoluteTol" : {
        "count" : 4096,
        "sum" : 6.3513638792755955E-12,
        "min" : 0.0,
        "max" : 1.1013412404281553E-13,
        "sumOfSquare" : 6.842480884273904E-25,
        "standardDeviation" : 1.2831535961681806E-14,
        "average" : 1.5506259470887684E-15
      },
      "relativeTol" : {
        "count" : 64,
        "sum" : 3.1756819396379666E-12,
        "min" : 2.9976021664879317E-15,
        "max" : 5.50670620214108E-14,
        "sumOfSquare" : 1.7106202210686628E-25,
        "standardDeviation" : 1.451539485400742E-14,
        "average" : 4.962003030684323E-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" : 4096,
        "sum" : 6.3513638792755955E-12,
        "min" : 0.0,
        "max" : 1.1013412404281553E-13,
        "sumOfSquare" : 6.842480884273904E-25,
        "standardDeviation" : 1.2831535961681806E-14,
        "average" : 1.5506259470887684E-15
      },
      "relativeTol" : {
        "count" : 64,
        "sum" : 3.1756819396379666E-12,
        "min" : 2.9976021664879317E-15,
        "max" : 5.50670620214108E-14,
        "sumOfSquare" : 1.7106202210686628E-25,
        "standardDeviation" : 1.451539485400742E-14,
        "average" : 4.962003030684323E-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: 1.5506e-15 +- 1.2832e-14 [0.0000e+00 - 1.1013e-13] (4096#)
relativeTol: 4.9620e-14 +- 1.4515e-14 [2.9976e-15 - 5.5067e-14] (64#)

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=1.5506e-15 +- 1.2832e-14 [0.0000e+00 - 1.1013e-13] (4096#), relativeTol=4.9620e-14 +- 1.4515e-14 [2.9976e-15 - 5.5067e-14] (64#)}OK
 
  {
    "result": "OK",
    "performance": {
      "execution_time": "1.852",
      "gc_time": "0.220"
    },
    "created_on": 1586738449741,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "OneThird",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ImgTileCycleLayerTest.OneThird",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/test/java/com/simiacryptus/mindseye/layers/cudnn/ImgTileCycleLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/cudnn/ImgTileCycleLayer/OneThird/derivativeTest/202004134049",
    "id": "c26f2168-b14e-4085-8e8e-ee713119c480",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "ImgTileCycleLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ImgTileCycleLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/main/java/com/simiacryptus/mindseye/layers/cudnn/ImgTileCycleLayer.java",
      "javaDoc": ""
    }
  }