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 122979769543309312

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 ] ],
[ [ 0.7 ], [ -1.72 ], [ 0.028 ], [ 0.3 ], [ 1.64 ], [ 1.876 ] ],
[ [ -0.128 ], [ -1.028 ], [ -0.712 ], [ 0.636 ], [ 0.392 ], [ -0.408 ] ],
[ [ 0.496 ], [ -0.384 ], [ 1.048 ], [ -0.176 ], [ 0.092 ], [ -0.384 ] ],
[ [ -0.608 ], [ -0.852 ], [ -1.616 ], [ 1.556 ], [ -0.556 ], [ -1.572 ] ],
[ [ 1.764 ], [ 1.912 ], [ 1.356 ], [ 0.788 ], [ -1.476 ], [ -1.516 ] ],
[ [ 0.048 ], [ -1.688 ], [ 1.512 ], [ -0.768 ], [ 1.704 ], [ -0.636 ] ],
[ [ 1.524 ], [ -0.804 ], [ 1.556 ], [ -0.068 ], [ -1.228 ], [ -1.492 ] ]
]
Inputs Statistics: {meanExponent=-0.15927984553930932, negative=22, min=-1.72, max=1.912, mean=0.1604166666666667, count=48, sum=7.700000000000002, positive=26, stdDev=1.1368718015042663, zeros=0}
Output: [
[ [ 1.556 ], [ -0.556 ], [ -1.572 ] ],
[ [ 0.788 ], [ -1.476 ], [ -1.516 ] ],
[ [ -0.768 ], [ 1.704 ], [ -0.636 ] ],
[ [ -0.068 ], [ -1.228 ], [ -1.492 ] ]
]
Outputs Statistics: {meanExponent=-0.050365605752469005, negative=9, min=-1.572, max=1.704, mean=-0.4386666666666667, count=12, sum=-5.264, positive=3, stdDev=1.1411506863201237, zeros=0}

Feedback Validation

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

SingleDerivativeTester.java:117 executed in 0.53 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 ] ],
[ [ 0.7 ], [ -1.72 ], [ 0.028 ], [ 0.3 ], [ 1.64 ], [ 1.876 ] ],
[ [ -0.128 ], [ -1.028 ], [ -0.712 ], [ 0.636 ], [ 0.392 ], [ -0.408 ] ],
[ [ 0.496 ], [ -0.384 ], [ 1.048 ], [ -0.176 ], [ 0.092 ], [ -0.384 ] ],
[ [ -0.608 ], [ -0.852 ], [ -1.616 ], [ 1.556 ], [ -0.556 ], [ -1.572 ] ],
[ [ 1.764 ], [ 1.912 ], [ 1.356 ], [ 0.788 ], [ -1.476 ], [ -1.516 ] ],
[ [ 0.048 ], [ -1.688 ], [ 1.512 ], [ -0.768 ], [ 1.704 ], [ -0.636 ] ],
[ [ 1.524 ], [ -0.804 ], [ 1.556 ], [ -0.068 ], [ -1.228 ], [ -1.492 ] ]
]
Value Statistics: {meanExponent=-0.15927984553930932, negative=22, min=-1.72, max=1.912, mean=0.1604166666666667, count=48, sum=7.700000000000002, positive=26, stdDev=1.1368718015042663, 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=0.020833333333333332, count=576, sum=12.0, positive=12, stdDev=0.1428261375083551, zeros=564}
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=-4.28081034527471E-14, negative=0, min=0.0, max=1.0000000000000286, mean=0.020833333333331278, count=576, sum=11.999999999998817, positive=12, stdDev=0.142826137508341, zeros=564}
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=-13.006819095219404, negative=11, min=-1.1013412404281553E-13, max=2.864375403532904E-14, mean=-2.053527101450767E-15, count=576, sum=-1.1828316104356418E-12, positive=1, stdDev=1.5127712448597675E-14, zeros=564}

Returns

    {
      "absoluteTol" : {
        "count" : 576,
        "sum" : 1.2401191185062999E-12,
        "min" : 0.0,
        "max" : 1.1013412404281553E-13,
        "sumOfSquare" : 1.3424524271069748E-25,
        "standardDeviation" : 1.511387822099097E-14,
        "average" : 2.152984580740104E-15
      },
      "relativeTol" : {
        "count" : 12,
        "sum" : 6.200595592531831E-13,
        "min" : 1.4321877017664317E-14,
        "max" : 5.50670620214108E-14,
        "sumOfSquare" : 3.3561310677678044E-26,
        "standardDeviation" : 1.1261374222586905E-14,
        "average" : 5.167162993776526E-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" : 576,
        "sum" : 1.2401191185062999E-12,
        "min" : 0.0,
        "max" : 1.1013412404281553E-13,
        "sumOfSquare" : 1.3424524271069748E-25,
        "standardDeviation" : 1.511387822099097E-14,
        "average" : 2.152984580740104E-15
      },
      "relativeTol" : {
        "count" : 12,
        "sum" : 6.200595592531831E-13,
        "min" : 1.4321877017664317E-14,
        "max" : 5.50670620214108E-14,
        "sumOfSquare" : 3.3561310677678044E-26,
        "standardDeviation" : 1.1261374222586905E-14,
        "average" : 5.167162993776526E-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: 2.1530e-15 +- 1.5114e-14 [0.0000e+00 - 1.1013e-13] (576#)
relativeTol: 5.1672e-14 +- 1.1261e-14 [1.4322e-14 - 5.5067e-14] (12#)

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=2.1530e-15 +- 1.5114e-14 [0.0000e+00 - 1.1013e-13] (576#), relativeTol=5.1672e-14 +- 1.1261e-14 [1.4322e-14 - 5.5067e-14] (12#)}OK
 
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.770",
      "gc_time": "0.162"
    },
    "created_on": 1586736544500,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "LR",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ImgTileSelectLayerTest.LR",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/test/java/com/simiacryptus/mindseye/layers/cudnn/ImgTileSelectLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/cudnn/ImgTileSelectLayer/LR/derivativeTest/202004130904",
    "id": "614967aa-4a5a-4e63-8f37-44e87986532a",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "ImgTileSelectLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ImgTileSelectLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/main/java/com/simiacryptus/mindseye/layers/cudnn/ImgTileSelectLayer.java",
      "javaDoc": ""
    }
  }