Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
This is a network apply the following layout:
LayerTests.java:203 executed in 0.08 seconds (0.000 gc):
return Graphviz.fromGraph((Graph) TestUtil.toGraph(((DAGNetwork) layer).addRef())).height(400).width(600)
.render(Format.PNG).toImage();
executing command [/bin/sh, -c, dot -Tsvg /tmp/GraphvizJava/DotEngine3773980287197258206/dotfile.dot -ooutfile.svg]
Returns
Using Seed 8898514483537609728
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)));
Inputs: [
[ [ 0.08, -1.72, -0.712, -0.176 ], [ 0.496, -0.852, 1.356, -0.768 ], [ 0.048, -0.804, 1.032, 1.64 ] ],
[ [ 0.7, -1.028, 1.048, 1.556 ], [ -0.608, 1.912, 1.512, -0.068 ], [ 1.524, 1.108, 0.3, 0.392 ] ],
[ [ -0.128, -0.384, -1.616, 0.788 ], [ 1.764, -1.688, 1.556, 1.612 ], [ 1.208, 0.028, 0.636, 0.092 ] ]
]
Inputs Statistics: {meanExponent=-0.2192709808999687, negative=13, min=-1.72, max=1.912, mean=0.3287777777777778, count=36, sum=11.836, positive=23, stdDev=1.0387145129948714, zeros=0}
Output: [
[ [ 15.156448, -1.4011359999999997, -1.643791999999999, -6.296256 ], [ 2.2260639999999996, -4.328784000000001, 3.016927999999999, 1.2111999999999994 ], [ 0.6324480000000008, -7.023039999999999, -10.086528000000001, -5.9387680000000005 ] ],
[ [ -4.07248, -5.42976, 0.05492799999999942, 2.702528000000001 ], [ 0.22632000000000074, -2.5425759999999995, 3.147952, -1.5849119999999997 ], [ 18.297615999999998, -3.7311200000000007, -11.860064000000001, 9.935008 ] ],
[ [ 10.721504, -9.546576000000002, 7.0836000000000015, 0.8813760000000002 ], [ -5.35928, 9.971487999999999, 3.378367999999999, 2.772864000000001 ], [ -5.129424, 2.296688, -7.195888, -11.910879999999999 ] ]
]
Outputs Statistics: {meanExponent=0.5472950399544234, negative=18, min=-11.910879999999999, max=18.297615999999998, mean=-0.3157760000000004, count=36, sum=-11.367936000000014, positive=18, stdDev=7.0343644461166015, zeros=0}
We validate the agreement between the implemented derivative of the inputs apply finite difference estimations:
SingleDerivativeTester.java:117 executed in 1.64 seconds (0.000 gc):
return testFeedback(
statistics,
component.addRef(),
RefUtil.addRef(inputPrototype),
outputPrototype.addRef());
},
outputPrototype.addRef(),
RefUtil.addRef(inputPrototype),
component.addRef()));
Feedback for input 0
Inputs Values: [
[ [ 0.08, -1.72, -0.712, -0.176 ], [ 0.496, -0.852, 1.356, -0.768 ], [ 0.048, -0.804, 1.032, 1.64 ] ],
[ [ 0.7, -1.028, 1.048, 1.556 ], [ -0.608, 1.912, 1.512, -0.068 ], [ 1.524, 1.108, 0.3, 0.392 ] ],
[ [ -0.128, -0.384, -1.616, 0.788 ], [ 1.764, -1.688, 1.556, 1.612 ], [ 1.208, 0.028, 0.636, 0.092 ] ]
]
Value Statistics: {meanExponent=-0.2192709808999687, negative=13, min=-1.72, max=1.912, mean=0.3287777777777778, count=36, sum=11.836, positive=23, stdDev=1.0387145129948714, zeros=0}
Implemented Feedback: [ [ 1.288, 0.016, 0.0, -1.764, 0.692, 0.0, 0.0, 0.0, ... ], [ 1.352, 1.288, 0.016, 1.628, -1.764, 0.692, 0.0, 0.0, ... ], [ 0.0, 1.352, 1.288, 0.0, 1.628, -1.764, 0.0, 0.0, ... ], [ 1.916, -1.484, 0.0, 1.288, 0.016, 0.0, -1.764, 0.692, ... ], [ -1.724, 1.916, -1.484, 1.352, 1.288, 0.016, 1.628, -1.764, ... ], [ 0.0, -1.724, 1.916, 0.0, 1.352, 1.288, 0.0, 1.628, ... ], [ 0.0, 0.0, 0.0, 1.916, -1.484, 0.0, 1.288, 0.016, ... ], [ 0.0, 0.0, 0.0, -1.724, 1.916, -1.484, 1.352, 1.288, ... ], ... ]
Implemented Statistics: {meanExponent=-0.09474715290711827, negative=408, min=-2.0, max=1.98, mean=-0.018688271604938318, count=1296, sum=-24.22000000000006, positive=376, stdDev=0.9449478634050678, zeros=512}
Measured Feedback: [ [ 1.288000000005951, 0.01600000000046009, 0.0, -1.7640000000040956, 0.6920000000043558, 0.0, 0.0, 0.0, ... ], [ 1.3520000000077914, 1.2879999999970693, 0.015999999991578306, 1.627999999995744, -1.7639999999996547, 0.691999999995474, 0.0, 0.0, ... ], [ 0.0, 1.3519999999989096, 1.2879999999881875, 0.0, 1.6280000000001849, -1.7640000000085365, 0.0, 0.0, ... ], [ 1.915999999990703, -1.4840000000049258, 0.0, 1.2880000000015102, 0.01600000000046009, 0.0, -1.7639999999996547, 0.6920000000221194, ... ], [ -1.7240000000029454, 1.9159999999995847, -1.4840000000049258, 1.3519999999989096, 1.2879999999970693, 0.01600000000046009, 1.627999999995744, -1.7639999999730094, ... ], [ 0.0, -1.7240000000029454, 1.915999999990703, 0.0, 1.3519999999989096, 1.2879999999970693, 0.0, 1.6280000000179484, ... ], [ 0.0, 0.0, 0.0, 1.9159999999995847, -1.483999999996044, 0.0, 1.2879999999970693, 0.016000000009341875, ... ], [ 0.0, 0.0, 0.0, -1.7239999999985045, 1.9159999999995847, -1.4840000000049258, 1.3519999999989096, 1.2880000000237146, ... ], ... ]
Measured Statistics: {meanExponent=-0.09474715290716917, negative=408, min=-2.0000000000131024, max=1.980000000001425, mean=-0.018688271604889707, count=1296, sum=-24.21999999993706, positive=376, stdDev=0.9449478634051424, zeros=512}
Feedback Error: [ [ 5.951017456595764E-12, 4.600902991924727E-13, 0.0, -4.0956127378422025E-12, 4.355849014814339E-12, 0.0, 0.0, 0.0, ... ], [ 7.791323142214424E-12, -2.9307667404054882E-12, -8.42169389780878E-12, -4.255928942598075E-12, 3.452793606584237E-13, -4.525935182186913E-12, 0.0, 0.0, ... ], [ 0.0, -1.0904610547868288E-12, -1.181255093740674E-11, 0.0, 1.8496315590255108E-13, -8.536504836342829E-12, 0.0, 0.0, ... ], [ -9.297007608211061E-12, -4.9258375156568945E-12, 0.0, 1.510125358095138E-12, 4.600902991924727E-13, 0.0, 3.452793606584237E-13, 2.2119417408816844E-11, ... ], [ -2.9454216843305403E-12, -4.1522341120980855E-13, -4.9258375156568945E-12, -1.0904610547868288E-12, -2.9307667404054882E-12, 4.600902991924727E-13, -4.255928942598075E-12, 2.699063195166218E-11, ... ], [ 0.0, -2.9454216843305403E-12, -9.297007608211061E-12, 0.0, -1.0904610547868288E-12, -2.9307667404054882E-12, 0.0, 1.7948531549905056E-11, ... ], [ 0.0, 0.0, 0.0, -4.1522341120980855E-13, 3.955946681344358E-12, 0.0, -2.9307667404054882E-12, 9.341874496193725E-12, ... ], [ 0.0, 0.0, 0.0, 1.4954704141700859E-12, -4.1522341120980855E-13, -4.9258375156568945E-12, -1.0904610547868288E-12, 2.371458585059827E-11, ... ], ... ]
Error Statistics: {meanExponent=-11.673991212150908, negative=395, min=-2.4835022927049977E-11, max=3.4861891151649615E-11, mean=4.855955208411451E-14, count=1296, sum=6.29331795010124E-11, positive=389, stdDev=4.8269060936782724E-12, zeros=512}
Returns
{
"absoluteTol" : {
"count" : 1296,
"sum" : 3.204749909890836E-9,
"min" : 0.0,
"max" : 3.4861891151649615E-11,
"sumOfSquare" : 3.019858908560402E-20,
"standardDeviation" : 4.14567683157866E-12,
"average" : 2.47280085639725E-12
},
"relativeTol" : {
"count" : 784,
"sum" : 4.717508104413696E-9,
"min" : 1.3980586236020684E-14,
"max" : 2.9193357792082866E-10,
"sumOfSquare" : 4.071117833950918E-19,
"standardDeviation" : 2.1978812077969027E-11,
"average" : 6.017229725017469E-12
}
}
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" : 1296,
"sum" : 3.204749909890836E-9,
"min" : 0.0,
"max" : 3.4861891151649615E-11,
"sumOfSquare" : 3.019858908560402E-20,
"standardDeviation" : 4.14567683157866E-12,
"average" : 2.47280085639725E-12
},
"relativeTol" : {
"count" : 784,
"sum" : 4.717508104413696E-9,
"min" : 1.3980586236020684E-14,
"max" : 2.9193357792082866E-10,
"sumOfSquare" : 4.071117833950918E-19,
"standardDeviation" : 2.1978812077969027E-11,
"average" : 6.017229725017469E-12
}
}
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));
Finite-Difference Derivative Accuracy:
absoluteTol: 2.4728e-12 +- 4.1457e-12 [0.0000e+00 - 3.4862e-11] (1296#)
relativeTol: 6.0172e-12 +- 2.1979e-11 [1.3981e-14 - 2.9193e-10] (784#)
SingleDerivativeTester.java:156 executed in 0.05 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());
| class | details | result |
|---|---|---|
| com.simiacryptus.mindseye.test.unit.SingleDerivativeTester | ToleranceStatistics{absoluteTol=2.4728e-12 +- 4.1457e-12 [0.0000e+00 - 3.4862e-11] (1296#), relativeTol=6.0172e-12 +- 2.1979e-11 [1.3981e-14 - 2.9193e-10] (784#)} | OK |
{
"result": "OK",
"performance": {
"execution_time": "2.301",
"gc_time": "0.379"
},
"created_on": 1586748362615,
"file_name": "derivativeTest",
"report": {
"simpleName": "SqGrid",
"canonicalName": "com.simiacryptus.mindseye.layers.cudnn.conv.ConvolutionLayerTest.SqGrid",
"link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/test/java/com/simiacryptus/mindseye/layers/cudnn/conv/ConvolutionLayerTest.java",
"javaDoc": ""
},
"archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/cudnn/conv/ConvolutionLayer/SqGrid/derivativeTest/202004132602",
"id": "bbbfe9cb-7af3-4fe9-b093-eadee91315d3",
"report_type": "Components",
"display_name": "Derivative Validation",
"target": {
"simpleName": "ConvolutionLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.cudnn.conv.ConvolutionLayer",
"link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/main/java/com/simiacryptus/mindseye/layers/cudnn/conv/ConvolutionLayer.java",
"javaDoc": ""
}
}