public void DropoutSerialization()
{
var layer = new DropoutLayer {
DropProbability = 0.1
};
layer.Init(28, 24, 1);
var data = layer.GetData();
Assert.AreEqual(28, data["InputWidth"]);
Assert.AreEqual(24, data["InputHeight"]);
Assert.AreEqual(1, data["InputDepth"]);
var deserialized = LayerBase <double> .FromData(data) as DropoutLayer;
Assert.IsNotNull(deserialized);
Assert.AreEqual(28, deserialized.InputWidth);
Assert.AreEqual(24, deserialized.InputHeight);
Assert.AreEqual(1, deserialized.InputDepth);
Assert.AreEqual(layer.OutputWidth, deserialized.OutputWidth);
Assert.AreEqual(layer.OutputHeight, deserialized.OutputHeight);
Assert.AreEqual(layer.OutputDepth, deserialized.OutputDepth);
Assert.AreEqual(layer.DropProbability, deserialized.DropProbability);
}
public void NotLearning()
{
var n = 1000000;
var dropProbability = 0.2;
var layer = new DropoutLayer <double>(dropProbability);
layer.Init(1, 1, n);
var input = BuilderInstance.Volume.From(new double[n].Populate(1.0), new Shape(1, 1, n, 1));
var result = layer.DoForward(input, false);
var average = result.ToArray().Average();
Assert.AreEqual(1.0, average); // Let everything go through
}
public void Learning()
{
var n = 1000000;
var dropProbability = 0.2;
var layer = new DropoutLayer <double>(dropProbability);
layer.Init(1, 1, n);
var input = BuilderInstance.Volume.From(new double[n].Populate(1.0), new Shape(1, 1, n, 1));
var result = layer.DoForward(input, true);
var val = result.ToArray().First(o => o != 0.0);
var scalingFactor = 1.0 / (1.0 - dropProbability);
Assert.AreEqual(scalingFactor, val); // Make sure output is scaled during learning
var average = result.ToArray().Average();
var measuredProba = average * dropProbability;
Assert.AreEqual(dropProbability, measuredProba, 0.001); // Make sure dropout really happened
}