public void SvmLayer_Backward()
{
var batchSize = 1;
var width = 28;
var height = 28;
var depth = 3;
var numberOfClasses = 10;
var random = new Random(232);
var sut = new SvmLayer(numberOfClasses);
sut.Initialize(width, height, depth, batchSize, Initialization.GlorotUniform, random);
var input = Matrix <float> .Build.Random(batchSize, numberOfClasses, random.Next());
sut.Forward(input);
var delta = Matrix <float> .Build.Random(batchSize, numberOfClasses, random.Next());
var actual = sut.Backward(delta);
Trace.WriteLine(string.Join(", ", actual.ToColumnMajorArray()));
var expected = Matrix <float> .Build.Dense(batchSize, numberOfClasses, new float[] { 1f, 1f, 1f, 1f, 1f, -9f, 1f, 1f, 1f, 1f });
MatrixAsserts.AreEqual(expected, actual);
}
public void SerializationTest()
{
// Create a SvmLayer
var layer = new SvmLayer(7);
layer.Init(10, 10, 3);
SvmLayer deserialized;
using (var ms = new MemoryStream())
{
// Serialize
IFormatter formatter = new BinaryFormatter();
formatter.Serialize(ms, layer);
// Deserialize
ms.Position = 0;
deserialized = formatter.Deserialize(ms) as SvmLayer;
}
Assert.AreEqual(layer.InputDepth, deserialized.InputDepth);
Assert.AreEqual(layer.InputHeight, deserialized.InputHeight);
Assert.AreEqual(layer.InputWidth, deserialized.InputWidth);
Assert.AreEqual(layer.OutputDepth, deserialized.OutputDepth);
Assert.AreEqual(layer.OutputHeight, deserialized.OutputHeight);
Assert.AreEqual(layer.OutputWidth, deserialized.OutputWidth);
Assert.AreEqual(layer.ClassCount, deserialized.ClassCount);
}
public static SvmLayer Svm(this LayerBase layer, int classCount)
{
var svm = new SvmLayer(classCount);
layer.ConnectTo(svm);
return(svm);
}
public void SvmLayer_CopyLayerForPredictionModel()
{
var batchSize = 1;
var width = 28;
var height = 28;
var depth = 3;
var numberOfClasses = 10;
var sut = new SvmLayer(numberOfClasses);
sut.Initialize(width, height, depth, batchSize, Initialization.GlorotUniform, new Random(232));
var layers = new List <ILayer>();
sut.CopyLayerForPredictionModel(layers);
var actual = (SvmLayer)layers.Single();
Assert.AreEqual(sut.Width, actual.Width);
Assert.AreEqual(sut.NumberOfClasses, actual.NumberOfClasses);
}
public void SvmLayer_Forward()
{
var batchSize = 1;
var width = 28;
var height = 28;
var depth = 3;
var numberOfClasses = 10;
var random = new Random(232);
var sut = new SvmLayer(numberOfClasses);
sut.Initialize(width, height, depth, batchSize, Initialization.GlorotUniform, random);
var input = Matrix <float> .Build.Random(batchSize, numberOfClasses, random.Next());
var actual = sut.Forward(input);
Trace.WriteLine(string.Join(", ", actual.ToColumnMajorArray()));
var expected = Matrix <float> .Build.Dense(batchSize, numberOfClasses, new float[] { 0.1234713f, 0.7669879f, -0.9698473f, 1.814438f, 0.2316814f, -0.05312517f, 0.5537131f, -0.2031853f, 0.01274186f, -0.4482329f });
MatrixAsserts.AreEqual(expected, actual);
}
