public void OutputShapeIsEqualToKernelSize()
{
var graph = new TFGraph();
var input = new Input(new[] { 10L });
input.Compile(new ModelCompilationContext(graph));
var dense = new Dense(2, input, name: "Dense0");
dense.Compile(new ModelCompilationContext(graph));
dense.OutputShape.Should().BeEquivalentTo(new long[] { -1, 2 });
}
public void CreatesLayerConfigurationDuringCompilation()
{
var graph = new TFGraph();
var input = new Input(new[] { 10L });
var dense = new Dense(2, input, name: "Dense0");
dense.Compile(new ModelCompilationContext(graph));
dense.Configuration.Initializers.Count().Should().Be(2);
dense.Configuration.Parameters.Count().Should().Be(2);
dense.Configuration.Output.Should().NotBeNull();
}
public void CanBeOptimized()
{
var graph = new TFGraph();
var context = new ModelCompilationContext(graph);
var input = new Input(new long[] { 10 }, name: "Input0");
var output = new Dense(2, input, name: "Dense0");
var compiledOutput = output.Compile(context);
var loss = new NegativeLogLikelihood();
var compiledLoss = loss.Compile(context, compiledOutput,
context.Graph.Placeholder(TFDataType.Double, new TFShape(-1, 2)));
var gradients = graph.AddGradients(
new[] { compiledLoss },
context.Parameters.ToArray());
}
public void ShouldBeOptimizable()
{
var graph = new TFGraph();
var context = new ModelCompilationContext(graph);
var input = new Input(new long[] { 10 }, name: "Input0");
var output = new Dense(2, input, name: "Dense0");
var compiledInput = input.Compile(context);
var compiledOutput = output.Compile(context);
var loss = new CategoricalCrossEntropy();
var compiledLoss = loss.Compile(context, compiledOutput,
context.Graph.Placeholder(TFDataType.Double, new TFShape(-1, 2)));
var gradients = graph.AddGradients(
new [] { compiledLoss },
context.Parameters.ToArray());
}