public Tensor binary_crossentropy(Tensor output, Tensor target, bool from_logits = false)
{
log(new { output, target, from_logits });
var _output = new Variable(In(output).function);
var _target = new Variable(In(target).function);
if (from_logits)
{
_output = C.Sigmoid(_output);
}
// scale preds so that the class probas of each sample sum to 1
var eps = InConstant(epsilon());
var omeps = InConstant(1.0);
// avoid numerical instability with _EPSILON clipping
_output = C.Clip(_output, eps, omeps);
var a = new Variable(C.Negate(C.ElementTimes(_target, C.Log(_output))));
var b = new Variable(C.Negate(
C.Minus(C.ElementTimes(InConstant(1.0), _target),
C.Minus(C.Log(InConstant(1.0)), _output))));
_output = a + b;
return(Out(_output));
}
public Tensor subtract <T>(T a, Tensor b, string name = null)
{
if (name == null)
{
return(Out(C.Minus(InGeneric(a), In(b))));
}
return(Out(C.Minus(InGeneric(a), In(b), name: name)));
}
public Tensor Sub(float a, Tensor b)
{
return(Out(C.Minus(In(a, b.Shape), In(b))));
}
public Tensor Sub(Tensor a, float b)
{
return(Out(C.Minus(In(a), In(b, a.Shape))));
}
public Tensor Sub(Tensor a, Tensor b)
{
return(Out(C.Minus(In(a), In(b))));
}
void create_network()
{
imageVariable = Util.inputVariable(input_shape, "image");
var conv1 = Layers.Convolution2D(
imageVariable, 256, new int[] { 9, 9 }, computeDevice,
use_padding: false, activation: CC.ReLU, name: "conv1");
var primarycaps = create_primary_cap(
conv1, dim_capsule: 8, n_channels: 32,
kernel_size: new int[] { 9, 9 }, strides: new int[] { 2, 2 }, pad: false);
var digitcaps = create_capsule_layer(
primarycaps, num_capsule: 10, dim_capsule: 16,
routings: routings, name: "digitcaps");
var out_caps = get_length_and_remove_last_dimension(digitcaps, name: "capsnet");
categoricalLabel = Util.inputVariable(new int[] { 10 }, "label");
var masked_by_y = get_mask_and_infer_from_last_dimension(digitcaps, CC.Combine(new C.VariableVector()
{
categoricalLabel
}));
var masked = get_mask_and_infer_from_last_dimension(digitcaps, null);
var decoder = create_decoder(masked.Output.Shape.Dimensions.ToArray());
var decoder_output_training = Model.invoke_model(decoder, new C.Variable[] { masked_by_y });
var decoder_output_evaluation = Model.invoke_model(decoder, new C.Variable[] { masked });
network = CC.Combine(new C.VariableVector()
{
out_caps, decoder_output_training
}, "overall_training_network");
Logging.log_number_of_parameters(network);
// first component of the loss
var y_true = categoricalLabel;
var y_pred = out_caps;
var digit_loss = CC.Plus(
CC.ElementTimes(y_true, CC.Square(CC.ElementMax(DC(0), CC.Minus(DC(0.9), y_pred), ""))),
CC.ElementTimes(DC(0.5),
CC.ElementTimes(CC.Minus(DC(1), y_true), CC.Square(CC.ElementMax(DC(0), CC.Minus(y_pred, DC(0.1)), "")))));
digit_loss = CC.ReduceSum(digit_loss, C.Axis.AllStaticAxes());
// second component of the loss
var num_pixels_at_output = Util.np_prod(decoder_output_training.Output.Shape.Dimensions.ToArray());
var squared_error = CC.SquaredError(decoder_output_training, imageVariable);
var image_mse = CC.ElementDivide(squared_error, DC(num_pixels_at_output));
loss_function = CC.Plus(digit_loss, CC.ElementTimes(DC(0.35), image_mse));
eval_function = CC.ClassificationError(y_pred, y_true);
learner = CC.AdamLearner(
new C.ParameterVector(network.Parameters().ToArray()),
new C.TrainingParameterScheduleDouble(0.001 * batch_size, (uint)batch_size),
new C.TrainingParameterScheduleDouble(0.9),
true,
new C.TrainingParameterScheduleDouble(0.99));
trainer = CC.CreateTrainer(network, loss_function, eval_function, new C.LearnerVector(new C.Learner[] { learner }));
evaluator = CC.CreateEvaluator(eval_function);
}
public Tensor subtract <T>(Tensor a, T b, string name = null)
{
return(Out(C.Minus(In(a), InGeneric(b), name: name)));
}
