public Tensor categorical_crossentropy(Tensor target, Tensor output, bool from_logits = false)
{
// https://github.com/fchollet/keras/blob/f65a56fb65062c8d14d215c9f4b1015b97cc5bf3/keras/backend/cntk_backend.py#L1480
var _output = In(output);
var _target = In(target);
if (from_logits)
{
var result = C.CrossEntropyWithSoftmax(_output, _target);
// cntk's result shape is (batch, 1), while keras expect (batch, )
CNTK.Function r = C.Reshape(result, NDShape.CreateNDShape(new int[] { }));
return(Out(r));
}
else
{
// scale preds so that the class probas of each sample sum to 1
var o = C.ElementDivide(_output.function, C.ReduceSum(_output, Axis.EndStaticAxis()));
var eps = Constant.Scalar(epsilon(), DeviceDescriptor.CPUDevice);
var omeps = Constant.Scalar(1.0 - epsilon(), DeviceDescriptor.CPUDevice);
// avoid numerical instability with _EPSILON clipping
o = C.Clip(o, eps, omeps);
CNTK.Function r = C.Negate(C.ReduceSum(C.ElementTimes(_target, C.Log(_output)), Axis.EndStaticAxis()));
return(Out(r));
}
}
void create_network()
{
Console.WriteLine("Compute Device: " + computeDevice.AsString());
imageVariable = Util.inputVariable(new int[] { 28, 28, 1 }, "image_tensor");
categoricalVariable = Util.inputVariable(new int[] { 10 }, "label_tensor");
network = imageVariable;
network = Layers.Convolution2D(network, 32, new int[] { 3, 3 }, computeDevice, CC.ReLU);
network = CC.Pooling(network, C.PoolingType.Max, new int[] { 2, 2 }, new int[] { 2 });
network = Layers.Convolution2D(network, 64, new int[] { 3, 3 }, computeDevice, CC.ReLU);
network = CC.Pooling(network, C.PoolingType.Max, new int[] { 2, 2 }, new int[] { 2 });
network = Layers.Convolution2D(network, 64, new int[] { 3, 3 }, computeDevice, CC.ReLU);
network = Layers.Dense(network, 64, computeDevice, activation: CC.ReLU);
network = Layers.Dense(network, 10, computeDevice);
Logging.detailed_summary(network);
Logging.log_number_of_parameters(network);
loss_function = CC.CrossEntropyWithSoftmax(network, categoricalVariable);
eval_function = CC.ClassificationError(network, categoricalVariable);
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);
}
