The following classes are available globally.

  • A mutable, shareable, owning reference to a tensor.

    Declaration

    public final class Parameter<Scalar> where Scalar : TensorFlowScalar

  • Adam optimizer.

    Reference: Adam - A Method for Stochastic Optimization

    Declaration

    public class Adam<Model: Layer>: Optimizer
    where Model.AllDifferentiableVariables == Model.CotangentVector

  • RMSProp optimizer.

    It is recommended to leave the parameters of this optimizer at their default values (except the learning rate, which can be freely tuned). This optimizer is usually a good choice for recurrent neural networks.

    Reference: rmsprop: Divide the gradient by a running average of its recent magnitude

    Declaration

    public class RMSProp<Model: Layer>: Optimizer
    where Model.AllDifferentiableVariables == Model.CotangentVector

  • SGD

    Stochastic gradient descent (SGD) optimizer.

    An optimizer that implements stochastic gradient descent, with support for momentum, learning rate decay, and Nesterov momentum.

    Declaration

    public class SGD<Model: Layer>: Optimizer
    where Model.AllDifferentiableVariables == Model.CotangentVector

  • A Riemann manifold stochastic gradient descent (SGD) optimizer.

    Declaration

    public class RiemannSGD<Model: Layer, Scalar: FloatingPoint>: Optimizer
    where Model.TangentVector: VectorNumeric, Model.TangentVector.Scalar == Scalar

  • TensorHandle is the type used by ops and the #tfop() syntax specifically. It includes a Scalar type, which compiler internals use to determine the datatypes of parameters when they are extracted into a tensor program.

    Declaration

    public final class TensorHandle<Scalar> : _AnyTensorHandle
  where Scalar : _TensorFlowDataTypeCompatible

  • ResourceHandle is the type used by ops and the #tfop() syntax to represent TensorFlow resource values.

    Declaration

    public final class ResourceHandle : _AnyTensorHandle

  • VariantHandle is the type used by ops and the #tfop() syntax to represent TensorFlow variant values.

    Declaration

    public final class VariantHandle : _AnyTensorHandle