Trait LayerExt

pub trait LayerExt<S, D>: Layer<S, D>
where
    D: Dimension,
    S: RawData<Elem = Self::Elem>,
{
    // Provided methods
    fn set_params(&mut self, params: ParamsBase<S, D>) { ... }
    fn backward<X, Y, Z, Dt>(
        &mut self,
        input: X,
        error: Y,
        gamma: Self::Elem,
    ) -> Result<Z>
       where S: Data,
             Self: ActivatorGradient<X, Input = Y, Output = Z, Delta = Dt>,
             Self::Elem: Clone,
             ParamsBase<S, D>: Backward<X, Dt, Elem = Self::Elem, Output = Z> { ... }
    fn forward<X, Y>(&self, input: &X) -> Result<Y>
       where Y: NdTensor<S::Elem, D, Repr = S>,
             ParamsBase<S, D>: Forward<X, Output = Y>,
             Self: Activator<Y, Output = Y> { ... }
}

The LayerExt trait extends the base Layer trait with additional methods that are commonly used in neural network layers. It provides methods for setting parameters, performing backward propagation of errors, and completing a forward pass through the layer.

Provided Methods

fn set_params(&mut self, params: ParamsBase<S, D>)

update the layer parameters

fn backward<X, Y, Z, Dt>( &mut self, input: X, error: Y, gamma: Self::Elem, ) -> Result<Z>

where S: Data, Self: ActivatorGradient<X, Input = Y, Output = Z, Delta = Dt>, Self::Elem: Clone, ParamsBase<S, D>: Backward<X, Dt, Elem = Self::Elem, Output = Z>,

backward propagate error through the layer

fn forward<X, Y>(&self, input: &X) -> Result<Y>

where Y: NdTensor<S::Elem, D, Repr = S>, ParamsBase<S, D>: Forward<X, Output = Y>, Self: Activator<Y, Output = Y>,

complete a forward pass through the layer

Dyn Compatibility

This trait is not dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety", so this trait is not object safe.

Implementors