Struct Hardtanh 

pub struct Hardtanh<D: Float, T, const RANK: usize> {
    pub min_val: f64,
    pub max_val: f64,
    /* private fields */
}

Hardtanh activation layer: clamps input to [min_val, max_val].

Fields

min_val: f64

Lower clamp bound.

max_val: f64

Upper clamp bound.

Implementations

impl<D: Float, T, const RANK: usize> Hardtanh<D, T, RANK>

pub fn new(min_val: f64, max_val: f64) -> Self

Creates a new Hardtanh layer clamping to [min_val, max_val].

Trait Implementations

impl<D: Float, const RANK: usize> Layer<SymTensor> for Hardtanh<D, SymTensor, RANK>

type Output = SymTensor

This layer’s output type.

fn call(&self, input: SymTensor) -> SymTensor

Applies this layer to input.

impl<D: Float, T: Tensor<D, RANK> + EagerTensor, const RANK: usize> Layer<T> for Hardtanh<D, T, RANK>

type Output = T

This layer’s output type.

fn call(&self, _input: T) -> Self::Output

Applies this layer to input.