Function dfdx::losses::huber_loss

pub fn huber_loss<S: Shape, E: Dtype, D: Device<E>, T: Tape<E, D>>(
    pred: Tensor<S, E, D, T>,
    targ: Tensor<S, E, D>,
    delta: impl Into<f64>
) -> Tensor<Rank0, E, D, T>

Huber Loss uses absolute error when the error is higher than beta, and squared error when the error is lower than beta.

See huber_error()