Enum juice::solver::LRPolicy

pub enum LRPolicy {
    Fixed,
    Step,
    Exp,
}

Learning Rate Policy for a [Solver][1] [1]: ./struct.Solver.html

The variables mentioned below are defined in the SolverConfig apart from iter, which is the current iteration of the solver, that is supplied as a parameter for the learning rate calculation.

Variants

Fixed

always return base_lr

Step

learning rate decays every step iterations. return base_lr * gamma ^ (floor(iter / step))

Exp

return base_lr * gamma ^ iter

Trait Implementations

impl Clone for LRPolicy

fn clone(&self) -> LRPolicy

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for LRPolicy

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Copy for LRPolicy