Enum DiffPolicy 

pub enum DiffPolicy {
    Strict,
    StopGradient,
}

Differentiation policy for non-smooth branching operations.

Examples

use ad_tensors_rs::DiffPolicy;

let policy = DiffPolicy::StopGradient;
assert_eq!(policy, DiffPolicy::StopGradient);

Variants

Strict

Return an explicit mode-not-supported error.

StopGradient

Allow primal evaluation and block derivative flow.

Trait Implementations

impl Clone for DiffPolicy

fn clone(&self) -> DiffPolicy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DiffPolicy

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

Formats the value using the given formatter.

impl Default for DiffPolicy

fn default() -> DiffPolicy

Returns the “default value” for a type.

impl PartialEq for DiffPolicy

fn eq(&self, other: &DiffPolicy) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for DiffPolicy

impl Eq for DiffPolicy

impl StructuralPartialEq for DiffPolicy