Enum Loss 

pub enum Loss {
    MSE,
    SoftmaxAndCrossEntropy,
    BinaryCrossEntropy,
}

Variants

MSE

Mean Squared Error, defined as 0.5*(y_true - y_pred)^2, with the derivative being (y_pred - y_true). This is the textbook definition, but is different to keras and other frameworks which has derivative as 2(y_pred - y_true).

SoftmaxAndCrossEntropy

Will apply Softmax, then compute multi-class cross-entropy with the derivative wrt to logits being y_pred - y_true

BinaryCrossEntropy

Will apply Sigmoid, then compute binary cross-entropy with the derivative wrt to logits being y_pred - y_true

Implementations

impl Loss

pub fn gradient( &self, outputs: &Array2<f32>, target: &Array2<f32>, ) -> Array2<f32>

calc gradient for each example

Trait Implementations

impl Clone for Loss

fn clone(&self) -> Loss

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Loss

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

Formats the value using the given formatter.

impl Display for Loss

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

Formats the value using the given formatter.

impl PartialEq for Loss

fn eq(&self, other: &Loss) -> 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 Sede for Loss

fn serialize(&self) -> String

fn deserialize(s: &str) -> Result<Loss, Error>

impl Copy for Loss

impl Eq for Loss

impl StructuralPartialEq for Loss