Struct XavierNormal

pub struct XavierNormal<T>
where
    StandardNormal: Distribution<T>,
{ /* private fields */ }

Normal Xavier initializers leverage a normal distribution centered around 0 and using a standard deviation ($\sigma$) computed by:

\sigma = \sqrt{\frac{2}{d_{in} + d_{out}}}

Implementations

impl<T> XavierNormal<T>

where T: Float, StandardNormal: Distribution<T>,

pub fn new(inputs: usize, outputs: usize) -> XavierNormal<T>

where T: FromPrimitive,

pub fn distr(&self) -> Result<Normal<T>, InitError>

tries creating a new Normal distribution with a mean of 0 and the computed standard deviation ($\sigma$) based on the number of inputs and outputs.

pub const fn std_dev(&self) -> T

returns a reference to the standard deviation of the distribution

Trait Implementations

impl<T> Clone for XavierNormal<T>

where T: Clone, StandardNormal: Distribution<T>,

fn clone(&self) -> XavierNormal<T>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<T> Debug for XavierNormal<T>

where T: Debug, StandardNormal: Distribution<T>,

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

Formats the value using the given formatter.

impl<T> Distribution<T> for XavierNormal<T>

where T: Float, StandardNormal: Distribution<T>,

fn sample<R>(&self, rng: &mut R) -> T

where R: RngCore + ?Sized,

Generate a random value of T, using rng as the source of randomness.

fn sample_iter<R>(self, rng: R) -> Iter<Self, R, T>

where R: Rng, Self: Sized,

Create an iterator that generates random values of T, using rng as the source of randomness.

fn map<F, S>(self, func: F) -> Map<Self, F, T, S>

where F: Fn(T) -> S, Self: Sized,

Map sampled values to type S

impl<T> Hash for XavierNormal<T>

where T: Hash, StandardNormal: Distribution<T>,

fn hash<__H>(&self, state: &mut __H)

where __H: Hasher,

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl<T> Ord for XavierNormal<T>

where T: Ord, StandardNormal: Distribution<T>,

fn cmp(&self, other: &XavierNormal<T>) -> Ordering

This method returns an Ordering between self and other.

fn max(self, other: Self) -> Self

where Self: Sized,

Compares and returns the maximum of two values.

fn min(self, other: Self) -> Self

where Self: Sized,

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Self

where Self: Sized,

Restrict a value to a certain interval.

impl<T> PartialEq for XavierNormal<T>

where T: PartialEq, StandardNormal: Distribution<T>,

fn eq(&self, other: &XavierNormal<T>) -> bool

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

const 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<T> PartialOrd for XavierNormal<T>

where T: PartialOrd, StandardNormal: Distribution<T>,

fn partial_cmp(&self, other: &XavierNormal<T>) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

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

Tests less than (for self and other) and is used by the < operator.

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

Tests less than or equal to (for self and other) and is used by the <= operator.

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

Tests greater than (for self and other) and is used by the > operator.

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

Tests greater than or equal to (for self and other) and is used by the >= operator.

impl<T> Copy for XavierNormal<T>

where T: Copy, StandardNormal: Distribution<T>,

impl<T> Eq for XavierNormal<T>

where T: Eq, StandardNormal: Distribution<T>,

impl<T> StructuralPartialEq for XavierNormal<T>

where StandardNormal: Distribution<T>,