Enum OptimizerAlgorithm

Source

pub enum OptimizerAlgorithm {
    Adam {
        lr: f64,
        beta1: f64,
        beta2: f64,
        epsilon: f64,
    },
    AdaGrad {
        lr: f64,
        epsilon: f64,
    },
    RmsProp {
        lr: f64,
        alpha: f64,
        epsilon: f64,
        momentum: f64,
    },
    AdamW {
        lr: f64,
        beta1: f64,
        beta2: f64,
        epsilon: f64,
        weight_decay: f64,
    },
}

Expand description

Choice of adaptive gradient algorithm and its hyper-parameters.

Variants§

§

Adam

Adam optimiser (Kingma & Ba, 2015).

Fields

§lr: f64

Learning rate. Default 0.001.

§beta1: f64

Exponential decay for first-moment estimates. Default 0.9.

§beta2: f64

Exponential decay for second-moment estimates. Default 0.999.

§epsilon: f64

Numerical stability constant. Default 1e-8.

§

AdaGrad

Adaptive gradient descent (Duchi et al., 2011).

Fields

§lr: f64

Learning rate. Default 0.01.

§epsilon: f64

Numerical stability constant. Default 1e-8.

§

RmsProp

Root-mean-square propagation (Hinton, 2012).

Fields

§lr: f64

Learning rate. Default 0.01.

§alpha: f64

Smoothing constant (decay for squared-gradient average). Default 0.99.

§epsilon: f64

Numerical stability constant. Default 1e-8.

§momentum: f64

Momentum coefficient. Default 0.0 (no momentum).

§

AdamW

Adam with decoupled weight decay (Loshchilov & Hutter, 2019).

Fields

§lr: f64

Learning rate. Default 0.001.

§beta1: f64

Exponential decay for first-moment estimates. Default 0.9.

§beta2: f64

Exponential decay for second-moment estimates. Default 0.999.

§epsilon: f64

Numerical stability constant. Default 1e-8.

§weight_decay: f64

Decoupled weight-decay coefficient. Default 0.01.

Implementations§

Source §

impl OptimizerAlgorithm

Source

pub fn adam_default() -> Self

Construct an Adam instance with default hyper-parameters.

Source

pub fn adagrad_default() -> Self

Construct an AdaGrad instance with default hyper-parameters.

Source

pub fn rmsprop_default() -> Self

Construct an RmsProp instance with default hyper-parameters.

Source

pub fn adamw_default() -> Self

Construct an AdamW instance with default hyper-parameters.

Trait Implementations§

Source §

impl Clone for OptimizerAlgorithm

Source §

fn clone(&self) -> OptimizerAlgorithm

Returns a duplicate of the value. Read more

1.0.0 (const: unstable) · Source§

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

Performs copy-assignment from source. Read more

Source §

impl Debug for OptimizerAlgorithm

Source §

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

Formats the value using the given formatter. Read more

Source §

impl PartialEq for OptimizerAlgorithm

Source §

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

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

1.0.0 (const: unstable) · Source§

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

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

Source §

impl StructuralPartialEq for OptimizerAlgorithm

Auto Trait Implementations§

§

impl UnwindSafe for OptimizerAlgorithm

Blanket Implementations§

Source §

impl<T> Allocation for T
where T: RefUnwindSafe + Send + Sync,

Source §

impl<T> Any for T
where T: 'static + ?Sized,

Source §

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

Source §

impl<T> Borrow<T> for T
where T: ?Sized,

Source §

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

Source §

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source §

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more

Source §

impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
where ST: ?Sized, DT: ?Sized,

Source §

impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
where ST: ?Sized, DT: ?Sized,

Source §

impl<T> CloneToUninit for T
where T: Clone,

Source §

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)

Performs copy-assignment from self to dest. Read more

Source §

impl<T> From<T> for T

Source §

fn from(t: T) -> T

Returns the argument unchanged.

Source §

impl<T> Instrument for T

Source §

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more

Source §

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more

Source §

impl<T, U> Into for T
where U: From<T>,

Source §

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source §

impl<T> IntoEither for T

Source §

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

Source §

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

Source §