Struct LearningRate

pub struct LearningRate {
    pub decay: f64,
    pub end: f64,
    pub record: LearningRateRecord,
}

A learning rate that can be a constant or exponentially decayed.

Fields

decay: f64

The decay factor. 1.0 means no decay.

end: f64

The final value of the learning rate.

record: LearningRateRecord

The record of the learning rate.

Implementations

impl LearningRate

pub fn update(&mut self) -> &mut Self

Update the learning rate.

pub fn load_record(&mut self, record: LearningRateRecord) -> &mut Self

Load the record of the learning rate.

pub fn into_record(self) -> LearningRateRecord

Unload the record of the learning rate.

Methods from Deref<Target = f64>

pub const RADIX: u32 = 2u32

pub const MANTISSA_DIGITS: u32 = 53u32

pub const DIGITS: u32 = 15u32

pub const EPSILON: f64 = 2.2204460492503131E-16f64

pub const MIN: f64 = -1.7976931348623157E+308f64

pub const MIN_POSITIVE: f64 = 2.2250738585072014E-308f64

pub const MAX: f64 = 1.7976931348623157E+308f64

pub const MIN_EXP: i32 = -1_021i32

pub const MAX_EXP: i32 = 1_024i32

pub const MIN_10_EXP: i32 = -307i32

pub const MAX_10_EXP: i32 = 308i32

pub const NAN: f64 = NaN_f64

pub const INFINITY: f64 = +Inf_f64

pub const NEG_INFINITY: f64 = -Inf_f64

pub fn total_cmp(&self, other: &f64) -> Ordering

Returns the ordering between self and other.

Unlike the standard partial comparison between floating point numbers, this comparison always produces an ordering in accordance to the totalOrder predicate as defined in the IEEE 754 (2008 revision) floating point standard. The values are ordered in the following sequence:

• negative quiet NaN
• negative signaling NaN
• negative infinity
• negative numbers
• negative subnormal numbers
• negative zero
• positive zero
• positive subnormal numbers
• positive numbers
• positive infinity
• positive signaling NaN
• positive quiet NaN.

The ordering established by this function does not always agree with the PartialOrd and PartialEq implementations of f64. For example, they consider negative and positive zero equal, while total_cmp doesn’t.

The interpretation of the signaling NaN bit follows the definition in the IEEE 754 standard, which may not match the interpretation by some of the older, non-conformant (e.g. MIPS) hardware implementations.

Example

struct GoodBoy {
    name: String,
    weight: f64,
}

let mut bois = vec![
    GoodBoy { name: "Pucci".to_owned(), weight: 0.1 },
    GoodBoy { name: "Woofer".to_owned(), weight: 99.0 },
    GoodBoy { name: "Yapper".to_owned(), weight: 10.0 },
    GoodBoy { name: "Chonk".to_owned(), weight: f64::INFINITY },
    GoodBoy { name: "Abs. Unit".to_owned(), weight: f64::NAN },
    GoodBoy { name: "Floaty".to_owned(), weight: -5.0 },
];

bois.sort_by(|a, b| a.weight.total_cmp(&b.weight));

// `f64::NAN` could be positive or negative, which will affect the sort order.
if f64::NAN.is_sign_negative() {
    assert!(bois.into_iter().map(|b| b.weight)
        .zip([f64::NAN, -5.0, 0.1, 10.0, 99.0, f64::INFINITY].iter())
        .all(|(a, b)| a.to_bits() == b.to_bits()))
} else {
    assert!(bois.into_iter().map(|b| b.weight)
        .zip([-5.0, 0.1, 10.0, 99.0, f64::INFINITY, f64::NAN].iter())
        .all(|(a, b)| a.to_bits() == b.to_bits()))
}

Trait Implementations

impl Clone for LearningRate

fn clone(&self) -> LearningRate

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for LearningRate

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

Formats the value using the given formatter.

impl Default for LearningRate

fn default() -> Self

Returns the “default value” for a type.

impl Deref for LearningRate

type Target = f64

The resulting type after dereferencing.

fn deref(&self) -> &Self::Target

Dereferences the value.

impl DerefMut for LearningRate

fn deref_mut(&mut self) -> &mut Self::Target

Mutably dereferences the value.

impl From<f64> for LearningRate

fn from(start: f64) -> Self

Converts to this type from the input type.