pub enum PreScale {
None,
Some(Positive<f32>),
ReciprocalMeanNorm,
}Expand description
Pre-scaling selector for spherical quantization training. Pre-scaling adjusts the dynamic range of the data (usually decreasing it uniformly) to keep the correction terms within the range expressible by 16-bit floating point numbers.
Variants§
None
Do not use any pre-scaling.
Some(Positive<f32>)
Pre-scale all data by the specified amount.
ReciprocalMeanNorm
Heuristically estimate a pre-scaling parameter by using the inverse approximate mean norm. This will nearly normalize in-distribution vectors.
Trait Implementations§
Auto Trait Implementations§
impl Freeze for PreScale
impl RefUnwindSafe for PreScale
impl Send for PreScale
impl Sync for PreScale
impl Unpin for PreScale
impl UnwindSafe for PreScale
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
Source§impl<T> IntoEither for T
impl<T> IntoEither for T
Source§fn into_either(self, into_left: bool) -> Either<Self, Self>
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 moreSource§fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
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