pub struct LinearQuantizationParams {
pub scale: Vec<f32>,
pub bias: Vec<f32>,
}Fields§
§scale: Vec<f32>Stores scale and bias values corresponding to the quantized weights. Must be an array of 1 element, or an array of C elements, where C is number of output channels. For recurrent layers it is equal to the output vector size.
Relationship between quantized weights, unquantized weights, scale and bias:
W_unquantized = W_quantized * scale + bias
bias: Vec<f32>Trait Implementations§
Source§impl Clone for LinearQuantizationParams
impl Clone for LinearQuantizationParams
Source§fn clone(&self) -> LinearQuantizationParams
fn clone(&self) -> LinearQuantizationParams
Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreSource§impl Debug for LinearQuantizationParams
impl Debug for LinearQuantizationParams
Source§impl Default for LinearQuantizationParams
impl Default for LinearQuantizationParams
Source§impl Message for LinearQuantizationParams
impl Message for LinearQuantizationParams
Source§fn encoded_len(&self) -> usize
fn encoded_len(&self) -> usize
Returns the encoded length of the message without a length delimiter.
Source§fn encode(&self, buf: &mut impl BufMut) -> Result<(), EncodeError>where
Self: Sized,
fn encode(&self, buf: &mut impl BufMut) -> Result<(), EncodeError>where
Self: Sized,
Encodes the message to a buffer. Read more
Source§fn encode_to_vec(&self) -> Vec<u8> ⓘwhere
Self: Sized,
fn encode_to_vec(&self) -> Vec<u8> ⓘwhere
Self: Sized,
Encodes the message to a newly allocated buffer.
Source§fn encode_length_delimited(
&self,
buf: &mut impl BufMut,
) -> Result<(), EncodeError>where
Self: Sized,
fn encode_length_delimited(
&self,
buf: &mut impl BufMut,
) -> Result<(), EncodeError>where
Self: Sized,
Encodes the message with a length-delimiter to a buffer. Read more
Source§fn encode_length_delimited_to_vec(&self) -> Vec<u8> ⓘwhere
Self: Sized,
fn encode_length_delimited_to_vec(&self) -> Vec<u8> ⓘwhere
Self: Sized,
Encodes the message with a length-delimiter to a newly allocated buffer.
Source§fn decode(buf: impl Buf) -> Result<Self, DecodeError>where
Self: Default,
fn decode(buf: impl Buf) -> Result<Self, DecodeError>where
Self: Default,
Decodes an instance of the message from a buffer. Read more
Source§fn decode_length_delimited(buf: impl Buf) -> Result<Self, DecodeError>where
Self: Default,
fn decode_length_delimited(buf: impl Buf) -> Result<Self, DecodeError>where
Self: Default,
Decodes a length-delimited instance of the message from the buffer.
Source§fn merge(&mut self, buf: impl Buf) -> Result<(), DecodeError>where
Self: Sized,
fn merge(&mut self, buf: impl Buf) -> Result<(), DecodeError>where
Self: Sized,
Decodes an instance of the message from a buffer, and merges it into
self. Read moreSource§fn merge_length_delimited(&mut self, buf: impl Buf) -> Result<(), DecodeError>where
Self: Sized,
fn merge_length_delimited(&mut self, buf: impl Buf) -> Result<(), DecodeError>where
Self: Sized,
Decodes a length-delimited instance of the message from buffer, and
merges it into
self.Source§impl PartialEq for LinearQuantizationParams
impl PartialEq for LinearQuantizationParams
Source§fn eq(&self, other: &LinearQuantizationParams) -> bool
fn eq(&self, other: &LinearQuantizationParams) -> bool
Tests for
self and other values to be equal, and is used by ==.impl StructuralPartialEq for LinearQuantizationParams
Auto Trait Implementations§
impl Freeze for LinearQuantizationParams
impl RefUnwindSafe for LinearQuantizationParams
impl Send for LinearQuantizationParams
impl Sync for LinearQuantizationParams
impl Unpin for LinearQuantizationParams
impl UnsafeUnpin for LinearQuantizationParams
impl UnwindSafe for LinearQuantizationParams
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