Struct ModelData 

pub struct ModelData {
    pub weights: Vec<f32>,
    pub biases: Vec<f32>,
    pub architecture: ModelArchitecture,
}

Neural network weights and architecture

Fields

weights: Vec<f32>

Weight values

biases: Vec<f32>

Bias values

architecture: ModelArchitecture

Network architecture

Implementations

impl ModelData

pub fn compress(&self) -> Result<Vec<u8>, AprError>

Compress model data using DEFLATE

Errors

Returns error if compression fails

pub fn decompress(bytes: &[u8]) -> Result<Self, AprError>

Decompress model data

Errors

Returns error if decompression fails

Trait Implementations

impl Clone for ModelData

fn clone(&self) -> ModelData

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelData

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ModelData

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ModelData

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

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

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 Serialize for ModelData

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ModelData