Struct EmbeddingConfig

pub struct EmbeddingConfig {
    pub n_embedding: usize,
    pub d_model: usize,
    pub initializer: Initializer,
}

Configuration to create an Embedding layer using the init function.

Fields

n_embedding: usize

The number of embedding vectors.

d_model: usize

The size of each vector.

initializer: Initializer

The type of function used to initialize neural network parameters

Implementations

impl EmbeddingConfig

pub fn new(n_embedding: usize, d_model: usize) -> Self

Create a new instance of the config.

impl EmbeddingConfig

pub fn with_initializer(self, initializer: Initializer) -> Self

The type of function used to initialize neural network parameters

impl EmbeddingConfig

pub fn init<B: Backend>(&self, device: &B::Device) -> Embedding<B>

Initialize a new embedding module.

Trait Implementations

impl Clone for EmbeddingConfig

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Config for EmbeddingConfig

fn save<P: AsRef<Path>>(&self, file: P) -> Result<()>

Available on crate feature std only.

Saves the configuration to a file.

fn load<P: AsRef<Path>>(file: P) -> Result<Self, ConfigError>

Available on crate feature std only.

Loads the configuration from a file.

fn load_binary(data: &[u8]) -> Result<Self, ConfigError>

Loads the configuration from a binary buffer.

impl<'de> Deserialize<'de> for EmbeddingConfig

fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for EmbeddingConfig

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

Formats the value using the given formatter.

impl Serialize for EmbeddingConfig

fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>

where S: Serializer,

Serialize this value into the given Serde serializer.