Struct burn::nn::attention::MultiHeadAttention

pub struct MultiHeadAttention<B>
where
    B: Backend,
{
    pub query: Linear<B>,
    pub key: Linear<B>,
    pub value: Linear<B>,
    pub output: Linear<B>,
    pub dropout: Dropout,
    pub activation: Gelu,
    pub d_model: usize,
    pub n_heads: usize,
    pub d_k: usize,
    pub min_float: f64,
    pub quiet_softmax: bool,
}

The multihead attention module as describe in the paper Attention Is All You Need.

Params

• query: Linear layer with d_model input and output features.
• key: Linear layer with d_model input and output features.
• value: Linear layer with d_model input and output features.
• output: Linear layer with d_model input and output features.

Should be created with MultiHeadAttentionConfig.

Fields

query: Linear<B>

Linear layer to transform the input features into the query space.

key: Linear<B>

Linear layer to transform the input features into the key space.

value: Linear<B>

Linear layer to transform the input features into the value space.

output: Linear<B>

Linear layer to transform the output features back to the original space.

dropout: Dropout

Dropout layer.

activation: Gelu

Activation function.

d_model: usize

The size of each linear layer.

n_heads: usize

The number of heads.

d_k: usize

Size of the key and query vectors.

min_float: f64

Minimum value a float can take.

quiet_softmax: bool

Use “quiet softmax” instead of regular softmax.

Implementations

impl<B> MultiHeadAttention<B>

where B: Backend,

pub fn forward(&self, input: MhaInput<B>) -> MhaOutput<B>

Applies the forward pass on the input tensors.

See MultiHeadAttention for more information.

Shapes

• query: [batch_size, seq_length_1, d_model]
• key: [batch_size, seq_length_2, d_model]
• value: [batch_size, seq_length_2, d_model]
• output: [batch_size, seq_length_1, d_model]

pub fn forward_cache( &self, input: MhaInput<B>, cache: &mut MhaCache<B>, ) -> MhaOutput<B>

Applies the forward pass using a cache.

Shapes

• query: [batch_size, seq_length_1, d_model]
• key: [batch_size, seq_length_2, d_model]
• value: [batch_size, seq_length_2, d_model]
• output: [batch_size, seq_length_1, d_model]

Trait Implementations

impl<B> AutodiffModule<B> for MultiHeadAttention<B>

where B: Backend + AutodiffBackend, <B as AutodiffBackend>::InnerBackend: Backend,

type InnerModule = MultiHeadAttention<<B as AutodiffBackend>::InnerBackend>

Inner module without auto-differentiation.

fn valid(&self) -> <MultiHeadAttention<B> as AutodiffModule<B>>::InnerModule

Get the same module, but on the inner backend without auto-differentiation.

impl<B> Clone for MultiHeadAttention<B>

where B: Backend,

fn clone(&self) -> MultiHeadAttention<B>

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<B> Debug for MultiHeadAttention<B>

where B: Debug + Backend,

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

Formats the value using the given formatter.

impl<B> Display for MultiHeadAttention<B>

where B: Backend,

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

Formats the value using the given formatter.

impl<B> Module<B> for MultiHeadAttention<B>

where B: Backend,

type Record = MultiHeadAttentionRecord<B>

Type to save and load the module.

fn load_record( self, record: <MultiHeadAttention<B> as Module<B>>::Record, ) -> MultiHeadAttention<B>

Load the module state from a record.

fn into_record(self) -> <MultiHeadAttention<B> as Module<B>>::Record

Convert the module into a record containing the state.

fn num_params(&self) -> usize

Get the number of parameters the module has, including all of its sub-modules.

fn visit<Visitor>(&self, visitor: &mut Visitor)

where Visitor: ModuleVisitor<B>,

Visit each tensor parameter in the module with a visitor.

fn map<Mapper>(self, mapper: &mut Mapper) -> MultiHeadAttention<B>

where Mapper: ModuleMapper<B>,

Map each tensor parameter in the module with a mapper.

fn collect_devices( &self, devices: Vec<<B as Backend>::Device>, ) -> Vec<<B as Backend>::Device>

Return all the devices found in the underneath module tree added to the given vector without duplicates.

fn to_device(self, device: &<B as Backend>::Device) -> MultiHeadAttention<B>

Move the module and all of its sub-modules to the given device.

fn fork(self, device: &<B as Backend>::Device) -> MultiHeadAttention<B>

Fork the module and all of its sub-modules to the given device.

fn devices(&self) -> Vec<<B as Backend>::Device>

Return all the devices found in the underneath module tree without duplicates.

fn no_grad(self) -> Self

Each tensor in the module tree will not require grad.

fn save_file<FR, PB>( self, file_path: PB, recorder: &FR, ) -> Result<(), RecorderError>

where FR: FileRecorder<B>, PB: Into<PathBuf>,

Save the module to a file using the provided file recorder.

fn load_file<FR, PB>( self, file_path: PB, recorder: &FR, device: &<B as Backend>::Device, ) -> Result<Self, RecorderError>

where FR: FileRecorder<B>, PB: Into<PathBuf>,

Load the module from a file using the provided file recorder.

fn quantize_weights<C>(self, quantizer: &mut Quantizer<C>) -> Self

where C: Calibration,

Quantize the weights of the module.

impl<B> ModuleDisplay for MultiHeadAttention<B>

where B: Backend,

fn custom_settings(&self) -> Option<DisplaySettings>

Custom display settings for the module.

fn custom_content(&self, content: Content) -> Option<Content>

Custom attributes for the module.

fn format(&self, passed_settings: DisplaySettings) -> String

Formats the module with provided display settings.

impl<B> ModuleDisplayDefault for MultiHeadAttention<B>

where B: Backend,

fn content(&self, content: Content) -> Option<Content>

Attributes of the module used for display purposes.

fn num_params(&self) -> usize

Gets the number of the parameters of the module.