Struct burn_core::nn::Linear

pub struct Linear<B: Backend> {
    pub weight: Param<Tensor<B, 2>>,
    pub bias: Option<Param<Tensor<B, 1>>>,
}

Applies a linear transformation to the input tensor:

O = IW + b

Fields

weight: Param<Tensor<B, 2>>

Matrix of shape [d_input, d_output] initialized from a uniform distribution: U(-k, k), where k = sqrt(1 / d_input)

bias: Option<Param<Tensor<B, 1>>>

Vector of size d_output initialized from a uniform distribution: U(-k, k), where k = sqrt(1 / d_input)

Implementations

impl<B: Backend> Linear<B>

pub fn forward<const D: usize>(&self, input: Tensor<B, D>) -> Tensor<B, D>

Applies the forward pass on the input tensor.

Shapes

• input: [..., any, d_input]
• output: [..., any, d_output]

Trait Implementations

impl<B> AutodiffModule<B> for Linear<B>where B: AutodiffBackend + Backend, <B as AutodiffBackend>::InnerBackend: Backend,

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

Inner module without auto-differentiation.

fn valid(&self) -> Self::InnerModule

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

impl<B: Backend> Clone for Linear<B>

fn clone(&self) -> Self

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<B: Debug + Backend> Debug for Linear<B>

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

Formats the value using the given formatter.

impl<B: Backend> Display for Linear<B>

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

Formats the value using the given formatter.

impl<B: Backend> Module<B> for Linear<B>

type Record = LinearRecord<B>

Type to save and load the module.

fn load_record(self, record: Self::Record) -> Self

Load the module state from a record.

fn into_record(self) -> Self::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<V: ModuleVisitor<B>>(&self, visitor: &mut V)

Visit each tensor parameter in the module with a visitor.

fn map<M: ModuleMapper<B>>(self, mapper: &mut M) -> Self

Map each tensor parameter in the module with a mapper.

fn collect_devices(&self, devices: Devices<B>) -> Devices<B>

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

fn to_device(self, device: &B::Device) -> Self

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

fn fork(self, device: &B::Device) -> Self

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

fn devices(&self) -> Devices<B>

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: FileRecorder, PB: Into<PathBuf>>( self, file_path: PB, recorder: &FR ) -> Result<(), RecorderError>

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

fn load_file<FR: FileRecorder, PB: Into<PathBuf>>( self, file_path: PB, recorder: &FR ) -> Result<Self, RecorderError>

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