pub struct Linear<T: Scalar, B: BackendOps<T> + Default = MoiraiBackend> {
pub weight: Var<T, B>,
pub bias: Option<Var<T, B>>,
}Expand description
Fully-connected linear layer.
Fields§
§weight: Var<T, B>Weight matrix: [out_features × in_features].
bias: Option<Var<T, B>>Bias vector: [out_features].
Implementations§
Source§impl<T, B> Linear<T, B>
Construction needs more of T and B than holding a layer does – the
weights are drawn, so the scalar must be sampleable and the backend must be
able to sample it. The bounds sit here rather than on the type so
Linear<T, B> stays nameable for any scalar.
impl<T, B> Linear<T, B>
Construction needs more of T and B than holding a layer does – the
weights are drawn, so the scalar must be sampleable and the backend must be
able to sample it. The bounds sit here rather than on the type so
Linear<T, B> stays nameable for any scalar.
Sourcepub fn new(
in_features: usize,
out_features: usize,
bias: bool,
) -> Result<Self, InitializationError<B::Error>>
pub fn new( in_features: usize, out_features: usize, bias: bool, ) -> Result<Self, InitializationError<B::Error>>
Create a Linear layer with given input/output features.
Weights are drawn Kaiming-uniform over in_features from a fixed seed,
so a layer built the same way twice is the same layer; use
Linear::with_seed to choose the draw. Biases are zero.
§Errors
Returns InitializationError when in_features is zero, or when the
backend’s draw fails.
Trait Implementations§
Source§impl<T: Scalar + RealScalar, B: BackendOps<T> + Default> Module<T, B> for Linear<T, B>
impl<T: Scalar + RealScalar, B: BackendOps<T> + Default> Module<T, B> for Linear<T, B>
Source§fn parameters(&self) -> Vec<Var<T, B>>
fn parameters(&self) -> Vec<Var<T, B>>
Collect all trainable parameters (including from sub-modules).
Source§fn forward(&self, input: &Var<T, B>) -> Result<Var<T, B>, ModuleError<B::Error>>
fn forward(&self, input: &Var<T, B>) -> Result<Var<T, B>, ModuleError<B::Error>>
Evaluate this module. Read more
Source§fn load_parameters(&mut self, params: &[Var<T, B>])
fn load_parameters(&mut self, params: &[Var<T, B>])
Write optimizer-updated parameter values back into this module’s own
fields, consuming
params in the same order parameters() enumerates
them (i.e. params.len() == parameters().len()). Read moreSource§fn named_parameters(&self) -> Vec<Parameter<T, B>>
fn named_parameters(&self) -> Vec<Parameter<T, B>>
Collect trainable parameters with stable hierarchical names. Read more
Source§fn load_named_parameters(
&mut self,
parameters: &[Parameter<T, B>],
) -> Result<(), ParameterLoadError>
fn load_named_parameters( &mut self, parameters: &[Parameter<T, B>], ) -> Result<(), ParameterLoadError>
Load optimizer-updated named parameters after validating the complete
stable path inventory. Read more
Auto Trait Implementations§
impl<T, B = MoiraiBackend> !RefUnwindSafe for Linear<T, B>
impl<T, B = MoiraiBackend> !UnwindSafe for Linear<T, B>
impl<T, B> Forget for Linear<T, B>
impl<T, B> Freeze for Linear<T, B>
impl<T, B> Move for Linear<T, B>
impl<T, B> Send for Linear<T, B>
impl<T, B> Sync for Linear<T, B>
impl<T, B> Unpin for Linear<T, B>
impl<T, B> UnsafeUnpin for Linear<T, B>
Blanket Implementations§
Source§impl<T> ArchivePointee for T
impl<T> ArchivePointee for T
Source§type ArchivedMetadata = ()
type ArchivedMetadata = ()
The archived version of the pointer metadata for this type.
Source§fn pointer_metadata(
_: &<T as ArchivePointee>::ArchivedMetadata,
) -> <T as Pointee>::Metadata
fn pointer_metadata( _: &<T as ArchivePointee>::ArchivedMetadata, ) -> <T as Pointee>::Metadata
Converts some archived metadata to the pointer metadata for itself.
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
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
Source§impl<T> Instrument for T
impl<T> Instrument for T
Source§fn instrument(self, span: Span) -> Instrumented<Self> ⓘ
fn instrument(self, span: Span) -> Instrumented<Self> ⓘ
Source§fn in_current_span(self) -> Instrumented<Self> ⓘ
fn in_current_span(self) -> Instrumented<Self> ⓘ
Source§impl<T> LayoutRaw for T
impl<T> LayoutRaw for T
Source§fn layout_raw(_: <T as Pointee>::Metadata) -> Result<Layout, LayoutError>
fn layout_raw(_: <T as Pointee>::Metadata) -> Result<Layout, LayoutError>
Returns the layout of the type.
Source§impl<T, N1, N2> Niching<NichedOption<T, N1>> for N2
impl<T, N1, N2> Niching<NichedOption<T, N1>> for N2
Source§unsafe fn is_niched(niched: *const NichedOption<T, N1>) -> bool
unsafe fn is_niched(niched: *const NichedOption<T, N1>) -> bool
Returns whether the given value has been niched. Read more
Source§fn resolve_niched(out: Place<NichedOption<T, N1>>)
fn resolve_niched(out: Place<NichedOption<T, N1>>)
Writes data to
out indicating that a T is niched.