Struct BiLstm
pub struct BiLstm {
pub forward: Lstm,
pub reverse: Lstm,
pub d_hidden: usize,
pub batch_first: bool,
}Expand description
The BiLstm module. This implementation is for Bidirectional LSTM.
Introduced in the paper: Framewise phoneme classification with bidirectional LSTM and other neural network architectures.
Should be created with BiLstmConfig.
Fields§
§forward: LstmLSTM for the forward direction.
reverse: LstmLSTM for the reverse direction.
The size of the hidden state.
batch_first: boolIf true, input is [batch_size, seq_length, input_size].
If false, input is [seq_length, batch_size, input_size].
Implementations§
§impl BiLstm
impl BiLstm
pub fn forward(
&self,
batched_input: Tensor<3>,
state: Option<LstmState<3>>,
) -> (Tensor<3>, LstmState<3>)
pub fn forward( &self, batched_input: Tensor<3>, state: Option<LstmState<3>>, ) -> (Tensor<3>, LstmState<3>)
Applies the forward pass on the input tensor. This Bidirectional LSTM implementation returns the state for each element in a sequence (i.e., across seq_length) and a final state.
§Parameters:
- batched_input: The input tensor of shape:
[batch_size, sequence_length, input_size]ifbatch_firstis true (default)[sequence_length, batch_size, input_size]ifbatch_firstis false
- state: An optional
LstmStaterepresenting the initial cell state and hidden state. Each state tensor has shape[2, batch_size, hidden_size]. If no initial state is provided, these tensors are initialized to zeros.
§Returns:
- output: A tensor represents the output features of LSTM. Shape:
[batch_size, sequence_length, hidden_size * 2]ifbatch_firstis true[sequence_length, batch_size, hidden_size * 2]ifbatch_firstis false
- state: A
LstmStaterepresents the final forward and reverse states. Bothstate.cellandstate.hiddenhave the shape[2, batch_size, hidden_size].
Trait Implementations§
§impl Module for BiLstm
impl Module for BiLstm
§fn num_params(&self) -> usize
fn num_params(&self) -> usize
Get the number of parameters the module has, including all of its sub-modules, without
initializing the ones not initialized yet.
§fn visit<Visitor>(&self, visitor: &mut Visitor)where
Visitor: ModuleVisitor,
fn visit<Visitor>(&self, visitor: &mut Visitor)where
Visitor: ModuleVisitor,
Visit each parameter and module-owned control value with a visitor.
§fn map<Mapper>(self, mapper: &mut Mapper) -> BiLstmwhere
Mapper: ModuleMapper,
fn map<Mapper>(self, mapper: &mut Mapper) -> BiLstmwhere
Mapper: ModuleMapper,
Map each parameter and module-owned control value with a mapper.
§fn collect_devices(&self, devices: Vec<Device>) -> Vec<Device>
fn collect_devices(&self, devices: Vec<Device>) -> Vec<Device>
Return all the devices found in the underneath module tree added to the given vector
without duplicates. Read more
§fn to_device(self, device: &Device) -> BiLstm
fn to_device(self, device: &Device) -> BiLstm
Move the module and all of its sub-modules to the given device. Read more
§fn fork(self, device: &Device) -> BiLstm
fn fork(self, device: &Device) -> BiLstm
Fork the module and all of its sub-modules to the given device. Read more
§fn valid(&self) -> BiLstm
fn valid(&self) -> BiLstm
Returns a validation snapshot without autodiff or active training flags. Read more
§fn train(self) -> BiLstm
fn train(self) -> BiLstm
Enables autodiff and restores configured training state throughout the module. Read more
§fn materialize(self) -> BiLstm
fn materialize(self) -> BiLstm
Fold parameter reparameterizations into their effective values and remove them. Read more
§fn devices(&self) -> Vec<Device>
fn devices(&self) -> Vec<Device>
Return all the devices found in the underneath module tree without duplicates. Read more
§fn set_require_grad(self, require_grad: bool) -> Self
fn set_require_grad(self, require_grad: bool) -> Self
Set whether every floating-point tensor parameter in the module tree requires gradients. Read more
§fn set_require_grad_group(self, group: ParamGroup, require_grad: bool) -> Self
fn set_require_grad_group(self, group: ParamGroup, require_grad: bool) -> Self
Set whether matched floating-point tensor parameters require gradients. Read more
§fn no_grad(self) -> Self
fn no_grad(self) -> Self
Disable gradients for every floating-point tensor parameter in the module tree. Read more
§fn freeze_group(self, group: ParamGroup) -> Self
fn freeze_group(self, group: ParamGroup) -> Self
Freeze every module-owned value in the given group, leaving the rest of the module
untouched. Read more
§fn unfreeze_group(self, group: ParamGroup) -> Self
fn unfreeze_group(self, group: ParamGroup) -> Self
Unfreeze every module-owned value in the given group, leaving the rest of the module
untouched. Read more
§fn quantize_weights(self, quantizer: &mut Quantizer) -> Self
fn quantize_weights(self, quantizer: &mut Quantizer) -> Self
Quantize the weights of the module.
§fn quantize_weights_group(
self,
quantizer: &mut Quantizer,
group: ParamGroup,
) -> Self
fn quantize_weights_group( self, quantizer: &mut Quantizer, group: ParamGroup, ) -> Self
Quantize the weights of the given parameter group.
§fn apply_reparameterization<R>(self, reparameterizer: R) -> Selfwhere
Self: Sized,
R: Reparameterizer,
fn apply_reparameterization<R>(self, reparameterizer: R) -> Selfwhere
Self: Sized,
R: Reparameterizer,
Attach reparameterizations using the given
Reparameterizer. Read more§fn apply_lora(self, lora: Lora) -> Selfwhere
Self: Sized,
fn apply_lora(self, lora: Lora) -> Selfwhere
Self: Sized,
Attach LoRA adapters to the module’s 2-D weights, freezing all base tensor parameters. Read more
§fn apply_qlora(self, qlora: QLora) -> Selfwhere
Self: Sized,
fn apply_qlora(self, qlora: QLora) -> Selfwhere
Self: Sized,
Apply QLoRA to the module: quantize the (frozen) base tensor parameters and attach trainable
LoRA adapters to 2-D weights. Read more
§fn into_record(self) -> ModuleRecordwhere
Self: Sized,
fn into_record(self) -> ModuleRecordwhere
Self: Sized,
Collect this module’s tensor parameters into a
ModuleRecord. Read more§fn into_record_group(self, group: ParamGroup) -> ModuleRecordwhere
Self: Sized,
fn into_record_group(self, group: ParamGroup) -> ModuleRecordwhere
Self: Sized,
§fn try_load_record(self, record: ModuleRecord) -> Result<Self, RecordError>where
Self: Sized,
fn try_load_record(self, record: ModuleRecord) -> Result<Self, RecordError>where
Self: Sized,
Apply a
ModuleRecord to this module, returning the loaded
module. Read more§fn load_record(self, record: ModuleRecord) -> Selfwhere
Self: Sized,
fn load_record(self, record: ModuleRecord) -> Selfwhere
Self: Sized,
Apply a
ModuleRecord to this module, consuming and returning
it. Read more§fn save_file<P>(self, path: P) -> Result<(), RecordError>
fn save_file<P>(self, path: P) -> Result<(), RecordError>
Save this module’s parameters to a burnpack file on disk. Read more
§fn load_file<P>(self, path: P) -> Self
fn load_file<P>(self, path: P) -> Self
Load this module’s parameters from a burnpack file on disk, returning the loaded module. Read more
§fn try_load_file<P>(self, path: P) -> Result<Self, RecordError>
fn try_load_file<P>(self, path: P) -> Result<Self, RecordError>
§impl ModuleDisplay for BiLstm
impl ModuleDisplay for BiLstm
§fn custom_settings(&self) -> Option<DisplaySettings>
fn custom_settings(&self) -> Option<DisplaySettings>
Custom display settings for the module. Read more
§fn custom_content(&self, content: Content) -> Option<Content>
fn custom_content(&self, content: Content) -> Option<Content>
Custom attributes for the module. Read more
§fn format(&self, passed_settings: DisplaySettings) -> String
fn format(&self, passed_settings: DisplaySettings) -> String
Formats the module with provided display settings. Read more
Auto Trait Implementations§
impl !RefUnwindSafe for BiLstm
impl !UnwindSafe for BiLstm
impl Freeze for BiLstm
impl Send for BiLstm
impl Sync for BiLstm
impl Unpin for BiLstm
impl UnsafeUnpin for BiLstm
Blanket Implementations§
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
impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
§impl<K, Q> Comparable<Q> for K
impl<K, Q> Comparable<Q> for K
§impl<K, Q> Equivalent<Q> for K
impl<K, Q> Equivalent<Q> for K
§fn equivalent(&self, key: &Q) -> bool
fn equivalent(&self, key: &Q) -> bool
Compare self to
key and return true if they are equal.impl<T> ErasedDestructor for Twhere
T: 'static,
§impl<T> Instrument for T
impl<T> Instrument for T
§fn instrument(self, span: Span) -> Instrumented<Self>
fn instrument(self, span: Span) -> Instrumented<Self>
§fn in_current_span(self) -> Instrumented<Self>
fn in_current_span(self) -> Instrumented<Self>
Source§impl<T> IntoEither for T
impl<T> IntoEither for T
Source§fn into_either(self, into_left: bool) -> Either<Self, Self>
fn into_either(self, into_left: bool) -> Either<Self, Self>
Converts
self into a Left variant of Either<Self, Self>
if into_left is true.
Converts self into a Right variant of Either<Self, Self>
otherwise. Read moreSource§fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
Converts
self into a Left variant of Either<Self, Self>
if into_left(&self) returns true.
Converts self into a Right variant of Either<Self, Self>
otherwise. Read more§impl<T> Pointable for T
impl<T> Pointable for T
§impl<T> PolicyExt for Twhere
T: ?Sized,
impl<T> PolicyExt for Twhere
T: ?Sized,
impl<T> Read<Exclusive, BecauseExclusive> for Twhere
T: ?Sized,
§impl<T> ToCompactString for Twhere
T: Display,
impl<T> ToCompactString for Twhere
T: Display,
§fn try_to_compact_string(&self) -> Result<CompactString, ToCompactStringError>
fn try_to_compact_string(&self) -> Result<CompactString, ToCompactStringError>
Fallible version of [
ToCompactString::to_compact_string()] Read more§fn to_compact_string(&self) -> CompactString
fn to_compact_string(&self) -> CompactString
Converts the given value to a [
CompactString]. Read more