Struct XLNetForTokenClassification

Source
pub struct XLNetForTokenClassification { /* private fields */ }
Expand description

§XLNetForTokenClassification

XLNet model with a classification head for token-level classification tasks It is made of the following blocks:

  • base_model: XLNetModel
  • classifier: Linear layer projecting the hidden layer output to the target space

Implementations§

Source§

impl XLNetForTokenClassification

Source

pub fn new<'p, P>( p: P, config: &XLNetConfig, ) -> Result<XLNetForTokenClassification, RustBertError>
where P: Borrow<Path<'p>>,

Build a new XLNetForTokenClassification

§Arguments
  • p - Variable store path for the root of the XLNet model
  • config - XLNetConfig object defining the model architecture
§Example
use rust_bert::xlnet::{XLNetConfig, XLNetForTokenClassification};
use rust_bert::Config;
use std::path::Path;
use tch::{nn, Device};

let config_path = Path::new("path/to/config.json");
let device = Device::Cpu;
let p = nn::VarStore::new(device);
let config = XLNetConfig::from_file(config_path);
let xlnet_model = XLNetForTokenClassification::new(&p.root(), &config).unwrap();
Source

pub fn forward_t( &self, input_ids: Option<&Tensor>, attention_mask: Option<&Tensor>, old_layer_states: Option<Vec<Option<LayerState>>>, perm_mask: Option<&Tensor>, target_mapping: Option<&Tensor>, token_type_ids: Option<&Tensor>, input_embeds: Option<&Tensor>, train: bool, ) -> XLNetTokenClassificationOutput

Forward pass through the model

§Arguments
  • input_ids - Optional input tensor of shape (batch size, sequence_length). This or input_embeds must be provided.
  • attention_mask - Optional attention mask of shape (batch size, sequence_length) for the encoder positions. Positions with a mask with value 0 will be masked.
  • perm_mask - Optional tensor of shape (batch size, sequence_length, sequence_length). Mask to indicate the attention pattern for each input token (only used for pre-training over permutations, rather than simple token masking).
  • target_mapping - Optional tensor of shape (batch size, num_tokens, sequence_length) indicating the position of the masked words to predict.
  • token_type_ids - Optional tensor (batch size, sequence_length) indicating the sentence ID of the token (0: first sentence, 1: second sentence).
  • input_embeds - Optional input tensor of shape (batch size, sequence_length, embeddings dimension). This or input_ids must be provided.
  • old_layer_states - Optional vector of length num_layers containing optional LayerStates containing the last calculated content for the attention layers. This avoids recomputing attention weights at past positions and speeds up decoding.
  • train - boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.
§Returns
  • XLNetTokenClassificationOutput containing:
    • logits - Tensor of shape (batch size, sequence_length, num_classes) representing the logits for each batch item, token position and class
    • next_cache - Option<Vec<Option<LayerState>>> of length n_layer containing the past content for the the attention layers with shape (past_sequence_length, batch size, hidden_size)
    • all_hidden_states - Option<Vec<(Tensor, Option<Tensor>)>> of length n_layer with shape (batch size, sequence_length, hidden_size) (with optional query stream states if used)
    • all_attentions - Option<Vec<(Tensor, Option<Tensor>)>> of length n_layer with shape (batch size, sequence_length, hidden_size) (with optional query stream states if used)
§Example
use rust_bert::xlnet::{XLNetConfig, XLNetForTokenClassification};
let (batch_size, sequence_length) = (64, 128);
let input_tensor = Tensor::rand(&[batch_size, sequence_length], (Int64, device));
let attention_mask = Tensor::ones(&[batch_size, sequence_length], (Int64, device));
let target_tensor = Tensor::ones(&[batch_size, sequence_length], (Int64, device));
let target_mapping = Tensor::zeros(&[64, 1, 128], (Kind::Float, device));
let _ = target_mapping.narrow(2, 3, 1).fill_(1.0);

let model_output = no_grad(|| {
    xlnet_model.forward_t(
        Some(&input_tensor),
        Some(&attention_mask),
        None,
        Some(&target_mapping),
        None,
        None,
        None,
        false
    )
});

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

Source§

impl<T> Instrument for T

Source§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more
Source§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> IntoEither for T

Source§

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 more
Source§

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

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
Source§

impl<T> Pointable for T

Source§

const ALIGN: usize

The alignment of pointer.
Source§

type Init = T

The type for initializers.
Source§

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more
Source§

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more
Source§

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more
Source§

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more
Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
Source§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

Source§

fn vzip(self) -> V

Source§

impl<T> WithSubscriber for T

Source§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

impl<T> ErasedDestructor for T
where T: 'static,

Source§

impl<T> MaybeSendSync for T