Struct rust_bert::albert::AlbertForSequenceClassification

pub struct AlbertForSequenceClassification { /* fields omitted */ }

ALBERT for sequence classification

Base ALBERT model with a classifier head to perform sentence or document-level classification It is made of the following blocks:

• albert: Base AlbertModel
• dropout: Dropout layer
• classifier: linear layer for classification

Implementations

impl AlbertForSequenceClassification

pub fn new<'p, P>(
    p: P,
    config: &AlbertConfig
) -> AlbertForSequenceClassification where
    P: Borrow<Path<'p>>, 

Build a new AlbertForSequenceClassification

Arguments

• p - Variable store path for the root of the ALBERT model
• config - AlbertConfig object defining the model architecture and decoder status

Example

use rust_bert::albert::{AlbertConfig, AlbertForSequenceClassification};
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 = AlbertConfig::from_file(config_path);
let albert: AlbertForSequenceClassification =
    AlbertForSequenceClassification::new(&p.root(), &config);

pub fn forward_t(
    &self,
    input_ids: Option<&Tensor>,
    mask: Option<&Tensor>,
    token_type_ids: Option<&Tensor>,
    position_ids: Option<&Tensor>,
    input_embeds: Option<&Tensor>,
    train: bool
) -> AlbertSequenceClassificationOutput

Forward pass through the model

Arguments

• input_ids - Optional input tensor of shape (batch size, sequence_length). If None, pre-computed embeddings must be provided (see input_embeds)
• mask - Optional mask of shape (batch size, sequence_length). Masked position have value 0, non-masked value 1. If None set to 1
• token_type_ids - Optional segment id of shape (batch size, sequence_length). Convention is value of 0 for the first sentence (incl. SEP) and 1 for the second sentence. If None set to 0.
• position_ids - Optional position ids of shape (batch size, sequence_length). If None, will be incremented from 0.
• input_embeds - Optional pre-computed input embeddings of shape (batch size, sequence_length, hidden_size). If None, input ids must be provided (see input_ids)
• train - boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.

Returns

• AlbertSequenceClassificationOutput containing:
  • logits - Tensor of shape (batch size, num_labels)
  • all_hidden_states - Option<Vec<Tensor>> of length num_hidden_layers with shape (batch size, sequence_length, hidden_size)
  • all_attentions - Option<Vec<Vec<Tensor>>> of length num_hidden_layers of nested length inner_group_num with shape (batch size, sequence_length, hidden_size)

Example

use rust_bert::albert::{AlbertConfig, AlbertForSequenceClassification};
 let (batch_size, sequence_length) = (64, 128);
 let input_tensor = Tensor::rand(&[batch_size, sequence_length], (Int64, device));
 let mask = Tensor::zeros(&[batch_size, sequence_length], (Int64, device));
 let token_type_ids = Tensor::zeros(&[batch_size, sequence_length], (Int64, device));
 let position_ids = Tensor::arange(sequence_length, (Int64, device)).expand(&[batch_size, sequence_length], true);

 let classification_output = no_grad(|| {
   albert_model
        .forward_t(Some(&input_tensor),
                   Some(&mask),
                   Some(&token_type_ids),
                   Some(&position_ids),
                   None,
                   false)
   });