Struct rust_bert::bert::BertForSequenceClassification

pub struct BertForSequenceClassification { /* fields omitted */ }

BERT for sequence classification

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

• bert: Base BertModel
• classifier: BERT linear layer for classification

Implementations

impl BertForSequenceClassification

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

Build a new BertForSequenceClassification

Arguments

• p - Variable store path for the root of the BertForSequenceClassification model
• config - BertConfig object defining the model architecture and number of classes

Example

use rust_bert::bert::{BertConfig, BertForSequenceClassification};
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 = BertConfig::from_file(config_path);
let bert = BertForSequenceClassification::new(&p.root() / "bert", &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
) -> (Tensor, Option<Vec<Tensor>>, Option<Vec<Tensor>>)

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

• labels - Tensor of shape (batch size, num_labels)
• hidden_states - Option<Vec<Tensor>> of length num_hidden_layers with shape (batch size, sequence_length, hidden_size)
• attentions - Option<Vec<Tensor>> of length num_hidden_layers with shape (batch size, sequence_length, hidden_size)

Example

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 (labels, all_hidden_states, all_attentions) = no_grad(|| {
    bert_model.forward_t(
        Some(input_tensor),
        Some(mask),
        Some(token_type_ids),
        Some(position_ids),
        None,
        false,
    )
});