model.py

import torch
import torch.nn as nn
from transformers import (
    AutoTokenizer,
    BertPreTrainedModel,
    BertModel
)
from transformers.modeling_outputs import TokenClassifierOutput
from typing import Dict, List, Optional, Tuple, Union

class BertForTokenClassificationSingleLabel(BertPreTrainedModel):

    _keys_to_ignore_on_load_unexpected = [r"pooler"]

    def __init__(self, config, class_weights=None):
        super().__init__(config)
        self.num_labels = config.num_labels

        self.bert = BertModel(config, add_pooling_layer=False)
        classifier_dropout = (
            config.classifier_dropout if config.classifier_dropout is not None else config.hidden_dropout_prob
        )
        self.dropout = nn.Dropout(classifier_dropout)
        self.classifier = nn.Linear(config.hidden_size, config.num_labels)

        # TODO: FIND A BETTER WAY
        self.class_weights = class_weights if class_weights is not None else None

        # Initialize weights and apply final processing
        self.post_init()


    def forward(
        self,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        labels: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[torch.Tensor], TokenClassifierOutput]:
        r"""
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.
        """
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        outputs = self.bert(
            input_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output = outputs[0]

        sequence_output = self.dropout(sequence_output)
        logits = self.classifier(sequence_output)

        loss = None

        if labels is not None:
            if self.class_weights is not None:
                self.class_weights = self.class_weights.to(self.device)

            loss_fct = nn.CrossEntropyLoss(ignore_index=-100, weight=self.class_weights)

            # ignoring unk tokens when computing the loss
            indices = (labels != -200)
            _logits = logits[indices]
            _labels  = labels[indices]

            loss = loss_fct(_logits, _labels)

        if not return_dict:
            output = (logits,) + outputs[2:]
            return ((loss,) + output) if loss is not None else output

        return TokenClassifierOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )