roberta_cls.py

import torch
from torch.nn import Softmax
from torch.nn import CrossEntropyLoss, MSELoss
from typing import Optional, Tuple

from transformers import RobertaForSequenceClassification

from transformers.modeling_outputs import SequenceClassifierOutput

from dataclasses import dataclass

@dataclass
class SequenceClassifierOutputWithLastLayer(SequenceClassifierOutput):

    loss: Optional[torch.FloatTensor] = None
    logits: torch.FloatTensor = None
    last_hidden_state: torch.FloatTensor = None
    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
    attentions: Optional[Tuple[torch.FloatTensor]] = None


class RobertaForContrastiveClassification(RobertaForSequenceClassification):
    _keys_to_ignore_on_load_missing = [r"position_ids"]

    def __init__(self, config):
        super().__init__(config)

        self.soft_max = Softmax(dim=1)

    def forward(
        self,
        input_ids=None,
        attention_mask=None,
        token_type_ids=None,
        position_ids=None,
        head_mask=None,
        inputs_embeds=None,
        labels=None,
        output_attentions=None,
        output_hidden_states=None,
        return_dict=None,
    ):
        r"""
        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
            Labels for computing the sequence classification/regression loss. Indices should be in :obj:`[0, ...,
            config.num_labels - 1]`. If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
            If :obj:`config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        """
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        outputs = self.roberta(
            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]
        logits = self.classifier(sequence_output)

        loss = None
        if labels is not None:
            loss = None
            if labels is not None:
                if self.num_labels == 1:
                    #  We are doing regression
                    loss_fct = MSELoss()
                    loss = loss_fct(logits.view(-1), labels.view(-1))
                else:
                    loss_fct = CrossEntropyLoss()
                    loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))

        softmax_logits = self.soft_max(logits)

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

        return SequenceClassifierOutputWithLastLayer(
            loss=loss,
            logits=softmax_logits,
            last_hidden_state=sequence_output,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )