Method forward

bert/modeling_bert.py:1307–1381

r""" labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`): Labels for computing the multiple choice classification loss. Indices should be in ``[0, ..., num_choices-1]`` where `num_choices` is the size of the second dimen

(
        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,
    )

    @add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING.format("(batch_size, num_choices, sequence_length)"))
    @add_code_sample_docstrings(tokenizer_class=_TOKENIZER_FOR_DOC, checkpoint="bert-base-uncased")
    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,
    ):
        r"""
        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
            Labels for computing the multiple choice classification loss.
            Indices should be in ``[0, ..., num_choices-1]`` where `num_choices` is the size of the second dimension
            of the input tensors. (see `input_ids` above)

    Returns:
        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
        loss (:obj:`torch.FloatTensor` of shape `(1,)`, `optional`, returned when :obj:`labels` is provided):
            Classification loss.
        classification_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, num_choices)`):
            `num_choices` is the second dimension of the input tensors. (see `input_ids` above).

            Classification scores (before SoftMax).
        hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``output_hidden_states=True`` is passed or when ``config.output_hidden_states=True``):
            Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
            of shape :obj:`(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``output_attentions=True`` is passed or when ``config.output_attentions=True``):
            Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
            :obj:`(batch_size, num_heads, sequence_length, sequence_length)`.

            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
            heads.
        """
        num_choices = input_ids.shape[1] if input_ids is not None else inputs_embeds.shape[1]

        input_ids = input_ids.view(-1, input_ids.size(-1)) if input_ids is not None else None
        attention_mask = attention_mask.view(-1, attention_mask.size(-1)) if attention_mask is not None else None
        token_type_ids = token_type_ids.view(-1, token_type_ids.size(-1)) if token_type_ids is not None else None
        position_ids = position_ids.view(-1, position_ids.size(-1)) if position_ids is not None else None
        inputs_embeds = (
            inputs_embeds.view(-1, inputs_embeds.size(-2), inputs_embeds.size(-1))
            if inputs_embeds is not None
            else None
        )

        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,