Bert_for_Sequence_Classification.py

class BertForSequenceClassification(BertPreTrainedModel):
    r"""
        **labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
            Labels for computing the sequence classification/regression loss.
            Indices should be in ``[0, ..., config.num_labels - 1]``.
            If ``config.num_labels == 1`` a regression loss is computed (Mean-Square loss),
            If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy).

    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
        **loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
            Classification (or regression if config.num_labels==1) loss.
        **logits**: ``torch.FloatTensor`` of shape ``(batch_size, config.num_labels)``
            Classification (or regression if config.num_labels==1) scores (before SoftMax).
        **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
            list of ``torch.FloatTensor`` (one for the output of each layer + the output of the embeddings)
            of shape ``(batch_size, sequence_length, hidden_size)``:
            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        **attentions**: (`optional`, returned when ``config.output_attentions=True``)
            list of ``torch.FloatTensor`` (one for each layer) of shape ``(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.

    Examples::

        tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
        model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
        input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)  # Batch size 1
        labels = torch.tensor([1]).unsqueeze(0)  # Batch size 1
        outputs = model(input_ids, labels=labels)
        loss, logits = outputs[:2]

    """
    def __init__(self, config):
        super(BertForSequenceClassification, self).__init__(config)
        self.num_labels = config.num_labels

        self.bert = BertModel(config)
        self.dropout = nn.Dropout(config.hidden_dropout_prob)
        self.classifier = nn.Linear(config.hidden_size, self.config.num_labels)

        self.apply(self.init_weights)

    def forward(self, input_ids, token_type_ids=None, attention_mask=None, labels=None,
                position_ids=None, head_mask=None):
        outputs = self.bert(input_ids, position_ids=position_ids, token_type_ids=token_type_ids,
                            attention_mask=attention_mask, head_mask=head_mask)
        pooled_output = outputs[1]

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

        outputs = (logits,) + outputs[2:]  # add hidden states and attention if they are here

        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))
            outputs = (loss,) + outputs

        return outputs  # (loss), logits, (hidden_states), (attentions)

Roberta_for_Sequence_Classification.py

class RobertaForSequenceClassification(BertPreTrainedModel):
    r"""
        **labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
            Labels for computing the sequence classification/regression loss.
            Indices should be in ``[0, ..., config.num_labels]``.
            If ``config.num_labels == 1`` a regression loss is computed (Mean-Square loss),
            If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy).

    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
        **loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
            Classification (or regression if config.num_labels==1) loss.
        **logits**: ``torch.FloatTensor`` of shape ``(batch_size, config.num_labels)``
            Classification (or regression if config.num_labels==1) scores (before SoftMax).
        **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
            list of ``torch.FloatTensor`` (one for the output of each layer + the output of the embeddings)
            of shape ``(batch_size, sequence_length, hidden_size)``:
            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        **attentions**: (`optional`, returned when ``config.output_attentions=True``)
            list of ``torch.FloatTensor`` (one for each layer) of shape ``(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.

    Examples::

        tokenizer = RoertaTokenizer.from_pretrained('roberta-base')
        model = RobertaForSequenceClassification.from_pretrained('roberta-base')
        input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)  # Batch size 1
        labels = torch.tensor([1]).unsqueeze(0)  # Batch size 1
        outputs = model(input_ids, labels=labels)
        loss, logits = outputs[:2]

    """
    config_class = RobertaConfig
    pretrained_model_archive_map = ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP
    base_model_prefix = "roberta"

    def __init__(self, config):
        super(RobertaForSequenceClassification, self).__init__(config)
        self.num_labels = config.num_labels

        self.roberta = RobertaModel(config)
        self.classifier = RobertaClassificationHead(config)
    
    def forward(self, input_ids, token_type_ids=None, attention_mask=None, labels=None,
                position_ids=None, head_mask=None):
        outputs = self.roberta(input_ids, position_ids=position_ids, token_type_ids=token_type_ids,
                            attention_mask=attention_mask, head_mask=head_mask)
        sequence_output = outputs[0]
        logits = self.classifier(sequence_output)

        outputs = (logits,) + outputs[2:]
        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))
            outputs = (loss,) + outputs

        return outputs  # (loss), logits, (hidden_states), (attentions)