from typing import Optional, Union, Tuple import torch from torch import nn from torch.nn import CrossEntropyLoss, MSELoss, BCEWithLogitsLoss from transformers.modeling_outputs import SequenceClassifierOutput, QuestionAnsweringModelOutput, TokenClassifierOutput from .modeling_bert import BertPreTrainedModel, BertModel from .configuration_bert import JinaBertConfig class BertForSequenceClassification(BertPreTrainedModel): def __init__(self, config: JinaBertConfig): super().__init__(config) self.num_labels = config.num_labels self.config = config self.bert = BertModel(config) 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) # 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], SequenceClassifierOutput]: r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): 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). """ return_dict = ( return_dict if return_dict is not None else self.config.use_return_dict ) assert head_mask is None assert inputs_embeds is None assert output_attentions is None assert output_hidden_states is None assert return_dict outputs = self.bert( input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids, position_ids=position_ids, ) pooled_output = outputs[1] pooled_output = self.dropout(pooled_output) logits = self.classifier(pooled_output) loss = None if labels is not None: if self.config.problem_type is None: if self.num_labels == 1: self.config.problem_type = "regression" elif self.num_labels > 1 and ( labels.dtype == torch.long or labels.dtype == torch.int ): self.config.problem_type = "single_label_classification" else: self.config.problem_type = "multi_label_classification" if self.config.problem_type == "regression": loss_fct = MSELoss() if self.num_labels == 1: loss = loss_fct(logits.squeeze(), labels.squeeze()) else: loss = loss_fct(logits, labels) elif self.config.problem_type == "single_label_classification": loss_fct = CrossEntropyLoss() loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1)) elif self.config.problem_type == "multi_label_classification": loss_fct = BCEWithLogitsLoss() loss = loss_fct(logits, labels) if not return_dict: output = (logits,) + outputs[2:] return ((loss,) + output) if loss is not None else output return SequenceClassifierOutput( loss=loss, logits=logits, hidden_states=outputs.hidden_states, attentions=outputs.attentions, ) class BertForQuestionAnswering(BertPreTrainedModel): def __init__(self, config: JinaBertConfig): super().__init__(config) self.num_labels = config.num_labels self.bert = BertModel(config, add_pooling_layer=False) self.qa_outputs = nn.Linear(config.hidden_size, config.num_labels) # 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, start_positions: Optional[torch.Tensor] = None, end_positions: Optional[torch.Tensor] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, ) -> Union[Tuple[torch.Tensor], QuestionAnsweringModelOutput]: r""" start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence are not taken into account for computing the loss. end_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence are not taken into account for computing the loss. """ return_dict = ( return_dict if return_dict is not None else self.config.use_return_dict ) assert head_mask is None assert inputs_embeds is None assert output_attentions is None assert output_hidden_states is None assert return_dict outputs = self.bert( input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids, position_ids=position_ids, ) sequence_output = outputs[0] logits = self.qa_outputs(sequence_output) start_logits, end_logits = logits.split(1, dim=-1) start_logits = start_logits.squeeze(-1).contiguous() end_logits = end_logits.squeeze(-1).contiguous() total_loss = None if start_positions is not None and end_positions is not None: # If we are on multi-GPU, split add a dimension if len(start_positions.size()) > 1: start_positions = start_positions.squeeze(-1) if len(end_positions.size()) > 1: end_positions = end_positions.squeeze(-1) # sometimes the start/end positions are outside our model inputs, we ignore these terms ignored_index = start_logits.size(1) start_positions = start_positions.clamp(0, ignored_index) end_positions = end_positions.clamp(0, ignored_index) loss_fct = CrossEntropyLoss(ignore_index=ignored_index) start_loss = loss_fct(start_logits, start_positions) end_loss = loss_fct(end_logits, end_positions) total_loss = (start_loss + end_loss) / 2 if not return_dict: output = (start_logits, end_logits) + outputs[2:] return ((total_loss,) + output) if total_loss is not None else output return QuestionAnsweringModelOutput( loss=total_loss, start_logits=start_logits, end_logits=end_logits, hidden_states=outputs.hidden_states, attentions=outputs.attentions, ) class BertForTokenClassification(BertPreTrainedModel): def __init__(self, config: JinaBertConfig): 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) # 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 ) assert head_mask is None assert inputs_embeds is None assert output_attentions is None assert output_hidden_states is None assert return_dict outputs = self.bert( input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids, position_ids=position_ids, ) sequence_output = outputs[0] sequence_output = self.dropout(sequence_output) logits = self.classifier(sequence_output) loss = None if labels is not None: loss_fct = CrossEntropyLoss() loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1)) 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, )