|
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_xlm_roberta import XLMRobertaPreTrainedModel, XLMRobertaModel |
|
from .configuration_xlm_roberta import XLMRobertaFlashConfig |
|
|
|
|
|
class XLMRobertaForSequenceClassification(XLMRobertaPreTrainedModel): |
|
def __init__(self, config: XLMRobertaFlashConfig): |
|
super().__init__(config) |
|
self.num_labels = config.num_labels |
|
self.config = config |
|
|
|
self.roberta = XLMRobertaModel(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) |
|
|
|
|
|
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.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, |
|
) |
|
|
|
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, |
|
) |
