s444465/projekt-glebokie
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

roberta custom head test7

Browse Source
This commit is contained in:
s444501 2023-02-12 20:34:20 +01:00
parent 930d8c7d71
commit ba21870e77
1 changed files with 11 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
roberta.py
View File

@ -22,7 +22,6 @@ class RobertaLeakyHead(nn.Module):
classifier_dropout = ( classifier_dropout = (
config.classifier_dropout if config.classifier_dropout is not None else config.hidden_dropout_prob config.classifier_dropout if config.classifier_dropout is not None else config.hidden_dropout_prob
) )
self.leaky_relu = nn.LeakyReLU()
self.dropout = nn.Dropout(classifier_dropout) self.dropout = nn.Dropout(classifier_dropout)
self.out_proj = nn.Linear(hidden_size, config.num_labels) self.out_proj = nn.Linear(hidden_size, config.num_labels)
@ -78,17 +77,17 @@ class RobertaLeaky(RobertaForSequenceClassification):
self.post_init() self.post_init()
def forward( def forward(
self, self,
input_ids: Optional[torch.LongTensor] = None, input_ids: Optional[torch.LongTensor] = None,
attention_mask: Optional[torch.FloatTensor] = None, attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids: Optional[torch.LongTensor] = None, token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None, position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None, head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None, inputs_embeds: Optional[torch.FloatTensor] = None,
labels: Optional[torch.LongTensor] = None, labels: Optional[torch.LongTensor] = None,
output_attentions: Optional[bool] = None, output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None, output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None, return_dict: Optional[bool] = None,
) -> Union[Tuple[torch.Tensor], SequenceClassifierOutput]: ) -> Union[Tuple[torch.Tensor], SequenceClassifierOutput]:
r""" r"""
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):