SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

fix #976

Browse Source
This commit is contained in:
LysandreJik
2019-08-08 10:38:57 -04:00
parent 7df303f5ad
commit f2b300df6b
3 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
pytorch_transformers/modeling_bert.py
View File

@@ -925,7 +925,7 @@ class BertForSequenceClassification(BertPreTrainedModel):
r""" r"""
**labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``: **labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
Labels for computing the sequence classification/regression loss. Labels for computing the sequence classification/regression loss.
Indices should be in ``[0, ..., config.num_labels]``. 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 regression loss is computed (Mean-Square loss),
If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy). If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy).
@@ -1099,7 +1099,7 @@ class BertForTokenClassification(BertPreTrainedModel):
r""" r"""
**labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``: **labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
Labels for computing the token classification loss. Labels for computing the token classification loss.
Indices should be in ``[0, ..., config.num_labels]``. Indices should be in ``[0, ..., config.num_labels - 1]``.
Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs: Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
**loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``: **loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:

2
pytorch_transformers/modeling_xlm.py
View File

@@ -784,7 +784,7 @@ class XLMForSequenceClassification(XLMPreTrainedModel):
r""" r"""
**labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``: **labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
Labels for computing the sequence classification/regression loss. Labels for computing the sequence classification/regression loss.
Indices should be in ``[0, ..., config.num_labels]``. 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 regression loss is computed (Mean-Square loss),
If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy). If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy).

2
pytorch_transformers/modeling_xlnet.py
View File

@@ -1075,7 +1075,7 @@ class XLNetForSequenceClassification(XLNetPreTrainedModel):
r""" r"""
**labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``: **labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
Labels for computing the sequence classification/regression loss. Labels for computing the sequence classification/regression loss.
Indices should be in ``[0, ..., config.num_labels]``. 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 regression loss is computed (Mean-Square loss),
If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy). If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy).