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

Merge branch 'master' into run_multiple_choice_merge

Browse Source 
# Please enter a commit message to explain why this merge is necessary,
# especially if it merges an updated upstream into a topic branch.
#
# Lines starting with '#' will be ignored, and an empty message aborts
# the commit.
This commit is contained in:
erenup
2019-09-18 21:43:46 +08:00
parent 15143fbad6 5a81e79e25
commit 46ffc28329
5 changed files with 198 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
pytorch_transformers/modeling_roberta.py
View File

@@ -296,7 +296,7 @@ class RobertaForSequenceClassification(BertPreTrainedModel):
Examples::
tokenizer = RoertaTokenizer.from_pretrained('roberta-base')
tokenizer = RobertaTokenizer.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
@@ -338,8 +338,75 @@ class RobertaForSequenceClassification(BertPreTrainedModel):
return outputs # (loss), logits, (hidden_states), (attentions)
@add_start_docstrings("""Roberta Model with a multiple choice classification head on top (a linear layer on top of
the pooled output and a softmax) e.g. for RocStories/SWAG tasks. """,
ROBERTA_START_DOCSTRING, ROBERTA_INPUTS_DOCSTRING)
class RobertaForMultipleChoice(BertPreTrainedModel):
r"""
Inputs:
**input_ids**: ``torch.LongTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
Indices of input sequence tokens in the vocabulary.
The second dimension of the input (`num_choices`) indicates the number of choices to score.
To match pre-training, RoBerta input sequence should be formatted with [CLS] and [SEP] tokens as follows:
(a) For sequence pairs:
``tokens: [CLS] is this jack ##son ##ville ? [SEP] [SEP] no it is not . [SEP]``
``token_type_ids: 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1``
(b) For single sequences:
``tokens: [CLS] the dog is hairy . [SEP]``
``token_type_ids: 0 0 0 0 0 0 0``
Indices can be obtained using :class:`pytorch_transformers.BertTokenizer`.
See :func:`pytorch_transformers.PreTrainedTokenizer.encode` and
:func:`pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids` for details.
**token_type_ids**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
Segment token indices to indicate first and second portions of the inputs.
The second dimension of the input (`num_choices`) indicates the number of choices to score.
Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
**attention_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
Mask to avoid performing attention on padding token indices.
The second dimension of the input (`num_choices`) indicates the number of choices to score.
Mask values selected in ``[0, 1]``:
``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
**head_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``:
Mask to nullify selected heads of the self-attention modules.
Mask values selected in ``[0, 1]``:
``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
**labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
Labels for computing the multiple choice classification loss.
Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
of the input tensors. (see `input_ids` above)
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 loss.
**classification_scores**: ``torch.FloatTensor`` of shape ``(batch_size, num_choices)`` where `num_choices` is the size of the second dimension
of the input tensors. (see `input_ids` above).
Classification 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 = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaForMultipleChoice.from_pretrained('roberta-base')
choices = ["Hello, my dog is cute", "Hello, my cat is amazing"]
input_ids = torch.tensor([tokenizer.encode(s, add_special_tokens=True) for s in choices]).unsqueeze(0) # Batch size 1, 2 choices
labels = torch.tensor(1).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=labels)
loss, classification_scores = outputs[:2]
"""
config_class = RobertaConfig
pretrained_model_archive_map = ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP
base_model_prefix = "roberta"
@@ -351,7 +418,7 @@ class RobertaForMultipleChoice(BertPreTrainedModel):
self.dropout = nn.Dropout(config.hidden_dropout_prob)
self.classifier = nn.Linear(config.hidden_size, 1)
self.apply(self.init_weights)
self.init_weights()
def forward(self, input_ids, token_type_ids=None, attention_mask=None, labels=None,
position_ids=None, head_mask=None):

53
pytorch_transformers/modeling_xlnet.py
View File

@@ -1011,9 +1011,56 @@ class XLNetForSequenceClassification(XLNetPreTrainedModel):
return outputs # return (loss), logits, mems, (hidden states), (attentions)
@add_start_docstrings("""XLNet Model with a multiple choice classification head on top (a linear layer on top of
the pooled output and a softmax) e.g. for RACE/SWAG tasks. """,
XLNET_START_DOCSTRING, XLNET_INPUTS_DOCSTRING)
class XLNetForMultipleChoice(XLNetPreTrainedModel):
r"""
Inputs:
**input_ids**: ``torch.LongTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
Indices of input sequence tokens in the vocabulary.
The second dimension of the input (`num_choices`) indicates the number of choices to scores.
**token_type_ids**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
Segment token indices to indicate first and second portions of the inputs.
The second dimension of the input (`num_choices`) indicates the number of choices to score.
Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
**attention_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
Mask to avoid performing attention on padding token indices.
The second dimension of the input (`num_choices`) indicates the number of choices to score.
Mask values selected in ``[0, 1]``:
``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
**head_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``:
Mask to nullify selected heads of the self-attention modules.
Mask values selected in ``[0, 1]``:
``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
**labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
Labels for computing the multiple choice classification loss.
Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
of the input tensors. (see `input_ids` above)
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 loss.
**classification_scores**: ``torch.FloatTensor`` of shape ``(batch_size, num_choices)`` where `num_choices` is the size of the second dimension
of the input tensors. (see `input_ids` above).
Classification 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 = XLNetTokenizer.from_pretrained('xlnet-base-cased')
model = XLNetForMultipleChoice.from_pretrained('xlnet-base-cased')
choices = ["Hello, my dog is cute", "Hello, my cat is amazing"]
input_ids = torch.tensor([tokenizer.encode(s) for s in choices]).unsqueeze(0) # Batch size 1, 2 choices
labels = torch.tensor(1).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=labels)
loss, classification_scores = outputs[:2]
"""
def __init__(self, config):
@@ -1023,7 +1070,7 @@ class XLNetForMultipleChoice(XLNetPreTrainedModel):
self.sequence_summary = SequenceSummary(config)
self.logits_proj = nn.Linear(config.d_model, 1)
self.apply(self.init_weights)
self.init_weights()
def forward(self, input_ids, token_type_ids=None, input_mask=None, attention_mask=None,
mems=None, perm_mask=None, target_mapping=None,
@@ -1110,7 +1157,7 @@ class XLNetForQuestionAnswering(XLNetPreTrainedModel):
Examples::
tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
tokenizer = XLNetTokenizer.from_pretrained('xlnet-large-cased')
model = XLMForQuestionAnswering.from_pretrained('xlnet-large-cased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0) # Batch size 1
start_positions = torch.tensor([1])