Python allennlp.modules.InputVariationalDropout() Examples
The following are 6
code examples of allennlp.modules.InputVariationalDropout().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
allennlp.modules
, or try the search function
.
.
Example #1
| Source File: esim_comparator.py From multee with Apache License 2.0 | 6 votes |
|
def __init__(self,
encoder: Seq2SeqEncoder,
projection_feedforward: FeedForward,
inference_encoder: Seq2SeqEncoder,
output_feedforward: FeedForward,
similarity_function: SimilarityFunction = None,
dropout: float = 0.5) -> None:
super().__init__()
self._encoder = encoder
self._matrix_attention = LegacyMatrixAttention(similarity_function)
self._projection_feedforward = projection_feedforward
self._inference_encoder = inference_encoder
if dropout:
self.dropout = torch.nn.Dropout(dropout)
self.rnn_input_dropout = InputVariationalDropout(dropout)
else:
self.dropout = None
self.rnn_input_dropout = None
self._output_feedforward = output_feedforward
Example #2
| Source File: esim_comparator.py From multee with Apache License 2.0 | 6 votes |
|
def __init__(self,
projection_feedforward: FeedForward,
inference_encoder: Seq2SeqEncoder,
output_feedforward: FeedForward,
dropout: float = 0.5) -> None:
super().__init__()
if dropout:
self.dropout = torch.nn.Dropout(dropout)
self.rnn_input_dropout = InputVariationalDropout(dropout)
else:
self.dropout = None
self.rnn_input_dropout = None
self._projection_feedforward = projection_feedforward
self._inference_encoder = inference_encoder
self._output_feedforward = output_feedforward
# self._weight_premise_token = weight_premise_token
Example #3
| Source File: esim_comparator.py From multee with Apache License 2.0 | 5 votes |
|
def __init__(self,
encoder: Seq2SeqEncoder,
dropout: float = 0.5) -> None:
super().__init__()
self._encoder = encoder
if dropout:
self.dropout = torch.nn.Dropout(dropout)
self.rnn_input_dropout = InputVariationalDropout(dropout)
else:
self.dropout = None
self.rnn_input_dropout = None
Example #4
| Source File: model.py From HGL-pytorch with MIT License | 4 votes |
|
def __init__(self,
vocab: Vocabulary,
span_encoder: Seq2SeqEncoder,
reasoning_encoder: Seq2SeqEncoder,
input_dropout: float = 0.3,
hidden_dim_maxpool: int = 1024,
class_embs: bool = True,
reasoning_use_obj: bool = True,
reasoning_use_answer: bool = True,
reasoning_use_question: bool = True,
pool_reasoning: bool = True,
pool_answer: bool = True,
pool_question: bool = False,
initializer: InitializerApplicator = InitializerApplicator(),
):
super(HGL_Model, self).__init__(vocab)
self.detector = SimpleDetector(pretrained=True, average_pool=True, semantic=class_embs, final_dim=512)
###################################################################################################
self.rnn_input_dropout = TimeDistributed(InputVariationalDropout(input_dropout)) if input_dropout > 0 else None
self.span_encoder = TimeDistributed(span_encoder)
self.reasoning_encoder = TimeDistributed(reasoning_encoder)
self.Graph_reasoning = Graph_reasoning(512)
self.QAHG = BilinearMatrixAttention(
matrix_1_dim=span_encoder.get_output_dim(),
matrix_2_dim=span_encoder.get_output_dim(),
)
self.VAHG = BilinearMatrixAttention(
matrix_1_dim=span_encoder.get_output_dim(),
matrix_2_dim=self.detector.final_dim,
)
self.reasoning_use_obj = reasoning_use_obj
self.reasoning_use_answer = reasoning_use_answer
self.reasoning_use_question = reasoning_use_question
self.pool_reasoning = pool_reasoning
self.pool_answer = pool_answer
self.pool_question = pool_question
dim = sum([d for d, to_pool in [(reasoning_encoder.get_output_dim(), self.pool_reasoning),
(span_encoder.get_output_dim(), self.pool_answer),
(span_encoder.get_output_dim(), self.pool_question)] if to_pool])
self.final_mlp = torch.nn.Sequential(
torch.nn.Dropout(input_dropout, inplace=False),
torch.nn.Linear(dim, hidden_dim_maxpool),
torch.nn.ReLU(inplace=True),
torch.nn.Dropout(input_dropout, inplace=False),
torch.nn.Linear(hidden_dim_maxpool, 1),
)
self._accuracy = CategoricalAccuracy()
self._loss = torch.nn.CrossEntropyLoss()
initializer(self)
Example #5
| Source File: esim.py From magnitude with MIT License | 4 votes |
|
def __init__(self, vocab ,
text_field_embedder ,
encoder ,
similarity_function ,
projection_feedforward ,
inference_encoder ,
output_feedforward ,
output_logit ,
dropout = 0.5,
initializer = InitializerApplicator(),
regularizer = None) :
super(ESIM, self).__init__(vocab, regularizer)
self._text_field_embedder = text_field_embedder
self._encoder = encoder
self._matrix_attention = LegacyMatrixAttention(similarity_function)
self._projection_feedforward = projection_feedforward
self._inference_encoder = inference_encoder
if dropout:
self.dropout = torch.nn.Dropout(dropout)
self.rnn_input_dropout = InputVariationalDropout(dropout)
else:
self.dropout = None
self.rnn_input_dropout = None
self._output_feedforward = output_feedforward
self._output_logit = output_logit
self._num_labels = vocab.get_vocab_size(namespace=u"labels")
check_dimensions_match(text_field_embedder.get_output_dim(), encoder.get_input_dim(),
u"text field embedding dim", u"encoder input dim")
check_dimensions_match(encoder.get_output_dim() * 4, projection_feedforward.get_input_dim(),
u"encoder output dim", u"projection feedforward input")
check_dimensions_match(projection_feedforward.get_output_dim(), inference_encoder.get_input_dim(),
u"proj feedforward output dim", u"inference lstm input dim")
self._accuracy = CategoricalAccuracy()
self._loss = torch.nn.CrossEntropyLoss()
initializer(self)
Example #6
| Source File: model.py From r2c with MIT License | 4 votes |
|
def __init__(self,
vocab: Vocabulary,
span_encoder: Seq2SeqEncoder,
reasoning_encoder: Seq2SeqEncoder,
input_dropout: float = 0.3,
hidden_dim_maxpool: int = 1024,
class_embs: bool=True,
reasoning_use_obj: bool=True,
reasoning_use_answer: bool=True,
reasoning_use_question: bool=True,
pool_reasoning: bool = True,
pool_answer: bool = True,
pool_question: bool = False,
initializer: InitializerApplicator = InitializerApplicator(),
):
super(AttentionQA, self).__init__(vocab)
self.detector = SimpleDetector(pretrained=True, average_pool=True, semantic=class_embs, final_dim=512)
###################################################################################################
self.rnn_input_dropout = TimeDistributed(InputVariationalDropout(input_dropout)) if input_dropout > 0 else None
self.span_encoder = TimeDistributed(span_encoder)
self.reasoning_encoder = TimeDistributed(reasoning_encoder)
self.span_attention = BilinearMatrixAttention(
matrix_1_dim=span_encoder.get_output_dim(),
matrix_2_dim=span_encoder.get_output_dim(),
)
self.obj_attention = BilinearMatrixAttention(
matrix_1_dim=span_encoder.get_output_dim(),
matrix_2_dim=self.detector.final_dim,
)
self.reasoning_use_obj = reasoning_use_obj
self.reasoning_use_answer = reasoning_use_answer
self.reasoning_use_question = reasoning_use_question
self.pool_reasoning = pool_reasoning
self.pool_answer = pool_answer
self.pool_question = pool_question
dim = sum([d for d, to_pool in [(reasoning_encoder.get_output_dim(), self.pool_reasoning),
(span_encoder.get_output_dim(), self.pool_answer),
(span_encoder.get_output_dim(), self.pool_question)] if to_pool])
self.final_mlp = torch.nn.Sequential(
torch.nn.Dropout(input_dropout, inplace=False),
torch.nn.Linear(dim, hidden_dim_maxpool),
torch.nn.ReLU(inplace=True),
torch.nn.Dropout(input_dropout, inplace=False),
torch.nn.Linear(hidden_dim_maxpool, 1),
)
self._accuracy = CategoricalAccuracy()
self._loss = torch.nn.CrossEntropyLoss()
initializer(self)
