本文整理汇总了Python中allennlp.nn.util.get_lengths_from_binary_sequence_mask方法的典型用法代码示例。如果您正苦于以下问题:Python util.get_lengths_from_binary_sequence_mask方法的具体用法?Python util.get_lengths_from_binary_sequence_mask怎么用?Python util.get_lengths_from_binary_sequence_mask使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类allennlp.nn.util
的用法示例。
在下文中一共展示了util.get_lengths_from_binary_sequence_mask方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: forward
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def forward(self, tokens: torch.Tensor, mask: torch.BoolTensor = None):
if mask is not None:
tokens = tokens * mask.unsqueeze(-1)
# Our input has shape `(batch_size, num_tokens, embedding_dim)`, so we sum out the `num_tokens`
# dimension.
summed = tokens.sum(1)
if self._averaged:
if mask is not None:
lengths = get_lengths_from_binary_sequence_mask(mask)
length_mask = lengths > 0
# Set any length 0 to 1, to avoid dividing by zero.
lengths = torch.max(lengths, lengths.new_ones(1))
else:
lengths = tokens.new_full((1,), fill_value=tokens.size(1))
length_mask = None
summed = summed / lengths.unsqueeze(-1).float()
if length_mask is not None:
summed = summed * (length_mask > 0).unsqueeze(-1)
return summed
示例2: test_forward_pulls_out_correct_tensor_with_sequence_lengths
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def test_forward_pulls_out_correct_tensor_with_sequence_lengths(self):
lstm = LSTM(bidirectional=True, num_layers=3, input_size=3, hidden_size=7, batch_first=True)
encoder = PytorchSeq2SeqWrapper(lstm)
input_tensor = torch.rand([5, 7, 3])
input_tensor[1, 6:, :] = 0
input_tensor[2, 4:, :] = 0
input_tensor[3, 2:, :] = 0
input_tensor[4, 1:, :] = 0
mask = torch.ones(5, 7).bool()
mask[1, 6:] = False
mask[2, 4:] = False
mask[3, 2:] = False
mask[4, 1:] = False
sequence_lengths = get_lengths_from_binary_sequence_mask(mask)
packed_sequence = pack_padded_sequence(
input_tensor, sequence_lengths.data.tolist(), batch_first=True
)
lstm_output, _ = lstm(packed_sequence)
encoder_output = encoder(input_tensor, mask)
lstm_tensor, _ = pad_packed_sequence(lstm_output, batch_first=True)
assert_almost_equal(encoder_output.data.numpy(), lstm_tensor.data.numpy())
示例3: decode
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def decode(self, output_dict: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
head_tags = output_dict.pop("head_tags").cpu().detach().numpy()
heads = output_dict.pop("heads").cpu().detach().numpy()
mask = output_dict.pop("mask")
lengths = get_lengths_from_binary_sequence_mask(mask)
head_tag_labels = []
head_indices = []
for instance_heads, instance_tags, length in zip(heads, head_tags, lengths):
instance_heads = list(instance_heads[1:length])
instance_tags = instance_tags[1:length]
labels = [self.vocab.get_token_from_index(label, "head_tags")
for label in instance_tags]
head_tag_labels.append(labels)
head_indices.append(instance_heads)
output_dict["predicted_dependencies"] = head_tag_labels
output_dict["predicted_heads"] = head_indices
return output_dict
示例4: forward
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def forward(self, tokens , mask = None): #pylint: disable=arguments-differ
if mask is not None:
tokens = tokens * mask.unsqueeze(-1).float()
# Our input has shape `(batch_size, num_tokens, embedding_dim)`, so we sum out the `num_tokens`
# dimension.
summed = tokens.sum(1)
if self._averaged:
if mask is not None:
lengths = get_lengths_from_binary_sequence_mask(mask)
length_mask = (lengths > 0)
# Set any length 0 to 1, to avoid dividing by zero.
lengths = torch.max(lengths, lengths.new_ones(1))
else:
lengths = tokens.new_full((1,), fill_value=tokens.size(1))
length_mask = None
summed = summed / lengths.unsqueeze(-1).float()
if length_mask is not None:
summed = summed * (length_mask > 0).float().unsqueeze(-1)
return summed
示例5: decode
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def decode(self, output_dict ) :
u"""
Does constrained viterbi decoding on class probabilities output in :func:`forward`. The
constraint simply specifies that the output tags must be a valid BIO sequence. We add a
``"tags"`` key to the dictionary with the result.
"""
all_predictions = output_dict[u'class_probabilities']
sequence_lengths = get_lengths_from_binary_sequence_mask(output_dict[u"mask"]).data.tolist()
if all_predictions.dim() == 3:
predictions_list = [all_predictions[i].detach().cpu() for i in range(all_predictions.size(0))]
else:
predictions_list = [all_predictions]
all_tags = []
transition_matrix = self.get_viterbi_pairwise_potentials()
for predictions, length in izip(predictions_list, sequence_lengths):
max_likelihood_sequence, _ = viterbi_decode(predictions[:length], transition_matrix)
tags = [self.vocab.get_token_from_index(x, namespace=u"labels")
for x in max_likelihood_sequence]
all_tags.append(tags)
output_dict[u'tags'] = all_tags
return output_dict
示例6: decode
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def decode(self, output_dict ) :
head_tags = output_dict.pop(u"head_tags").cpu().detach().numpy()
heads = output_dict.pop(u"heads").cpu().detach().numpy()
mask = output_dict.pop(u"mask")
lengths = get_lengths_from_binary_sequence_mask(mask)
head_tag_labels = []
head_indices = []
for instance_heads, instance_tags, length in izip(heads, head_tags, lengths):
instance_heads = list(instance_heads[1:length])
instance_tags = instance_tags[1:length]
labels = [self.vocab.get_token_from_index(label, u"head_tags")
for label in instance_tags]
head_tag_labels.append(labels)
head_indices.append(instance_heads)
output_dict[u"predicted_dependencies"] = head_tag_labels
output_dict[u"predicted_heads"] = head_indices
return output_dict
示例7: test_forward_pulls_out_correct_tensor_with_sequence_lengths
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def test_forward_pulls_out_correct_tensor_with_sequence_lengths(self):
lstm = LSTM(bidirectional=True, num_layers=3, input_size=3, hidden_size=7, batch_first=True)
encoder = PytorchSeq2SeqWrapper(lstm)
input_tensor = torch.rand([5, 7, 3])
input_tensor[1, 6:, :] = 0
input_tensor[2, 4:, :] = 0
input_tensor[3, 2:, :] = 0
input_tensor[4, 1:, :] = 0
mask = torch.ones(5, 7)
mask[1, 6:] = 0
mask[2, 4:] = 0
mask[3, 2:] = 0
mask[4, 1:] = 0
sequence_lengths = get_lengths_from_binary_sequence_mask(mask)
packed_sequence = pack_padded_sequence(input_tensor, sequence_lengths.data.tolist(), batch_first=True)
lstm_output, _ = lstm(packed_sequence)
encoder_output = encoder(input_tensor, mask)
lstm_tensor, _ = pad_packed_sequence(lstm_output, batch_first=True)
assert_almost_equal(encoder_output.data.numpy(), lstm_tensor.data.numpy())
示例8: test_forward_pulls_out_correct_tensor_for_unsorted_batches
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def test_forward_pulls_out_correct_tensor_for_unsorted_batches(self):
lstm = LSTM(bidirectional=True, num_layers=3, input_size=3, hidden_size=7, batch_first=True)
encoder = PytorchSeq2SeqWrapper(lstm)
input_tensor = torch.rand([5, 7, 3])
input_tensor[0, 3:, :] = 0
input_tensor[1, 4:, :] = 0
input_tensor[2, 2:, :] = 0
input_tensor[3, 6:, :] = 0
mask = torch.ones(5, 7)
mask[0, 3:] = 0
mask[1, 4:] = 0
mask[2, 2:] = 0
mask[3, 6:] = 0
sequence_lengths = get_lengths_from_binary_sequence_mask(mask)
sorted_inputs, sorted_sequence_lengths, restoration_indices, _ = sort_batch_by_length(input_tensor,
sequence_lengths)
packed_sequence = pack_padded_sequence(sorted_inputs,
sorted_sequence_lengths.data.tolist(),
batch_first=True)
lstm_output, _ = lstm(packed_sequence)
encoder_output = encoder(input_tensor, mask)
lstm_tensor, _ = pad_packed_sequence(lstm_output, batch_first=True)
assert_almost_equal(encoder_output.data.numpy(),
lstm_tensor.index_select(0, restoration_indices).data.numpy())
示例9: test_forward_pulls_out_correct_tensor_with_sequence_lengths
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def test_forward_pulls_out_correct_tensor_with_sequence_lengths(self):
lstm = LSTM(bidirectional=True, num_layers=3, input_size=3, hidden_size=7, batch_first=True)
encoder = PytorchSeq2VecWrapper(lstm)
input_tensor = torch.rand([5, 7, 3])
input_tensor[1, 6:, :] = 0
input_tensor[2, 4:, :] = 0
input_tensor[3, 2:, :] = 0
input_tensor[4, 1:, :] = 0
mask = torch.ones(5, 7)
mask[1, 6:] = 0
mask[2, 4:] = 0
mask[3, 2:] = 0
mask[4, 1:] = 0
sequence_lengths = get_lengths_from_binary_sequence_mask(mask)
packed_sequence = pack_padded_sequence(input_tensor, sequence_lengths.tolist(), batch_first=True)
_, state = lstm(packed_sequence)
# Transpose output state, extract the last forward and backward states and
# reshape to be of dimension (batch_size, 2 * hidden_size).
reshaped_state = state[0].transpose(0, 1)[:, -2:, :].contiguous()
explicitly_concatenated_state = torch.cat([reshaped_state[:, 0, :].squeeze(1),
reshaped_state[:, 1, :].squeeze(1)], -1)
encoder_output = encoder(input_tensor, mask)
assert_almost_equal(encoder_output.data.numpy(), explicitly_concatenated_state.data.numpy())
示例10: test_forward_pulls_out_correct_tensor_for_unsorted_batches
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def test_forward_pulls_out_correct_tensor_for_unsorted_batches(self):
lstm = LSTM(bidirectional=True, num_layers=3, input_size=3, hidden_size=7, batch_first=True)
encoder = PytorchSeq2SeqWrapper(lstm)
input_tensor = torch.rand([5, 7, 3])
input_tensor[0, 3:, :] = 0
input_tensor[1, 4:, :] = 0
input_tensor[2, 2:, :] = 0
input_tensor[3, 6:, :] = 0
mask = torch.ones(5, 7).bool()
mask[0, 3:] = False
mask[1, 4:] = False
mask[2, 2:] = False
mask[3, 6:] = False
sequence_lengths = get_lengths_from_binary_sequence_mask(mask)
sorted_inputs, sorted_sequence_lengths, restoration_indices, _ = sort_batch_by_length(
input_tensor, sequence_lengths
)
packed_sequence = pack_padded_sequence(
sorted_inputs, sorted_sequence_lengths.data.tolist(), batch_first=True
)
lstm_output, _ = lstm(packed_sequence)
encoder_output = encoder(input_tensor, mask)
lstm_tensor, _ = pad_packed_sequence(lstm_output, batch_first=True)
assert_almost_equal(
encoder_output.data.numpy(),
lstm_tensor.index_select(0, restoration_indices).data.numpy(),
)
示例11: setup_method
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def setup_method(self):
super().setup_method()
self.lstm = LSTM(
bidirectional=True, num_layers=3, input_size=3, hidden_size=7, batch_first=True
)
self.rnn = RNN(
bidirectional=True, num_layers=3, input_size=3, hidden_size=7, batch_first=True
)
self.encoder_base = _EncoderBase(stateful=True)
tensor = torch.rand([5, 7, 3])
tensor[1, 6:, :] = 0
tensor[3, 2:, :] = 0
self.tensor = tensor
mask = torch.ones(5, 7).bool()
mask[1, 6:] = False
mask[2, :] = False # <= completely masked
mask[3, 2:] = False
mask[4, :] = False # <= completely masked
self.mask = mask
self.batch_size = 5
self.num_valid = 3
sequence_lengths = get_lengths_from_binary_sequence_mask(mask)
_, _, restoration_indices, sorting_indices = sort_batch_by_length(tensor, sequence_lengths)
self.sorting_indices = sorting_indices
self.restoration_indices = restoration_indices
示例12: test_forward_pulls_out_correct_tensor_with_sequence_lengths
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def test_forward_pulls_out_correct_tensor_with_sequence_lengths(self):
lstm = LSTM(bidirectional=True, num_layers=3, input_size=3, hidden_size=7, batch_first=True)
encoder = PytorchSeq2VecWrapper(lstm)
input_tensor = torch.rand([5, 7, 3])
input_tensor[1, 6:, :] = 0
input_tensor[2, 4:, :] = 0
input_tensor[3, 2:, :] = 0
input_tensor[4, 1:, :] = 0
mask = torch.ones(5, 7).bool()
mask[1, 6:] = False
mask[2, 4:] = False
mask[3, 2:] = False
mask[4, 1:] = False
sequence_lengths = get_lengths_from_binary_sequence_mask(mask)
packed_sequence = pack_padded_sequence(
input_tensor, sequence_lengths.tolist(), batch_first=True
)
_, state = lstm(packed_sequence)
# Transpose output state, extract the last forward and backward states and
# reshape to be of dimension (batch_size, 2 * hidden_size).
reshaped_state = state[0].transpose(0, 1)[:, -2:, :].contiguous()
explicitly_concatenated_state = torch.cat(
[reshaped_state[:, 0, :].squeeze(1), reshaped_state[:, 1, :].squeeze(1)], -1
)
encoder_output = encoder(input_tensor, mask)
assert_almost_equal(encoder_output.data.numpy(), explicitly_concatenated_state.data.numpy())
示例13: test_get_sequence_lengths_from_binary_mask
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def test_get_sequence_lengths_from_binary_mask(self):
binary_mask = torch.tensor(
[
[True, True, True, False, False, False],
[True, True, False, False, False, False],
[True, True, True, True, True, True],
[True, False, False, False, False, False],
]
)
lengths = util.get_lengths_from_binary_sequence_mask(binary_mask)
numpy.testing.assert_array_equal(lengths.numpy(), numpy.array([3, 2, 6, 1]))
示例14: test_get_sequence_lengths_converts_to_long_tensor_and_avoids_variable_overflow
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def test_get_sequence_lengths_converts_to_long_tensor_and_avoids_variable_overflow(self):
# Tests the following weird behaviour in Pytorch 0.1.12
# doesn't happen for our sequence masks:
#
# mask = torch.ones([260]).bool()
# mask.sum() # equals 260.
# var_mask = t.a.V(mask)
# var_mask.sum() # equals 4, due to 8 bit precision - the sum overflows.
binary_mask = torch.ones(2, 260).bool()
lengths = util.get_lengths_from_binary_sequence_mask(binary_mask)
numpy.testing.assert_array_equal(lengths.data.numpy(), numpy.array([260, 260]))
示例15: get_length_and_mask
# 需要导入模块: from allennlp.nn import util [as 别名]
# 或者: from allennlp.nn.util import get_lengths_from_binary_sequence_mask [as 别名]
def get_length_and_mask(seq):
len_mask = (seq != 0).long()
len_t = get_lengths_from_binary_sequence_mask(len_mask)
return len_mask, len_t