本文整理汇总了Python中allennlp.modules.elmo.batch_to_ids方法的典型用法代码示例。如果您正苦于以下问题:Python elmo.batch_to_ids方法的具体用法?Python elmo.batch_to_ids怎么用?Python elmo.batch_to_ids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.modules.elmo
的用法示例。
在下文中一共展示了elmo.batch_to_ids方法的10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: batchify
# 需要导入模块: from allennlp.modules import elmo [as 别名]
# 或者: from allennlp.modules.elmo import batch_to_ids [as 别名]
def batchify(x_data, y_data, batch_size=128, shuffle=False):
batches = []
for i in range(0, len(x_data), batch_size):
start, stop = i, i + batch_size
x_batch = batch_to_ids(x_data[start:stop])
lengths = Variable(torch.from_numpy(np.array([max(len(x), 1) for x in x_data[start:stop]])).float()).view(-1, 1)
if CUDA:
y_batch = Variable(torch.from_numpy(np.array(y_data[start:stop])).cuda())
else:
y_batch = Variable(torch.from_numpy(np.array(y_data[start:stop])))
batches.append((x_batch, y_batch, lengths))
if shuffle:
random.shuffle(batches)
return batches
示例2: forward
# 需要导入模块: from allennlp.modules import elmo [as 别名]
# 或者: from allennlp.modules.elmo import batch_to_ids [as 别名]
def forward(self, lines: List[Line]):
texts = []
for line in lines:
line_tokens = line.tokens[self.word_tokens_namespace]
line_tokens = list(map(lambda tok: tok.text, line_tokens))
texts.append(line_tokens)
character_ids = batch_to_ids(texts)
character_ids = character_ids.to(self.device)
output_dict = self.elmo(character_ids)
# batch_size, max_seq_length * 1024
embeddings = output_dict["elmo_representations"][0]
return embeddings
示例3: emb
# 需要导入模块: from allennlp.modules import elmo [as 别名]
# 或者: from allennlp.modules.elmo import batch_to_ids [as 别名]
def emb(self, word, default=None):
from allennlp.modules.elmo import batch_to_ids
idx = batch_to_ids([[word]])
emb = self.embeddings(idx)['token_embedding']
return emb[0, 1].tolist()
示例4: test_batch_to_char_ids
# 需要导入模块: from allennlp.modules import elmo [as 别名]
# 或者: from allennlp.modules.elmo import batch_to_ids [as 别名]
def test_batch_to_char_ids():
sentences = [
["This", "is", "a", "sentence"],
["Here", "'s", "one"],
["Another", "one"],
]
t1 = utils.batch_to_char_ids(sentences)
t2 = batch_to_ids(sentences)
np.testing.assert_array_equal(t1.numpy(), t2.numpy())
sentences = [["one"]]
t1 = utils.batch_to_char_ids(sentences)
t2 = batch_to_ids(sentences)
np.testing.assert_array_equal(t1.numpy(), t2.numpy())
示例5: forward
# 需要导入模块: from allennlp.modules import elmo [as 别名]
# 或者: from allennlp.modules.elmo import batch_to_ids [as 别名]
def forward(self, batch):
questions = [q.split() for q in batch['question']]
question_ids = batch_to_ids(questions).cuda()
elmo_vectors = self.elmo(question_ids)
cnn_vector = self.cnn_encoder(elmo_vectors['elmo_representations'][0], elmo_vectors['mask'])
loss = self.loss(cnn_vector, batch['class'].cuda())
preds = torch.argmax(cnn_vector, dim=1)
softmax = torch.nn.functional.softmax(cnn_vector, dim=1)
return loss, preds, softmax
示例6: batch_to_embeddings
# 需要导入模块: from allennlp.modules import elmo [as 别名]
# 或者: from allennlp.modules.elmo import batch_to_ids [as 别名]
def batch_to_embeddings(self, batch ) :
u"""
Parameters
----------
batch : ``List[List[str]]``, required
A list of tokenized sentences.
Returns
-------
A tuple of tensors, the first representing activations (batch_size, 3, num_timesteps, 1024) and
the second a mask (batch_size, num_timesteps).
"""
character_ids = batch_to_ids(batch)
if self.cuda_device >= 0:
character_ids = character_ids.cuda(device=self.cuda_device)
bilm_output = self.elmo_bilm(character_ids)
layer_activations = bilm_output[u'activations']
mask_with_bos_eos = bilm_output[u'mask']
# without_bos_eos is a 3 element list of (activation, mask) tensor pairs,
# each with size (batch_size, num_timesteps, dim and (batch_size, num_timesteps)
# respectively.
without_bos_eos = [remove_sentence_boundaries(layer, mask_with_bos_eos)
for layer in layer_activations]
# Converts a list of pairs (activation, mask) tensors to a single tensor of activations.
activations = torch.cat([ele[0].unsqueeze(1) for ele in without_bos_eos], dim=1)
# The mask is the same for each ELMo vector, so just take the first.
mask = without_bos_eos[0][1]
return activations, mask
示例7: elmo_process
# 需要导入模块: from allennlp.modules import elmo [as 别名]
# 或者: from allennlp.modules.elmo import batch_to_ids [as 别名]
def elmo_process(batch, device):
elmo_tensor = batch_to_ids(batch)
elmo_tensor = elmo_tensor.to(device=device)
torchtext_tensor = torchtext_process(batch, device)
return (elmo_tensor, torchtext_tensor)
示例8: transform
# 需要导入模块: from allennlp.modules import elmo [as 别名]
# 或者: from allennlp.modules.elmo import batch_to_ids [as 别名]
def transform(self, X, y=None):
"""Transform documents to document ids.
Uses the vocabulary learned by fit.
Args:
X : iterable
an iterable which yields either str, unicode or file objects.
y : iterabl, label strings.
Returns:
features: document id matrix.
y: label id matrix.
"""
word_ids = [self._word_vocab.doc2id(doc) for doc in X]
word_ids = pad_sequences(word_ids, padding='post')
char_ids = [[self._char_vocab.doc2id(w) for w in doc] for doc in X]
char_ids = pad_nested_sequences(char_ids)
character_ids = batch_to_ids(X)
elmo_embeddings = self._elmo(character_ids)['elmo_representations'][1]
elmo_embeddings = elmo_embeddings.detach().numpy()
features = [word_ids, char_ids, elmo_embeddings]
if y is not None:
y = [self._label_vocab.doc2id(doc) for doc in y]
y = pad_sequences(y, padding='post')
y = to_categorical(y, self.label_size).astype(int)
# In 2018/06/01, to_categorical is a bit strange.
# >>> to_categorical([[1,3]], num_classes=4).shape
# (1, 2, 4)
# >>> to_categorical([[1]], num_classes=4).shape
# (1, 4)
# So, I expand dimensions when len(y.shape) == 2.
y = y if len(y.shape) == 3 else np.expand_dims(y, axis=0)
return features, y
else:
return features
示例9: forward
# 需要导入模块: from allennlp.modules import elmo [as 别名]
# 或者: from allennlp.modules.elmo import batch_to_ids [as 别名]
def forward(self, batch_text):
# batch_char = batch_to_ids(batch_text)
return self.elmo(batch_text)['elmo_representations']
示例10: create_cached_cnn_embeddings
# 需要导入模块: from allennlp.modules import elmo [as 别名]
# 或者: from allennlp.modules.elmo import batch_to_ids [as 别名]
def create_cached_cnn_embeddings(self, tokens: List[str]) -> None:
"""
Given a list of tokens, this method precomputes word representations
by running just the character convolutions and highway layers of elmo,
essentially creating uncontextual word vectors. On subsequent forward passes,
the word ids are looked up from an embedding, rather than being computed on
the fly via the CNN encoder.
This function sets 3 attributes:
_word_embedding : ``torch.Tensor``
The word embedding for each word in the tokens passed to this method.
_bos_embedding : ``torch.Tensor``
The embedding for the BOS token.
_eos_embedding : ``torch.Tensor``
The embedding for the EOS token.
Parameters
----------
tokens : ``List[str]``, required.
A list of tokens to precompute character convolutions for.
"""
tokens = [ELMoCharacterMapper.bos_token, ELMoCharacterMapper.eos_token] + tokens
timesteps = 32
batch_size = 32
chunked_tokens = lazy_groups_of(iter(tokens), timesteps)
all_embeddings = []
device = get_device_of(next(self.parameters()))
for batch in lazy_groups_of(chunked_tokens, batch_size):
# Shape (batch_size, timesteps, 50)
batched_tensor = batch_to_ids(batch)
# NOTE: This device check is for when a user calls this method having
# already placed the model on a device. If this is called in the
# constructor, it will probably happen on the CPU. This isn't too bad,
# because it's only a few convolutions and will likely be very fast.
if device >= 0:
batched_tensor = batched_tensor.cuda(device)
output = self._token_embedder(batched_tensor, add_bos=False, add_eos=False)
token_embedding = output["token_embedding"]
mask = output["mask"]
token_embedding, _ = remove_sentence_boundaries(token_embedding, mask, rmv_bos=False, rmv_eos=False)
all_embeddings.append(token_embedding.view(-1, token_embedding.size(-1)))
full_embedding = torch.cat(all_embeddings, 0)
# We might have some trailing embeddings from padding in the batch, so
# we clip the embedding and lookup to the right size.
full_embedding = full_embedding[:len(tokens), :]
embedding = full_embedding[2:len(tokens), :]
vocab_size, embedding_dim = list(embedding.size())
from allennlp.modules.token_embedders import Embedding # type: ignore
self._bos_embedding = full_embedding[0, :]
self._eos_embedding = full_embedding[1, :]
self._word_embedding = Embedding(vocab_size, # type: ignore
embedding_dim,
weight=embedding.data,
trainable=self._requires_grad,
padding_index=0)