def load_pretrained_embeddings(self, vocabulary, path):
File_object = open(r"results.txt", "a")
"""
Loads GloVe vectors and initializes the embedding matrix.
Args:
vocabulary: `Vocabulary` object.
path: Embedding path, e.g. "glove/glove.6B.300d.txt".
"""
embedding_map = load_cached_embeddings(path)
# Create embedding matrix. By default, embeddings are randomly
# initialized from Uniform(-0.1, 0.1).
embeddings = torch.zeros(
(len(vocabulary), self.args.embedding_dim)).uniform_(-0.1, 0.1)
# Initialize pre-trained embeddings.
num_pretrained = 0
for (i, word) in enumerate(vocabulary.words):
if word in embedding_map:
embeddings[i] = torch.tensor(embedding_map[word])
num_pretrained += 1
# Place embedding matrix on GPU.
self.embedding.weight.data = cuda(self.args, embeddings)
return num_pretrained
def load_pretrained_embeddings(self, vocabulary, path):
"""
Loads GloVe vectors and initializes the embedding matrix.
Args:
vocabulary: `Vocabulary` object.
path: Embedding path, e.g. "glove/glove.6B.300d.txt".
"""
if path == 'glove/biowordvec_train.vec.bin':
print('Using Bio2Word Embedding')
embedding_map = KeyedVectors.load_word2vec_format(path,
binary=True,
limit=100000)
else:
print('Using GloVe')
embedding_map = load_cached_embeddings(path)
# Create embedding matrix. By default, embeddings are randomly
# initialized from Uniform(-0.1, 0.1).
embeddings = torch.zeros(
(len(vocabulary), self.args.embedding_dim)).uniform_(-0.1, 0.1)
# Initialize pre-trained embeddings.
num_pretrained = 0
for (i, word) in enumerate(vocabulary.words):
if word in embedding_map:
embeddings[i] = torch.tensor(embedding_map[word])
num_pretrained += 1
# Place embedding matrix on GPU.
self.embedding.weight.data = cuda(self.args, embeddings)
return num_pretrained
def load_input_data(self, dataset_root_folder, word_vectors_cache_file, \
train_set_folder, dev_set_folder, test_set_folder, load_ext_feats=True):
for set_folder in [test_set_folder, dev_set_folder, train_set_folder]:
if set_folder:
questions, sentences, labels, maxlen_q, maxlen_s, vocab = \
utils.read_in_dataset(dataset_root_folder, set_folder)
self.data_splits[set_folder] = [
questions, sentences, labels, maxlen_q, maxlen_s
]
default_ext_feats = [np.zeros(4)] * len(
self.data_splits[set_folder][0])
self.data_splits[set_folder].append(default_ext_feats)
utils.load_cached_embeddings(
word_vectors_cache_file, vocab, self.embeddings,
[] if "train" in set_folder else self.unk_term)
def load_input_data(self, dataset_root_folder, word_vectors_cache_file,
train_set_folder, dev_set_folder, test_set_folder):
for set_folder in [test_set_folder, dev_set_folder, train_set_folder]:
if set_folder:
self.datasets[set_folder] = utils.read_in_dataset(
dataset_root_folder, set_folder)
# NOTE: self.datasets[set_folder] = questions, sentences, labels, vocab, maxlen_q, maxlen_s, ext_feats
self.embeddings[set_folder] = utils.load_cached_embeddings(
word_vectors_cache_file, self.datasets[set_folder][3],
[] if "train" in set_folder else self.unk_term)
def load_pretrained_embeddings(self, vocabulary, path, sentences):
"""
Loads GloVe vectors and initializes the embedding matrix.
Args:
vocabulary: `Vocabulary` object.
path: Embedding path, e.g. "glove/glove.6B.300d.txt".
"""
self.vocabulary = vocabulary
'''options_file = "https://s3-us-west-2.amazonaws.com/allennlp/models/elmo/2x4096_512_2048cnn_2xhighway/elmo_2x4096_512_2048cnn_2xhighway_options.json"
weight_file = "https://s3-us-west-2.amazonaws.com/allennlp/models/elmo/2x4096_512_2048cnn_2xhighway/elmo_2x4096_512_2048cnn_2xhighway_weights.hdf5"
# Note the "1", since we want only 1 output representation for each token.
elmo = Elmo(options_file, weight_file, 1, dropout=0)
print ("made it here the prequel")
sentences = sentences[0:5]
print (sentences)
character_ids = batch_to_ids(sentences)
print ("made it here")
print ("charids: " + str(character_ids))
embeddings = elmo(character_ids)'''
#return len(vocabulary)
embedding_map = load_cached_embeddings(path)
# Create embedding matrix. By default, embeddings are randomly
# initialized from Uniform(-0.1, 0.1).
embeddings = torch.zeros(
(len(vocabulary), self.args.embedding_dim)).uniform_(-0.1, 0.1)
# Initialize pre-trained embeddings.
num_pretrained = 0
for (i, word) in enumerate(vocabulary.words):
if word in embedding_map:
embeddings[i] = torch.tensor(embedding_map[word])
num_pretrained += 1
# Place embedding matrix on GPU.
self.embedding.weight.data = cuda(self.args, embeddings)
return num_pretrained