def load_embeddings(self, src_embeddings, tgt_embeddings,
vocabulary: Vocabulary):
aligned_embeddings = torch.div(torch.randn(vocabulary.size(), 300), 10)
found_count = 0
for i in range(len(vocabulary.index2word)):
word = vocabulary.get_word(i)
language = vocabulary.get_language(i)
if language == "src" and word in src_embeddings.wv:
aligned_embeddings[i] = torch.FloatTensor(
src_embeddings.wv[word])
found_count += 1
elif language == "src" and word.lower() in src_embeddings.wv:
aligned_embeddings[i] = torch.FloatTensor(
src_embeddings.wv[word.lower()])
found_count += 1
if language == "tgt" and word in tgt_embeddings.wv:
aligned_embeddings[i] = torch.FloatTensor(
tgt_embeddings.wv[word])
found_count += 1
elif language == "tgt" and word.lower() in tgt_embeddings.wv:
aligned_embeddings[i] = torch.FloatTensor(
tgt_embeddings.wv[word.lower()])
found_count += 1
logger.info("Embeddings filled: " + str(found_count) + " of " +
str(vocabulary.size()))
enable_training = self.encoder.embedding.weight.requires_grad
self.encoder.embedding.weight = nn.Parameter(
aligned_embeddings, requires_grad=enable_training)
self.decoder.embedding.weight = nn.Parameter(
aligned_embeddings, requires_grad=enable_training)
def __init__(self, vocabulary: Vocabulary, use_cuda):
weight = torch.ones(vocabulary.size())
weight[vocabulary.get_pad("src")] = 0
weight[vocabulary.get_pad("tgt")] = 0
weight = weight.cuda() if use_cuda else weight
self.criterion = nn.NLLLoss(weight, size_average=False)
