def test_get_embedding_layer_uses_correct_embedding_dim(self):
vocab = Vocabulary()
vocab.add_token_to_namespace('word1')
vocab.add_token_to_namespace('word2')
embeddings_filename = str(self.TEST_DIR / "embeddings.gz")
with gzip.open(embeddings_filename, 'wb') as embeddings_file:
embeddings_file.write("word1 1.0 2.3 -1.0\n".encode('utf-8'))
embeddings_file.write("word2 0.1 0.4 -4.0\n".encode('utf-8'))
embedding_weights = _read_pretrained_embedding_file(embeddings_filename, 3, vocab)
assert tuple(embedding_weights.size()) == (4, 3) # 4 because of padding and OOV
with pytest.raises(ConfigurationError):
_read_pretrained_embedding_file(embeddings_filename, 4, vocab)
def test_get_embedding_layer_uses_correct_embedding_dim(self):
vocab = Vocabulary()
vocab.add_token_to_namespace('word1')
vocab.add_token_to_namespace('word2')
embeddings_filename = self.TEST_DIR + "embeddings.gz"
with gzip.open(embeddings_filename, 'wb') as embeddings_file:
embeddings_file.write("word1 1.0 2.3 -1.0\n".encode('utf-8'))
embeddings_file.write("word2 0.1 0.4 -4.0\n".encode('utf-8'))
embedding_weights = _read_pretrained_embedding_file(embeddings_filename, 3, vocab)
assert tuple(embedding_weights.size()) == (4, 3) # 4 because of padding and OOV
with pytest.raises(ConfigurationError):
_read_pretrained_embedding_file(embeddings_filename, 4, vocab)