def __init__(self,
my_device=torch.device('cuda:2'),
model_name='roberta.hdf5',
model_path=current_directory_path +
'/external_pretrained_models/'):
self.answ = "UNKNOWN ERROR"
self.model_name = model_name
self.model_path = model_path
self.first_object = ''
self.second_object = ''
self.predicates = ''
self.aspects = ''
cuda_device = my_device
self.spans = [
] # we can't use set because span object is dict and dict is unchashable. We add function add_span to keep non-repeatability
try:
print(self.model_path + self.model_name)
print(model_path + "vocab_dir")
vocab = Vocabulary.from_files(model_path + "vocab_dir")
BERT_MODEL = 'google/electra-base-discriminator'
embedder = PretrainedTransformerMismatchedEmbedder(
model_name=BERT_MODEL)
text_field_embedder = BasicTextFieldEmbedder({'tokens': embedder})
seq2seq_encoder = PassThroughEncoder(
input_dim=embedder.get_output_dim())
print("encoder loaded")
self.indexer = PretrainedTransformerMismatchedIndexer(
model_name=BERT_MODEL)
print("indexer loaded")
self.model = SimpleTagger(
text_field_embedder=text_field_embedder,
vocab=vocab,
encoder=seq2seq_encoder,
calculate_span_f1=True,
label_encoding='IOB1').cuda(device=cuda_device)
self.model.load_state_dict(
torch.load(self.model_path + self.model_name))
print("model loaded")
self.reader = Conll2003DatasetReader(
token_indexers={'tokens': self.indexer})
print("reader loaded")
except:
e = sys.exc_info()[0]
print("exeption while mapping to gpu in extractor ", e)
raise RuntimeError(
"Init extractor: can't map to gpu. Maybe it is OOM")
try:
self.predictor = SentenceTaggerPredictor(self.model, self.reader)
except:
e = sys.exc_info()[0]
print("exeption in creating predictor ", e)
raise RuntimeError(
"Init extractor: can't map to gpu. Maybe it is WTF")
def model_ctor():
# model = BertForTokenClassificationCustom.from_pretrained(self._bert_model_type,
# cache_dir=self._cache_dir,
# num_labels=len(self._tag2idx)).cuda()
#
# seq_tagger = SequenceTaggerBert(model, self._bert_tokenizer, idx2tag=self._idx2tag,
# tag2idx=self._tag2idx, pred_batch_size=self._ebs)
embedder = PretrainedTransformerMismatchedEmbedder(
model_name=self._bert_model_type)
text_field_embedder = BasicTextFieldEmbedder({'tokens': embedder})
seq2seq_encoder = PassThroughEncoder(
input_dim=embedder.get_output_dim())
tagger = SimpleTagger(text_field_embedder=text_field_embedder,
vocab=self.vocab,
encoder=seq2seq_encoder,
calculate_span_f1=True,
label_encoding='IOB1').cuda()
return tagger