python - Segmentation fault when training SpaCy NER model -
when trained spacy own annotations, randomly crash python probability. training data 50000 records , each of them unicode text , ner annotations.
nlp = spacy.load('en', entity=false, parser=false) ner = entityrecognizer(nlp.vocab, entity_types=entity_types) itn in range(5): random.shuffle(train_data) raw_text, entity_offsets in train_data: doc = nlp.make_doc(raw_text) gold = goldparse(doc, entities=entity_offsets) nlp.tagger(doc) ner.update(doc, gold) ner.model.end_training() return ner
the error message like: enter image description here
Comments
Post a Comment