NER_bLSTM-CRF
NER_bLSTM-CRF copied to clipboard
gensim version?
run data_preprocessing.ipynb has a error:
w2v_vocab, w2v_model = create_embeddings(train_sent_texts, embeddings_path='../embeddings/text_embeddings.gensimmodel', vocab_path='../embeddings/text_mapping.json', size=300, workers=4, iter=20)
Traceback (most recent call last): File "D:\Anaconda3\lib\threading.py", line 916, in _bootstrap_inner self.run() File "D:\Anaconda3\lib\threading.py", line 864, in run self._target(*self._args, **self._kwargs) File "D:\Anaconda3\lib\site-packages\gensim\models\word2vec.py", line 806, in worker_loop tally, raw_tally = self._do_train_job(sentences, alpha, (work, neu1)) File "D:\Anaconda3\lib\site-packages\gensim\models\word2vec.py", line 742, in _do_train_job tally += train_batch_cbow(self, sentences, alpha, work, neu1) File "D:\Anaconda3\lib\site-packages\gensim\models\word2vec.py", line 161, in train_batch_cbow train_cbow_pair(model, word, word2_indices, l1, alpha) File "D:\Anaconda3\lib\site-packages\gensim\models\word2vec.py", line 303, in train_cbow_pair fb = sigmoid(dot(l1, l2b.T)) # propagate hidden -> output File "D:\Anaconda3\lib\site-packages\gensim\models\word2vec.py", line 277, in sigmoid if p > 0: ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()