Gensim doc2vec most similar gives unsupported operand type(s) error

Question

I am using a pre-trained doc2vec model, when I try to find out most similar document to that of my sample document. It gives me unsupported operand type(s) error. from gensim.models import Doc2Vec filename = "doc2vec.bin" doc1 =["This is a sample document."] model = Doc2Vec.load(filename) inferred_vector = model.infer_vector(doc1) sims = model.docvecs.most_similar(positive=[inferred_vector],topn=1) print(sims) This gives me following error File "D:\doc2vectest.py", line 10, in sims = model.docvecs.most_similar(positive=[inferred_vector],topn=1) File "C:\Users\admin\Anaconda3\lib\site-packages\gensim\models\keyedvectors.py", line 1667, in most_similar self.init_sims() File "C:\Users\admin\Anaconda3\lib\site-packages\gensim\models\keyedvectors.py", line 1630, in init_sims self.vectors_docs_norm = _l2_norm(self.vectors_docs, replace=replace) File "C:\Users\admin\Anaconda3\lib\site-packages\gensim\models\keyedvectors.py", line 2346, in _l2_norm dist = sqrt((m ** 2).sum(-1))[..., newaxis] TypeError: unsupported operand type(s) for ** or pow(): 'list' and 'int' JavaScript questions and answers, JavaScript questions pdf, JavaScript question bank, JavaScript questions and answers pdf, mcq on JavaScript pdf, JavaScript questions and solutions, JavaScript mcq Test , Interview JavaScript questions, JavaScript Questions for Interview, JavaScript MCQ (Multiple Choice Questions)

Answer 1

It's possible your pre-trained model isn't compatible with the version of gensim in your environment. Where did the model originate? (Separately: infer_document() requires a list-of-tokens, not a string. And, those tokens should have been preprocessed in exactly the same was as whatever training data was used to train the model.)