Python framework for fast (approximated) nearest neighbour search in large, high-dimensional data sets using different locality-sensitive hashes.
759
stars
152
forks
source link
ValueError: dimension mismatch, When using space coo matrix #38
Closed
kharazi closed 8 years ago
Hi there, I have this error when updating nearpy to new version,
my vector is:
and vectorizer is a sklearn hashing vectrozier (n_features=2**18). np.linalg.norm will dot(v, v) and since v is an sparce matrix this error occurs.