skipthoughts.encode is very slow on large number of sentences

ryankiros / skip-thoughts

Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"

2.05k stars 544 forks source link

skipthoughts.encode is very slow on large number of sentences #26

Open alahiri-quora opened 8 years ago

alahiri-quora commented 8 years ago

If the number of sentences I'm trying to encode (i.e., the list X in the encode function in skipthoughts.py) is large - say around 10K or 100K then it takes a very long time to run encode. What can be done to speed it up? It's seems the theano functions - 'w2v' and 'w2v2' - are very slow. Any help will be really appreciated... thanks!

maliktiomoko commented 6 years ago

Hi have you found a solution to speed up the encoding of large number of sentences? Thanks