Issue
I have trained in unsupervised way fasttext model and now I am using get_sentence_vector()
function to get vectors of sentences. But it outputs vectors with length 100. How could I make those vectors longer (300 values)? Is there any hyper parameter for that?
Solution
As you can read in the documentation, if you want vectors with size 300, you have to train your unsupervised model, by setting dim
parameter to 300.
model = fasttext.train_unsupervised(YOUR_DATA, dim=300)
Once the model has been trained and learned a linguistic representation from your data, as far as I know there is no way to increase the size of the generated vectors.
Answered By - Stefano Fiorucci - anakin87
0 comments:
Post a Comment
Note: Only a member of this blog may post a comment.