New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
PV-DBOW or PV-DM? #11
Comments
@hiyijian would be great to have an answer on this |
Both models are implemented. |
@rekola where in the c++ code can you call dm and pv-dbow |
It seems my information was based on your work in
Is this not true? I've been working on a fork of doc2vec to remove the word and sentence length limits. This original version also crashes, if you have more than 30 million documents in your dataset. |
Yes, that is indeed my interpretation
and I would prefer to have a validation from @hiyijian as in the R wrapper I call: https://github.com/bnosac/doc2vec/blob/3e947562a0a69e11eb292283116a4fdc9cf5c0f4/src/rcpp_doc2vec.cpp#L14 which calls the train functionality from this repository https://github.com/hiyijian/doc2vec/blob/master/cpp/Doc2Vec.cpp#L65 and I make the above assumption |
Is this implementation the distributed bag of words ('PV-DBOW') or the distributed memory ('PV-DM') model
The text was updated successfully, but these errors were encountered: