I've created a couple of scikit-learn compatible wrappers and model generators for scikit-multilearn: http://scikit.ml/multilabeldnn.html
Depends on what library you prefer, here's some examples on how to use LSTMs via: - Keras: https://medium.com/@dclengacher/keras-lstm-recurrent-neural-networks-c1f5febde03d - pyTorch: https://pytorch.org/tutorials/beginner/nlp/sequence_models_tutorial.html Just create a relevant model generating function, take a wrapper from scikit-multilearn, and put it into the scikit pipeline anyway you want. Best, Piotr Szymanski Scikit-multilearn Maintainer On Sun, Feb 17, 2019 at 7:55 PM David Burns <[email protected]> wrote: > There is an sklearn wrapper for Keras models in the Keras library. That's > an easy way to use LSTM in sklearn. Also the sklearn estimator API is > pretty easy to figure out if you want to roll your own wrapper for any > model really. > _______________________________________________ > scikit-learn mailing list > [email protected] > https://mail.python.org/mailman/listinfo/scikit-learn > -- Piotr Szymański [email protected]
_______________________________________________ scikit-learn mailing list [email protected] https://mail.python.org/mailman/listinfo/scikit-learn
