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
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
> scikit-learn@python.org
> https://mail.python.org/mailman/listinfo/scikit-learn
>
--
Piotr Szymański
nied...@gmail.com
___
scikit-learn mailing list
scikit-learn@python.org
https://mail.python.org/mailman/listinfo/scikit-learn
