0

Im using Azure ML Studio to create an automated ML pipeline. I've successfully gotten my model to be trained and tested in Azure, but it fails on model.to_json() and model.save_weights().

I believe these functions do not exist on my model as scikit-multilearn is a wrapper around Keras. However, I want to be able to save my model and weight so I can deploy them to a webservice service. The scikit-multilearn model I'm using is Binary Relevance.

Thanks to anyone who helps.

James Fisher
  • 87
  • 9
  • The class Keras of scikit-multilearn is based on the sklearn.base.BaseEstimator which have the get_params method. You should be able to get your parameters from it and then save it in a file. – Yoann A. Apr 25 '20 at 19:13
  • I see, thanks. Could you suggest how I would then load the model back up for production? If you post an answer I will accept it. – James Fisher Apr 25 '20 at 19:17
  • The get_params method only returns the epochs and batch size params etc, not the Keras model or its weights. – James Fisher Apr 25 '20 at 19:34

0 Answers0