I’m currently working on a Recommender System using Collaborative Filtering and the MovieLens dataset. The goal is to export a trained collab_learner to later import and use it in an application so that you can later also upload your own movie-data as a CSV, retrain the model and get your recommendations:
At the moment, I am stuck when importing the model correctly after exporting it with learner.export(export.pkl)
.
After importing the model with learner = load_learner(path=learn.path)
, it appears to have changed its architecture from a CollabLearner to a Learner, the model changed from a EmbeddingDotBias model to a TabularModel.
Is it possible to correctly export and import a CollabLearner like this?
The used Fast AI version is 1.0.50.post1 and I followed the documentation here https://docs.fast.ai/tutorial.inference.html