sagemaker - factorization machines - deserialize model

Question

I estimated a factorization machine model in sagemaker and it saved a file model.tar.gz into an s3 folder.

Is there a way I can load this file in Python and access the parameter of the model, ie the factors, directly?

Thanks

Answer 1

As of April 2019: yes. An official AWS blog post was created to show how to open the SageMaker Factorization Machines artifact and extract its parameters: https://aws.amazon.com/blogs/machine-learning/extending-amazon-sagemaker-factorization-machines-algorithm-to-predict-top-x-recommendations/

That being said, be aware that Amazon SageMaker built-in algorithm are primarily built for deployment on AWS, and only SageMaker XGBoost and SageMaker BlazingText are designed to produce artifacts interoperable with their open-source equivalent.