What happens after we train a model in a Jupyter notebook? It’s time to deploy it!
In this talk, we’ll learn about putting ML models into production and deploying it as a web service. We’ll cover:
- Saving and loading models with pickle
- Serving the model with Flask
- Creating and managing virtual environments with Pipenv
- Packaging the service in Docker
- Deploying the model to the cloud with AWS Beanstalk
By the end of this session, you’ll be able to deploy any Scikit-Learn model to production.