After training a model, data scientists might want other members of their team including their manager to try out their model. However, their team members might have different operating systems from them and might be not familiar with their programming language. Thus, it is necessary for data scientists to containerize their model and create an intuitive API endpoint for their teammates to interact with. However, data scientists might not have all the time and skills to do all of the things above. Luckily, BentoML allows data scientists to put their models into production with ease. This presentation will show how data practitioners can containerize and share their local machine learning model with their teammates in a couple of lines of Python code
Khuyen Tran is a data science intern at Ocelot Consulting. She wrote over 150 data science articles with over 100k views per month on Towards Data Science. She also wrote over 500 daily data science tips at Data Science Simplified. Her current mission is to make open-source more accessible to the data science community.
