Model Deployment

#Terms

WHAT IS… ?

Model Deployment is the second step in the machine learning lifecycle that focuses on taking the model you built in the first step and deploying it in production. In this step, we focus on identifying which model should be deployed, determining how to create production versions of the code and packages, and testing, debugging, and validating your model.

HOW IS IT USED ?

Model Deployment refers to the putting in production ML models. These models may come from different libraries: TensorFlow, Keras, Pytorch or other frameworks.