DevOps Articles

Deploying Machine learning Models With Docker

I won’t be talking about how to create machine learning or deep learning models here, there are plenty of articles, blog post, and tutorials on that subject and I would recommend checking out Machine Learning Mastery if that is what you’re looking for or if you're looking to improve your machine learning skills in general. Docker is a containerization service that allows for websites, APIs, databases, and, in our case, data science models to be deployed anywhere and ran with a few to only one line of code.

It may be tempting to add the code that creates/trains the model, and you can, but it’s best practice for an image to have one purpose and in this case, it’s hosting the model.

Step one, we add our base image, this is an image pulled from DockerHub — a site that holds repositories of other Dockerfiles/images similar to Github.

This step is easy and if you created a docker-compose.yml file, you can do both in one command.