Deployment Archives - Page 2 of 2

Kubernetes Services for Machine Learning

In my previous Kubernetes for Machine Learning post, we used a Kubernetes Deployment to build a REST API to serve a trained machine learning model. In that setup, issuing requests to generate predictions was only possible from within our Kubernetes… Read More

The Ultimate Guide to Model Retraining

Machine learning models are trained by learning a mapping between a set of input features and an output target. Typically, this mapping is learned by optimizing some cost function to minimize prediction error. Once the optimal model is found, it’s… Read More

Kubernetes Deployments for Machine Learning

Suppose your data science team has deployed a couple of batch machine learning processes on Kubernetes. You’ve successfully used Kubernetes Jobs to deploy model training and you’ve scheduled daily batch inference tasks using CronJobs. But now you’re tasked with serving… Read More

Kubernetes CronJobs for Machine Learning

In my previous post we discussed how to leverage Kubernetes Jobs to perform common production machine learning tasks such as model training and batch inference. Jobs allow us to reliably run batch processes in a fault tolerant way. Even if… Read More

Kubernetes Jobs for Machine Learning

In my previous post I introduced Kubernetes Pods, the basic building block of the Kubernetes ecosystem. In that post I discussed what a Pod is, how it fits into the Kubernetes system, and how to create, view, and delete a… Read More

Using Docker to Generate Machine Learning Predictions in Real Time

Figure 1. A REST API serves as the communication layer between a machine learning model and incoming data. Introduction In Part III of our Docker for Machine Learning series, we learned how to use Docker to perform model training and… Read More

Batch Inference vs Online Inference

Introduction You’ve spent the last few weeks training a new machine learning model. After working with the product team to define the business objectives, translating these objectives into appropriate evaluation metrics, and several rounds of iterative feature engineering, you’re ready… Read More