Seldon —MLOps

  1. Data Scientist prepares Machine learning model either by training the new model or fine-tuning the pre-trained model with data.
  2. The trained is saved in the storage location may be in any cloud storage as required.
  3. Then one has to create an inference class to read the model from the storage and provide a prediction.
  4. Now using Seldon core build a reusable model server image(docker image) and upload that to the registry.
  5. This model server provides REST or GRPC microservice for scoring.
  6. This can be deployed to the cluster for batch data or streaming data.
  1. All the hard work is done in the Seldon platform.
  2. Seldon provides very complex inference graphs where one can do even A/B testing, break the inference into different modules, etc. The below figure shows where one can even set up a simple Seldon core Inference Graph or a complex Graph with Multi-Arm Bandit, outlier detection, and others.
Image source: Seldon
Image source: Seldon
Image source: Seldon




Data Scientist | ML-Ops| | |

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

The Total Cost of Ownership

Nuvola 4.20 brings Audible and Emby, prepares for feature requests voting

SparkFun Edge: First Impressions

5 Best Practices for Beginners in Web Development with Flask (Python)

[iOS] How to Solve UIScrollView Constraint Ambiguity

How much of HTML and CSS you need to know as a junior back-end software developer.

How to do installation of ClipBucket and Nginx on CentOS

Dataiku the new French Unicorn recruits tech talents partnering with Tchoozz!

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Abhishek Maheshwarappa

Abhishek Maheshwarappa

Data Scientist | ML-Ops| | |

More from Medium

Enhancing MLflow with Comet

Aim 3.7 — Revamped Run Single Page and Aim Docker Image


Who Puts Your Machine Learning Models in Production?