Overview
Get started with MLOps and Github Actions to package a container with an ONNX model that does live inferencing with a Flask application. By using Azure ML, learn how to download the large ONNX model
into the Github Action workflow, package it as a container and then push it to a container registry. For reference use the https://github.com/alfredodeza/flask-roberta repository
Topics include:
* Create a container that does live inferencing with Flask and the ONNX runtime
* Package the model and verify it works locally
* Setup a Github Action to authenticate to Azure ML and download a previously registered model
* Build the new container as a Github Action, authenticate to Docker Hub or Github Packages
* Push the new container to the Github registry or any other registry like Docker Hub
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Watch now
Unlock full access