Covers: theory of Model Serving
Estimated time needed to finish: 14 minutes
Questions this item addresses:
  • How to serve a trained Iris model?
How to use this item?

In this video, you learn how to build a Flask web application:

  • Loading requirements
  • Route definitions
  • Running server
  • Predict endpoint
Fail to play? Open the link directly: https://youtu.be/8BJvk4j9X24
Author(s) / creator(s) / reference(s)
Brendan McGivern
0 comment
Recipe
publicShare
Star(0)

Delivering your Models to End Users

Contributors
Total time needed: ~2 hours
Objectives
This recipe aims to walk you through steps necessary to prepare and deliver your ML models as a service
Potential Use Cases
Serving ML models to users
Who is This For ?
INTERMEDIATEData Scientists, Machine Learning Engineers
Click on each of the following annotated items to see details.
Resource Asset4/7
VIDEO 1. Inference model serving overview
  • How to serve trained models?
14 minutes
VIDEO 2. Flask Iris Model Serving
  • How to serve a trained Iris model?
14 minutes
REPO 3. Hands-on Model Serving
  • How can i serve a model in practice?
30 minutes
VIDEO 4. Serve a container on AWS ec2
  • How to serve a container on EC2?
  • How to serve a container on a VM?
12 minutes
RECIPE 5. Model Deployment
10 minutes
VIDEO 6. Flask Tutorial: Full-Featured Web App
  • How to create a web application using ML models?
17 minutes
VIDEO 7. REST API concepts and examples
  • What are REST API's?
8 minutes

Concepts Covered

0 comment