How to automatically deploy a ML classifier to the cloud with AWS CDK

 By Medium - 2021-03-15

Description

In this step-by-step guide you will learn how to set up a basic deployment pipeline for a machine learning classifier using Amazon’s cloud development kit (CDK). The pipeline is going to include all…

Summary

  • In this step-by-step guide you will learn how to set up a basic deployment pipeline for a machine learning classifier using Amazon’s cloud development kit (CDK).
  • Repository for our code → GitHub Classifier → Sklearn model CI/CD pipeline → AWS CodePipeline Web framework → FastAPI Serving platform → AWS Elastic Container Service (ECS) with Fargate The solutions above are picked out of many alternatives mainly due to their simplicity and ease of extension and scaling.
  • Create the CDK Infrastructure So now we are ready to create the infrastructure code for CDK, which is comprised of three main stacks: CodePipeline of the project on the AWS console Optionally, one could add a third (deployment) stage that explicitly updates the running service cluster whenever a new image is pushed.

 

Topics

  1. Backend (0.47)
  2. Machine_Learning (0.13)
  3. NLP (0.11)

Similar Articles

How to Build a Serverless Application Using AWS SAM

By freeCodeCamp.org - 2020-10-19

In my previous article, I talked about how AWS Chalice helps you quickly build a Python-based serverless application and deploy it on AWS within a few minutes. While it was a quick and fun prototype, ...

Developing and Deploying React Apps using AWS Amplify

By harshcasper - 2020-11-02

As a React Developer, you might have studied about Serverless Architecture and how they are being used to dynamically manage memory and resources allocation allowing rapid scaling of Services. With th