Scikit-learn Model Serving with Online Prediction Using AI Platform

search share 加入 登录

Scikit-learn Model Serving with Online Prediction Using AI Platform

1 个小时 20 分钟 5 个积分


Google Cloud Self-Paced Labs


If you've built machine learning models with scikit-learn, and you want to serve your models in real time for an application, managing the resulting infrastructure may sound like a nightmare. Fortunately, there's an alternative - serving your trained scikit-learn models on AI Platform.

You can now upload a model you've already trained onto Cloud Storage and use AI Platform Prediction to support scalable prediction requests against your trained model.

In this lab you learn how to train a simple scikit-learn model, deploy the model to AI Platform Prediction, and make online predictions against that model.

How to bring a scikit-learn model to AI Platform

Getting your model ready for prediction can be done in 5 steps:

  1. Create and save a model to a file
  2. Upload the saved model to Cloud Storage
  3. Create a model resource in AI Platform
  4. Create a model version (linking your scikit-learn model)
  5. Make an online prediction

This lab walks you through the five steps listed above.

What you will build


What you'll learn

  • How to create a model on AI Platform
  • How to make online predictions against your model on AI Platform

Before you jump in to the lab, learn about the different tools you'll be using to get online prediction up and running on AI Platform:

Google Cloud lets you build and host applications and websites, store data, and analyze data on Google's scalable infrastructure.

AI Platform Prediction is a managed service that enables you to easily build machine learning models that work on any type of data, of any size.

Cloud Storage is a unified object storage for developers and enterprises, from live data serving to data analytics/ML to data archiving.

Cloud SDK is a command line tool which allows you to interact with Google Cloud products.

加入 Qwiklabs 即可阅读本实验的剩余内容…以及更多精彩内容!

  • 获取对“Google Cloud Console”的临时访问权限。
  • 200 多项实验,从入门级实验到高级实验,应有尽有。
  • 内容短小精悍,便于您按照自己的节奏进行学习。