This is part seven in a series on getting beyond the basics with Azure ML.

What Did We Learn?

Throughout this series, we gained a better understanding of how we can use Azure Machine Learning for more than drag-and-drop model training. In the first post of the series, we looked at using notebooks in Azure ML Studio as a “halfway house” between work in the Designer and full-on application development. The second post in the series showed how to use a Visual Studio Code extension to work from a separate machine from an Azure ML compute instance. From there, we took a look at the Python SDK and I complained for a little bit about how R is being kicked out of a moving car. Then, we looked at model tracking in Azure ML. With both of those posts in mind, we dove into ML pipelines in code, showing how to train, register, and use a ML model from our local machine. Finally, we wrapped things up with a brief primer on MLOps. All of this works together to get us to stable, rapid deployment of code, data, and model artifacts in our environment. And that gets us beyond the basics in Azure ML.

I have quite a few links to resources on my presentation page. I used those resources to gain a better understanding of Azure ML, MLflow, and MLOps. Most of that documentation comes from Microsoft Docs, where the Azure ML documentation tends to be pretty solid, going in-depth on a lot of topics. I do recommend it as your go-to when working with Azure ML, especially as you dive deeper into topics and the pool of relevant blog posts tends to shrink.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s