Introduction Azure offers a rich set of pre-trained AI models called Cognitive Services which can help you solving a large variety of tasks. For example, services like OCR (Optical Character Recognition), form recognition or Speech-to-Text enable you to automate otherwise labor-intensive business processes. Let’s take invoice processing as an example. Historically, this has been performed […]
This is a quick post for showing how to call Azure Machine Learning Pipelines from Azure Data Factory. This includes passing data dynamically into the Machine Learning Pipeline using DataPath. Pipeline Creation First, let’s create an AzureML Pipeline that we can use for this example. Please note that this code is syntactically correct, but probably […]
This post is a quick tip, showing how you can automatically enforce an Init Script during Azure Machine Learning Compute Instance provisioning. This ensures that even when the user did not specify a script, a default script is always being executed. For more details on the init script capabilities, have a look at the documentation. […]
This post will explain deploying Azure Machine Learning models to Azure App Service. This allows for easier model deployments, especially for those users who do not want to deploy to e.g., Azure Kubernetes Service. In this post, we will follow the proposed approach from the official documentation to a certain degree, but we will also […]
This posts shows how to use custom images in Azure Machine Learning for model training. “Why would I need that?” – you might ask – “Doesn’t AML handle all of this?” – and yes, you’re right, Azure Machine Learning does all of that. However, there are a few scenarios where building your own custom images […]
This post shows how to perform a full Azure Machine Learning deployment using Terraform. This includes enterprise features like setting up VNET-bindings and Private Link. You can reuse this sample and adapt it to your own needs. In short, the proposed Terraform deployment will roll out the following environment: This includes: Azure Machine Learning Workspace […]
This post outlines how you can mount a Dataset to a Compute Instance in Azure Machine. This can help exploring file-based datasets in Jupyter, especially for large datasets where download to the disk of the Compute Instance is impractical. Furthermore, this method can also help during exploration phase, where you probably want to read only […]
In last week’s post, we looked into how we can use Automated Machine Learning for building and deploying Models as APIs. This week, we’ll take the same model we have trained, but deploy it to Azure Kubernetes Service (AKS). Machine Learning Model deployment is such a critical task, and using AKS is the production-approved way […]
In this post we’ll look into using Azure Automated Machine Learning for deploying Machine Learning Models as APIs into production. As an example, we will be training and deploying a simple text sentiment analysis service, using the IMDB reviews dataset (subsampled to 1000 examples). We will achieve this by building the following architecture: In detail, we […]
Updated – August 2019: Deployment will now work properly even when including additional pip packages in the Function App! In this post, we’re looking at deploying Azure Functions in Python by using Azure DevOps for Continuous Integration or Continuous Deployment. We’ve already covered how to write Azure Functions in Python in this last post, so […]