onno101 / aml-batch-endpoint

Creating batch endpoints in Azure ML

For a detailed explanation of the code, check out the accompanying blog post: Creating batch endpoints in Azure ML.

You can find below the steps needed to create and invoke the endpoints in this project.

Azure ML setup

• You need to have an Azure subscription. You can get a free subscription to try it out.
• Create a resource group.
• Create a new machine learning workspace by following the "Create the workspace" section of the documentation. Keep in mind that you'll be creating a "machine learning workspace" Azure resource, not a "workspace" Azure resource, which is entirely different!
• If you have access to GitHub Codespaces, click on the "Code" button in this GitHub repo, select the "Codespaces" tab, and then click on "New codespace."
• Alternatively, if you plan to use your local machine:
  • Install the Azure CLI by following the instructions in the documentation.
  • Install the ML extension to the Azure CLI by following the "Installation" section of the documentation.
• In a terminal window, login to Azure by executing az login --use-device-code.
• Set your default subscription by executing az account set -s "<YOUR_SUBSCRIPTION_NAME_OR_ID>". You can verify your default subscription by executing az account show, or by looking at ~/.azure/azureProfile.json.
• Set your default resource group and workspace by executing az configure --defaults group="<YOUR_RESOURCE_GROUP>" workspace="<YOUR_WORKSPACE>". You can verify your defaults by executing az configure --list-defaults or by looking at ~/.azure/config.
• You can now open the Azure Machine Learning studio, where you'll be able to see and manage all the machine learning resources we'll be creating.
• Although not essential to run the code in this post, I highly recommend installing the Azure Machine Learning extension for VS Code.

Create the model

cd aml-batch-endpoint

Execute the following command:

az ml model create -f cloud/model.yml

Create the cluster

Execute the following command:

az ml compute create -f cloud/cluster-cpu.yml

Create the endpoint

Execute the following commands:

az ml batch-endpoint create -f cloud/endpoint/endpoint.yml
az ml batch-deployment create -f cloud/endpoint/deployment.yml --set-default

Invoke the endpoint

Execute the following command:

az ml batch-endpoint invoke --input sample-request --name endpoint-batch

Get the prediction results

Go to the Azure ML portal, click on "Endpoints," "Batch endpoints," and click on the name of the endpoint. Then click on "Runs," and on the latest run, which is displayed at the top. Once the run has completed, write click on the circle that says "score," and choose "Access data." This will take you to the blob storage location where the prediction results are located.

Delete the endpoint

Execute the fllowing command when you're done:

az ml batch-endpoint delete -n endpoint-batch -y