Notatnik do tego ćwiczenia

Lab 7B: Creating a Batch Inferencing Service

In many scenarios, inferencing is performed as a batch process that uses a predictive model to score a large number of cases. To implement this kind of inferencing solution in Azure Machine Learning, you can create a batch endpoint.

Before You Start

Before you start this lab, ensure that you have completed Lab 1A and Lab 1B, which include tasks to create the Azure Machine Learning workspace and other resources used in this lab.

Task 1: Create a Batch Inferencing Service

In this task, you'll deploy a model to a batch endpoint for batch inferencing.

1. In Azure Machine Learning studio, view the Compute page for your workspace; and on the Compute Instances tab, ensure your compute instance is running. If not, start it.
2. When the compute instance is running, click the JupyterLab link to open JupyterLab in a new browser tab.
3. In the JupyterLab file browser, open the MachineLearningCourse/materialy/azure-ml/en folder you cloned in Lab 1B, then open the 07B - Creating a Batch Inferencing Service.ipynb notebook. Confirm that it uses the Python 3.10 - SDK v2 kernel, then read the notes in the notebook, running each code cell in turn.

Note: If you intend to continue straight to the next exercise, leave your compute instance running. If you're taking a break, you might want to close all JupyterLab tabs and Stop your compute instance to avoid incurring unnecessary costs.