Exam DP-100 topic 4 question 19 discussion

The right answer is D. Deployment and runtime errors can be easier to diagnose by deploying the service as a container in a local Docker instance, like this: from azureml.core.webservice import LocalWebservice deployment_config = LocalWebservice.deploy_configuration(port=8890) service = Model.deploy(ws, 'test-svc', [model], inference_config, deployment_config) You can then troubleshoot runtime issues by making changes to the scoring file that is referenced in the inference configuration, and reloading the service without redeploying it (something you can only do with a local service): service.reload() print(service.run(input_data = json_data))

D: If you encounter problems deploying a model to ACI or AKS, try deploying it as a local web service. Using a local web service makes it easier to troubleshoot problems. The Docker image containing the model is downloaded and started on your local system. https://docs.microsoft.com/en-us/azure/machine-learning/how-to-troubleshoot-deployment

you need to test and debug locally before deploying to prod. Check this link: https://learn.microsoft.com/en-us/azure/machine-learning/how-to-debug-managed-online-endpoints-visual-studio-code?view=azureml-api-2&tabs=cli

On exam Aug 18 2023

On exam Aug 18 2023

D. D. Create a local web service deployment configuration and deploy the model to a local Docker container. This option provides a flexible and quick environment for debugging and testing. Using a local Docker container, you can quickly change the code in your entry script and immediately see the effect of your changes without going through the entire deployment process on Azure Kubernetes Service (AKS) or Azure Container Instances (ACI). Once you've debugged your entry script locally, you can then deploy it to AKS.

C. Add a breakpoint to the first line of the entry script and redeploy the service to AKS. Adding a breakpoint to the first line of the entry script and redeploying the service to AKS will allow you to iteratively modify and test the code without requiring a re-deployment of the service for each code update. This will enable you to identify and fix the error in the entry script, without having to repeatedly deploy the service, saving time and resources. You can use tools like Visual Studio Code or PyCharm to attach a debugger to the running service, set a breakpoint on the first line of the entry script, and then use the debugger to step through the code and identify the error. Once you have identified and fixed the error, you can update the code, remove the breakpoint, and redeploy the service to AKS.

The right answer is D.

If you encounter problems deploying a model to ACI or AKS, try deploying it as a local web service.

On exam 2021/7/10

Correct answer should be D

D, agreed. ACI is for production of low resource models. 1GB size and 48 GB ram or less