Search code examples
azureazure-machine-learning-service

Deploying Model to Kubernetes


I am trying to deploy a model to Kubernetes in Azure Machine Learning Studio, it was working for a while, but now, it fails during deployment, the error message is as follows:

Deploy: Failed on step WaitServiceCreating. Details: AzureML service API error. 
Your container application crashed. This may be caused by errors in your scoring file's init() function.
Please check the logs for your container instance: pipeline-created-on-07-28-2020-r.
From the AML SDK, you can run print(service.get_logs()) if you have service object to fetch the logs.
You can also try to run image viennaglobal.azurecr.io/azureml/azureml_6ae744633f749472feb283065055dc2c:latest locally.
Please refer to http://aka.ms/debugimage#service-launch-fails for more information.
{
    "code": "KubernetesDeploymentFailed",
    "statusCode": 400,
    "message": "Kubernetes Deployment failed",
    "details": [
        {
            "code": "CrashLoopBackOff",
            "message": "Your container application crashed. This may be caused by errors in your scoring file's init() function.
Please check the logs for your container instance: pipeline-created-on-07-28-2020-r. From the AML SDK, you can run print(service.get_logs()) if you have service object to fetch the logs. \nYou can also try to run image viennaglobal.azurecr.io/azureml/azureml_6ae744633f749472feb283065055dc2c:latest locally. Please refer to http://aka.ms/debugimage#service-launch-fails for more information."
        }
    ]
}

Solution

  • It seems it was a bug, got corrected by itself today. Closing this question now