将模型部署到 Kubernetes

Question

我正在尝试在 Azure Machine Learning Studio 中部署一个模型到 Kubernetes，它运行了一段时间，但现在部署失败，错误信息如下：

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."
        }
    ]
}

Answer 1

我知道这个问题是关于不同的错误，但调试步骤应该还是一样的。

Answer 2

好像是个bug，今天自己修复了。现在关闭这个问题

将模型部署到 Kubernetes

Deploying Model to Kubernetes

azure

azure-machine-learning-studio

azure-machine-learning-service

azureml