简体繁体 English

安排 sagemaker 模型的部署

[英]Schedule the deployment of a sagemaker model

原文 2020-03-04 22:39:47 5 2 python/ amazon-web-services/ amazon-sagemaker

I'm trying out SageMaker and I've created a model using autopilot.我正在试用 SageMaker，并使用自动驾驶仪创建了一个模型。 The point is that SageMaker only allows you to deploy directly to an endpoint.关键是 SageMaker 只允许您直接部署到端点。 But since I'll only be using the model a couple of times a day, what is the most direct way to schedule deployments by events (for example when loading new csv's into an s3 directory or when I see a queue in sqs) or at least periodically?但是由于我每天只会使用该模型几次，所以按事件安排部署的最直接方法是什么（例如，将新的 csv 加载到 s3 目录中或当我在 sqs 中看到队列时）或在至少定期？

2 个解决方案

The answer above is incorrect.上面的答案是错误的。 Boto3 is part of the Lambda Python environment, so all you need to do is create a SageMaker client and invoke the appropriate API. Boto3 是 Lambda Python 环境的一部分，因此您需要做的就是创建一个 SageMaker 客户端并调用适当的 API。

https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker.html https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker.html

You can use a trigger (eg Cloudwatch Events/EventBridge, S3 event, etc.) to run a Lambda function that deploys your SageMaker model.您可以使用触发器（例如 Cloudwatch Events/EventBridge、S3 事件等）来运行部署 SageMaker 模型的 Lambda 函数。 The Lambda function, however, requires a runtime that can call SageMaker APIs.但是，Lambda 函数需要可以调用 SageMaker API 的运行时。 You will have to create a custom runtime (via Layers) for that.您必须为此创建一个自定义运行时（通过层）。 If you're using Python, use this as reference: https://dev.to/vealkind/getting-started-with-aws-lambda-layers-4ipk .如果您使用 Python，请将其用作参考： https : //dev.to/vealkind/getting-started-with-aws-lambda-layers-4ipk 。