在AWS SageMaker上重新托管训练有素的模型 [英] Re-hosting a trained model on AWS SageMaker

问题描述

我已经开始从以下这些提供的示例开始探索AWS SageMaker通过AWS .然后，我对该特定设置进行了一些修改，以便它使用我的用例中的数据进行训练.

I have started exploring AWS SageMaker starting with these examples provided by AWS. I then made some modifications to this particular setup so that it uses the data from my use case for training.

现在，当我继续研究该模型并进行调整时，一次删除推理端点后，我希望能够重新创建相同的端点-即使在停止并重新启动笔记本实例之后(因此，笔记本/内核会话不再有效)-使用已经受过训练的模型工件，该工件被上传到/output文件夹下的S3.

Now, as I continue to work on this model and tuning, after I delete the inference endpoint once, I would like to be able to recreate the same endpoint -- even after stopping and restarting the notebook instance (so the notebook / kernel session is no longer valid) -- using the already trained model artifacts that gets uploaded to S3 under /output folder.

现在，我不能简单地直接跳到以下代码行:

Now I cannot simply jump directly to this line of code:

bt_endpoint = bt_model.deploy(initial_instance_count = 1,instance_type = 'ml.m4.xlarge')

我进行了一些搜索-包括 amazon自己的示例托管预先训练的模型，但我有点迷失了.我将不胜感激，可以模仿并适应我的情况下提供的任何指导，示例或文档.

I did some searching -- including amazon's own example of hosting pre-trained models, but I am a little lost. I would appreciate any guidance, examples, or documentation that I could emulate and adapt to my case.

推荐答案

您的注释正确-您可以在给定现有EndpointConfiguration的情况下重新创建一个Endpoint.可以通过控制台，AWS CLI或SageMaker boto客户端完成此操作.

Your comment is correct - you can re-create an Endpoint given an existing EndpointConfiguration. This can be done via the console, the AWS CLI, or the SageMaker boto client.

• https://docs.aws.amazon .com/cli/latest/reference/sagemaker/create-endpoint.html
• https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker.html#SageMaker.Client.create_endpoint

• https://docs.aws.amazon.com/cli/latest/reference/sagemaker/create-endpoint.html
• https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker.html#SageMaker.Client.create_endpoint

这篇关于在AWS SageMaker上重新托管训练有素的模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！