I have a sagemaker account setup in US-WEST-2 region. I have successfully trained and deployed my model; however, how can I chose to deploy the endpoint in a different region?

Assume I have a sagemaker account in one region where I have all my code, data and model artifacts etc.. I have been able to successfully deploy these models using the estimator.deploy() API after calling the estimator.fit() method. However, what If I dont want to deploy the model in the same region as my sagemaker account and want to deploy the endpoint in another region, how can I do that?

Victor Ghadban 전문가
일 년 전
With AWS Model registry you can share models accross accounts. You can register your model in the region you choose then deploy it from there.

주제

기계 학습 및 AI DevOps

태그

아마존 SageMaker DevOps

언어

English

rePost-User-6868729

질문됨 일 년 전762회 조회

1개 답변

최신
최다 투표
가장 많은 댓글

이 답변이 도움이 되었나요?커뮤니티가 여러분의 지식을 활용할 수 있도록 정답을 찬성하세요.

You can specify the region using either AWS SDK for Python (Boto3) or SageMaker Python SDK. Amazon SageMaker documentation provide a step by step guide for each one of them. You need

SageMaker region name
SageMaker execution role
Your framework
model data path

Zmnako

답변함 일 년 전

I have a sagemaker account setup in US-WEST-2 region. I have successfully trained and deployed my model; however, how can I chose to deploy the endpoint in a different region?

관련 콘텐츠