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?

0

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?

  • 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.

asked a year ago689 views
1 Answer
0

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

  1. SageMaker region name
  2. SageMaker execution role
  3. Your framework
  4. model data path
AWS
Zmnako
answered a year ago

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Guidelines for Answering Questions