Sagemaker ML - Load Tensorflow model endpoint directly inside a lambda function

Question

I've already managed to create a lambda function that loads a model.pb from S3 and apply object detection to an input image (installed tensorflow 1.12)

Is it possible to load a Sagemaker model/endpoint-configuration inside a lambda function ? I mean install all packages needed inside the lambda, without deploying an endpoint/ec2-like instance.

I guess inference performance would drop, but the solution seems to be more cost effective and scalable ready.

Josh Davis · Accepted Answer · 2019-12-12 20:37:29Z

1

SageMaker Endpoints only run on EC2 instances which are configured as part of the EndpointConfig. You can't use SageMaker models and deploy them onto Lambda.

answered Dec 12, 2019 at 20:37

Josh Davis

6,8712 gold badges27 silver badges25 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Sagemaker ML - Load Tensorflow model endpoint directly inside a lambda function

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related