How can I deploy a re-trained Sagemaker model to an endpoint?

Question

With an sagemaker.estimator.Estimator, I want to re-deploy a model after retraining (calling fit with new data).

When I call this

estimator.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge')

I get an error

botocore.exceptions.ClientError: An error occurred (ValidationException) 
when calling the CreateEndpoint operation: 
Cannot create already existing endpoint "arn:aws:sagemaker:eu-east- 
1:1776401913911:endpoint/zyx".

Apparently I want to use functionality like UpdateEndpoint. How do I access that functionality from this API?

Olivier Cruchant · Accepted Answer · 2020-10-08 07:06:36Z

6

Yes, under the hood the model.deploy creates a model, an endpoint configuration and an endpoint. When you call again the method from an already-deployed, trained estimator it will create an error because a similarly-configured endpoint is already deployed. What I encourage you to try:

use the update_endpoint=True parameter. From the SageMaker SDK doc: "Additionally, it is possible to deploy a different endpoint configuration, which links to your model, to an already existing SageMaker endpoint. This can be done by specifying the existing endpoint name for the endpoint_name parameter along with the update_endpoint parameter as True within your deploy() call."
Alternatively, if you want to create a separate model you can specify a new model_name in your deploy

edited Oct 8, 2020 at 7:06

answered Oct 5, 2020 at 9:51

Olivier Cruchant

4,06718 silver badges19 bronze badges

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

2 Comments

geominded Over a year ago

This method of adding update_endpoint=True to the .deploy() call does not appear to work if deploying from a ModelPackage obj. docs.aws.amazon.com/sagemaker/latest/dg/…

bmasri Over a year ago

This is a very good answer. I have a question though, if I have real time inference requests and the update endpoint is set to true, knowing that I have a few dozen requests per second, how would sagemaker handle inference while re-deploying ? would it use the old model to make inferences while updating is still in progress? thanks!

Ram K · Accepted Answer · 2022-06-13 17:38:27Z

update_endpoint has been deprecated since AFAIK . To re-create the UpdateEndpoint functionality from this API itself and deploy a newly fit training job to an existing endpoint , we could do something like this (this example uses the sagemaker sklearn API):

from sagemaker.sklearn.estimator import SKLearn

sklearn_estimator = SKLearn(
    entry_point=model.py,
    instance_type=<instance_type>,
    framework_version=<framework_version>,
    role=<role>,
    dependencies=[
         <comma seperated names of files>
    ],
    hyperparameters={
         'key_1':value,
         'key_2':value,
         ...
    }
)

sklearn_estimator.fit()

sm_client = boto3.client('sagemaker')

# Create the model
sklearn_model = sklearn_estimator.create_model()

# Define an endpoint config and an endpoint
endpoint_config_name = 'endpoint-' + datetime.utcnow().strftime("%Y%m%d%H%m%s")
current_endpoint = endpoint_config_name

# From the Model : create the endpoint config and the endpoint
sklearn_model.deploy(
    initial_instance_count=<count>,
    instance_type=<instance_type>,
    endpoint_name=current_endpoint
)

# Update the existing endpoint if it exists or create a new one
try:
    sm_client.update_endpoint(
        EndpointName=DESIRED_ENDPOINT_NAME, # The Prod/Existing Endpoint Name
        EndpointConfigName=endpoint_config_name
    )
except Exception as e:
    try:
        sm_client.create_endpoint(
            EndpointName=DESIRED_ENDPOINT_NAME, # The Prod Endpoint name
            EndpointConfigName=endpoint_config_name
        )
    except Exception as e:
        logger.info(e)

sm_client.delete_endpoint(EndpointName=current_endpoint)

Collectives™ on Stack Overflow

How can I deploy a re-trained Sagemaker model to an endpoint?

2 Answers 2

2 Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

2 Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related