Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
SPDX-License-Identifier: CC-BY-SA-4.0

You can create a Neo compilation job in the Amazon SageMaker console. In the Amazon SageMaker console, choose Compilation jobs, and then choose Create compilation job.

On the Create compilation job page, for Job name, enter a name. Then select an IAM role.

If you don’t have an IAM role, choose Create a new role.

On the Create an IAM role page, choose Any S3 bucket, and choose Create role.

In the Input configuration section, for Location of model artifacts, enter the path of the S3 bucket that contains your model artifacts. For Data input configuration, enter the JSON string that specifies how many data matrix inputs you and the shape of each data matrices. For Machine learning framework, choose the framework.

In the Output configuration section, for S3 Output location, enter the path to the S3 bucket or folder where you want to store the model. For Target device, choose which device you want to deploy your model to, and choose Create job.

Check the status of the compilation job when started.

Check the status of the compilation job when completed.