AWS::SageMaker::ModelCard InferenceSpecification - AWS CloudFormation

AWS::SageMaker::ModelCard InferenceSpecification

Defines how to perform inference generation after a training job is run.

Syntax

To declare this entity in your AWS CloudFormation template, use the following syntax:

JSON

{ "Containers" : [ Container, ... ] }

Properties

Containers

The Amazon ECR registry path of the Docker image that contains the inference code.

Required: Yes

Type: Array of Container

Minimum: 1

Maximum: 15

Update requires: No interruption