Kvasir-Image-Segmentation-Deployment/endpoint-config-template.yml

AWSTemplateFormatVersion: 2010-09-09
Description:
  This template is built and deployed by the infrastructure pipeline in various stages (staging/production) as required.
  It specifies the resources that need to be created, like the SageMaker Endpoint. It can be extended to include resources like
  AutoScalingPolicy, API Gateway, etc,. as required.
Parameters:    
  SageMakerProjectName:
    Type: String
    Description: Name of the project
    MinLength: 1
    MaxLength: 32
    AllowedPattern: ^[a-zA-Z](-*[a-zA-Z0-9])*
  ModelExecutionRoleArn:
    Type: String
    Description: Execution role used for deploying the model.
  ModelDataLocation:
    Type: String
    Description: The model.tar.gz file location
  ContainerImageURI:
    Type: String
    Description: The inference container image URI
  StageName:
    Type: String
    Description:
      The name for a project pipeline stage, such as Staging or Prod, for
      which resources are provisioned and deployed.
  EndpointInstanceCount:
    Type: Number
    Description: Number of instances to launch for the endpoint.
    MinValue: 1
  DataCaptureUploadPath:
    Type: String
    Description: The s3 path to which the captured data is uploaded.
  EndpointInstanceType:
    Type: String
    Description: The ML compute instance type for the endpoint.
  SamplingPercentage:
    Type: Number
    Description: The sampling percentage
    MinValue: 0
    MaxValue: 100
  EnableDataCapture:
    Description: Enable Data capture.
    Default: true
    Type: String
    AllowedValues: [true, false]  

Resources:
  Model:
    Type: AWS::SageMaker::Model
    Properties:
      Containers:
        - Image: !Ref ContainerImageURI
          ModelDataUrl: !Ref ModelDataLocation
      ExecutionRoleArn: !Ref ModelExecutionRoleArn

  EndpointConfig:
    Type: AWS::SageMaker::EndpointConfig
    Properties:
      ProductionVariants:
        - InitialInstanceCount: !Ref EndpointInstanceCount
          InitialVariantWeight: 1.0
          InstanceType: !Ref EndpointInstanceType
          ModelName: !GetAtt Model.ModelName
          VariantName: AllTraffic
      DataCaptureConfig:
          EnableCapture: !Ref EnableDataCapture 
          InitialSamplingPercentage: !Ref SamplingPercentage
          DestinationS3Uri: !Ref DataCaptureUploadPath
          CaptureOptions:
            - CaptureMode: Input
            - CaptureMode: Output

  Endpoint:
    Type: AWS::SageMaker::Endpoint
    Properties:
      EndpointName: !Sub ${SageMakerProjectName}-${StageName}
      EndpointConfigName: !GetAtt EndpointConfig.EndpointConfigName