ModelPackage

sagemaker.services.k8s.aws/v1alpha1

TypeLink
GoDocsagemaker-controller/apis/v1alpha1#ModelPackage

Metadata

PropertyValue
ScopeNamespaced
KindModelPackage
ListKindModelPackageList
Pluralmodelpackages
Singularmodelpackage

A versioned model that can be deployed for SageMaker inference.

Spec

additionalInferenceSpecifications:
  containers:
  - containerHostname: string
    environment: {}
    framework: string
    frameworkVersion: string
    image: string
    imageDigest: string
    modelDataURL: string
    modelInput: 
      dataInputConfig: string
    nearestModelName: string
    productID: string
  description: string
  name: string
  supportedContentTypes:
  - string
  supportedRealtimeInferenceInstanceTypes:
  - string
  supportedResponseMIMETypes:
  - string
  supportedTransformInstanceTypes:
  - string
approvalDescription: string
certifyForMarketplace: boolean
clientToken: string
customerMetadataProperties: {}
domain: string
driftCheckBaselines: 
  bias: 
    configFile: 
      contentDigest: string
      contentType: string
      s3URI: string
    postTrainingConstraints: 
      contentDigest: string
      contentType: string
      s3URI: string
    preTrainingConstraints: 
      contentDigest: string
      contentType: string
      s3URI: string
  explainability: 
    configFile: 
      contentDigest: string
      contentType: string
      s3URI: string
    constraints: 
      contentDigest: string
      contentType: string
      s3URI: string
  modelDataQuality: 
    constraints: 
      contentDigest: string
      contentType: string
      s3URI: string
    statistics: 
      contentDigest: string
      contentType: string
      s3URI: string
  modelQuality: 
    constraints: 
      contentDigest: string
      contentType: string
      s3URI: string
    statistics: 
      contentDigest: string
      contentType: string
      s3URI: string
inferenceSpecification: 
  containers:
  - containerHostname: string
    environment: {}
    framework: string
    frameworkVersion: string
    image: string
    imageDigest: string
    modelDataURL: string
    modelInput: 
      dataInputConfig: string
    nearestModelName: string
    productID: string
  supportedContentTypes:
  - string
  supportedRealtimeInferenceInstanceTypes:
  - string
  supportedResponseMIMETypes:
  - string
  supportedTransformInstanceTypes:
  - string
metadataProperties: 
  commitID: string
  generatedBy: string
  projectID: string
  repository: string
modelApprovalStatus: string
modelMetrics: 
  bias: 
    postTrainingReport: 
      contentDigest: string
      contentType: string
      s3URI: string
    preTrainingReport: 
      contentDigest: string
      contentType: string
      s3URI: string
    report: 
      contentDigest: string
      contentType: string
      s3URI: string
  explainability: 
    report: 
      contentDigest: string
      contentType: string
      s3URI: string
  modelDataQuality: 
    constraints: 
      contentDigest: string
      contentType: string
      s3URI: string
    statistics: 
      contentDigest: string
      contentType: string
      s3URI: string
  modelQuality: 
    constraints: 
      contentDigest: string
      contentType: string
      s3URI: string
    statistics: 
      contentDigest: string
      contentType: string
      s3URI: string
modelPackageDescription: string
modelPackageGroupName: string
modelPackageName: string
samplePayloadURL: string
sourceAlgorithmSpecification: 
  sourceAlgorithms:
  - algorithmName: string
    modelDataURL: string
tags:
- key: string
  value: string
task: string
validationSpecification: 
  validationProfiles:
  - profileName: string
    transformJobDefinition: 
      batchStrategy: string
      environment: {}
      maxConcurrentTransforms: integer
      maxPayloadInMB: integer
      transformInput: 
        compressionType: string
        contentType: string
        dataSource: 
          s3DataSource: 
            s3DataType: string
            s3URI: string
        splitType: string
      transformOutput: 
        accept: string
        assembleWith: string
        kmsKeyID: string
        s3OutputPath: string
      transformResources: 
        instanceCount: integer
        instanceType: string
        volumeKMSKeyID: string
  validationRole: string
FieldDescription
additionalInferenceSpecifications
Optional		array
An array of additional Inference Specification objects. Each additional Inference Specification specifies artifacts based on this model package that can be used on inference endpoints. Generally used with SageMaker Neo to store the compiled artifacts.
additionalInferenceSpecifications.[]
Required		object
A structure of additional Inference Specification. Additional Inference Specification specifies details about inference jobs that can be run with models based on this model package
additionalInferenceSpecifications.[].containers.[]
Required		object
Describes the Docker container for the model package.
additionalInferenceSpecifications.[].containers.[].environment
Optional		object
additionalInferenceSpecifications.[].containers.[].framework
Optional		string
additionalInferenceSpecifications.[].containers.[].frameworkVersion
Optional		string
additionalInferenceSpecifications.[].containers.[].image
Optional		string
additionalInferenceSpecifications.[].containers.[].imageDigest
Optional		string
additionalInferenceSpecifications.[].containers.[].modelDataURL
Optional		string
additionalInferenceSpecifications.[].containers.[].modelInput
Optional		object
Input object for the model.
additionalInferenceSpecifications.[].containers.[].modelInput.dataInputConfig
Optional		string
additionalInferenceSpecifications.[].containers.[].nearestModelName
Optional		string
additionalInferenceSpecifications.[].containers.[].productID
Optional		string
additionalInferenceSpecifications.[].description
Optional		string
additionalInferenceSpecifications.[].name
Optional		string
additionalInferenceSpecifications.[].supportedContentTypes
Optional		array
additionalInferenceSpecifications.[].supportedContentTypes.[]
Required		string
additionalInferenceSpecifications.[].supportedRealtimeInferenceInstanceTypes.[]
Required		string
additionalInferenceSpecifications.[].supportedResponseMIMETypes.[]
Required		string
additionalInferenceSpecifications.[].supportedTransformInstanceTypes.[]
Required		string
certifyForMarketplace
Optional		boolean
Whether to certify the model package for listing on Amazon Web Services Marketplace.
This parameter is optional for unversioned models, and does not apply to versioned models.
clientToken
Optional		string
A unique token that guarantees that the call to this API is idempotent.
customerMetadataProperties
Optional		object
The metadata properties associated with the model package versions.
domain
Optional		string
The machine learning domain of your model package and its components. Common machine learning domains include computer vision and natural language processing.
driftCheckBaselines
Optional		object
Represents the drift check baselines that can be used when the model monitor is set using the model package. For more information, see the topic on Drift Detection against Previous Baselines in SageMaker Pipelines (https://docs.aws.amazon.com/sagemaker/latest/dg/pipelines-quality-clarify-baseline-lifecycle.html#pipelines-quality-clarify-baseline-drift-detection) in the Amazon SageMaker Developer Guide.
driftCheckBaselines.bias
Optional		object
Represents the drift check bias baselines that can be used when the model monitor is set using the model package.
driftCheckBaselines.bias.configFile
Optional		object
Contains details regarding the file source.
driftCheckBaselines.bias.configFile.contentDigest
Optional		string
driftCheckBaselines.bias.configFile.contentType
Optional		string
driftCheckBaselines.bias.configFile.s3URI
Optional		string
driftCheckBaselines.bias.postTrainingConstraints
Optional		object
Details about the metrics source.
driftCheckBaselines.bias.postTrainingConstraints.contentDigest
Optional		string
driftCheckBaselines.bias.postTrainingConstraints.contentType
Optional		string
driftCheckBaselines.bias.postTrainingConstraints.s3URI
Optional		string
driftCheckBaselines.bias.preTrainingConstraints
Optional		object
Details about the metrics source.
driftCheckBaselines.bias.preTrainingConstraints.contentDigest
Optional		string
driftCheckBaselines.bias.preTrainingConstraints.contentType
Optional		string
driftCheckBaselines.bias.preTrainingConstraints.s3URI
Optional		string
driftCheckBaselines.explainability
Optional		object
Represents the drift check explainability baselines that can be used when the model monitor is set using the model package.
driftCheckBaselines.explainability.configFile
Optional		object
Contains details regarding the file source.
driftCheckBaselines.explainability.configFile.contentDigest
Optional		string
driftCheckBaselines.explainability.configFile.contentType
Optional		string
driftCheckBaselines.explainability.configFile.s3URI
Optional		string
driftCheckBaselines.explainability.constraints
Optional		object
Details about the metrics source.
driftCheckBaselines.explainability.constraints.contentDigest
Optional		string
driftCheckBaselines.explainability.constraints.contentType
Optional		string
driftCheckBaselines.explainability.constraints.s3URI
Optional		string
driftCheckBaselines.modelDataQuality
Optional		object
Represents the drift check data quality baselines that can be used when the model monitor is set using the model package.
driftCheckBaselines.modelDataQuality.constraints
Optional		object
Details about the metrics source.
driftCheckBaselines.modelDataQuality.constraints.contentDigest
Optional		string
driftCheckBaselines.modelDataQuality.constraints.contentType
Optional		string
driftCheckBaselines.modelDataQuality.constraints.s3URI
Optional		string
driftCheckBaselines.modelDataQuality.statistics
Optional		object
Details about the metrics source.
driftCheckBaselines.modelDataQuality.statistics.contentDigest
Optional		string
driftCheckBaselines.modelDataQuality.statistics.contentType
Optional		string
driftCheckBaselines.modelDataQuality.statistics.s3URI
Optional		string
driftCheckBaselines.modelQuality
Optional		object
Represents the drift check model quality baselines that can be used when the model monitor is set using the model package.
driftCheckBaselines.modelQuality.constraints
Optional		object
Details about the metrics source.
driftCheckBaselines.modelQuality.constraints.contentDigest
Optional		string
driftCheckBaselines.modelQuality.constraints.contentType
Optional		string
driftCheckBaselines.modelQuality.constraints.s3URI
Optional		string
driftCheckBaselines.modelQuality.statistics
Optional		object
Details about the metrics source.
driftCheckBaselines.modelQuality.statistics.contentDigest
Optional		string
driftCheckBaselines.modelQuality.statistics.contentType
Optional		string
driftCheckBaselines.modelQuality.statistics.s3URI
Optional		string
inferenceSpecification
Optional		object
Specifies details about inference jobs that can be run with models based on this model package, including the following:
* The Amazon ECR paths of containers that contain the inference code and model artifacts.
* The instance types that the model package supports for transform jobs and real-time endpoints used for inference.
* The input and output content formats that the model package supports for inference.
inferenceSpecification.containers
Optional		array
inferenceSpecification.containers.[]
Required		object
Describes the Docker container for the model package.
inferenceSpecification.containers.[].environment
Optional		object
inferenceSpecification.containers.[].framework
Optional		string
inferenceSpecification.containers.[].frameworkVersion
Optional		string
inferenceSpecification.containers.[].image
Optional		string
inferenceSpecification.containers.[].imageDigest
Optional		string
inferenceSpecification.containers.[].modelDataURL
Optional		string
inferenceSpecification.containers.[].modelInput
Optional		object
Input object for the model.
inferenceSpecification.containers.[].modelInput.dataInputConfig
Optional		string
inferenceSpecification.containers.[].nearestModelName
Optional		string
inferenceSpecification.containers.[].productID
Optional		string
inferenceSpecification.supportedContentTypes
Optional		array
inferenceSpecification.supportedContentTypes.[]
Required		string
inferenceSpecification.supportedRealtimeInferenceInstanceTypes.[]
Required		string
inferenceSpecification.supportedResponseMIMETypes.[]
Required		string
inferenceSpecification.supportedTransformInstanceTypes.[]
Required		string
metadataProperties.commitID
Optional		string
metadataProperties.generatedBy
Optional		string
metadataProperties.projectID
Optional		string
metadataProperties.repository
Optional		string
modelApprovalStatus
Optional		string
Whether the model is approved for deployment.
This parameter is optional for versioned models, and does not apply to unversioned models.
For versioned models, the value of this parameter must be set to Approved to deploy the model.
modelMetrics
Optional		object
A structure that contains model metrics reports.
modelMetrics.bias
Optional		object
Contains bias metrics for a model.
modelMetrics.bias.postTrainingReport
Optional		object
Details about the metrics source.
modelMetrics.bias.postTrainingReport.contentDigest
Optional		string
modelMetrics.bias.postTrainingReport.contentType
Optional		string
modelMetrics.bias.postTrainingReport.s3URI
Optional		string
modelMetrics.bias.preTrainingReport
Optional		object
Details about the metrics source.
modelMetrics.bias.preTrainingReport.contentDigest
Optional		string
modelMetrics.bias.preTrainingReport.contentType
Optional		string
modelMetrics.bias.preTrainingReport.s3URI
Optional		string
modelMetrics.bias.report
Optional		object
Details about the metrics source.
modelMetrics.bias.report.contentDigest
Optional		string
modelMetrics.bias.report.contentType
Optional		string
modelMetrics.bias.report.s3URI
Optional		string
modelMetrics.explainability
Optional		object
Contains explainability metrics for a model.
modelMetrics.explainability.report
Optional		object
Details about the metrics source.
modelMetrics.explainability.report.contentDigest
Optional		string
modelMetrics.explainability.report.contentType
Optional		string
modelMetrics.explainability.report.s3URI
Optional		string
modelMetrics.modelDataQuality
Optional		object
Data quality constraints and statistics for a model.
modelMetrics.modelDataQuality.constraints
Optional		object
Details about the metrics source.
modelMetrics.modelDataQuality.constraints.contentDigest
Optional		string
modelMetrics.modelDataQuality.constraints.contentType
Optional		string
modelMetrics.modelDataQuality.constraints.s3URI
Optional		string
modelMetrics.modelDataQuality.statistics
Optional		object
Details about the metrics source.
modelMetrics.modelDataQuality.statistics.contentDigest
Optional		string
modelMetrics.modelDataQuality.statistics.contentType
Optional		string
modelMetrics.modelDataQuality.statistics.s3URI
Optional		string
modelMetrics.modelQuality
Optional		object
Model quality statistics and constraints.
modelMetrics.modelQuality.constraints
Optional		object
Details about the metrics source.
modelMetrics.modelQuality.constraints.contentDigest
Optional		string
modelMetrics.modelQuality.constraints.contentType
Optional		string
modelMetrics.modelQuality.constraints.s3URI
Optional		string
modelMetrics.modelQuality.statistics
Optional		object
Details about the metrics source.
modelMetrics.modelQuality.statistics.contentDigest
Optional		string
modelMetrics.modelQuality.statistics.contentType
Optional		string
modelMetrics.modelQuality.statistics.s3URI
Optional		string
modelPackageDescription
Optional		string
A description of the model package.
modelPackageGroupName
Optional		string
The name or Amazon Resource Name (ARN) of the model package group that this model version belongs to.
This parameter is required for versioned models, and does not apply to unversioned models.
modelPackageName
Optional		string
The name of the model package. The name must have 1 to 63 characters. Valid characters are a-z, A-Z, 0-9, and - (hyphen).
This parameter is required for unversioned models. It is not applicable to versioned models.
samplePayloadURL
Optional		string
The Amazon Simple Storage Service (Amazon S3) path where the sample payload is stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). This archive can hold multiple files that are all equally used in the load test. Each file in the archive must satisfy the size constraints of the InvokeEndpoint (https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_runtime_InvokeEndpoint.html#API_runtime_InvokeEndpoint_RequestSyntax) call.
sourceAlgorithmSpecification
Optional		object
Details about the algorithm that was used to create the model package.
sourceAlgorithmSpecification.sourceAlgorithms
Optional		array
sourceAlgorithmSpecification.sourceAlgorithms.[]
Required		object
Specifies an algorithm that was used to create the model package. The algorithm must be either an algorithm resource in your SageMaker account or an algorithm in Amazon Web Services Marketplace that you are subscribed to.
sourceAlgorithmSpecification.sourceAlgorithms.[].modelDataURL
Optional		string
tags
Optional		array
A list of key value pairs associated with the model. For more information, see Tagging Amazon Web Services resources (https://docs.aws.amazon.com/general/latest/gr/aws_tagging.html) in the Amazon Web Services General Reference Guide.
tags.[]
Required		object
A tag object that consists of a key and an optional value, used to manage metadata for SageMaker Amazon Web Services resources.
You can add tags to notebook instances, training jobs, hyperparameter tuning jobs, batch transform jobs, models, labeling jobs, work teams, endpoint configurations, and endpoints. For more information on adding tags to SageMaker resources, see AddTags.
For more information on adding metadata to your Amazon Web Services resources with tagging, see Tagging Amazon Web Services resources (https://docs.aws.amazon.com/general/latest/gr/aws_tagging.html). For advice on best practices for managing Amazon Web Services resources with tagging, see Tagging Best Practices: Implement an Effective Amazon Web Services Resource Tagging Strategy (https://d1.awsstatic.com/whitepapers/aws-tagging-best-practices.pdf).
tags.[].value
Optional		string
task
Optional		string
The machine learning task your model package accomplishes. Common machine learning tasks include object detection and image classification. The following tasks are supported by Inference Recommender: “IMAGE_CLASSIFICATION”
validationSpecification
Optional		object
Specifies configurations for one or more transform jobs that SageMaker runs to test the model package.
validationSpecification.validationProfiles
Optional		array
validationSpecification.validationProfiles.[]
Required		object
Contains data, such as the inputs and targeted instance types that are used in the process of validating the model package.
The data provided in the validation profile is made available to your buyers on Amazon Web Services Marketplace.
validationSpecification.validationProfiles.[].transformJobDefinition
Optional		object
Defines the input needed to run a transform job using the inference specification specified in the algorithm.
validationSpecification.validationProfiles.[].transformJobDefinition.batchStrategy
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.environment
Optional		object
validationSpecification.validationProfiles.[].transformJobDefinition.maxConcurrentTransforms
Optional		integer
validationSpecification.validationProfiles.[].transformJobDefinition.maxPayloadInMB
Optional		integer
validationSpecification.validationProfiles.[].transformJobDefinition.transformInput
Optional		object
Describes the input source of a transform job and the way the transform job consumes it.
validationSpecification.validationProfiles.[].transformJobDefinition.transformInput.compressionType
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.transformInput.contentType
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.transformInput.dataSource
Optional		object
Describes the location of the channel data.
validationSpecification.validationProfiles.[].transformJobDefinition.transformInput.dataSource.s3DataSource
Optional		object
Describes the S3 data source.
validationSpecification.validationProfiles.[].transformJobDefinition.transformInput.dataSource.s3DataSource.s3DataType
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.transformInput.dataSource.s3DataSource.s3URI
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.transformInput.splitType
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.transformOutput
Optional		object
Describes the results of a transform job.
validationSpecification.validationProfiles.[].transformJobDefinition.transformOutput.accept
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.transformOutput.assembleWith
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.transformOutput.kmsKeyID
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.transformOutput.s3OutputPath
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.transformResources
Optional		object
Describes the resources, including ML instance types and ML instance count, to use for transform job.
validationSpecification.validationProfiles.[].transformJobDefinition.transformResources.instanceCount
Optional		integer
validationSpecification.validationProfiles.[].transformJobDefinition.transformResources.instanceType
Optional		string
validationSpecification.validationProfiles.[].transformJobDefinition.transformResources.volumeKMSKeyID
Optional		string
validationSpecification.validationRole
Optional		string

Status

ackResourceMetadata: 
  arn: string
  ownerAccountID: string
  region: string
conditions:
- lastTransitionTime: string
  message: string
  reason: string
  status: string
  type: string
creationTime: string
lastModifiedTime: string
modelPackageStatus: string
modelPackageStatusDetails: 
  imageScanStatuses:
  - failureReason: string
    name: string
    status: string
  validationStatuses:
  - failureReason: string
    name: string
    status: string
FieldDescription
ackResourceMetadata
Optional		object
All CRs managed by ACK have a common Status.ACKResourceMetadata member that is used to contain resource sync state, account ownership, constructed ARN for the resource
ackResourceMetadata.arn
Optional		string
ARN is the Amazon Resource Name for the resource. This is a globally-unique identifier and is set only by the ACK service controller once the controller has orchestrated the creation of the resource OR when it has verified that an “adopted” resource (a resource where the ARN annotation was set by the Kubernetes user on the CR) exists and matches the supplied CR’s Spec field values. TODO(vijat@): Find a better strategy for resources that do not have ARN in CreateOutputResponse https://github.com/aws/aws-controllers-k8s/issues/270
ackResourceMetadata.ownerAccountID
Required		string
OwnerAccountID is the AWS Account ID of the account that owns the backend AWS service API resource.
ackResourceMetadata.region
Required		string
Region is the AWS region in which the resource exists or will exist.
conditions
Optional		array
All CRS managed by ACK have a common Status.Conditions member that contains a collection of ackv1alpha1.Condition objects that describe the various terminal states of the CR and its backend AWS service API resource
conditions.[]
Required		object
Condition is the common struct used by all CRDs managed by ACK service controllers to indicate terminal states of the CR and its backend AWS service API resource
conditions.[].message
Optional		string
A human readable message indicating details about the transition.
conditions.[].reason
Optional		string
The reason for the condition’s last transition.
conditions.[].status
Optional		string
Status of the condition, one of True, False, Unknown.
conditions.[].type
Optional		string
Type is the type of the Condition
creationTime
Optional		string
A timestamp specifying when the model package was created.
lastModifiedTime
Optional		string
The last time that the model package was modified.
modelPackageStatus
Optional		string
The current status of the model package.
modelPackageStatusDetails
Optional		object
Details about the current status of the model package.
modelPackageStatusDetails.imageScanStatuses
Optional		array
modelPackageStatusDetails.imageScanStatuses.[]
Required		object
Represents the overall status of a model package.
modelPackageStatusDetails.imageScanStatuses.[].name
Optional		string
modelPackageStatusDetails.imageScanStatuses.[].status
Optional		string
modelPackageStatusDetails.validationStatuses
Optional		array
modelPackageStatusDetails.validationStatuses.[]
Required		object
Represents the overall status of a model package.
modelPackageStatusDetails.validationStatuses.[].name
Optional		string
modelPackageStatusDetails.validationStatuses.[].status
Optional		string