Class: Aws::SageMaker::Types::CreateModelPackageInput

Inherits:

Struct

Object
Struct
Aws::SageMaker::Types::CreateModelPackageInput

show all

Defined in:: gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb

Overview

Constant Summary collapse

SENSITIVE =

[]

Instance Attribute Summary collapse

#additional_inference_specifications ⇒ Array<Types::AdditionalInferenceSpecificationDefinition>
An array of additional Inference Specification objects.
#certify_for_marketplace ⇒ Boolean
Whether to certify the model package for listing on Amazon Web Services Marketplace.
#client_token ⇒ String
A unique token that guarantees that the call to this API is idempotent.
#customer_metadata_properties ⇒ Hash<String,String>
The metadata properties associated with the model package versions.
#domain ⇒ String
The machine learning domain of your model package and its components.
#drift_check_baselines ⇒ Types::DriftCheckBaselines
Represents the drift check baselines that can be used when the model monitor is set using the model package.
#inference_specification ⇒ Types::InferenceSpecification
Specifies details about inference jobs that you can run with models based on this model package, including the following information:.
#metadata_properties ⇒ Types::MetadataProperties
Metadata properties of the tracking entity, trial, or trial component.
#model_approval_status ⇒ String
Whether the model is approved for deployment.
#model_metrics ⇒ Types::ModelMetrics
A structure that contains model metrics reports.
#model_package_description ⇒ String
A description of the model package.
#model_package_group_name ⇒ String
The name or Amazon Resource Name (ARN) of the model package group that this model version belongs to.
#model_package_name ⇒ String
The name of the model package.
#sample_payload_url ⇒ String
The Amazon Simple Storage Service (Amazon S3) path where the sample payload is stored.
#skip_model_validation ⇒ String
Indicates if you want to skip model validation.
#source_algorithm_specification ⇒ Types::SourceAlgorithmSpecification
Details about the algorithm that was used to create the model package.
#source_uri ⇒ String
The URI of the source for the model package.
#tags ⇒ Array<Types::Tag>
A list of key value pairs associated with the model.
#task ⇒ String
The machine learning task your model package accomplishes.
#validation_specification ⇒ Types::ModelPackageValidationSpecification
Specifies configurations for one or more transform jobs that SageMaker runs to test the model package.

Instance Attribute Details

#additional_inference_specifications ⇒ `Array<Types::AdditionalInferenceSpecificationDefinition>`

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.

Returns:

(Array<Types::AdditionalInferenceSpecificationDefinition>)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#certify_for_marketplace ⇒ `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.

Returns:

(Boolean)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#client_token ⇒ `String`

A unique token that guarantees that the call to this API is idempotent.

A suitable default value is auto-generated. You should normally not need to pass this option.

Returns:

(String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#customer_metadata_properties ⇒ `Hash<String,String>`

The metadata properties associated with the model package versions.

Returns:

(Hash<String,String>)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#domain ⇒ `String`

The machine learning domain of your model package and its components. Common machine learning domains include computer vision and natural language processing.

Returns:

(String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#drift_check_baselines ⇒ `Types::DriftCheckBaselines`

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 in the Amazon SageMaker Developer Guide.

Returns:

(Types::DriftCheckBaselines)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#inference_specification ⇒ `Types::InferenceSpecification`

Specifies details about inference jobs that you can run with models based on this model package, including the following information:

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.

Returns:

(Types::InferenceSpecification)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#metadata_properties ⇒ `Types::MetadataProperties`

Metadata properties of the tracking entity, trial, or trial component.

Returns:

(Types::MetadataProperties)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#model_approval_status ⇒ `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.

Returns:

(String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#model_metrics ⇒ `Types::ModelMetrics`

A structure that contains model metrics reports.

Returns:

(Types::ModelMetrics)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#model_package_description ⇒ `String`

A description of the model package.

Returns:

(String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#model_package_group_name ⇒ `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.

Returns:

(String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#model_package_name ⇒ `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.

Returns:

(String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#sample_payload_url ⇒ `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 call.

Returns:

(String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#skip_model_validation ⇒ `String`

Indicates if you want to skip model validation.

Returns:

(String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#source_algorithm_specification ⇒ `Types::SourceAlgorithmSpecification`

Details about the algorithm that was used to create the model package.

Returns:

(Types::SourceAlgorithmSpecification)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#source_uri ⇒ `String`

The URI of the source for the model package. If you want to clone a model package, set it to the model package Amazon Resource Name (ARN). If you want to register a model, set it to the model ARN.

Returns:

(String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#tags ⇒ `Array<Types::Tag>`

A list of key value pairs associated with the model. For more information, see Tagging Amazon Web Services resources in the Amazon Web Services General Reference Guide.

If you supply ModelPackageGroupName, your model package belongs to the model group you specify and uses the tags associated with the model group. In this case, you cannot supply a tag argument.

Returns:

(Array<Types::Tag>)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#task ⇒ `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" | "OBJECT_DETECTION" | "TEXT_GENERATION" |"IMAGE_SEGMENTATION" | "FILL_MASK" | "CLASSIFICATION" | "REGRESSION" | "OTHER".

Specify "OTHER" if none of the tasks listed fit your use case.

Returns:

(String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

#validation_specification ⇒ `Types::ModelPackageValidationSpecification`

Specifies configurations for one or more transform jobs that SageMaker runs to test the model package.

Returns:

(Types::ModelPackageValidationSpecification)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 7972

class CreateModelPackageInput < Struct.new(
  :model_package_name,
  :model_package_group_name,
  :model_package_description,
  :inference_specification,
  :validation_specification,
  :source_algorithm_specification,
  :certify_for_marketplace,
  :tags,
  :model_approval_status,
  :metadata_properties,
  :model_metrics,
  :client_token,
  :domain,
  :task,
  :sample_payload_url,
  :customer_metadata_properties,
  :drift_check_baselines,
  :additional_inference_specifications,
  :skip_model_validation,
  :source_uri)
  SENSITIVE = []
  include Aws::Structure
end

Class: Aws::SageMaker::Types::CreateModelPackageInput

Overview

Constant Summary collapse

Instance Attribute Summary collapse

Instance Attribute Details

#additional_inference_specifications ⇒ Array<Types::AdditionalInferenceSpecificationDefinition>

#certify_for_marketplace ⇒ Boolean

#client_token ⇒ String

#customer_metadata_properties ⇒ Hash<String,String>

#domain ⇒ String

#drift_check_baselines ⇒ Types::DriftCheckBaselines

#inference_specification ⇒ Types::InferenceSpecification

#metadata_properties ⇒ Types::MetadataProperties

#model_approval_status ⇒ String

#model_metrics ⇒ Types::ModelMetrics

#model_package_description ⇒ String

#model_package_group_name ⇒ String

#model_package_name ⇒ String

#sample_payload_url ⇒ String

#skip_model_validation ⇒ String

#source_algorithm_specification ⇒ Types::SourceAlgorithmSpecification

#source_uri ⇒ String

#tags ⇒ Array<Types::Tag>

#task ⇒ String

#validation_specification ⇒ Types::ModelPackageValidationSpecification

#additional_inference_specifications ⇒ `Array<Types::AdditionalInferenceSpecificationDefinition>`

#certify_for_marketplace ⇒ `Boolean`

#client_token ⇒ `String`

#customer_metadata_properties ⇒ `Hash<String,String>`

#domain ⇒ `String`

#drift_check_baselines ⇒ `Types::DriftCheckBaselines`

#inference_specification ⇒ `Types::InferenceSpecification`

#metadata_properties ⇒ `Types::MetadataProperties`

#model_approval_status ⇒ `String`

#model_metrics ⇒ `Types::ModelMetrics`

#model_package_description ⇒ `String`

#model_package_group_name ⇒ `String`

#model_package_name ⇒ `String`

#sample_payload_url ⇒ `String`

#skip_model_validation ⇒ `String`

#source_algorithm_specification ⇒ `Types::SourceAlgorithmSpecification`

#source_uri ⇒ `String`

#tags ⇒ `Array<Types::Tag>`

#task ⇒ `String`

#validation_specification ⇒ `Types::ModelPackageValidationSpecification`