Struct ModelPackage

#[non_exhaustive]
pub struct ModelPackage {

    pub model_package_name: Option<String>,
    pub model_package_group_name: Option<String>,
    pub model_package_version: Option<i32>,
    pub model_package_arn: Option<String>,
    pub model_package_description: Option<String>,
    pub creation_time: Option<DateTime>,
    pub inference_specification: Option<InferenceSpecification>,
    pub source_algorithm_specification: Option<SourceAlgorithmSpecification>,
    pub validation_specification: Option<ModelPackageValidationSpecification>,
    pub model_package_status: Option<ModelPackageStatus>,
    pub model_package_status_details: Option<ModelPackageStatusDetails>,
    pub certify_for_marketplace: Option<bool>,
    pub model_approval_status: Option<ModelApprovalStatus>,
    pub created_by: Option<UserContext>,
    pub metadata_properties: Option<MetadataProperties>,
    pub model_metrics: Option<ModelMetrics>,
    pub last_modified_time: Option<DateTime>,
    pub last_modified_by: Option<UserContext>,
    pub approval_description: Option<String>,
    pub domain: Option<String>,
    pub task: Option<String>,
    pub sample_payload_url: Option<String>,
    pub additional_inference_specifications: Option<Vec<AdditionalInferenceSpecificationDefinition>>,
    pub source_uri: Option<String>,
    pub security_config: Option<ModelPackageSecurityConfig>,
    pub model_card: Option<ModelPackageModelCard>,
    pub model_life_cycle: Option<ModelLifeCycle>,
    pub tags: Option<Vec<Tag>>,
    pub customer_metadata_properties: Option<HashMap<String, String>>,
    pub drift_check_baselines: Option<DriftCheckBaselines>,
    pub skip_model_validation: Option<SkipModelValidation>,
}

A container for your trained model that can be deployed for SageMaker inference. This can include inference code, artifacts, and metadata. The model package type can be one of the following.

• Versioned model: A part of a model package group in Model Registry.

• Unversioned model: Not part of a model package group and used in Amazon Web Services Marketplace.

For more information, see CreateModelPackage .

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

model_package_name: Option<String>

The name of the model package. The name can be as follows:

• For a versioned model, the name is automatically generated by SageMaker Model Registry and follows the format 'ModelPackageGroupName/ModelPackageVersion'.

• For an unversioned model, you must provide the name.

model_package_group_name: Option<String>

The model group to which the model belongs.

model_package_version: Option<i32>

The version number of a versioned model.

model_package_arn: Option<String>

The Amazon Resource Name (ARN) of the model package.

model_package_description: Option<String>

The description of the model package.

creation_time: Option<DateTime>

The time that the model package was created.

inference_specification: Option<InferenceSpecification>

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

source_algorithm_specification: Option<SourceAlgorithmSpecification>

A list of algorithms that were used to create a model package.

validation_specification: Option<ModelPackageValidationSpecification>

Specifies batch transform jobs that SageMaker runs to validate your model package.

model_package_status: Option<ModelPackageStatus>

The status of the model package. This can be one of the following values.

• PENDING - The model package is pending being created.

• IN_PROGRESS - The model package is in the process of being created.

• COMPLETED - The model package was successfully created.

• FAILED - The model package failed.

• DELETING - The model package is in the process of being deleted.

model_package_status_details: Option<ModelPackageStatusDetails>

Specifies the validation and image scan statuses of the model package.

certify_for_marketplace: Option<bool>

Whether the model package is to be certified to be listed on Amazon Web Services Marketplace. For information about listing model packages on Amazon Web Services Marketplace, see List Your Algorithm or Model Package on Amazon Web Services Marketplace.

model_approval_status: Option<ModelApprovalStatus>

The approval status of the model. This can be one of the following values.

• APPROVED - The model is approved

• REJECTED - The model is rejected.

• PENDING_MANUAL_APPROVAL - The model is waiting for manual approval.

created_by: Option<UserContext>

Information about the user who created or modified an experiment, trial, trial component, lineage group, or project.

metadata_properties: Option<MetadataProperties>

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

model_metrics: Option<ModelMetrics>

Metrics for the model.

last_modified_time: Option<DateTime>

The last time the model package was modified.

last_modified_by: Option<UserContext>

Information about the user who created or modified an experiment, trial, trial component, lineage group, or project.

approval_description: Option<String>

A description provided when the model approval is set.

domain: Option<String>

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

task: Option<String>

The machine learning task your model package accomplishes. Common machine learning tasks include object detection and image classification.

sample_payload_url: Option<String>

The Amazon Simple Storage Service path where the sample payload are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

additional_inference_specifications: Option<Vec<AdditionalInferenceSpecificationDefinition>>

An array of additional Inference Specification objects.

source_uri: Option<String>

The URI of the source for the model package.

security_config: Option<ModelPackageSecurityConfig>

An optional Key Management Service key to encrypt, decrypt, and re-encrypt model package information for regulated workloads with highly sensitive data.

model_card: Option<ModelPackageModelCard>

The model card associated with the model package. Since ModelPackageModelCard is tied to a model package, it is a specific usage of a model card and its schema is simplified compared to the schema of ModelCard. The ModelPackageModelCard schema does not include model_package_details, and model_overview is composed of the model_creator and model_artifact properties. For more information about the model package model card schema, see Model package model card schema. For more information about the model card associated with the model package, see View the Details of a Model Version.

model_life_cycle: Option<ModelLifeCycle>

A structure describing the current state of the model in its life cycle.

tags: Option<Vec<Tag>>

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

customer_metadata_properties: Option<HashMap<String, String>>

The metadata properties for the model package.

drift_check_baselines: Option<DriftCheckBaselines>

Represents the drift check baselines that can be used when the model monitor is set using the model package.

skip_model_validation: Option<SkipModelValidation>

Indicates if you want to skip model validation.

Implementations

impl ModelPackage

pub fn model_package_name(&self) -> Option<&str>

The name of the model package. The name can be as follows:

• For a versioned model, the name is automatically generated by SageMaker Model Registry and follows the format 'ModelPackageGroupName/ModelPackageVersion'.

• For an unversioned model, you must provide the name.

pub fn model_package_group_name(&self) -> Option<&str>

The model group to which the model belongs.

pub fn model_package_version(&self) -> Option<i32>

The version number of a versioned model.

pub fn model_package_arn(&self) -> Option<&str>

The Amazon Resource Name (ARN) of the model package.

pub fn model_package_description(&self) -> Option<&str>

The description of the model package.

pub fn creation_time(&self) -> Option<&DateTime>

The time that the model package was created.

pub fn inference_specification(&self) -> Option<&InferenceSpecification>

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

pub fn source_algorithm_specification( &self, ) -> Option<&SourceAlgorithmSpecification>

A list of algorithms that were used to create a model package.

pub fn validation_specification( &self, ) -> Option<&ModelPackageValidationSpecification>

Specifies batch transform jobs that SageMaker runs to validate your model package.

pub fn model_package_status(&self) -> Option<&ModelPackageStatus>

The status of the model package. This can be one of the following values.

• PENDING - The model package is pending being created.

• IN_PROGRESS - The model package is in the process of being created.

• COMPLETED - The model package was successfully created.

• FAILED - The model package failed.

• DELETING - The model package is in the process of being deleted.

pub fn model_package_status_details(&self) -> Option<&ModelPackageStatusDetails>

Specifies the validation and image scan statuses of the model package.

pub fn certify_for_marketplace(&self) -> Option<bool>

Whether the model package is to be certified to be listed on Amazon Web Services Marketplace. For information about listing model packages on Amazon Web Services Marketplace, see List Your Algorithm or Model Package on Amazon Web Services Marketplace.

pub fn model_approval_status(&self) -> Option<&ModelApprovalStatus>

The approval status of the model. This can be one of the following values.

• APPROVED - The model is approved

• REJECTED - The model is rejected.

• PENDING_MANUAL_APPROVAL - The model is waiting for manual approval.

pub fn created_by(&self) -> Option<&UserContext>

Information about the user who created or modified an experiment, trial, trial component, lineage group, or project.

pub fn metadata_properties(&self) -> Option<&MetadataProperties>

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

pub fn model_metrics(&self) -> Option<&ModelMetrics>

Metrics for the model.

pub fn last_modified_time(&self) -> Option<&DateTime>

The last time the model package was modified.

pub fn last_modified_by(&self) -> Option<&UserContext>

Information about the user who created or modified an experiment, trial, trial component, lineage group, or project.

pub fn approval_description(&self) -> Option<&str>

A description provided when the model approval is set.

pub fn domain(&self) -> Option<&str>

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

pub fn task(&self) -> Option<&str>

The machine learning task your model package accomplishes. Common machine learning tasks include object detection and image classification.

pub fn sample_payload_url(&self) -> Option<&str>

The Amazon Simple Storage Service path where the sample payload are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

pub fn additional_inference_specifications( &self, ) -> &[AdditionalInferenceSpecificationDefinition]

An array of additional Inference Specification objects.

If no value was sent for this field, a default will be set. If you want to determine if no value was sent, use .additional_inference_specifications.is_none().

pub fn source_uri(&self) -> Option<&str>

The URI of the source for the model package.

pub fn security_config(&self) -> Option<&ModelPackageSecurityConfig>

An optional Key Management Service key to encrypt, decrypt, and re-encrypt model package information for regulated workloads with highly sensitive data.

pub fn model_card(&self) -> Option<&ModelPackageModelCard>

The model card associated with the model package. Since ModelPackageModelCard is tied to a model package, it is a specific usage of a model card and its schema is simplified compared to the schema of ModelCard. The ModelPackageModelCard schema does not include model_package_details, and model_overview is composed of the model_creator and model_artifact properties. For more information about the model package model card schema, see Model package model card schema. For more information about the model card associated with the model package, see View the Details of a Model Version.

pub fn model_life_cycle(&self) -> Option<&ModelLifeCycle>

A structure describing the current state of the model in its life cycle.

pub fn tags(&self) -> &[Tag]

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

If no value was sent for this field, a default will be set. If you want to determine if no value was sent, use .tags.is_none().

pub fn customer_metadata_properties(&self) -> Option<&HashMap<String, String>>

The metadata properties for the model package.

pub fn drift_check_baselines(&self) -> Option<&DriftCheckBaselines>

Represents the drift check baselines that can be used when the model monitor is set using the model package.

pub fn skip_model_validation(&self) -> Option<&SkipModelValidation>

Indicates if you want to skip model validation.

impl ModelPackage

pub fn builder() -> ModelPackageBuilder

Creates a new builder-style object to manufacture ModelPackage.

Trait Implementations

impl Clone for ModelPackage

fn clone(&self) -> ModelPackage

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ModelPackage

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for ModelPackage

fn eq(&self, other: &ModelPackage) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for ModelPackage