Class: Aws::SageMaker::Types::ModelPackageContainerDefinition

Inherits:

Struct

• Object
• Struct
• Aws::SageMaker::Types::ModelPackageContainerDefinition

Includes:

Aws::Structure

Defined in:

lib/aws-sdk-sagemaker/types.rb

Overview

Describes the Docker container for the model package.

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[]

Instance Attribute Summary

• #additional_model_data_sources ⇒ Array<Types::AdditionalModelDataSource>

  Data sources that are available to your model in addition to the one that you specify for ‘ModelDataSource` when you use the `CreateModelPackage` action.

• #additional_s3_data_source ⇒ Types::AdditionalS3DataSource

  The additional data source that is used during inference in the Docker container for your model package.

• #base_model ⇒ Types::BaseModel

  Identifies the foundation model that was used as the starting point for model customization.

• #container_hostname ⇒ String

  The DNS host name for the Docker container.

• #environment ⇒ Hash<String,String>

  The environment variables to set in the Docker container.

• #framework ⇒ String

  The machine learning framework of the model package container image.

• #framework_version ⇒ String

  The framework version of the Model Package Container Image.

• #image ⇒ String

  The Amazon Elastic Container Registry (Amazon ECR) path where inference code is stored.

• #image_digest ⇒ String

  An MD5 hash of the training algorithm that identifies the Docker image used for training.

• #is_checkpoint ⇒ Boolean

  Specifies whether the model data is a training checkpoint.

• #model_data_etag ⇒ String

  The ETag associated with Model Data URL.

• #model_data_source ⇒ Types::ModelDataSource

  Specifies the location of ML model data to deploy during endpoint creation.

• #model_data_url ⇒ String

  The Amazon S3 path where the model artifacts, which result from model training, are stored.

• #model_input ⇒ Types::ModelInput

  A structure with Model Input details.

• #nearest_model_name ⇒ String

  The name of a pre-trained machine learning benchmarked by Amazon SageMaker Inference Recommender model that matches your model.

• #product_id ⇒ String

  The Amazon Web Services Marketplace product ID of the model package.

Instance Attribute Details

#additional_model_data_sources ⇒ Array<Types::AdditionalModelDataSource>

Data sources that are available to your model in addition to the one that you specify for ‘ModelDataSource` when you use the `CreateModelPackage` action.

Returns:

• (Array<Types::AdditionalModelDataSource>)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#additional_s3_data_source ⇒ Types::AdditionalS3DataSource

The additional data source that is used during inference in the Docker container for your model package.

Returns:

• (Types::AdditionalS3DataSource)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#base_model ⇒ Types::BaseModel

Identifies the foundation model that was used as the starting point for model customization.

Returns:

• (Types::BaseModel)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#container_hostname ⇒ String

The DNS host name for the Docker container.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#environment ⇒ Hash<String,String>

The environment variables to set in the Docker container. Each key and value in the ‘Environment` string to string map can have length of up to 1024. We support up to 16 entries in the map.

Returns:

• (Hash<String,String>)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#framework ⇒ String

The machine learning framework of the model package container image.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#framework_version ⇒ String

The framework version of the Model Package Container Image.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#image ⇒ String

The Amazon Elastic Container Registry (Amazon ECR) path where inference code is stored.

If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both ‘registry/repository` and `registry/repository` image path formats. For more information, see [Using Your Own Algorithms with Amazon SageMaker].

[1]: docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms.html

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#image_digest ⇒ String

An MD5 hash of the training algorithm that identifies the Docker image used for training.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#is_checkpoint ⇒ Boolean

Specifies whether the model data is a training checkpoint.

Returns:

• (Boolean)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#model_data_etag ⇒ String

The ETag associated with Model Data URL.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#model_data_source ⇒ Types::ModelDataSource

Specifies the location of ML model data to deploy during endpoint creation.

Returns:

• (Types::ModelDataSource)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#model_data_url ⇒ String

The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single ‘gzip` compressed tar archive (`.tar.gz` suffix).

<note markdown=“1”> The model artifacts must be in an S3 bucket that is in the same region as the model package.

</note>

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#model_input ⇒ Types::ModelInput

A structure with Model Input details.

Returns:

• (Types::ModelInput)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#nearest_model_name ⇒ String

The name of a pre-trained machine learning benchmarked by Amazon SageMaker Inference Recommender model that matches your model. You can find a list of benchmarked models by calling ‘ListModelMetadata`.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end

#product_id ⇒ String

The Amazon Web Services Marketplace product ID of the model package.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 41944

class ModelPackageContainerDefinition < Struct.new(
  :container_hostname,
  :image,
  :image_digest,
  :model_data_url,
  :model_data_source,
  :product_id,
  :environment,
  :model_input,
  :framework,
  :framework_version,
  :nearest_model_name,
  :additional_model_data_sources,
  :additional_s3_data_source,
  :model_data_etag,
  :is_checkpoint,
  :base_model)
  SENSITIVE = []
  include Aws::Structure
end