Amazonka.SageMaker.Types.ModelPackageContainerDefinition

Documentation

data ModelPackageContainerDefinition

Describes the Docker container for the model package.

See: newModelPackageContainerDefinition smart constructor.

Constructors

ModelPackageContainerDefinition'

Fields

• containerHostname :: Maybe Text

  The DNS host name for the Docker container.

• environment :: Maybe (HashMap Text Text)

  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.

• framework :: Maybe Text

  The machine learning framework of the model package container image.

• frameworkVersion :: Maybe Text

  The framework version of the Model Package Container Image.

• imageDigest :: Maybe Text

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

• modelDataUrl :: Maybe Text

  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).

  The model artifacts must be in an S3 bucket that is in the same region as the model package.

• modelInput :: Maybe ModelInput

  A structure with Model Input details.

• nearestModelName :: Maybe Text

  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.

• productId :: Maybe Text

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

• image :: Text

  The Amazon EC2 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[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.

Instances

FromJSON ModelPackageContainerDefinition

Defined in Amazonka.SageMaker.Types.ModelPackageContainerDefinition

Methods

parseJSON :: Value -> Parser ModelPackageContainerDefinition

parseJSONList :: Value -> Parser [ModelPackageContainerDefinition]

ToJSON ModelPackageContainerDefinition

Defined in Amazonka.SageMaker.Types.ModelPackageContainerDefinition

Methods

toJSON :: ModelPackageContainerDefinition -> Value

toEncoding :: ModelPackageContainerDefinition -> Encoding

toJSONList :: [ModelPackageContainerDefinition] -> Value

toEncodingList :: [ModelPackageContainerDefinition] -> Encoding

Generic ModelPackageContainerDefinition

Defined in Amazonka.SageMaker.Types.ModelPackageContainerDefinition

Associated Types

type Rep ModelPackageContainerDefinition :: Type -> Type

Methods

from :: ModelPackageContainerDefinition -> Rep ModelPackageContainerDefinition x

to :: Rep ModelPackageContainerDefinition x -> ModelPackageContainerDefinition

Read ModelPackageContainerDefinition

Defined in Amazonka.SageMaker.Types.ModelPackageContainerDefinition

Methods

readsPrec :: Int -> ReadS ModelPackageContainerDefinition

readList :: ReadS [ModelPackageContainerDefinition]

readPrec :: ReadPrec ModelPackageContainerDefinition

readListPrec :: ReadPrec [ModelPackageContainerDefinition]

Show ModelPackageContainerDefinition

Defined in Amazonka.SageMaker.Types.ModelPackageContainerDefinition

Methods

showsPrec :: Int -> ModelPackageContainerDefinition -> ShowS

show :: ModelPackageContainerDefinition -> String

showList :: [ModelPackageContainerDefinition] -> ShowS

NFData ModelPackageContainerDefinition

Defined in Amazonka.SageMaker.Types.ModelPackageContainerDefinition

Methods

rnf :: ModelPackageContainerDefinition -> ()

Eq ModelPackageContainerDefinition

Defined in Amazonka.SageMaker.Types.ModelPackageContainerDefinition

Methods

(==) :: ModelPackageContainerDefinition -> ModelPackageContainerDefinition -> Bool

(/=) :: ModelPackageContainerDefinition -> ModelPackageContainerDefinition -> Bool

Hashable ModelPackageContainerDefinition

Defined in Amazonka.SageMaker.Types.ModelPackageContainerDefinition

Methods

hashWithSalt :: Int -> ModelPackageContainerDefinition -> Int

hash :: ModelPackageContainerDefinition -> Int

type Rep ModelPackageContainerDefinition

Defined in Amazonka.SageMaker.Types.ModelPackageContainerDefinition

type Rep ModelPackageContainerDefinition = D1 ('MetaData "ModelPackageContainerDefinition" "Amazonka.SageMaker.Types.ModelPackageContainerDefinition" "amazonka-sagemaker-2.0-9SyrKZ4KqhsL1qX9u3ILA3" 'False) (C1 ('MetaCons "ModelPackageContainerDefinition'" 'PrefixI 'True) (((S1 ('MetaSel ('Just "containerHostname") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "environment") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (HashMap Text Text)))) :*: (S1 ('MetaSel ('Just "framework") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: (S1 ('MetaSel ('Just "frameworkVersion") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "imageDigest") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text))))) :*: ((S1 ('MetaSel ('Just "modelDataUrl") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "modelInput") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe ModelInput))) :*: (S1 ('MetaSel ('Just "nearestModelName") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: (S1 ('MetaSel ('Just "productId") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "image") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text))))))

newModelPackageContainerDefinition

Arguments

:: Text

$sel:image:ModelPackageContainerDefinition'

-> ModelPackageContainerDefinition

Create a value of ModelPackageContainerDefinition with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:containerHostname:ModelPackageContainerDefinition', modelPackageContainerDefinition_containerHostname - The DNS host name for the Docker container.

$sel:environment:ModelPackageContainerDefinition', modelPackageContainerDefinition_environment - 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.

$sel:framework:ModelPackageContainerDefinition', modelPackageContainerDefinition_framework - The machine learning framework of the model package container image.

$sel:frameworkVersion:ModelPackageContainerDefinition', modelPackageContainerDefinition_frameworkVersion - The framework version of the Model Package Container Image.

$sel:imageDigest:ModelPackageContainerDefinition', modelPackageContainerDefinition_imageDigest - An MD5 hash of the training algorithm that identifies the Docker image used for training.

$sel:modelDataUrl:ModelPackageContainerDefinition', modelPackageContainerDefinition_modelDataUrl - 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).

The model artifacts must be in an S3 bucket that is in the same region as the model package.

$sel:modelInput:ModelPackageContainerDefinition', modelPackageContainerDefinition_modelInput - A structure with Model Input details.

$sel:nearestModelName:ModelPackageContainerDefinition', modelPackageContainerDefinition_nearestModelName - 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.

$sel:productId:ModelPackageContainerDefinition', modelPackageContainerDefinition_productId - The Amazon Web Services Marketplace product ID of the model package.

$sel:image:ModelPackageContainerDefinition', modelPackageContainerDefinition_image - The Amazon EC2 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[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.

modelPackageContainerDefinition_containerHostname :: Lens' ModelPackageContainerDefinition (Maybe Text)

The DNS host name for the Docker container.

modelPackageContainerDefinition_environment :: Lens' ModelPackageContainerDefinition (Maybe (HashMap Text Text))

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.

modelPackageContainerDefinition_framework :: Lens' ModelPackageContainerDefinition (Maybe Text)

The machine learning framework of the model package container image.

modelPackageContainerDefinition_frameworkVersion :: Lens' ModelPackageContainerDefinition (Maybe Text)

The framework version of the Model Package Container Image.

modelPackageContainerDefinition_imageDigest :: Lens' ModelPackageContainerDefinition (Maybe Text)

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

modelPackageContainerDefinition_modelDataUrl :: Lens' ModelPackageContainerDefinition (Maybe Text)

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).

The model artifacts must be in an S3 bucket that is in the same region as the model package.

modelPackageContainerDefinition_modelInput :: Lens' ModelPackageContainerDefinition (Maybe ModelInput)

A structure with Model Input details.

modelPackageContainerDefinition_nearestModelName :: Lens' ModelPackageContainerDefinition (Maybe Text)

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.

modelPackageContainerDefinition_productId :: Lens' ModelPackageContainerDefinition (Maybe Text)

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

modelPackageContainerDefinition_image :: Lens' ModelPackageContainerDefinition Text

The Amazon EC2 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[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.