Copyright	(c) 2013-2021 Brendan Hay
License	Mozilla Public License, v. 2.0.
Maintainer	Brendan Hay <brendan.g.hay+amazonka@gmail.com>
Stability	auto-generated
Portability	non-portable (GHC extensions)
Safe Haskell	None

Amazonka.SageMaker.Types.InferenceSpecification

Description

Synopsis

Documentation

data InferenceSpecification Source #

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

See: newInferenceSpecification smart constructor.

Constructors

InferenceSpecification'

Fields

supportedRealtimeInferenceInstanceTypes :: Maybe [ProductionVariantInstanceType]
A list of the instance types that are used to generate inferences in real-time.
This parameter is required for unversioned models, and optional for versioned models.
supportedTransformInstanceTypes :: Maybe (NonEmpty TransformInstanceType)
A list of the instance types on which a transformation job can be run or on which an endpoint can be deployed.
This parameter is required for unversioned models, and optional for versioned models.
containers :: NonEmpty ModelPackageContainerDefinition
The Amazon ECR registry path of the Docker image that contains the inference code.
supportedContentTypes :: [Text]
The supported MIME types for the input data.
supportedResponseMIMETypes :: [Text]
The supported MIME types for the output data.

Instances

Instances details

Eq InferenceSpecification Source #
Instance details Defined in Amazonka.SageMaker.Types.InferenceSpecification Methods (==) :: InferenceSpecification -> InferenceSpecification -> Bool # (/=) :: InferenceSpecification -> InferenceSpecification -> Bool #
Read InferenceSpecification Source #
Instance details Defined in Amazonka.SageMaker.Types.InferenceSpecification Methods readsPrec :: Int -> ReadS InferenceSpecification # readList :: ReadS [InferenceSpecification] # readPrec :: ReadPrec InferenceSpecification # readListPrec :: ReadPrec [InferenceSpecification] #
Show InferenceSpecification Source #
Instance details Defined in Amazonka.SageMaker.Types.InferenceSpecification Methods showsPrec :: Int -> InferenceSpecification -> ShowS # show :: InferenceSpecification -> String # showList :: [InferenceSpecification] -> ShowS #
Generic InferenceSpecification Source #
Instance details Defined in Amazonka.SageMaker.Types.InferenceSpecification Associated Types type Rep InferenceSpecification :: Type -> Type # Methods from :: InferenceSpecification -> Rep InferenceSpecification x # to :: Rep InferenceSpecification x -> InferenceSpecification #
NFData InferenceSpecification Source #
Instance details Defined in Amazonka.SageMaker.Types.InferenceSpecification Methods rnf :: InferenceSpecification -> () #
Hashable InferenceSpecification Source #
Instance details Defined in Amazonka.SageMaker.Types.InferenceSpecification Methods hashWithSalt :: Int -> InferenceSpecification -> Int # hash :: InferenceSpecification -> Int #
ToJSON InferenceSpecification Source #
Instance details Defined in Amazonka.SageMaker.Types.InferenceSpecification Methods toJSON :: InferenceSpecification -> Value # toEncoding :: InferenceSpecification -> Encoding # toJSONList :: [InferenceSpecification] -> Value # toEncodingList :: [InferenceSpecification] -> Encoding #
FromJSON InferenceSpecification Source #
Instance details Defined in Amazonka.SageMaker.Types.InferenceSpecification Methods parseJSON :: Value -> Parser InferenceSpecification # parseJSONList :: Value -> Parser [InferenceSpecification] #
type Rep InferenceSpecification Source #
Instance details Defined in Amazonka.SageMaker.Types.InferenceSpecification type Rep InferenceSpecification = D1 ('MetaData "InferenceSpecification" "Amazonka.SageMaker.Types.InferenceSpecification" "libZSservicesZSamazonka-sagemakerZSamazonka-sagemaker" 'False) (C1 ('MetaCons "InferenceSpecification'" 'PrefixI 'True) ((S1 ('MetaSel ('Just "supportedRealtimeInferenceInstanceTypes") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe [ProductionVariantInstanceType])) :: S1 ('MetaSel ('Just "supportedTransformInstanceTypes") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (NonEmpty TransformInstanceType)))) :: (S1 ('MetaSel ('Just "containers") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (NonEmpty ModelPackageContainerDefinition)) :: (S1 ('MetaSel ('Just "supportedContentTypes") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 [Text]) :: S1 ('MetaSel ('Just "supportedResponseMIMETypes") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 [Text])))))

newInferenceSpecification Source #

Arguments

:: NonEmpty ModelPackageContainerDefinition	`$sel:containers:InferenceSpecification'`
-> InferenceSpecification

Create a value of InferenceSpecification 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:supportedRealtimeInferenceInstanceTypes:InferenceSpecification', inferenceSpecification_supportedRealtimeInferenceInstanceTypes - A list of the instance types that are used to generate inferences in real-time.

This parameter is required for unversioned models, and optional for versioned models.

$sel:supportedTransformInstanceTypes:InferenceSpecification', inferenceSpecification_supportedTransformInstanceTypes - A list of the instance types on which a transformation job can be run or on which an endpoint can be deployed.

This parameter is required for unversioned models, and optional for versioned models.

$sel:containers:InferenceSpecification', inferenceSpecification_containers - The Amazon ECR registry path of the Docker image that contains the inference code.

$sel:supportedContentTypes:InferenceSpecification', inferenceSpecification_supportedContentTypes - The supported MIME types for the input data.

$sel:supportedResponseMIMETypes:InferenceSpecification', inferenceSpecification_supportedResponseMIMETypes - The supported MIME types for the output data.

inferenceSpecification_supportedRealtimeInferenceInstanceTypes :: Lens' InferenceSpecification (Maybe [ProductionVariantInstanceType]) Source #

A list of the instance types that are used to generate inferences in real-time.

This parameter is required for unversioned models, and optional for versioned models.

inferenceSpecification_supportedTransformInstanceTypes :: Lens' InferenceSpecification (Maybe (NonEmpty TransformInstanceType)) Source #

A list of the instance types on which a transformation job can be run or on which an endpoint can be deployed.

This parameter is required for unversioned models, and optional for versioned models.

inferenceSpecification_containers :: Lens' InferenceSpecification (NonEmpty ModelPackageContainerDefinition) Source #

The Amazon ECR registry path of the Docker image that contains the inference code.

inferenceSpecification_supportedContentTypes :: Lens' InferenceSpecification [Text] Source #

The supported MIME types for the input data.

inferenceSpecification_supportedResponseMIMETypes :: Lens' InferenceSpecification [Text] Source #

The supported MIME types for the output data.