amazonka-lookoutvision-2.0: Amazon Lookout for Vision SDK.
Copyright(c) 2013-2023 Brendan Hay
LicenseMozilla Public License, v. 2.0.
MaintainerBrendan Hay
Stabilityauto-generated
Portabilitynon-portable (GHC extensions)
Safe HaskellSafe-Inferred
LanguageHaskell2010

Amazonka.LookoutVision.Types.TargetPlatform

Description

 
Synopsis

Documentation

data TargetPlatform Source #

The platform on which a model runs on an AWS IoT Greengrass core device.

See: newTargetPlatform smart constructor.

Constructors

TargetPlatform' 

Fields

  • accelerator :: Maybe TargetPlatformAccelerator

    The target accelerator for the model. Currently, Amazon Lookout for Vision only supports NVIDIA (Nvidia graphics processing unit) and CPU accelerators. If you specify NVIDIA as an accelerator, you must also specify the gpu-code, trt-ver, and cuda-ver compiler options. If you don't specify an accelerator, Lookout for Vision uses the CPU for compilation and we highly recommend that you use the GreengrassConfiguration$CompilerOptions field. For example, you can use the following compiler options for CPU:

    • mcpu: CPU micro-architecture. For example, {'mcpu': 'skylake-avx512'}
    • mattr: CPU flags. For example, {'mattr': ['+neon', '+vfpv4']}
  • os :: TargetPlatformOs

    The target operating system for the model. Linux is the only operating system that is currently supported.

  • arch :: TargetPlatformArch

    The target architecture for the model. The currently supported architectures are X86_64 (64-bit version of the x86 instruction set) and ARM_64 (ARMv8 64-bit CPU).

Instances

Instances details
FromJSON TargetPlatform Source # 
Instance details

Defined in Amazonka.LookoutVision.Types.TargetPlatform

ToJSON TargetPlatform Source # 
Instance details

Defined in Amazonka.LookoutVision.Types.TargetPlatform

Generic TargetPlatform Source # 
Instance details

Defined in Amazonka.LookoutVision.Types.TargetPlatform

Associated Types

type Rep TargetPlatform :: Type -> Type #

Read TargetPlatform Source # 
Instance details

Defined in Amazonka.LookoutVision.Types.TargetPlatform

Show TargetPlatform Source # 
Instance details

Defined in Amazonka.LookoutVision.Types.TargetPlatform

NFData TargetPlatform Source # 
Instance details

Defined in Amazonka.LookoutVision.Types.TargetPlatform

Methods

rnf :: TargetPlatform -> () #

Eq TargetPlatform Source # 
Instance details

Defined in Amazonka.LookoutVision.Types.TargetPlatform

Hashable TargetPlatform Source # 
Instance details

Defined in Amazonka.LookoutVision.Types.TargetPlatform

type Rep TargetPlatform Source # 
Instance details

Defined in Amazonka.LookoutVision.Types.TargetPlatform

type Rep TargetPlatform = D1 ('MetaData "TargetPlatform" "Amazonka.LookoutVision.Types.TargetPlatform" "amazonka-lookoutvision-2.0-3cIJAF9xWxx8xGDY24BOkS" 'False) (C1 ('MetaCons "TargetPlatform'" 'PrefixI 'True) (S1 ('MetaSel ('Just "accelerator") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe TargetPlatformAccelerator)) :*: (S1 ('MetaSel ('Just "os") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 TargetPlatformOs) :*: S1 ('MetaSel ('Just "arch") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 TargetPlatformArch))))

newTargetPlatform Source #

Create a value of TargetPlatform 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:

$sel:accelerator:TargetPlatform', targetPlatform_accelerator - The target accelerator for the model. Currently, Amazon Lookout for Vision only supports NVIDIA (Nvidia graphics processing unit) and CPU accelerators. If you specify NVIDIA as an accelerator, you must also specify the gpu-code, trt-ver, and cuda-ver compiler options. If you don't specify an accelerator, Lookout for Vision uses the CPU for compilation and we highly recommend that you use the GreengrassConfiguration$CompilerOptions field. For example, you can use the following compiler options for CPU:

  • mcpu: CPU micro-architecture. For example, {'mcpu': 'skylake-avx512'}
  • mattr: CPU flags. For example, {'mattr': ['+neon', '+vfpv4']}

$sel:os:TargetPlatform', targetPlatform_os - The target operating system for the model. Linux is the only operating system that is currently supported.

$sel:arch:TargetPlatform', targetPlatform_arch - The target architecture for the model. The currently supported architectures are X86_64 (64-bit version of the x86 instruction set) and ARM_64 (ARMv8 64-bit CPU).

targetPlatform_accelerator :: Lens' TargetPlatform (Maybe TargetPlatformAccelerator) Source #

The target accelerator for the model. Currently, Amazon Lookout for Vision only supports NVIDIA (Nvidia graphics processing unit) and CPU accelerators. If you specify NVIDIA as an accelerator, you must also specify the gpu-code, trt-ver, and cuda-ver compiler options. If you don't specify an accelerator, Lookout for Vision uses the CPU for compilation and we highly recommend that you use the GreengrassConfiguration$CompilerOptions field. For example, you can use the following compiler options for CPU:

  • mcpu: CPU micro-architecture. For example, {'mcpu': 'skylake-avx512'}
  • mattr: CPU flags. For example, {'mattr': ['+neon', '+vfpv4']}

targetPlatform_os :: Lens' TargetPlatform TargetPlatformOs Source #

The target operating system for the model. Linux is the only operating system that is currently supported.

targetPlatform_arch :: Lens' TargetPlatform TargetPlatformArch Source #

The target architecture for the model. The currently supported architectures are X86_64 (64-bit version of the x86 instruction set) and ARM_64 (ARMv8 64-bit CPU).