Amazon Lookout for Vision · JSON Structure

Amazon Lookout For Vision Target Platform Structure

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

Type: object Properties: 3 Required: 2
Computer VisionMachine LearningManufacturingQuality InspectionAnomaly Detection

TargetPlatform is a JSON Structure definition published by Amazon Lookout for Vision, describing 3 properties, of which 2 are required. It conforms to the https://json-structure.org/meta/core/v0/# meta-schema.

Properties

Os Arch Accelerator

Meta-schema: https://json-structure.org/meta/core/v0/#

JSON Structure

Raw ↑
{
  "$schema": "https://json-structure.org/meta/core/v0/#",
  "$id": "https://raw.githubusercontent.com/api-evangelist/amazon-lookout-for-vision/refs/heads/main/json-structure/amazon-lookout-for-vision-target-platform-structure.json",
  "name": "TargetPlatform",
  "description": "The platform on which a model runs on an AWS IoT Greengrass core device.",
  "type": "object",
  "properties": {
    "Os": {
      "allOf": [
        {
          "$ref": "#/components/schemas/TargetPlatformOs"
        },
        {
          "description": "The target operating system for the model. Linux is the only operating system that is currently supported. "
        }
      ]
    },
    "Arch": {
      "allOf": [
        {
          "$ref": "#/components/schemas/TargetPlatformArch"
        },
        {
          "description": "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). "
        }
      ]
    },
    "Accelerator": {
      "allOf": [
        {
          "$ref": "#/components/schemas/TargetPlatformAccelerator"
        },
        {
          "description": "<p>The target accelerator for the model. Currently, Amazon Lookout for Vision only supports NVIDIA (Nvidia graphics processing unit) and CPU accelerators. If you specify NVIDIA as an accelerator, you must also specify the <code>gpu-code</code>, <code>trt-ver</code>, and <code>cuda-ver</code> compiler options. If you don't specify an accelerator, Lookout for Vision uses the CPU for compilation and we highly recommend that you use the <a>GreengrassConfiguration$CompilerOptions</a> field. For example, you can use the following compiler options for CPU: </p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{'mcpu': 'skylake-avx512'}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{'mattr': ['+neon', '+vfpv4']}</code> </p> </li> </ul>"
        }
      ]
    }
  },
  "required": [
    "Os",
    "Arch"
  ]
}