A model best tailored to be used within Google Cloud, and which c annot
be exported. Default.
MobileCoralLowLatency1
A model that trades off quality for low latency, to be exported (see
ModelService.ExportModel) and used on a Google Coral device.
MobileCoralVersatile1
A versatile model that is meant to be exported (see
ModelService.ExportModel) and used on a Google Coral device.
MobileJetsonLowLatency1
A model that trades off quality for low latency, to be exported (see
ModelService.ExportModel) and used on an NVIDIA Jetson device.
MobileJetsonVersatile1
A versatile model that is meant to be exported (see
ModelService.ExportModel) and used on an NVIDIA Jetson device.
MobileVersatile1
A model that, in addition to being available within Google Cloud, can
also be exported (see ModelService.ExportModel) as a TensorFlow or
TensorFlow Lite model and used on a mobile or edge device afterwards.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-03-25 UTC."],[[["This page details the `ModelType` enum within the `Google.Cloud.AIPlatform.V1.Schema.TrainingJob.Definition` namespace, part of the Google.Cloud.AIPlatform.V1.dll assembly."],["The latest version documented is 3.22.0, with a comprehensive history of previous versions available, ranging from 1.0.0 up to the most recent."],["The `ModelType` enum specifies various model types, including `Cloud` for Google Cloud use, several mobile-optimized options such as `MobileCoralLowLatency1`, `MobileJetsonVersatile1` and `MobileVersatile1` for deployment on edge devices, as well as an `Unspecified` field."],["Several model types are tailored for specific hardware, like Google Coral (`MobileCoral`) and NVIDIA Jetson (`MobileJetson`) devices, with variations for low-latency and versatile performance."],["Exporting models for mobile or edge device deployment is possible for certain types, such as `MobileVersatile1`, `MobileCoralLowLatency1`, and `MobileJetsonVersatile1` as TensorFlow or TensorFlow Lite models, enabling on-device use after export via `ModelService.ExportModel`."]]],[]]
