A Model best tailored to be used within Google Cloud, and which cannot
be exported.
Default.
MobileTfHighAccuracy1
A model that, in addition to being available within Google
Cloud, can also be exported (see ModelService.ExportModel) as TensorFlow
or Core ML model and used on a mobile or edge device afterwards.
Expected to have a higher latency, but should also have a higher
prediction quality than other mobile models.
MobileTfLowLatency1
A model that, in addition to being available within Google
Cloud, can also be exported (see ModelService.ExportModel) as TensorFlow
or Core ML model and used on a mobile or edge device afterwards.
Expected to have low latency, but may have lower prediction
quality than other mobile models.
MobileTfVersatile1
A model that, in addition to being available within Google
Cloud, can also be exported (see ModelService.ExportModel) as TensorFlow
or Core ML model and used on a mobile or edge device with 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 documents the `AutoMlImageClassificationInputs.Types.ModelType` enum, which is part of the `Google.Cloud.AIPlatform.V1Beta1.Schema.TrainingJob.Definition` namespace and the `Google.Cloud.AIPlatform.V1Beta1.dll` assembly."],["The `ModelType` enum defines different types of models for AutoML image classification, including `Cloud`, `MobileTfHighAccuracy1`, `MobileTfLowLatency1`, `MobileTfVersatile1`, and `Unspecified`."],["`Cloud` models are designed for use within Google Cloud and are not exportable, while the mobile models can be exported as TensorFlow or Core ML for use on mobile or edge devices."],["The mobile model types differ in latency and prediction accuracy, with `MobileTfHighAccuracy1` emphasizing higher accuracy and `MobileTfLowLatency1` emphasizing low latency."]]],[]]
