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 2025-08-20 UTC."],[[["\u003cp\u003eThis page lists the available versions of the \u003ccode\u003eAutoMlImageClassificationInputs.Types.ModelType\u003c/code\u003e enum within the \u003ccode\u003eGoogle.Cloud.AIPlatform.V1\u003c/code\u003e library, ranging from version 1.0.0 to the latest, 3.22.0.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eAutoMlImageClassificationInputs.Types.ModelType\u003c/code\u003e enum defines the different types of models available for AutoML image classification, including \u003ccode\u003eCloud\u003c/code\u003e, \u003ccode\u003eMobileTfHighAccuracy1\u003c/code\u003e, \u003ccode\u003eMobileTfLowLatency1\u003c/code\u003e, \u003ccode\u003eMobileTfVersatile1\u003c/code\u003e, and \u003ccode\u003eUnspecified\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eCloud\u003c/code\u003e model type is designed for use within Google Cloud and cannot be exported, while the mobile model types (\u003ccode\u003eMobileTfHighAccuracy1\u003c/code\u003e, \u003ccode\u003eMobileTfLowLatency1\u003c/code\u003e, \u003ccode\u003eMobileTfVersatile1\u003c/code\u003e) can be exported as TensorFlow or Core ML models for mobile or edge devices.\u003c/p\u003e\n"],["\u003cp\u003eThe mobile model types offer different trade-offs between prediction quality and latency, with \u003ccode\u003eMobileTfHighAccuracy1\u003c/code\u003e offering higher quality but with higher latency, and \u003ccode\u003eMobileTfLowLatency1\u003c/code\u003e offering lower latency, but with potentially reduced quality.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eUnspecified\u003c/code\u003e model type is intended to be a placeholder value that should not be explicitly set, while the most recent version of the model type is 3.22.0.\u003c/p\u003e\n"]]],[],null,[]]
