A model to be used via prediction calls to uCAIP API. Expected
to have a higher latency, but should also have a higher prediction
quality than other models.
CloudLowAccuracy1
A model to be used via prediction calls to uCAIP API. Expected
to have a lower latency but relatively lower prediction quality.
MobileTfLowLatency1
A model that, in addition to being available within Google
Cloud, can also be exported (see ModelService.ExportModel) as TensorFlow
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.
[[["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\u003eThe latest version of the \u003ccode\u003eAutoMlImageSegmentationInputs.Types.ModelType\u003c/code\u003e is 3.22.0, which can be found in the \u003ccode\u003eGoogle.Cloud.AIPlatform.V1\u003c/code\u003e namespace.\u003c/p\u003e\n"],["\u003cp\u003eThis page provides a comprehensive list of historical versions of \u003ccode\u003eAutoMlImageSegmentationInputs.Types.ModelType\u003c/code\u003e, ranging from version 1.0.0 up to the latest 3.22.0.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eModelType\u003c/code\u003e enum defines four different types of models, including \u003ccode\u003eCloudHighAccuracy1\u003c/code\u003e, \u003ccode\u003eCloudLowAccuracy1\u003c/code\u003e, \u003ccode\u003eMobileTfLowLatency1\u003c/code\u003e, and \u003ccode\u003eUnspecified\u003c/code\u003e, each with distinct characteristics related to prediction quality and latency.\u003c/p\u003e\n"],["\u003cp\u003eEach of these model types have descriptions that explain when they should be used, for example \u003ccode\u003eCloudHighAccuracy1\u003c/code\u003e has a higher latency but higher prediction quality while \u003ccode\u003eMobileTfLowLatency1\u003c/code\u003e can be used on a mobile or edge device.\u003c/p\u003e\n"]]],[],null,[]]
