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 2025-03-25 UTC."],[[["This webpage provides documentation for the `ModelType` enum within the `Google.Cloud.AIPlatform.V1.Schema.TrainingJob.Definition` namespace, specifically detailing its use in AutoML image segmentation inputs."],["The latest version of the documentation available is 3.22.0, with a comprehensive list of versions dating back to 1.0.0 provided for reference and historical context."],["The `ModelType` enum includes four possible field values: `CloudHighAccuracy1`, `CloudLowAccuracy1`, `MobileTfLowLatency1`, and `Unspecified`, each with specific implications for prediction latency and quality, as well as exportability for mobile or edge devices."],["The `CloudHighAccuracy1` model field is expected to have higher quality predictions but increased latency compared to other fields, while the `CloudLowAccuracy1` field will have a lower latency but also a relatively lower quality in its predictions."],["The `MobileTfLowLatency1` field can be exported to mobile or edge devices for use, having low latency but a possibility of having lower quality predictions than other mobile models, and `Unspecified` should not be used."]]],[]]
