Package com.codename1.ai.inference

package com.codename1.ai.inference

Reusable on-device inference sessions for .tflite models.

Android uses LiteRT. iOS uses TensorFlow Lite Objective-C and may select the Core ML delegate. The builder links the runtime only when an application references InferenceSession. Other targets expose the same API with an explicit unsupported fallback.

  • Class
    Description
    InferenceException
    Failure while loading or executing a LiteRT model.
    InferenceOptions
    LiteRT session configuration.
    InferenceOptions.Accelerator
     
    InferenceSession
    Reusable LiteRT model session.
    ModelCache
    Downloads large LiteRT models once and exposes the cached file as a ModelSource.
    ModelSource
    A .tflite model supplied as bytes, a filesystem path, or an app resource.
    Tensor
    Named tensor value passed to or returned from an inference session.
    TensorInfo
    Immutable model input/output metadata.
    TensorType
    Tensor element types supported by the portable LiteRT contract.