Yolo8

Constructors

constructor(config: YoloConfig = YoloConfig())

open suspend override fun calculate(module: Module<FP32, Float>, inputValue: Tensor<FP32, Float>, executionContext: ExecutionContext, reportProgress: suspend (current: Int, total: Int, message: String?) -> Unit): Tensor<FP32, Float>

Runs the YOLO graph and returns all head outputs (small/medium/large) for downstream post-processing.

open override fun create(executionContext: ExecutionContext): Module<FP32, Float>

suspend fun infer(module: Module<FP32, Float>, input: YoloInput, executionContext: ExecutionContext, reportProgress: suspend (current: Int, total: Int, message: String?) -> Unit = { _, _, _ -> }): List<Detection>

Full inference: forward pass + decode + NMS. Expects the input tensor to be preprocessed to the configured model size (see YoloPreprocess).

open override fun modelCard(): ModelCard