skainet-model-yolo/sk.ainet.lang.model.dnn.yolo

Package-level declarations

Types

Box

data class Box(val x1: Float, val y1: Float, val x2: Float, val y2: Float)

Detection

data class Detection(val box: Box, val score: Float, val classId: Int, val label: String? = null)

HeadOutputs

data class HeadOutputs(val small: HeadTensor, val medium: HeadTensor, val large: HeadTensor)

HeadTensor

data class HeadTensor(val reg: Tensor<FP32, Float>, val cls: Tensor<FP32, Float>)

Yolo8

class Yolo8(config: YoloConfig = YoloConfig()) : Model<FP32, Float, Tensor<FP32, Float>, Tensor<FP32, Float>>

YoloConfig

data class YoloConfig(val numClasses: Int = 80, val inputSize: Int = 640, val confThreshold: Float = 0.25f, val iouThreshold: Float = 0.45f, val maxDetections: Int = 300, val classNames: List<String> = emptyList(), val regMax: Int = 16, val baseChannels: Int = 32, val depthMultiple: Float = 1.0f)

YOLO configuration used for decoding and thresholds.

YoloInput

data class YoloInput(val tensor: Tensor<FP32, Float>, val originalWidth: Int, val originalHeight: Int, val letterboxScale: Float = 1.0f, val padW: Int = 0, val padH: Int = 0)

YoloPreprocess

object YoloPreprocess

Preprocessing helpers for YOLOv8 inputs.