Struct NeuralNetworkDetect 

pub struct NeuralNetworkDetect {
    pub model: String,
    pub expected: Vec<i32>,
    pub roi: Target,
    pub roi_offset: Rect,
    pub labels: Vec<String>,
    pub threshold: Vec<f64>,
    pub order_by: String,
    pub index: i32,
}

Neural network detection - detects objects anywhere on screen.

Uses YOLO-style ONNX model to detect and locate objects.

Fields

model: String

Model file path relative to model/detect. Required.

expected: Vec<i32>

Expected class indices to match. Default: match all.

roi: Target

Recognition region. Default: \[0,0,0,0\] (full screen).

roi_offset: Rect

Offset applied to the ROI.

labels: Vec<String>

Class labels (auto-read from model metadata). Default: “Unknown”.

threshold: Vec<f64>

Confidence threshold(s). Default: [0.3].

order_by: String

Result sorting method. Default: “Horizontal”.

index: i32

Which result to select. Default: 0.

Trait Implementations

impl Clone for NeuralNetworkDetect

fn clone(&self) -> NeuralNetworkDetect

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for NeuralNetworkDetect

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for NeuralNetworkDetect

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for NeuralNetworkDetect

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.