Enum InferenceResult

pub enum InferenceResult {
    Classification {
        classification: HashMap<String, f32>,
    },
    ObjectDetection {
        bounding_boxes: Vec<BoundingBox>,
        classification: HashMap<String, f32>,
    },
    VisualAnomaly {
        visual_anomaly_grid: Vec<BoundingBox>,
        visual_anomaly_max: f32,
        visual_anomaly_mean: f32,
        anomaly: f32,
    },
}

Represents different types of inference results.

Models can produce different types of outputs depending on their type:

• Classification models return class probabilities
• Object detection models return bounding boxes and optional classifications

Variants

Classification

Result from a classification model

Fields

classification: HashMap<String, f32>

Map of class names to their probability scores

ObjectDetection

Result from an object detection model

Fields

bounding_boxes: Vec<BoundingBox>

Vector of detected objects with their bounding boxes

classification: HashMap<String, f32>

Optional classification results for the entire image

VisualAnomaly

Result from a visual anomaly detection model

Fields

visual_anomaly_grid: Vec<BoundingBox>

Grid of anomaly scores for different regions of the image

visual_anomaly_max: f32

Maximum anomaly score across all regions

visual_anomaly_mean: f32

Mean anomaly score across all regions

anomaly: f32

Overall anomaly score for the image

Trait Implementations

impl Debug for InferenceResult

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for InferenceResult

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for InferenceResult

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

where __S: Serializer,

Serialize this value into the given Serde serializer.