Struct InferenceConfig 

pub struct InferenceConfig {
    pub confidence_threshold: f32,
    pub iou_threshold: f32,
    pub max_det: usize,
    pub imgsz: Option<(usize, usize)>,
    pub batch: Option<usize>,
    pub num_threads: usize,
    pub half: bool,
    pub device: Option<Device>,
    pub save: bool,
    pub save_frames: bool,
    pub rect: bool,
    pub classes: Option<Vec<usize>>,
}

Configuration for YOLO inference.

This struct is used to customize the behavior of the inference engine. It uses a builder pattern for convenient construction.

Examples

Basic configuration:

use ultralytics_inference::InferenceConfig;

let config = InferenceConfig::new()
    .with_confidence(0.5)
    .with_iou(0.45)
    .with_max_det(300)
    .with_imgsz(640, 640);

With specific hardware device:

use ultralytics_inference::{InferenceConfig, Device};

let config = InferenceConfig::new()
    .with_confidence(0.5)
    .with_device(Device::Cuda(0));

Fields

confidence_threshold: f32

Confidence threshold for detections (0.0 to 1.0). Detections with confidence scores lower than this value will be discarded.

iou_threshold: f32

Intersection over Union (IoU) threshold for Non-Maximum Suppression (NMS) (0.0 to 1.0). Used to merge overlapping boxes. Lower values filter more duplicates.

max_det: usize

Maximum number of detections to return per image. The top-k detections sorted by confidence will be returned.

imgsz: Option<(usize, usize)>

Explicit input image size (height, width). If None, the model’s metadata will be used to determine input size.

batch: Option<usize>

Batch size for inference when using BatchProcessor. If None, defaults to 1 (single-image inference).

num_threads: usize

Number of intra-op threads for ONNX Runtime. Setting this to 0 allows ONNX Runtime to choose the optimal number.

half: bool

Whether to use FP16 (half-precision) inference. This can improve performance on compatible hardware (e.g., GPUs) but may result in slight precision loss.

device: Option<Device>

Hardware device to use for inference. If None, the best available device will be automatically selected.

save: bool

Whether to save annotated results. Defaults to true.

save_frames: bool

Whether to save individual frames instead of a video file when input is video. Defaults to false (save as video).

rect: bool

Whether to use minimal padding (rectangular inference). Defaults to true.

classes: Option<Vec<usize>>

Class IDs to filter predictions. If None, all classes are returned. Useful for focusing on specific objects in multi-class detection tasks.

Implementations

impl InferenceConfig

pub const DEFAULT_CONF: f32 = 0.25

Default confidence threshold (0.0 to 1.0).

pub const DEFAULT_IOU: f32 = 0.7

Default IoU threshold for NMS (0.0 to 1.0).

pub const DEFAULT_MAX_DET: usize = 300

Default maximum number of detections per image.

pub const DEFAULT_HALF: bool = false

Default for FP16 half-precision inference.

pub const DEFAULT_SAVE: bool = true

Default for saving annotated results.

pub const DEFAULT_SAVE_FRAMES: bool = false

Default for saving individual frames (vs video).

pub const DEFAULT_RECT: bool = true

Default for rectangular (minimal padding) inference.

pub fn new() -> Self

Create a new configuration with default values.

Returns

• A new InferenceConfig instance with default settings.

pub const fn with_batch(self, batch: usize) -> Self

Set the batch size.

Arguments

• batch - The batch size.

Returns

• The modified InferenceConfig.

pub const fn with_confidence(self, threshold: f32) -> Self

Set the confidence threshold.

Detections with a confidence score below this threshold will be filtered out.

Arguments

• threshold - The minimum confidence score (0.0 to 1.0).

Returns

• The modified InferenceConfig.

pub const fn with_iou(self, threshold: f32) -> Self

Set the IoU threshold for Non-Maximum Suppression (NMS).

NMS suppresses overlapping bounding boxes. This threshold determines how much overlap is allowed before boxes are considered duplicates.

Arguments

• threshold - The IoU threshold (0.0 to 1.0).

Returns

• The modified InferenceConfig.

pub const fn with_max_det(self, max: usize) -> Self

Set the maximum number of detections to return.

Only the top max detections (sorted by confidence) will be kept after NMS.

Arguments

• max - The maximum number of detections.

Returns

• The modified InferenceConfig.

pub const fn with_imgsz(self, height: usize, width: usize) -> Self

Set the input image size.

This explicitly sets the size to resize images to before inference. If not set, the model’s internal metadata size will be used.

Arguments

• height - The target image height.
• width - The target image width.

Returns

• The modified InferenceConfig.

pub const fn with_threads(self, threads: usize) -> Self

Set the number of threads for inference.

Arguments

• threads - The number of intra-op threads. Set to 0 for auto-configuration.

Returns

• The modified InferenceConfig.

pub const fn with_half(self, half: bool) -> Self

Enable or disable FP16 (half-precision) inference.

Using FP16 can significantly speed up inference on GPUs and some CPUS, at the cost of potential minor precision loss.

Arguments

• half - true to enable FP16, false for FP32.

Returns

• The modified InferenceConfig.

pub const fn with_device(self, device: Device) -> Self

Set the hardware device for inference.

Arguments

• device - The device to use (e.g., CPU, CUDA, MPS).

Example

use ultralytics_inference::{InferenceConfig, Device};

let config = InferenceConfig::new()
    .with_device(Device::Mps); // Use Apple Metal Performance Shaders

Returns

• The modified InferenceConfig.

pub const fn with_save(self, save: bool) -> Self

Set whether to save annotated results.

Arguments

• save - true to save results, false to skip saving.

Returns

• The modified InferenceConfig.

pub const fn with_save_frames(self, save_frames: bool) -> Self

Set whether to save individual frames for video inputs.

Arguments

• save_frames - true to save frames, false to save as video.

Returns

• The modified InferenceConfig.

pub const fn with_rect(self, rect: bool) -> Self

Set whether to use minimal padding (rectangular inference).

Arguments

• rect - true to enable, false to disable.

Returns

• The modified InferenceConfig.

pub fn with_classes(self, classes: Vec<usize>) -> Self

Set the class IDs to filter predictions.

Only detections belonging to the specified classes will be returned.

Arguments

• classes - A vector of class IDs to keep.

Example

use ultralytics_inference::InferenceConfig;

// Only detect persons (class 0) and cars (class 2)
let config = InferenceConfig::new()
    .with_classes(vec![0, 2]);

Returns

• The modified InferenceConfig.

pub fn keep_class(&self, class_id: usize) -> bool

Check if a class should be included in the results.

Arguments

• class_id - The class index to check.

Returns

• true if the class should be kept.
• false if the class should be filtered out.

Trait Implementations

impl Clone for InferenceConfig

fn clone(&self) -> InferenceConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for InferenceConfig

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

Formats the value using the given formatter.

impl Default for InferenceConfig

fn default() -> Self

Returns the “default value” for a type.