Skip to main content
Version: Next

Interface: InstanceSegmentationType<L>

Defined in: types/instanceSegmentation.ts:153

Return type for the useInstanceSegmentation hook. Manages the state and operations for instance segmentation models.

Type Parameters

L

L extends LabelEnum

The label map type for the model, must conform to LabelEnum.

Properties

downloadProgress

downloadProgress: number

Defined in: types/instanceSegmentation.ts:172

Represents the download progress of the model binary as a value between 0 and 1.


error

error: RnExecutorchError | null

Defined in: types/instanceSegmentation.ts:157

Contains the error object if the model failed to load, download, or encountered a runtime error during segmentation.


forward()

forward: (imageSource, options?) => Promise<SegmentedInstance<L>[]>

Defined in: types/instanceSegmentation.ts:181

Executes the model's forward pass to perform instance segmentation on the provided image.

Parameters

imageSource

A string (e.g., a file path, URI ) or PixelData representing the image source to be processed.

string | PixelData

options?

InstanceSegmentationOptions<L>

Optional configuration for the segmentation process.

Returns

Promise<SegmentedInstance<L>[]>

A Promise resolving to an array of SegmentedInstance objects.

Throws

If the model is not loaded or is currently processing another image.


getAvailableInputSizes()

getAvailableInputSizes: () => readonly number[] | undefined

Defined in: types/instanceSegmentation.ts:190

Returns the available input sizes for this model, or undefined if the model accepts single forward input size.

Returns

readonly number[] | undefined

An array of available input sizes, or undefined if not constrained.


isGenerating

isGenerating: boolean

Defined in: types/instanceSegmentation.ts:167

Indicates whether the model is currently processing an image.


isReady

isReady: boolean

Defined in: types/instanceSegmentation.ts:162

Indicates whether the instance segmentation model is loaded and ready to process images.


runOnFrame

runOnFrame: (frame, isFrontCamera, options?) => SegmentedInstance<L>[] | null

Defined in: types/instanceSegmentation.ts:205

Synchronous worklet function for real-time VisionCamera frame processing. Automatically handles native buffer extraction and cleanup.

Use this for VisionCamera frame processing in worklets. For async processing, use forward() instead.

Available after model is loaded (isReady: true).

Param

VisionCamera Frame object

Param

Whether the front camera is active (for mirroring correction).

Param

Optional configuration for the segmentation process.

Returns

Array of SegmentedInstance objects representing detected items in the frame.