The output result of ImageSegmenter.
Signature:
export declare class ImageSegmenterResult
Constructors
| Constructor | Modifiers | Description |
|---|---|---|
| (constructor)(confidenceMasks, categoryMask, qualityScores) | Constructs a new instance of the ImageSegmenterResult class |
Properties
| Property | Modifiers | Type | Description |
|---|---|---|---|
| categoryMask | MPMask | undefined | A category mask represented as a Uint8ClampedArray or WebGLTexture-backed MPImage where each pixel represents the class which the pixel in the original image was predicted to belong to. |
|
| confidenceMasks | MPMask[] | undefined | Multiple masks represented as Float32Array or WebGLTexture-backed MPImages where, for each mask, each pixel represents the prediction confidence, usually in the [0, 1] range. |
|
| qualityScores | number[] | undefined | The quality scores of the result masks, in the range of [0, 1]. Defaults to 1 if the model doesn't output quality scores. Each element corresponds to the score of the category in the model outputs. |
Methods
| Method | Modifiers | Description |
|---|---|---|
| close() | Frees the resources held by the category and confidence masks. |
ImageSegmenterResult.(constructor)
Constructs a new instance of the ImageSegmenterResult class
Signature:
constructor(
confidenceMasks?: MPMask[] | undefined,
categoryMask?: MPMask | undefined,
qualityScores?: number[] | undefined);
Parameters
| Parameter | Type | Description |
|---|---|---|
| confidenceMasks | MPMask[] | undefined | |
| categoryMask | MPMask | undefined | |
| qualityScores | number[] | undefined |
ImageSegmenterResult.categoryMask
A category mask represented as a Uint8ClampedArray or WebGLTexture-backed MPImage where each pixel represents the class which the pixel in the original image was predicted to belong to.
Signature:
readonly categoryMask?: MPMask | undefined;
ImageSegmenterResult.confidenceMasks
Multiple masks represented as Float32Array or WebGLTexture-backed MPImages where, for each mask, each pixel represents the prediction confidence, usually in the [0, 1] range.
Signature:
readonly confidenceMasks?: MPMask[] | undefined;
ImageSegmenterResult.qualityScores
The quality scores of the result masks, in the range of [0, 1]. Defaults to 1 if the model doesn't output quality scores. Each element corresponds to the score of the category in the model outputs.
Signature:
readonly qualityScores?: number[] | undefined;
ImageSegmenterResult.close()
Frees the resources held by the category and confidence masks.
Signature:
close(): void;
Returns:
void