Represent multi-dimensional arrays to feed to or fetch from model inferencing.

interface Tensor {
    data: string[] | Int8Array | Uint8Array | Int16Array | Uint16Array | Int32Array | Uint32Array | Float32Array | Float64Array | BigInt64Array | BigUint64Array;
    dims: readonly number[];
    gpuBuffer: GpuBufferTypeFallback;
    location: DataLocation;
    mlTensor: MLTensorTypeFallback;
    size: number;
    texture: WebGLTexture;
    type: keyof DataTypeMap;
    dispose(): void;
    getData(releaseData?): Promise<string[] | Int8Array | Uint8Array | Int16Array | Uint16Array | Int32Array | Uint32Array | Float32Array | Float64Array | BigInt64Array | BigUint64Array>;
    reshape(dims): TypedTensor<keyof DataTypeMap>;
    toDataURL(options?): string;
    toImageData(options?): ImageData;
}

Hierarchy

  • TypedTensorBase<Type>
  • TypedTensorUtils<Type>
    • Tensor

Properties

data: string[] | Int8Array | Uint8Array | Int16Array | Uint16Array | Int32Array | Uint32Array | Float32Array | Float64Array | BigInt64Array | BigUint64Array

Get the buffer data of the tensor.

If the data is not on CPU (eg. it's in the form of WebGL texture or WebGPU buffer), throw error.

dims: readonly number[]

Get the dimensions of the tensor.

Get the WebGPU buffer that holds the tensor data.

If the data is not on GPU as WebGPU buffer, throw error.

location: DataLocation

Get the location of the data.

Get the WebNN MLTensor that holds the tensor data.

If the data is not in a WebNN MLTensor, throw error.

size: number

Get the number of elements in the tensor.

texture: WebGLTexture

Get the WebGL texture that holds the tensor data.

If the data is not on GPU as WebGL texture, throw error.

type: keyof DataTypeMap

Get the data type of the tensor.

Methods

  • Dispose the tensor data.

    If the data is on CPU, remove its internal reference to the underlying data. If the data is on GPU, release the data on GPU.

    After calling this function, the tensor is considered no longer valid. Its location will be set to 'none'.

    Returns void

  • Get the buffer data of the tensor.

    If the data is on CPU, returns the data immediately. If the data is on GPU, downloads the data and returns the promise.

    Parameters

    • Optional releaseData: boolean

      whether release the data on GPU. Ignore if data is already on CPU.

    Returns Promise<string[] | Int8Array | Uint8Array | Int16Array | Uint16Array | Int32Array | Uint32Array | Float32Array | Float64Array | BigInt64Array | BigUint64Array>

  • creates a DataURL instance from tensor

    Parameters

    • Optional options: TensorToDataUrlOptions

      An optional object representing options for creating a DataURL instance from the tensor.

      The following default settings will be applied:

      • format: 'RGB'
      • tensorLayout: 'NCHW'

    Returns string

    a DataURL string representing the image converted from tensor data

  • creates an ImageData instance from tensor

    Parameters

    • Optional options: TensorToImageDataOptions

      An optional object representing options for creating an ImageData instance from the tensor.

      The following default settings will be applied:

      • format: 'RGB'
      • tensorLayout: 'NCHW'

    Returns ImageData

    an ImageData instance representing the image converted from tensor data

Generated using TypeDoc