Skip to content
opencv-wasm

gapi_onnx_ep_DirectML

gapiclassOpenCV 5.0.0
import { gapi_onnx_ep_DirectML } from '@banou/opencv-wasm'

Use after await initOpenCV(). See the initialization and named imports guide.

ARGUMENTSConstructor or factory
CLASSgapi_onnx_ep_DirectML
RETURN TYPEOwned native handle
Call structure. A void return can still write to destination arguments. The parameter descriptions define inputs, outputs and ownership.

Native object: release it with using or delete(). Factories can return null; check before calling methods.

This structure provides functions that fill inference options for ONNX DirectML Execution Provider. Please follow https://onnxruntime.ai/docs/execution-providers/DirectML-ExecutionProvider.html#directml-execution-provider

Upstream declaration ↗

Constructors and members

static new

Class constructor.

Constructs DirectML parameters based on device id.

new(device_id: number): gapi_onnx_ep_DirectML;
2 available overloads
new(): gapi_onnx_ep_DirectML;
new(device_id: number): gapi_onnx_ep_DirectML;
device_id

Target device id to use. ("0", "1", etc)

Returns

The gapi_onnx_ep_DirectML result.

Upstream declaration ↗Upstream declaration 2 ↗

static from2

Create network parameter configuration. These parameter objects describe an optional OpenVINO or ONNX Runtime backend, which is not linked in this WASM build. Use gapi.dnn.Params for executable CPU inference.

from2(_0: EmbindString): gapi_onnx_ep_DirectML | null;
_0

0 argument (EmbindString).

Returns

The gapi_onnx_ep_DirectML | null result.

clone

Create another handle to the same native object. This retains the object without copying its pixels or algorithm state; dispose both handles separately.

clone(): this;
Returns

The this result.

These signatures describe this package. Upstream documentation can mention optional backends that are absent from this build. Check runtime compatibility before choosing a backend or file format.