Anonymous View

Interface InferenceSession

Represent a runtime instance of an ONNX model.

interface InferenceSession {
    inputMetadata: readonly ValueMetadata[];
    inputNames: readonly string[];
    outputMetadata: readonly ValueMetadata[];
    outputNames: readonly string[];
    endProfiling(): void;
    release(): Promise<void>;
    run(
        feeds: OnnxValueMapType,
        options?: RunOptions,
    ): Promise<OnnxValueMapType>;
    run(
        feeds: OnnxValueMapType,
        fetches: FetchesType,
        options?: RunOptions,
    ): Promise<OnnxValueMapType>;
    startProfiling(): void;
}

Index

Properties

inputMetadata inputNames outputMetadata outputNames

Methods

endProfiling release run startProfiling

Properties

`Readonly`inputMetadata

inputMetadata: readonly ValueMetadata[]

Get input metadata of the loaded model.

`Readonly`inputNames

inputNames: readonly string[]

Get input names of the loaded model.

`Readonly`outputMetadata

outputMetadata: readonly ValueMetadata[]

Get output metadata of the loaded model.

`Readonly`outputNames

outputNames: readonly string[]

Get output names of the loaded model.

Methods

endProfiling

endProfiling(): void
End profiling.

Returns void
- Defined in inference-session.ts:572

release

release(): Promise<void>
Release the inference session and the underlying resources.

Returns Promise<void>
- Defined in inference-session.ts:558

run

run(feeds: OnnxValueMapType, options?: RunOptions): Promise<OnnxValueMapType>
Execute the model asynchronously with the given feeds and options.
Parameters
- feeds: OnnxValueMapType
  Representation of the model input. See type description of InferenceSession.InputType for detail.
- Optionaloptions: RunOptions
  Optional. A set of options that controls the behavior of model inference.
Returns Promise<OnnxValueMapType>
A promise that resolves to a map, which uses output names as keys and OnnxValue as corresponding values.
- Defined in inference-session.ts:534
run(
    feeds: OnnxValueMapType,
    fetches: FetchesType,
    options?: RunOptions,
): Promise<OnnxValueMapType>
Execute the model asynchronously with the given feeds, fetches and options.
Parameters
- feeds: OnnxValueMapType
  Representation of the model input. See type description of InferenceSession.InputType for detail.
- fetches: FetchesType
  Representation of the model output. See type description of InferenceSession.OutputType for detail.
- Optionaloptions: RunOptions
  Optional. A set of options that controls the behavior of model inference.
Returns Promise<OnnxValueMapType>
A promise that resolves to a map, which uses output names as keys and OnnxValue as corresponding values.
- Defined in inference-session.ts:545

startProfiling

startProfiling(): void
Start profiling.

Returns void
- Defined in inference-session.ts:567