LearningModelSession.EvaluateAsync(LearningModelBinding, String) Method

Definition

Asynchronously evaluate the machine learning model using the feature values already bound in bindings.

public:
 virtual IAsyncOperation<LearningModelEvaluationResult ^> ^ EvaluateAsync(LearningModelBinding ^ bindings, Platform::String ^ correlationId) = EvaluateAsync;
/// [Windows.Foundation.Metadata.RemoteAsync]
IAsyncOperation<LearningModelEvaluationResult> EvaluateAsync(LearningModelBinding const& bindings, winrt::hstring const& correlationId);
[Windows.Foundation.Metadata.RemoteAsync]
public IAsyncOperation<LearningModelEvaluationResult> EvaluateAsync(LearningModelBinding bindings, string correlationId);
function evaluateAsync(bindings, correlationId)
Public Function EvaluateAsync (bindings As LearningModelBinding, correlationId As String) As IAsyncOperation(Of LearningModelEvaluationResult)

Parameters

bindings
LearningModelBinding

The values bound to the named input and output features.

correlationId
String

Platform::String

winrt::hstring

Optional user-supplied string to connect the output results.

Returns

A LearningModelEvaluationResult from the evaluation.

Attributes

Examples

The following example retrieves the first input and output features from the model, creates an output frame, binds the input and output features, and evaluates the model.

private async Task EvaluateModelAsync(
    VideoFrame _inputFrame, 
    LearningModelSession _session, 
    IReadOnlyList<ILearningModelFeatureDescriptor> _inputFeatures, 
    IReadOnlyList<ILearningModelFeatureDescriptor> _outputFeatures,
    LearningModel _model)
{
    ImageFeatureDescriptor _inputImageDescription;
    TensorFeatureDescriptor _outputImageDescription;
    LearningModelBinding _binding = null;
    VideoFrame _outputFrame = null;
    LearningModelEvaluationResult _results;

    try
    {
        // Retrieve the first input feature which is an image
        _inputImageDescription =
            _inputFeatures.FirstOrDefault(feature => feature.Kind == LearningModelFeatureKind.Image)
            as ImageFeatureDescriptor;

        // Retrieve the first output feature which is a tensor
        _outputImageDescription =
            _outputFeatures.FirstOrDefault(feature => feature.Kind == LearningModelFeatureKind.Tensor)
            as TensorFeatureDescriptor;

        // Create output frame based on expected image width and height
        _outputFrame = new VideoFrame(
            BitmapPixelFormat.Bgra8, 
            (int)_inputImageDescription.Width, 
            (int)_inputImageDescription.Height);

        // Create binding and then bind input/output features
        _binding = new LearningModelBinding(_session);

        _binding.Bind(_inputImageDescription.Name, _inputFrame);
        _binding.Bind(_outputImageDescription.Name, _outputFrame);

        // Evaluate and get the results
        _results = await _session.EvaluateAsync(_binding, "test");
    }
    catch (Exception ex)
    {
        StatusBlock.Text = $"error: {ex.Message}";
        _model = null;
    }
}

Remarks

Windows Server

To use this API on Windows Server, you must use Windows Server 2019 with Desktop Experience.

Thread safety

This API is thread-safe.

Applies to