OnnxRuntime using and sklearn SVMRegressor in .NET

Question

I have created an svmregressor using sklearn and skl2onnx:

initial_type = [('double_input', DoubleTensorType([None, len(d)]))]
onx = convert_sklearn(results[i].estimator_, initial_types=initial_type)

with open(r"C:\my folder\x_" + str(i) + "_1.onnx", "wb") as f:
    f.write(onx.SerializeToString())

I call it in c# using

            session = new InferenceSession(modelPath);

            modelInputNames = session.InputMetadata.Keys.Single();

            dimensions = new int[] { 1, X.Length };

            DenseTensor<double> inputTensor = new DenseTensor<double>(X, dimensions);

            List<NamedOnnxValue> modelInput = new List<NamedOnnxValue>
            {
                NamedOnnxValue.CreateFromTensor(modelInputNames, inputTensor)
            };

            var result = session.Run(modelInput);

            var prediction = ((DenseTensor<double>)result.Single().Value).ToArray();

and I get the error in:

class NativeApiStatus
{
    private static string GetErrorMessage(IntPtr /*(ONNXStatus*)*/status)
    {
        // nativeString belongs to status, no need for separate release
        IntPtr nativeString = NativeMethods.OrtGetErrorMessage(status);
        return NativeOnnxValueHelper.StringFromNativeUtf8(nativeString);
    }

    /// <summary>
    /// Checks the native Status if the errocode is OK/Success. Otherwise constructs an appropriate exception and throws.
    /// Releases the native status object, as needed.
    /// </summary>
    /// <param name="nativeStatus"></param>
    /// <throws></throws>
    public static void VerifySuccess(IntPtr nativeStatus)
    {
        if (nativeStatus != IntPtr.Zero)
        {
            try
            {
                ErrorCode statusCode = NativeMethods.OrtGetErrorCode(nativeStatus);
                string errorMessage = GetErrorMessage(nativeStatus);
            }
            finally
            {
                NativeMethods.OrtReleaseStatus(nativeStatus);
            }
        }
    }
}

I get this error:

Microsoft.ML.OnnxRuntime.OnnxRuntimeException HResult=0x80131500 Message=[ErrorCode:NotImplemented] Could not find an implementation for SVMRegressor(1) node with name 'SVM' Source=Microsoft.ML.OnnxRuntime StackTrace: at Microsoft.ML.OnnxRuntime.NativeApiStatus.VerifySuccess(IntPtr nativeStatus) in D:\a_work\1\s\csharp\src\Microsoft.ML.OnnxRuntime\NativeApiStatus.cs:line 31 at Microsoft.ML.OnnxRuntime.InferenceSession.Init(String modelPath, SessionOptions options, PrePackedWeightsContainer prepackedWeightsContainer) in D:\a_work\1\s\csharp\src\Microsoft.ML.OnnxRuntime\InferenceSession.cs:line 776 at Microsoft.ML.OnnxRuntime.InferenceSession..ctor(String modelPath) in D:\a_work\1\s\csharp\src\Microsoft.ML.OnnxRuntime\InferenceSession.cs:line 59 ...

can you help?

OnnxRuntime using and sklearn SVMRegressor in .NET

0 Answers0