public void TestSimpleCase(bool useOptionsCtor)
{
var modelFile = "squeezenet/00000001/model.onnx";
var samplevector = GetSampleArrayData();
var dataView = ML.Data.LoadFromEnumerable(
new TestData[] {
new TestData()
{
data_0 = samplevector
},
new TestData()
{
data_0 = samplevector
}
});
var xyData = new List <TestDataXY> {
new TestDataXY()
{
A = new float[InputSize]
}
};
var stringData = new List <TestDataDifferentType> {
new TestDataDifferentType()
{
data_0 = new string[InputSize]
}
};
var sizeData = new List <TestDataSize> {
new TestDataSize()
{
data_0 = new float[2]
}
};
var options = new OnnxOptions()
{
OutputColumns = new[] { "softmaxout_1" },
InputColumns = new[] { "data_0" },
ModelFile = modelFile,
GpuDeviceId = _gpuDeviceId,
FallbackToCpu = _fallbackToCpu,
InterOpNumThreads = 1,
IntraOpNumThreads = 1
};
var pipe = useOptionsCtor ?
ML.Transforms.ApplyOnnxModel(options) :
ML.Transforms.ApplyOnnxModel(options.OutputColumns, options.InputColumns, modelFile, gpuDeviceId: _gpuDeviceId, fallbackToCpu: _fallbackToCpu);
var invalidDataWrongNames = ML.Data.LoadFromEnumerable(xyData);
var invalidDataWrongTypes = ML.Data.LoadFromEnumerable(stringData);
var invalidDataWrongVectorSize = ML.Data.LoadFromEnumerable(sizeData);
TestEstimatorCore(pipe, dataView, invalidInput: invalidDataWrongNames);
TestEstimatorCore(pipe, dataView, invalidInput: invalidDataWrongTypes);
pipe.GetOutputSchema(SchemaShape.Create(invalidDataWrongVectorSize.Schema));
try
{
var onnxTransformer = pipe.Fit(invalidDataWrongVectorSize);
(onnxTransformer as IDisposable)?.Dispose();
Assert.False(true);
}
catch (ArgumentOutOfRangeException) { }
catch (InvalidOperationException) { }
}
/// <summary>
/// Create a <see cref="OnnxScoringEstimator"/> using the specified <see cref="OnnxOptions"/>.
/// Please refer to <see cref="OnnxScoringEstimator"/> to learn more about the necessary dependencies,
/// and how to run it on a GPU.
/// </summary>
/// <param name="catalog">The transform's catalog.</param>
/// <param name="options">Options for the <see cref="OnnxScoringEstimator"/>.</param>
public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog, OnnxOptions options)
=> new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), options.OutputColumns, options.InputColumns, options.ModelFile,
options.GpuDeviceId, options.FallbackToCpu, options.ShapeDictionary, options.RecursionLimit, options.InterOpNumThreads, options.IntraOpNumThreads);
/// <summary>
/// Create a <see cref="OnnxScoringEstimator"/> using the specified <see cref="OnnxOptions"/>.
/// Please refer to <see cref="OnnxScoringEstimator"/> to learn more about the necessary dependencies,
/// and how to run it on a GPU.
/// </summary>
/// <remarks>
/// If the options.GpuDeviceId value is <see langword="null" /> the <see cref="P:MLContext.GpuDeviceId"/> value will be used if it is not <see langword="null" />.
/// </remarks>
/// <param name="catalog">The transform's catalog.</param>
/// <param name="options">Options for the <see cref="OnnxScoringEstimator"/>.</param>
public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog, OnnxOptions options)
{
var(env, gpuDeviceIdToUse, fallbackToCpuToUse) = GetGpuDeviceId(catalog, options.GpuDeviceId, options.FallbackToCpu);
return(new OnnxScoringEstimator(env, options.OutputColumns, options.InputColumns, options.ModelFile,
gpuDeviceIdToUse, fallbackToCpuToUse, options.ShapeDictionary, options.RecursionLimit, options.InterOpNumThreads, options.IntraOpNumThreads));
}
