private static ModelProto ConvertToOnnxProtobufCore(IHostEnvironment env, OnnxContextImpl ctx, ITransformer transform, IDataView inputData)
{
var outputData = transform.Transform(inputData);
LinkedList <ITransformCanSaveOnnx> transforms = null;
using (var ch = env.Start("ONNX conversion"))
{
SaveOnnxCommand.GetPipe(ctx, ch, outputData, out IDataView root, out IDataView sink, out transforms);
return(SaveOnnxCommand.ConvertTransformListToOnnxModel(ctx, ch, root, sink, transforms, null, null));
}
}
internal static ModelProto ConvertToOnnxProtobuf(this ModelOperationsCatalog catalog, ITransformer transform, IDataView inputData)
{
var env = catalog.Environment;
var ctx = new OnnxContextImpl(env, "model", "ML.NET", "0", 0, "machinelearning.dotnet", OnnxVersion.Stable);
var outputData = transform.Transform(inputData);
LinkedList <ITransformCanSaveOnnx> transforms = null;
using (var ch = env.Start("ONNX conversion"))
{
SaveOnnxCommand.GetPipe(ctx, ch, outputData, out IDataView root, out IDataView sink, out transforms);
return(SaveOnnxCommand.ConvertTransformListToOnnxModel(ctx, ch, root, sink, transforms, null, null));
}
}
public void RemoveVariablesInPipelineTest()
{
var mlContext = new MLContext(seed: 1);
string dataPath = GetDataPath("breast-cancer.txt");
var data = mlContext.Data.LoadFromTextFile <BreastCancerCatFeatureExample>(dataPath,
separatorChar: '\t',
hasHeader: true);
var pipeline = mlContext.Transforms.Categorical.OneHotEncoding("F2", "F2", Transforms.OneHotEncodingTransformer.OutputKind.Bag)
.Append(mlContext.Transforms.ReplaceMissingValues(new MissingValueReplacingEstimator.ColumnOptions("F2")))
.Append(mlContext.Transforms.Concatenate("Features", "F1", "F2"))
.Append(mlContext.Transforms.Normalize("Features"))
.Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumnName: "Label", featureColumnName: "Features", numberOfLeaves: 2, numberOfTrees: 1, minimumExampleCountPerLeaf: 2));
var model = pipeline.Fit(data);
var transformedData = model.Transform(data);
var onnxConversionContext = new OnnxContextImpl(mlContext, "A Simple Pipeline", "ML.NET", "0", 0, "machinelearning.dotnet", OnnxVersion.Stable);
LinkedList <ITransformCanSaveOnnx> transforms = null;
using (var conversionChannel = (mlContext as IChannelProvider).Start("ONNX conversion"))
{
SaveOnnxCommand.GetPipe(onnxConversionContext, conversionChannel, transformedData, out IDataView root, out IDataView sink, out transforms);
// Input columns' names to be excluded in the resulted ONNX model.
var redundantInputColumnNames = new HashSet <string> {
"Label"
};
// Output columns' names to be excluded in the resulted ONNX model.
var redundantOutputColumnNames = new HashSet <string> {
"Label", "F1", "F2", "Features"
};
var onnxModel = SaveOnnxCommand.ConvertTransformListToOnnxModel(onnxConversionContext, conversionChannel, root, sink, transforms,
redundantInputColumnNames, redundantOutputColumnNames);
// Check ONNX model's text format. We save the produced ONNX model as a text file and compare it against
// the associated file in ML.NET repo. Such a comparison can be retired if ONNXRuntime ported to ML.NET
// can support Linux and Mac.
var subDir = Path.Combine("..", "..", "BaselineOutput", "Common", "Onnx", "BinaryClassification", "BreastCancer");
var onnxTextName = "ExcludeVariablesInOnnxConversion.txt";
var onnxFileName = "ExcludeVariablesInOnnxConversion.onnx";
var onnxTextPath = GetOutputPath(subDir, onnxTextName);
var onnxFilePath = GetOutputPath(subDir, onnxFileName);
SaveOnnxModel(onnxModel, onnxFilePath, onnxTextPath);
CheckEquality(subDir, onnxTextName, digitsOfPrecision: 3);
}
Done();
}
private static ModelProto ConvertToOnnxProtobufCore(IHostEnvironment env, OnnxContextImpl ctx, ITransformer transform, IDataView inputData, string[] outputColumnNamesToKeep = null)
{
var outputData = transform.Transform(inputData);
LinkedList <ITransformCanSaveOnnx> transforms = null;
using (var ch = env.Start("ONNX conversion"))
{
SaveOnnxCommand.GetPipe(ctx, ch, outputData, out IDataView root, out IDataView sink, out transforms);
// We pass in the output names to keep, but this next call expects a list of ones to drop. Invert the list.
var outputColumnNamesToDrop = new HashSet <string>();
if (outputColumnNamesToKeep != null)
{
for (int i = 0; i < sink.Schema.Count; ++i)
{
if (!outputColumnNamesToKeep.Contains(sink.Schema[i].Name))
{
outputColumnNamesToDrop.Add(sink.Schema[i].Name);
}
}
}
return(SaveOnnxCommand.ConvertTransformListToOnnxModel(ctx, ch, root, sink, transforms, null, outputColumnNamesToDrop));
}
}
