Prototype of new ONNX converter and an end-to-end test

Author: wschin

src/Microsoft.ML.Onnx/TransformerChainOnnxConverter.cs

@@ -0,0 +1,42 @@
+using Microsoft.ML.Core.Data;
+using Microsoft.ML.Data;
+using Microsoft.ML.UniversalModelFormat.Onnx;
+
+namespace Microsoft.ML.Model.Onnx
+{
+    public class TransformerChainOnnxConverter
+    {
+        public static ModelProto Convert<T>(TransformerChain<T> chain, Schema inputSchema) where T : class, ITransformer
+        {
+            var env = new MLContext();
+            var onnxContext = new OnnxContextImpl(env, "model", "ML.NET", "0", 0, "com.test", Model.Onnx.OnnxVersion.Stable);
+
+            for (int i = 0; i < inputSchema.Count; i++)
+            {
+                string colName = inputSchema[i].Name;
+                onnxContext.AddInputVariable(inputSchema[i].Type, colName);
+            }
+
+            foreach (var t in chain)
+            {
+                var mapper = t.GetRowToRowMapper(inputSchema);
+                inputSchema = t.GetOutputSchema(inputSchema);
+                (mapper as ISaveAsOnnx).SaveAsOnnx(onnxContext);
+            }
+
+            for (int i = 0; i < inputSchema.Count; ++i)
+            {
+                if (inputSchema[i].IsHidden)
+                    continue;
+
+                var idataviewColumnName = inputSchema[i].Name;
+
+                var variableName = onnxContext.TryGetVariableName(idataviewColumnName);
+                var trueVariableName = onnxContext.AddIntermediateVariable(null, idataviewColumnName, true);
+                onnxContext.CreateNode("Identity", variableName, trueVariableName, onnxContext.GetNodeName("Identity"), "");
+                onnxContext.AddOutputVariable(inputSchema[i].Type, trueVariableName);
+            }
+            return onnxContext.MakeModel();
+        }
+    }
+}

test/Microsoft.ML.Tests/Microsoft.ML.Tests.csproj

@@ -14,6 +14,7 @@
     <ProjectReference Include="..\..\src\Microsoft.ML.KMeansClustering\Microsoft.ML.KMeansClustering.csproj" />
     <ProjectReference Include="..\..\src\Microsoft.ML.LightGBM\Microsoft.ML.LightGBM.csproj" />
     <ProjectReference Include="..\..\src\Microsoft.ML.Maml\Microsoft.ML.Maml.csproj" />
+    <ProjectReference Include="..\..\src\Microsoft.ML.OnnxTransform\Microsoft.ML.OnnxTransform.csproj" />
     <ProjectReference Include="..\..\src\Microsoft.ML.PCA\Microsoft.ML.PCA.csproj" />
     <ProjectReference Include="..\..\src\Microsoft.ML.KMeansClustering\Microsoft.ML.KMeansClustering.csproj" />
     <ProjectReference Include="..\..\src\Microsoft.ML.Recommender\Microsoft.ML.Recommender.csproj" />

test/Microsoft.ML.Tests/OnnxConversionTest.cs

@@ -0,0 +1,80 @@
+using System.Collections.Generic;
+using System.Linq;
+using Google.Protobuf;
+using Microsoft.ML.Data;
+using Microsoft.ML.Model.Onnx;
+using Microsoft.ML.RunTests;
+using Microsoft.ML.Transforms;
+using Xunit;
+using Xunit.Abstractions;
+
+namespace Microsoft.ML.Tests
+{
+    public class OnnxConversionTest : BaseTestBaseline
+    {
+        private class AdultData
+        {
+            [LoadColumn(0, 10), ColumnName("FeatureVector")]
+            public float Features { get; set; }
+
+            [LoadColumn(11)]
+            public float Target { get; set; }
+        }
+
+        public OnnxConversionTest(ITestOutputHelper output) : base(output)
+        {
+        }
+
+        [Fact]
+        public void SimplePipelineOnnxConversionTest()
+        {
+            var trainDataPath = GetDataPath(TestDatasets.generatedRegressionDataset.trainFilename);
+            var mlContext = new MLContext();
+
+            var trainData = mlContext.Data.ReadFromTextFile<AdultData>(trainDataPath,
+                hasHeader: true,
+                separatorChar: ';'
+            );
+
+            var cachedTrainData = mlContext.Data.Cache(trainData);
+
+            var dynamicPipeline =
+                mlContext.Transforms.Normalize("FeatureVector")
+                .AppendCacheCheckpoint(mlContext)
+                .Append(mlContext.Regression.Trainers.StochasticDualCoordinateAscent(labelColumn: "Target", featureColumn: "FeatureVector"));
+
+            var model = dynamicPipeline.Fit(trainData);
+            var transformedData = model.Transform(trainData);
+
+            var onnxModel = TransformerChainOnnxConverter.Convert(model, trainData.Schema);
+
+            var onnxFileName = "model.onnx";
+            var onnxFilePath = GetOutputPath(onnxFileName);
+            using (var file = (mlContext as IHostEnvironment).CreateOutputFile(onnxFilePath))
+            using (var stream = file.CreateWriteStream())
+                onnxModel.WriteTo(stream);
+
+            string[] inputNames = onnxModel.Graph.Input.Select(valueInfoProto => valueInfoProto.Name).ToArray();
+            string[] outputNames = onnxModel.Graph.Output.Select(valueInfoProto => valueInfoProto.Name).ToArray();
+            var onnxEstimator = new OnnxScoringEstimator(mlContext, onnxFilePath, inputNames, outputNames);
+            var onnxTransformer = onnxEstimator.Fit(trainData);
+            var onnxResult = onnxTransformer.Transform(trainData);
+
+            using (var expectedCursor = transformedData.GetRowCursor(columnIndex => columnIndex == transformedData.Schema["Score"].Index))
+            using (var actualCursor = onnxResult.GetRowCursor(columnIndex => columnIndex == onnxResult.Schema["Score0"].Index))
+            {
+                float expected = default;
+                VBuffer<float> actual = default;
+                var expectedGetter = expectedCursor.GetGetter<float>(transformedData.Schema["Score"].Index);
+                var actualGetter = actualCursor.GetGetter<VBuffer<float>>(onnxResult.Schema["Score0"].Index);
+                while(expectedCursor.MoveNext() && actualCursor.MoveNext())
+                {
+                    expectedGetter(ref expected);
+                    actualGetter(ref actual);
+
+                    Assert.Equal(expected, actual.GetValues()[0], 1);
+                }
+            }
+        }
+    }
+}