Skip to content

Fix for ColumnConcatenatingTransformer #4861

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 21, 2020
Merged

Fix for ColumnConcatenatingTransformer #4861

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
64df935
using concat for columnconcatenation
Lynx1820 Feb 20, 2020
f4b03d7
resolving comments
Lynx1820 Feb 20, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions src/Microsoft.ML.Data/Transforms/ColumnConcatenatingTransformer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -896,7 +896,7 @@ public void SaveAsOnnx(OnnxContext ctx)
Host.CheckValue(ctx, nameof(ctx));
Contracts.Assert(CanSaveOnnx(ctx));

string opType = "FeatureVectorizer";
string opType = "Concat";
for (int iinfo = 0; iinfo < _columns.Length; ++iinfo)
{
var colInfo = _parent._columns[iinfo];
Expand Down Expand Up @@ -926,9 +926,9 @@ public void SaveAsOnnx(OnnxContext ctx)
}

var node = ctx.CreateNode(opType, inputList.Select(t => t.Key),
new[] { ctx.AddIntermediateVariable(outColType, outName) }, ctx.GetNodeName(opType));
new[] { ctx.AddIntermediateVariable(outColType, outName) }, ctx.GetNodeName(opType), "");

node.AddAttribute("inputdimensions", inputList.Select(x => x.Value));
node.AddAttribute("axis", 1);
}
}
}
Expand Down
16 changes: 6 additions & 10 deletions ...Output/Common/Onnx/BinaryClassification/BreastCancer/ExcludeVariablesInOnnxConversion.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,19 +179,15 @@
"output": [
"Features"
],
"name": "FeatureVectorizer",
"opType": "FeatureVectorizer",
"name": "Concat",
"opType": "Concat",
"attribute": [
{
"name": "inputdimensions",
"ints": [
"1",
"10"
],
"type": "INTS"
"name": "axis",
"i": "1",
"type": "INT"
}
],
"domain": "ai.onnx.ml"
]
},
{
"input": [
Expand Down
34 changes: 15 additions & 19 deletions test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/ModelWithLessIO.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,19 +128,15 @@
"output": [
"Features"
],
"name": "FeatureVectorizer",
"opType": "FeatureVectorizer",
"name": "Concat",
"opType": "Concat",
"attribute": [
{
"name": "inputdimensions",
"ints": [
"8",
"9"
],
"type": "INTS"
"name": "axis",
"i": "1",
"type": "INT"
}
],
"domain": "ai.onnx.ml"
]
},
{
"input": [
Expand Down Expand Up @@ -677,27 +673,27 @@
"floats": [
-0.9850374,
-1,
-0.42857143,
-0.428571433,
0.05882353,
0.9655172,
0.47826087,
7E-45,
0.478260875,
7.006492E-45,
0.9354839,
-0.837172,
-0.89662564,
-0.896625638,
-0.3455931,
0.22312601,
0.223126009,
0.8040303,
0.60825175,
-0.06932944,
-0.40204307,
-0.402043074,
-0.7417274,
-0.40843493,
-0.408434927,
0.7105746,
0.1875386,
0.7631735,
0.70617324,
0.62590647,
0.706173241,
0.625906467,
-0.35968104
],
"type": "FLOATS"
Expand Down
20 changes: 8 additions & 12 deletions test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/OneHotBagPipeline.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,19 +179,15 @@
"output": [
"Features"
],
"name": "FeatureVectorizer",
"opType": "FeatureVectorizer",
"name": "Concat",
"opType": "Concat",
"attribute": [
{
"name": "inputdimensions",
"ints": [
"1",
"10"
],
"type": "INTS"
"name": "axis",
"i": "1",
"type": "INT"
}
],
"domain": "ai.onnx.ml"
]
},
{
"input": [
Expand Down Expand Up @@ -324,8 +320,8 @@
{
"name": "target_weights",
"floats": [
0.50476193,
-0.97911227
0.504761934,
-0.979112267
],
"type": "FLOATS"
}
Expand Down
30 changes: 26 additions & 4 deletions test/Microsoft.ML.Tests/OnnxConversionTest.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -562,6 +562,7 @@ public void KeyToVectorWithBagOnnxConversionTest()
.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 onnxModel = mlContext.Model.ConvertToOnnxProtobuf(model, data);

// Check ONNX model's text format. We save the produced ONNX model as a text file and compare it against
Expand All @@ -571,8 +572,19 @@ public void KeyToVectorWithBagOnnxConversionTest()
var onnxTextName = "OneHotBagPipeline.txt";
var onnxFileName = "OneHotBagPipeline.onnx";
var onnxTextPath = GetOutputPath(subDir, onnxTextName);
var onnxFilePath = GetOutputPath(subDir, onnxFileName);
SaveOnnxModel(onnxModel, onnxFilePath, onnxTextPath);
var onnxModelPath = GetOutputPath(subDir, onnxFileName);
SaveOnnxModel(onnxModel, onnxModelPath, onnxTextPath);
// Compare results produced by ML.NET and ONNX's runtime.
if (IsOnnxRuntimeSupported())
{
// Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(onnxModelPath);
var onnxTransformer = onnxEstimator.Fit(data);
var onnxResult = onnxTransformer.Transform(data);
CompareSelectedColumns<float>("Score", "Score", transformedData, onnxResult);
CompareSelectedColumns<float>("Probability", "Probability", transformedData, onnxResult);
CompareSelectedColumns<bool>("PredictedLabel", "PredictedLabel", transformedData, onnxResult);
}
CheckEquality(subDir, onnxTextName);
Done();
}
Expand Down Expand Up @@ -904,8 +916,18 @@ public void RemoveVariablesInPipelineTest()
var onnxTextName = "ExcludeVariablesInOnnxConversion.txt";
var onnxFileName = "ExcludeVariablesInOnnxConversion.onnx";
var onnxTextPath = GetOutputPath(subDir, onnxTextName);
var onnxFilePath = GetOutputPath(subDir, onnxFileName);
SaveOnnxModel(onnxModel, onnxFilePath, onnxTextPath);
var onnxModelPath = GetOutputPath(subDir, onnxFileName);
SaveOnnxModel(onnxModel, onnxModelPath, onnxTextPath);
if (IsOnnxRuntimeSupported())
{
// Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(onnxModelPath);
var onnxTransformer = onnxEstimator.Fit(data);
var onnxResult = onnxTransformer.Transform(data);
CompareSelectedColumns<float>("Score", "Score", transformedData, onnxResult);
CompareSelectedColumns<float>("Probability", "Probability", transformedData, onnxResult);
CompareSelectedColumns<bool>("PredictedLabel", "PredictedLabel", transformedData, onnxResult);
}
CheckEquality(subDir, onnxTextName, digitsOfPrecision: 3);
}
Done();
Expand Down