Added onnx export functionality for LpNormNormalizingTransformer#4161

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
harishsk merged 18 commits into from
Sep 6, 2019
Merged

Added onnx export functionality for LpNormNormalizingTransformer #4161

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
8749a10
Merge pull request #1 from dotnet/master
harishsk Jun 20, 2019
fe25bf6
Fixed build errors resulting from upgrade to VS2019 compilers
harishsk Jun 21, 2019
cb446be
Added additional message describing the previous fix
harishsk Jun 21, 2019
b5ee220
Merge pull request #2 from dotnet/master
harishsk Jun 21, 2019
b9a7471
Merge pull request #3 from dotnet/master
harishsk Jun 24, 2019
80e238d
Merge pull request #4 from dotnet/master
harishsk Jun 27, 2019
2ef424d
Merge pull request #5 from dotnet/master
harishsk Jul 9, 2019
3958f01
Merge pull request #6 from dotnet/master
harishsk Aug 7, 2019
00bc7ef
Merge pull request #7 from dotnet/master
harishsk Aug 14, 2019
d0462f1
Merge pull request #8 from dotnet/master
harishsk Aug 16, 2019
c0a430a
Merge pull request #9 from dotnet/master
harishsk Aug 21, 2019
0b55903
Syncing upstream fork (#10)
harishsk Aug 30, 2019
798359a
Added export functionality for LpNormNormalizingTransformer
harishsk Aug 30, 2019
56983d5
Syncing upstream fork (#11)
harishsk Aug 30, 2019
fe44d4a
Merge branch 'master' into onnxexport
harishsk Aug 30, 2019
9c31984
Merge pull request #12 from dotnet/master
harishsk Aug 30, 2019
6e75d8a
Merge branch 'onnxexport' of ssh://github.com/harishsk/machinelearnin…
harishsk Aug 30, 2019
1308b4a
Replaced hardcoded Features column name
harishsk Sep 4, 2019
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
131 changes: 130 additions & 1 deletion src/Microsoft.ML.Transforms/GcnTransform.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -12,6 +12,7 @@
using Microsoft.ML.EntryPoints;
using Microsoft.ML.Internal.CpuMath;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;

Expand DownExpand Up@@ -313,11 +314,13 @@ private protected override void SaveModel(ModelSaveContext ctx)

private protected override IRowMapper MakeRowMapper(DataViewSchema schema) => new Mapper(this, schema);

private sealed class Mapper : OneToOneMapperBase
private sealed class Mapper : OneToOneMapperBase, ISaveAsOnnx
{
private readonly DataViewType[] _srcTypes;
private readonly int[] _srcCols;
private readonly DataViewType[] _types;
private readonly LpNormNormalizingEstimatorBase.NormFunction[] _norms;
private readonly bool[] _ensureZeroMeans;
private readonly LpNormNormalizingTransformer _parent;

public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
Expand All@@ -327,12 +330,16 @@ public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
_types = new DataViewType[_parent.ColumnPairs.Length];
_srcTypes = new DataViewType[_parent.ColumnPairs.Length];
_srcCols = new int[_parent.ColumnPairs.Length];
_norms = new LpNormNormalizingEstimatorBase.NormFunction[_parent.ColumnPairs.Length];
_ensureZeroMeans = new bool[_parent.ColumnPairs.Length];
for (int i = 0; i < _parent.ColumnPairs.Length; i++)
{
inputSchema.TryGetColumnIndex(_parent.ColumnPairs[i].inputColumnName, out _srcCols[i]);
var srcCol = inputSchema[_srcCols[i]];
_srcTypes[i] = srcCol.Type;
_types[i] = srcCol.Type;
_norms[i] = _parent._columns[i].Norm;
_ensureZeroMeans[i] = _parent._columns[i].EnsureZeroMean;
}
}

Expand DownExpand Up@@ -594,6 +601,128 @@ private static float Mean(ReadOnlySpan<float> src, int length)
return 0;
return CpuMathUtils.Sum(src) / length;
}

public bool CanSaveOnnx(OnnxContext ctx) => true;

public void SaveAsOnnx(OnnxContext ctx)
{
Host.CheckValue(ctx, nameof(ctx));

for (int iinfo = 0; iinfo < _srcCols.Length; ++iinfo)
{
string inputColumnName = InputSchema[_srcCols[iinfo]].Name;
if (!ctx.ContainsColumn(inputColumnName))
{
ctx.RemoveColumn(inputColumnName, false);
continue;
}

if (!SaveAsOnnxCore(ctx, iinfo, ctx.GetVariableName(inputColumnName), ctx.AddIntermediateVariable(_srcTypes[iinfo], inputColumnName)))
{
ctx.RemoveColumn(inputColumnName, true);
}
}
}

private bool SaveAsOnnxCore(OnnxContext ctx, int iinfo, string srcVariableName, string dstVariableName)
{
string opType;

if ((_norms[iinfo] != LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation) && (_ensureZeroMeans[iinfo] == false))
{
string strNorm;
if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
strNorm = "L1";
else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
strNorm = "L2";
else
strNorm = "MAX";
opType = "Normalizer";
var node = ctx.CreateNode(opType, srcVariableName, dstVariableName, ctx.GetNodeName(opType));
node.AddAttribute("norm", strNorm);
return true;
}

opType = "ReduceMean";
string meanOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MeanOfInput", true);
var meanNode = ctx.CreateNode(opType, srcVariableName, meanOfInput, ctx.GetNodeName(opType), "");
meanNode.AddAttribute("axes", new long[] { 1 });

opType = "Sub";
string inputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "InputMinusMean");
var subtractNode = ctx.CreateNode(opType, new[] { srcVariableName, meanOfInput }, new[] { inputMinusMean }, ctx.GetNodeName(opType), "");

if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
{
opType = "Abs";
string absOfInput = ctx.AddIntermediateVariable(_types[iinfo], "AbsOfInput");
var absNode = ctx.CreateNode(opType, inputMinusMean, absOfInput, ctx.GetNodeName(opType), "");

opType = "ReduceSum";
string sumOfAbsOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SumOfAbsOfInput", true);
var sumOfAbsNode = ctx.CreateNode(opType, absOfInput, sumOfAbsOfInput, ctx.GetNodeName(opType), "");
sumOfAbsNode.AddAttribute("axes", new long[] { 1 });

opType = "Div";
var l1Node = ctx.CreateNode(opType, new[] { inputMinusMean, sumOfAbsOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
}
else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
{
opType = "Pow";
string two = ctx.AddInitializer(2.0f);
string squareOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInput", true);
var squareNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInput }, ctx.GetNodeName(opType), "");

opType = "ReduceSum";
string sumOfSquares = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInput, sumOfSquares, ctx.GetNodeName(opType), "");
sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

opType = "Sqrt";
string squareRoot = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
var squareRootNode = ctx.CreateNode(opType, sumOfSquares, squareRoot, ctx.GetNodeName(opType), "");

opType = "Div";
var l2Node = ctx.CreateNode(opType, new[] { inputMinusMean, squareRoot }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
}
else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.Infinity)
{
opType = "ReduceMax";
string maxOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MaxOfInput", true);
var maxNode = ctx.CreateNode(opType, inputMinusMean, maxOfInput, ctx.GetNodeName(opType), "");
maxNode.AddAttribute("axes", new long[] { 1 });

opType = "Div";
var lMaxNode = ctx.CreateNode(opType, new[] { inputMinusMean, maxOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
}
else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation)
{
// first calculate the standard deviation
opType = "Pow";
string two = ctx.AddInitializer(2.0f);
string squareOfInputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInputMinusMean", true);
var squareOfInputMinusMeanNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInputMinusMean }, ctx.GetNodeName(opType), "");

opType = "ReduceMean";
string average = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInputMinusMean, average, ctx.GetNodeName(opType), "");
sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

opType = "Sqrt";
string stdDev = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
var stdDevNode = ctx.CreateNode(opType, average, stdDev, ctx.GetNodeName(opType), "");

opType = "Div";
string input = _ensureZeroMeans[iinfo] ? inputMinusMean : srcVariableName;
var lStdDevNode = ctx.CreateNode(opType, new[] {input, stdDev }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
}
else
{
Contracts.Assert(false);
return false;
}
return true;
}
}
}

Expand Down
62 changes: 62 additions & 0 deletions test/Microsoft.ML.Tests/OnnxConversionTest.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -180,6 +180,68 @@ public void KmeansOnnxConversionTest()
Done();
}

private class DataPoint
{
[VectorType(3)]
public float[] Features { get; set; }
}

[Fact]
void LpNormOnnxConversionTest()
{
var mlContext = new MLContext(seed: 1);

var samples = new List<DataPoint>()
{
new DataPoint() { Features = new float[3] {0.01f, 0.02f, 0.03f} },
new DataPoint() { Features = new float[3] {0.04f, 0.05f, 0.06f} },
new DataPoint() { Features = new float[3] {0.07f, 0.08f, 0.09f} },
new DataPoint() { Features = new float[3] {0.10f, 0.11f, 0.12f} },
new DataPoint() { Features = new float[3] {0.13f, 0.14f, 0.15f} }
};
var dataView = mlContext.Data.LoadFromEnumerable(samples);

LpNormNormalizingEstimatorBase.NormFunction[] norms =
{
LpNormNormalizingEstimatorBase.NormFunction.L1,
LpNormNormalizingEstimatorBase.NormFunction.L2,
LpNormNormalizingEstimatorBase.NormFunction.Infinity,
LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation
};

bool[] ensureZeroMeans = { true, false};
foreach (var ensureZeroMean in ensureZeroMeans)
{
foreach (var norm in norms)
{
var pipe = mlContext.Transforms.NormalizeLpNorm(nameof(DataPoint.Features), norm:norm, ensureZeroMean: ensureZeroMean);

var model = pipe.Fit(dataView);
var transformedData = model.Transform(dataView);
var onnxModel = mlContext.Model.ConvertToOnnxProtobuf(model, dataView);

var onnxFileName = $"LpNorm-{norm.ToString()}-{ensureZeroMean}.onnx";
var onnxModelPath = GetOutputPath(onnxFileName);

SaveOnnxModel(onnxModel, onnxModelPath, null);

// Compare results produced by ML.NET and ONNX's runtime.
if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows) && Environment.Is64BitProcess)

@ganikganikSep 6, 2019

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

RuntimeInformation.IsOSPlatform(OSPlatform.Windows) [](start = 24, length = 51)

Do you need this condition? If its a linux will results match?

@harishskharishskSep 6, 2019

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it is that the test will run only on Windows. The results should still match. It appears that OnnxRuntime doesn't support Linux and Mac yet.

{
// Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
string[] inputNames = onnxModel.Graph.Input.Select(valueInfoProto => valueInfoProto.Name).ToArray();
string[] outputNames = onnxModel.Graph.Output.Select(valueInfoProto => valueInfoProto.Name).ToArray();
var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(outputNames, inputNames, onnxModelPath);
var onnxTransformer = onnxEstimator.Fit(dataView);
var onnxResult = onnxTransformer.Transform(dataView);
CompareSelectedR4VectorColumns(nameof(DataPoint.Features), outputNames[0], transformedData, onnxResult, 3);
}
}
}

Done();
}

[Fact]
void CommandLineOnnxConversionTest()
{
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Added onnx export functionality for LpNormNormalizingTransformer#4161

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

harishsk
merged 18 commits into

from

Sep 6, 2019
 Merged


Added onnx export functionality for LpNormNormalizingTransformer
#4161
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


18 commits


Select commit
Hold shift + click to select a range
8749a10

Merge pull request #1 from dotnet/master


harishsk Jun 20, 2019
fe25bf6

Fixed build errors resulting from upgrade to VS2019 compilers


harishsk Jun 21, 2019
cb446be

Added additional message describing the previous fix


harishsk Jun 21, 2019
b5ee220

Merge pull request #2 from dotnet/master


harishsk Jun 21, 2019
b9a7471

Merge pull request #3 from dotnet/master


harishsk Jun 24, 2019
80e238d

Merge pull request #4 from dotnet/master


harishsk Jun 27, 2019
2ef424d

Merge pull request #5 from dotnet/master


harishsk Jul 9, 2019
3958f01

Merge pull request #6 from dotnet/master


harishsk Aug 7, 2019
00bc7ef

Merge pull request #7 from dotnet/master


harishsk Aug 14, 2019
d0462f1

Merge pull request #8 from dotnet/master


harishsk Aug 16, 2019
c0a430a

Merge pull request #9 from dotnet/master


harishsk Aug 21, 2019
0b55903

Syncing upstream fork (#10)


harishsk Aug 30, 2019
798359a

Added export functionality for LpNormNormalizingTransformer


harishsk Aug 30, 2019
56983d5

Syncing upstream fork (#11)


harishsk Aug 30, 2019
fe44d4a

Merge branch 'master' into onnxexport


harishsk Aug 30, 2019
9c31984

Merge pull request #12 from dotnet/master


harishsk Aug 30, 2019
6e75d8a

Merge branch 'onnxexport' of ssh://github.com/harishsk/machinelearnin…


harishsk Aug 30, 2019
1308b4a

Replaced hardcoded Features column name


harishsk Sep 4, 2019

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


131 changes: 130 additions & 1 deletion
src/Microsoft.ML.Transforms/GcnTransform.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -12,6 +12,7 @@
using Microsoft.ML.EntryPoints;
using Microsoft.ML.Internal.CpuMath;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;

Expand DownExpand Up@@ -313,11 +314,13 @@ private protected override void SaveModel(ModelSaveContext ctx)

 private protected override IRowMapper MakeRowMapper(DataViewSchema schema) => new Mapper(this, schema);

 private sealed class Mapper : OneToOneMapperBase
 private sealed class Mapper : OneToOneMapperBase, ISaveAsOnnx
 {
 private readonly DataViewType[] _srcTypes;
 private readonly int[] _srcCols;
 private readonly DataViewType[] _types;
 private readonly LpNormNormalizingEstimatorBase.NormFunction[] _norms;
 private readonly bool[] _ensureZeroMeans;
 private readonly LpNormNormalizingTransformer _parent;

 public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
Expand All@@ -327,12 +330,16 @@ public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
 _types = new DataViewType[_parent.ColumnPairs.Length];
 _srcTypes = new DataViewType[_parent.ColumnPairs.Length];
 _srcCols = new int[_parent.ColumnPairs.Length];
 _norms = new LpNormNormalizingEstimatorBase.NormFunction[_parent.ColumnPairs.Length];
 _ensureZeroMeans = new bool[_parent.ColumnPairs.Length];
 for (int i = 0; i < _parent.ColumnPairs.Length; i++)
 {
 inputSchema.TryGetColumnIndex(_parent.ColumnPairs[i].inputColumnName, out _srcCols[i]);
 var srcCol = inputSchema[_srcCols[i]];
 _srcTypes[i] = srcCol.Type;
 _types[i] = srcCol.Type;
 _norms[i] = _parent._columns[i].Norm;
 _ensureZeroMeans[i] = _parent._columns[i].EnsureZeroMean;
 }
 }

Expand DownExpand Up@@ -594,6 +601,128 @@ private static float Mean(ReadOnlySpan<float> src, int length)
 return 0;
 return CpuMathUtils.Sum(src) / length;
 }

 public bool CanSaveOnnx(OnnxContext ctx) => true;

 public void SaveAsOnnx(OnnxContext ctx)
 {
 Host.CheckValue(ctx, nameof(ctx));

 for (int iinfo = 0; iinfo < _srcCols.Length; ++iinfo)
 {
 string inputColumnName = InputSchema[_srcCols[iinfo]].Name;
 if (!ctx.ContainsColumn(inputColumnName))
 {
 ctx.RemoveColumn(inputColumnName, false);
 continue;
 }

 if (!SaveAsOnnxCore(ctx, iinfo, ctx.GetVariableName(inputColumnName), ctx.AddIntermediateVariable(_srcTypes[iinfo], inputColumnName)))
 {
 ctx.RemoveColumn(inputColumnName, true);
 }
 }
 }

 private bool SaveAsOnnxCore(OnnxContext ctx, int iinfo, string srcVariableName, string dstVariableName)
 {
 string opType;

 if ((_norms[iinfo] != LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation) && (_ensureZeroMeans[iinfo] == false))
 {
 string strNorm;
 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 strNorm = "L1";
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 strNorm = "L2";
 else
 strNorm = "MAX";
 opType = "Normalizer";
 var node = ctx.CreateNode(opType, srcVariableName, dstVariableName, ctx.GetNodeName(opType));
 node.AddAttribute("norm", strNorm);
 return true;
 }

 opType = "ReduceMean";
 string meanOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MeanOfInput", true);
 var meanNode = ctx.CreateNode(opType, srcVariableName, meanOfInput, ctx.GetNodeName(opType), "");
 meanNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sub";
 string inputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "InputMinusMean");
 var subtractNode = ctx.CreateNode(opType, new[] { srcVariableName, meanOfInput }, new[] { inputMinusMean }, ctx.GetNodeName(opType), "");

 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 {
 opType = "Abs";
 string absOfInput = ctx.AddIntermediateVariable(_types[iinfo], "AbsOfInput");
 var absNode = ctx.CreateNode(opType, inputMinusMean, absOfInput, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfAbsOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SumOfAbsOfInput", true);
 var sumOfAbsNode = ctx.CreateNode(opType, absOfInput, sumOfAbsOfInput, ctx.GetNodeName(opType), "");
 sumOfAbsNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var l1Node = ctx.CreateNode(opType, new[] { inputMinusMean, sumOfAbsOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 {
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInput", true);
 var squareNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInput }, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfSquares = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInput, sumOfSquares, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string squareRoot = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var squareRootNode = ctx.CreateNode(opType, sumOfSquares, squareRoot, ctx.GetNodeName(opType), "");

 opType = "Div";
 var l2Node = ctx.CreateNode(opType, new[] { inputMinusMean, squareRoot }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.Infinity)
 {
 opType = "ReduceMax";
 string maxOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MaxOfInput", true);
 var maxNode = ctx.CreateNode(opType, inputMinusMean, maxOfInput, ctx.GetNodeName(opType), "");
 maxNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var lMaxNode = ctx.CreateNode(opType, new[] { inputMinusMean, maxOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation)
 {
 // first calculate the standard deviation
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInputMinusMean", true);
 var squareOfInputMinusMeanNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInputMinusMean }, ctx.GetNodeName(opType), "");

 opType = "ReduceMean";
 string average = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInputMinusMean, average, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string stdDev = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var stdDevNode = ctx.CreateNode(opType, average, stdDev, ctx.GetNodeName(opType), "");

 opType = "Div";
 string input = _ensureZeroMeans[iinfo] ? inputMinusMean : srcVariableName;
 var lStdDevNode = ctx.CreateNode(opType, new[] {input, stdDev }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else
 {
 Contracts.Assert(false);
 return false;
 }
 return true;
 }
 }
 }

Expand Down

62 changes: 62 additions & 0 deletions
test/Microsoft.ML.Tests/OnnxConversionTest.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -180,6 +180,68 @@ public void KmeansOnnxConversionTest()
 Done();
 }

 private class DataPoint
 {
 [VectorType(3)]
 public float[] Features { get; set; }
 }

 [Fact]
 void LpNormOnnxConversionTest()
 {
 var mlContext = new MLContext(seed: 1);

 var samples = new List<DataPoint>()
 {
 new DataPoint() { Features = new float[3] {0.01f, 0.02f, 0.03f} },
 new DataPoint() { Features = new float[3] {0.04f, 0.05f, 0.06f} },
 new DataPoint() { Features = new float[3] {0.07f, 0.08f, 0.09f} },
 new DataPoint() { Features = new float[3] {0.10f, 0.11f, 0.12f} },
 new DataPoint() { Features = new float[3] {0.13f, 0.14f, 0.15f} }
 };
 var dataView = mlContext.Data.LoadFromEnumerable(samples);

 LpNormNormalizingEstimatorBase.NormFunction[] norms =
 {
 LpNormNormalizingEstimatorBase.NormFunction.L1,
 LpNormNormalizingEstimatorBase.NormFunction.L2,
 LpNormNormalizingEstimatorBase.NormFunction.Infinity,
 LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation
 };

 bool[] ensureZeroMeans = { true, false};
 foreach (var ensureZeroMean in ensureZeroMeans)
 {
 foreach (var norm in norms)
 {
 var pipe = mlContext.Transforms.NormalizeLpNorm(nameof(DataPoint.Features), norm:norm, ensureZeroMean: ensureZeroMean);

 var model = pipe.Fit(dataView);
 var transformedData = model.Transform(dataView);
 var onnxModel = mlContext.Model.ConvertToOnnxProtobuf(model, dataView);

 var onnxFileName = $"LpNorm-{norm.ToString()}-{ensureZeroMean}.onnx";
 var onnxModelPath = GetOutputPath(onnxFileName);

 SaveOnnxModel(onnxModel, onnxModelPath, null);

 // Compare results produced by ML.NET and ONNX's runtime.
 if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows) && Environment.Is64BitProcess)
@ganikganikSep 6, 2019

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

RuntimeInformation.IsOSPlatform(OSPlatform.Windows) [](start = 24, length = 51)
Do you need this condition? If its a linux will results match?
@harishskharishskSep 6, 2019

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it is that the test will run only on Windows. The results should still match. It appears that OnnxRuntime doesn't support Linux and Mac yet.
 {
 // Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
 string[] inputNames = onnxModel.Graph.Input.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 string[] outputNames = onnxModel.Graph.Output.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(outputNames, inputNames, onnxModelPath);
 var onnxTransformer = onnxEstimator.Fit(dataView);
 var onnxResult = onnxTransformer.Transform(dataView);
 CompareSelectedR4VectorColumns(nameof(DataPoint.Features), outputNames[0], transformedData, onnxResult, 3);
 }
 }
 }

 Done();
 }

 [Fact]
 void CommandLineOnnxConversionTest()
 {
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Added onnx export functionality for LpNormNormalizingTransformer#4161

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

harishsk
merged 18 commits into

from

Sep 6, 2019
 Merged


Added onnx export functionality for LpNormNormalizingTransformer
#4161
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


18 commits


Select commit
Hold shift + click to select a range
8749a10

Merge pull request #1 from dotnet/master


harishsk Jun 20, 2019
fe25bf6

Fixed build errors resulting from upgrade to VS2019 compilers


harishsk Jun 21, 2019
cb446be

Added additional message describing the previous fix


harishsk Jun 21, 2019
b5ee220

Merge pull request #2 from dotnet/master


harishsk Jun 21, 2019
b9a7471

Merge pull request #3 from dotnet/master


harishsk Jun 24, 2019
80e238d

Merge pull request #4 from dotnet/master


harishsk Jun 27, 2019
2ef424d

Merge pull request #5 from dotnet/master


harishsk Jul 9, 2019
3958f01

Merge pull request #6 from dotnet/master


harishsk Aug 7, 2019
00bc7ef

Merge pull request #7 from dotnet/master


harishsk Aug 14, 2019
d0462f1

Merge pull request #8 from dotnet/master


harishsk Aug 16, 2019
c0a430a

Merge pull request #9 from dotnet/master


harishsk Aug 21, 2019
0b55903

Syncing upstream fork (#10)


harishsk Aug 30, 2019
798359a

Added export functionality for LpNormNormalizingTransformer


harishsk Aug 30, 2019
56983d5

Syncing upstream fork (#11)


harishsk Aug 30, 2019
fe44d4a

Merge branch 'master' into onnxexport


harishsk Aug 30, 2019
9c31984

Merge pull request #12 from dotnet/master


harishsk Aug 30, 2019
6e75d8a

Merge branch 'onnxexport' of ssh://github.com/harishsk/machinelearnin…


harishsk Aug 30, 2019
1308b4a

Replaced hardcoded Features column name


harishsk Sep 4, 2019

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


131 changes: 130 additions & 1 deletion
src/Microsoft.ML.Transforms/GcnTransform.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -12,6 +12,7 @@
using Microsoft.ML.EntryPoints;
using Microsoft.ML.Internal.CpuMath;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;

Expand DownExpand Up@@ -313,11 +314,13 @@ private protected override void SaveModel(ModelSaveContext ctx)

 private protected override IRowMapper MakeRowMapper(DataViewSchema schema) => new Mapper(this, schema);

 private sealed class Mapper : OneToOneMapperBase
 private sealed class Mapper : OneToOneMapperBase, ISaveAsOnnx
 {
 private readonly DataViewType[] _srcTypes;
 private readonly int[] _srcCols;
 private readonly DataViewType[] _types;
 private readonly LpNormNormalizingEstimatorBase.NormFunction[] _norms;
 private readonly bool[] _ensureZeroMeans;
 private readonly LpNormNormalizingTransformer _parent;

 public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
Expand All@@ -327,12 +330,16 @@ public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
 _types = new DataViewType[_parent.ColumnPairs.Length];
 _srcTypes = new DataViewType[_parent.ColumnPairs.Length];
 _srcCols = new int[_parent.ColumnPairs.Length];
 _norms = new LpNormNormalizingEstimatorBase.NormFunction[_parent.ColumnPairs.Length];
 _ensureZeroMeans = new bool[_parent.ColumnPairs.Length];
 for (int i = 0; i < _parent.ColumnPairs.Length; i++)
 {
 inputSchema.TryGetColumnIndex(_parent.ColumnPairs[i].inputColumnName, out _srcCols[i]);
 var srcCol = inputSchema[_srcCols[i]];
 _srcTypes[i] = srcCol.Type;
 _types[i] = srcCol.Type;
 _norms[i] = _parent._columns[i].Norm;
 _ensureZeroMeans[i] = _parent._columns[i].EnsureZeroMean;
 }
 }

Expand DownExpand Up@@ -594,6 +601,128 @@ private static float Mean(ReadOnlySpan<float> src, int length)
 return 0;
 return CpuMathUtils.Sum(src) / length;
 }

 public bool CanSaveOnnx(OnnxContext ctx) => true;

 public void SaveAsOnnx(OnnxContext ctx)
 {
 Host.CheckValue(ctx, nameof(ctx));

 for (int iinfo = 0; iinfo < _srcCols.Length; ++iinfo)
 {
 string inputColumnName = InputSchema[_srcCols[iinfo]].Name;
 if (!ctx.ContainsColumn(inputColumnName))
 {
 ctx.RemoveColumn(inputColumnName, false);
 continue;
 }

 if (!SaveAsOnnxCore(ctx, iinfo, ctx.GetVariableName(inputColumnName), ctx.AddIntermediateVariable(_srcTypes[iinfo], inputColumnName)))
 {
 ctx.RemoveColumn(inputColumnName, true);
 }
 }
 }

 private bool SaveAsOnnxCore(OnnxContext ctx, int iinfo, string srcVariableName, string dstVariableName)
 {
 string opType;

 if ((_norms[iinfo] != LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation) && (_ensureZeroMeans[iinfo] == false))
 {
 string strNorm;
 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 strNorm = "L1";
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 strNorm = "L2";
 else
 strNorm = "MAX";
 opType = "Normalizer";
 var node = ctx.CreateNode(opType, srcVariableName, dstVariableName, ctx.GetNodeName(opType));
 node.AddAttribute("norm", strNorm);
 return true;
 }

 opType = "ReduceMean";
 string meanOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MeanOfInput", true);
 var meanNode = ctx.CreateNode(opType, srcVariableName, meanOfInput, ctx.GetNodeName(opType), "");
 meanNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sub";
 string inputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "InputMinusMean");
 var subtractNode = ctx.CreateNode(opType, new[] { srcVariableName, meanOfInput }, new[] { inputMinusMean }, ctx.GetNodeName(opType), "");

 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 {
 opType = "Abs";
 string absOfInput = ctx.AddIntermediateVariable(_types[iinfo], "AbsOfInput");
 var absNode = ctx.CreateNode(opType, inputMinusMean, absOfInput, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfAbsOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SumOfAbsOfInput", true);
 var sumOfAbsNode = ctx.CreateNode(opType, absOfInput, sumOfAbsOfInput, ctx.GetNodeName(opType), "");
 sumOfAbsNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var l1Node = ctx.CreateNode(opType, new[] { inputMinusMean, sumOfAbsOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 {
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInput", true);
 var squareNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInput }, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfSquares = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInput, sumOfSquares, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string squareRoot = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var squareRootNode = ctx.CreateNode(opType, sumOfSquares, squareRoot, ctx.GetNodeName(opType), "");

 opType = "Div";
 var l2Node = ctx.CreateNode(opType, new[] { inputMinusMean, squareRoot }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.Infinity)
 {
 opType = "ReduceMax";
 string maxOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MaxOfInput", true);
 var maxNode = ctx.CreateNode(opType, inputMinusMean, maxOfInput, ctx.GetNodeName(opType), "");
 maxNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var lMaxNode = ctx.CreateNode(opType, new[] { inputMinusMean, maxOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation)
 {
 // first calculate the standard deviation
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInputMinusMean", true);
 var squareOfInputMinusMeanNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInputMinusMean }, ctx.GetNodeName(opType), "");

 opType = "ReduceMean";
 string average = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInputMinusMean, average, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string stdDev = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var stdDevNode = ctx.CreateNode(opType, average, stdDev, ctx.GetNodeName(opType), "");

 opType = "Div";
 string input = _ensureZeroMeans[iinfo] ? inputMinusMean : srcVariableName;
 var lStdDevNode = ctx.CreateNode(opType, new[] {input, stdDev }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else
 {
 Contracts.Assert(false);
 return false;
 }
 return true;
 }
 }
 }

Expand Down

62 changes: 62 additions & 0 deletions
test/Microsoft.ML.Tests/OnnxConversionTest.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -180,6 +180,68 @@ public void KmeansOnnxConversionTest()
 Done();
 }

 private class DataPoint
 {
 [VectorType(3)]
 public float[] Features { get; set; }
 }

 [Fact]
 void LpNormOnnxConversionTest()
 {
 var mlContext = new MLContext(seed: 1);

 var samples = new List<DataPoint>()
 {
 new DataPoint() { Features = new float[3] {0.01f, 0.02f, 0.03f} },
 new DataPoint() { Features = new float[3] {0.04f, 0.05f, 0.06f} },
 new DataPoint() { Features = new float[3] {0.07f, 0.08f, 0.09f} },
 new DataPoint() { Features = new float[3] {0.10f, 0.11f, 0.12f} },
 new DataPoint() { Features = new float[3] {0.13f, 0.14f, 0.15f} }
 };
 var dataView = mlContext.Data.LoadFromEnumerable(samples);

 LpNormNormalizingEstimatorBase.NormFunction[] norms =
 {
 LpNormNormalizingEstimatorBase.NormFunction.L1,
 LpNormNormalizingEstimatorBase.NormFunction.L2,
 LpNormNormalizingEstimatorBase.NormFunction.Infinity,
 LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation
 };

 bool[] ensureZeroMeans = { true, false};
 foreach (var ensureZeroMean in ensureZeroMeans)
 {
 foreach (var norm in norms)
 {
 var pipe = mlContext.Transforms.NormalizeLpNorm(nameof(DataPoint.Features), norm:norm, ensureZeroMean: ensureZeroMean);

 var model = pipe.Fit(dataView);
 var transformedData = model.Transform(dataView);
 var onnxModel = mlContext.Model.ConvertToOnnxProtobuf(model, dataView);

 var onnxFileName = $"LpNorm-{norm.ToString()}-{ensureZeroMean}.onnx";
 var onnxModelPath = GetOutputPath(onnxFileName);

 SaveOnnxModel(onnxModel, onnxModelPath, null);

 // Compare results produced by ML.NET and ONNX's runtime.
 if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows) && Environment.Is64BitProcess)
@ganikganikSep 6, 2019

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

RuntimeInformation.IsOSPlatform(OSPlatform.Windows) [](start = 24, length = 51)
Do you need this condition? If its a linux will results match?
@harishskharishskSep 6, 2019

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it is that the test will run only on Windows. The results should still match. It appears that OnnxRuntime doesn't support Linux and Mac yet.
 {
 // Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
 string[] inputNames = onnxModel.Graph.Input.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 string[] outputNames = onnxModel.Graph.Output.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(outputNames, inputNames, onnxModelPath);
 var onnxTransformer = onnxEstimator.Fit(dataView);
 var onnxResult = onnxTransformer.Transform(dataView);
 CompareSelectedR4VectorColumns(nameof(DataPoint.Features), outputNames[0], transformedData, onnxResult, 3);
 }
 }
 }

 Done();
 }

 [Fact]
 void CommandLineOnnxConversionTest()
 {
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Added onnx export functionality for LpNormNormalizingTransformer#4161

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

harishsk
merged 18 commits into

from

Sep 6, 2019
 Merged


Added onnx export functionality for LpNormNormalizingTransformer
#4161
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


18 commits


Select commit
Hold shift + click to select a range
8749a10

Merge pull request #1 from dotnet/master


harishsk Jun 20, 2019
fe25bf6

Fixed build errors resulting from upgrade to VS2019 compilers


harishsk Jun 21, 2019
cb446be

Added additional message describing the previous fix


harishsk Jun 21, 2019
b5ee220

Merge pull request #2 from dotnet/master


harishsk Jun 21, 2019
b9a7471

Merge pull request #3 from dotnet/master


harishsk Jun 24, 2019
80e238d

Merge pull request #4 from dotnet/master


harishsk Jun 27, 2019
2ef424d

Merge pull request #5 from dotnet/master


harishsk Jul 9, 2019
3958f01

Merge pull request #6 from dotnet/master


harishsk Aug 7, 2019
00bc7ef

Merge pull request #7 from dotnet/master


harishsk Aug 14, 2019
d0462f1

Merge pull request #8 from dotnet/master


harishsk Aug 16, 2019
c0a430a

Merge pull request #9 from dotnet/master


harishsk Aug 21, 2019
0b55903

Syncing upstream fork (#10)


harishsk Aug 30, 2019
798359a

Added export functionality for LpNormNormalizingTransformer


harishsk Aug 30, 2019
56983d5

Syncing upstream fork (#11)


harishsk Aug 30, 2019
fe44d4a

Merge branch 'master' into onnxexport


harishsk Aug 30, 2019
9c31984

Merge pull request #12 from dotnet/master


harishsk Aug 30, 2019
6e75d8a

Merge branch 'onnxexport' of ssh://github.com/harishsk/machinelearnin…


harishsk Aug 30, 2019
1308b4a

Replaced hardcoded Features column name


harishsk Sep 4, 2019

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


131 changes: 130 additions & 1 deletion
src/Microsoft.ML.Transforms/GcnTransform.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -12,6 +12,7 @@
using Microsoft.ML.EntryPoints;
using Microsoft.ML.Internal.CpuMath;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;

Expand DownExpand Up@@ -313,11 +314,13 @@ private protected override void SaveModel(ModelSaveContext ctx)

 private protected override IRowMapper MakeRowMapper(DataViewSchema schema) => new Mapper(this, schema);

 private sealed class Mapper : OneToOneMapperBase
 private sealed class Mapper : OneToOneMapperBase, ISaveAsOnnx
 {
 private readonly DataViewType[] _srcTypes;
 private readonly int[] _srcCols;
 private readonly DataViewType[] _types;
 private readonly LpNormNormalizingEstimatorBase.NormFunction[] _norms;
 private readonly bool[] _ensureZeroMeans;
 private readonly LpNormNormalizingTransformer _parent;

 public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
Expand All@@ -327,12 +330,16 @@ public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
 _types = new DataViewType[_parent.ColumnPairs.Length];
 _srcTypes = new DataViewType[_parent.ColumnPairs.Length];
 _srcCols = new int[_parent.ColumnPairs.Length];
 _norms = new LpNormNormalizingEstimatorBase.NormFunction[_parent.ColumnPairs.Length];
 _ensureZeroMeans = new bool[_parent.ColumnPairs.Length];
 for (int i = 0; i < _parent.ColumnPairs.Length; i++)
 {
 inputSchema.TryGetColumnIndex(_parent.ColumnPairs[i].inputColumnName, out _srcCols[i]);
 var srcCol = inputSchema[_srcCols[i]];
 _srcTypes[i] = srcCol.Type;
 _types[i] = srcCol.Type;
 _norms[i] = _parent._columns[i].Norm;
 _ensureZeroMeans[i] = _parent._columns[i].EnsureZeroMean;
 }
 }

Expand DownExpand Up@@ -594,6 +601,128 @@ private static float Mean(ReadOnlySpan<float> src, int length)
 return 0;
 return CpuMathUtils.Sum(src) / length;
 }

 public bool CanSaveOnnx(OnnxContext ctx) => true;

 public void SaveAsOnnx(OnnxContext ctx)
 {
 Host.CheckValue(ctx, nameof(ctx));

 for (int iinfo = 0; iinfo < _srcCols.Length; ++iinfo)
 {
 string inputColumnName = InputSchema[_srcCols[iinfo]].Name;
 if (!ctx.ContainsColumn(inputColumnName))
 {
 ctx.RemoveColumn(inputColumnName, false);
 continue;
 }

 if (!SaveAsOnnxCore(ctx, iinfo, ctx.GetVariableName(inputColumnName), ctx.AddIntermediateVariable(_srcTypes[iinfo], inputColumnName)))
 {
 ctx.RemoveColumn(inputColumnName, true);
 }
 }
 }

 private bool SaveAsOnnxCore(OnnxContext ctx, int iinfo, string srcVariableName, string dstVariableName)
 {
 string opType;

 if ((_norms[iinfo] != LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation) && (_ensureZeroMeans[iinfo] == false))
 {
 string strNorm;
 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 strNorm = "L1";
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 strNorm = "L2";
 else
 strNorm = "MAX";
 opType = "Normalizer";
 var node = ctx.CreateNode(opType, srcVariableName, dstVariableName, ctx.GetNodeName(opType));
 node.AddAttribute("norm", strNorm);
 return true;
 }

 opType = "ReduceMean";
 string meanOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MeanOfInput", true);
 var meanNode = ctx.CreateNode(opType, srcVariableName, meanOfInput, ctx.GetNodeName(opType), "");
 meanNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sub";
 string inputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "InputMinusMean");
 var subtractNode = ctx.CreateNode(opType, new[] { srcVariableName, meanOfInput }, new[] { inputMinusMean }, ctx.GetNodeName(opType), "");

 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 {
 opType = "Abs";
 string absOfInput = ctx.AddIntermediateVariable(_types[iinfo], "AbsOfInput");
 var absNode = ctx.CreateNode(opType, inputMinusMean, absOfInput, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfAbsOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SumOfAbsOfInput", true);
 var sumOfAbsNode = ctx.CreateNode(opType, absOfInput, sumOfAbsOfInput, ctx.GetNodeName(opType), "");
 sumOfAbsNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var l1Node = ctx.CreateNode(opType, new[] { inputMinusMean, sumOfAbsOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 {
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInput", true);
 var squareNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInput }, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfSquares = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInput, sumOfSquares, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string squareRoot = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var squareRootNode = ctx.CreateNode(opType, sumOfSquares, squareRoot, ctx.GetNodeName(opType), "");

 opType = "Div";
 var l2Node = ctx.CreateNode(opType, new[] { inputMinusMean, squareRoot }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.Infinity)
 {
 opType = "ReduceMax";
 string maxOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MaxOfInput", true);
 var maxNode = ctx.CreateNode(opType, inputMinusMean, maxOfInput, ctx.GetNodeName(opType), "");
 maxNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var lMaxNode = ctx.CreateNode(opType, new[] { inputMinusMean, maxOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation)
 {
 // first calculate the standard deviation
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInputMinusMean", true);
 var squareOfInputMinusMeanNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInputMinusMean }, ctx.GetNodeName(opType), "");

 opType = "ReduceMean";
 string average = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInputMinusMean, average, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string stdDev = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var stdDevNode = ctx.CreateNode(opType, average, stdDev, ctx.GetNodeName(opType), "");

 opType = "Div";
 string input = _ensureZeroMeans[iinfo] ? inputMinusMean : srcVariableName;
 var lStdDevNode = ctx.CreateNode(opType, new[] {input, stdDev }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else
 {
 Contracts.Assert(false);
 return false;
 }
 return true;
 }
 }
 }

Expand Down

62 changes: 62 additions & 0 deletions
test/Microsoft.ML.Tests/OnnxConversionTest.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -180,6 +180,68 @@ public void KmeansOnnxConversionTest()
 Done();
 }

 private class DataPoint
 {
 [VectorType(3)]
 public float[] Features { get; set; }
 }

 [Fact]
 void LpNormOnnxConversionTest()
 {
 var mlContext = new MLContext(seed: 1);

 var samples = new List<DataPoint>()
 {
 new DataPoint() { Features = new float[3] {0.01f, 0.02f, 0.03f} },
 new DataPoint() { Features = new float[3] {0.04f, 0.05f, 0.06f} },
 new DataPoint() { Features = new float[3] {0.07f, 0.08f, 0.09f} },
 new DataPoint() { Features = new float[3] {0.10f, 0.11f, 0.12f} },
 new DataPoint() { Features = new float[3] {0.13f, 0.14f, 0.15f} }
 };
 var dataView = mlContext.Data.LoadFromEnumerable(samples);

 LpNormNormalizingEstimatorBase.NormFunction[] norms =
 {
 LpNormNormalizingEstimatorBase.NormFunction.L1,
 LpNormNormalizingEstimatorBase.NormFunction.L2,
 LpNormNormalizingEstimatorBase.NormFunction.Infinity,
 LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation
 };

 bool[] ensureZeroMeans = { true, false};
 foreach (var ensureZeroMean in ensureZeroMeans)
 {
 foreach (var norm in norms)
 {
 var pipe = mlContext.Transforms.NormalizeLpNorm(nameof(DataPoint.Features), norm:norm, ensureZeroMean: ensureZeroMean);

 var model = pipe.Fit(dataView);
 var transformedData = model.Transform(dataView);
 var onnxModel = mlContext.Model.ConvertToOnnxProtobuf(model, dataView);

 var onnxFileName = $"LpNorm-{norm.ToString()}-{ensureZeroMean}.onnx";
 var onnxModelPath = GetOutputPath(onnxFileName);

 SaveOnnxModel(onnxModel, onnxModelPath, null);

 // Compare results produced by ML.NET and ONNX's runtime.
 if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows) && Environment.Is64BitProcess)
@ganikganikSep 6, 2019

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

RuntimeInformation.IsOSPlatform(OSPlatform.Windows) [](start = 24, length = 51)
Do you need this condition? If its a linux will results match?
@harishskharishskSep 6, 2019

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it is that the test will run only on Windows. The results should still match. It appears that OnnxRuntime doesn't support Linux and Mac yet.
 {
 // Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
 string[] inputNames = onnxModel.Graph.Input.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 string[] outputNames = onnxModel.Graph.Output.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(outputNames, inputNames, onnxModelPath);
 var onnxTransformer = onnxEstimator.Fit(dataView);
 var onnxResult = onnxTransformer.Transform(dataView);
 CompareSelectedR4VectorColumns(nameof(DataPoint.Features), outputNames[0], transformedData, onnxResult, 3);
 }
 }
 }

 Done();
 }

 [Fact]
 void CommandLineOnnxConversionTest()
 {
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Added onnx export functionality for LpNormNormalizingTransformer#4161

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

harishsk
merged 18 commits into

from

Sep 6, 2019
 Merged


Added onnx export functionality for LpNormNormalizingTransformer
#4161
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


18 commits


Select commit
Hold shift + click to select a range
8749a10

Merge pull request #1 from dotnet/master


harishsk Jun 20, 2019
fe25bf6

Fixed build errors resulting from upgrade to VS2019 compilers


harishsk Jun 21, 2019
cb446be

Added additional message describing the previous fix


harishsk Jun 21, 2019
b5ee220

Merge pull request #2 from dotnet/master


harishsk Jun 21, 2019
b9a7471

Merge pull request #3 from dotnet/master


harishsk Jun 24, 2019
80e238d

Merge pull request #4 from dotnet/master


harishsk Jun 27, 2019
2ef424d

Merge pull request #5 from dotnet/master


harishsk Jul 9, 2019
3958f01

Merge pull request #6 from dotnet/master


harishsk Aug 7, 2019
00bc7ef

Merge pull request #7 from dotnet/master


harishsk Aug 14, 2019
d0462f1

Merge pull request #8 from dotnet/master


harishsk Aug 16, 2019
c0a430a

Merge pull request #9 from dotnet/master


harishsk Aug 21, 2019
0b55903

Syncing upstream fork (#10)


harishsk Aug 30, 2019
798359a

Added export functionality for LpNormNormalizingTransformer


harishsk Aug 30, 2019
56983d5

Syncing upstream fork (#11)


harishsk Aug 30, 2019
fe44d4a

Merge branch 'master' into onnxexport


harishsk Aug 30, 2019
9c31984

Merge pull request #12 from dotnet/master


harishsk Aug 30, 2019
6e75d8a

Merge branch 'onnxexport' of ssh://github.com/harishsk/machinelearnin…


harishsk Aug 30, 2019
1308b4a

Replaced hardcoded Features column name


harishsk Sep 4, 2019

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


131 changes: 130 additions & 1 deletion
src/Microsoft.ML.Transforms/GcnTransform.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -12,6 +12,7 @@
using Microsoft.ML.EntryPoints;
using Microsoft.ML.Internal.CpuMath;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;

Expand DownExpand Up@@ -313,11 +314,13 @@ private protected override void SaveModel(ModelSaveContext ctx)

 private protected override IRowMapper MakeRowMapper(DataViewSchema schema) => new Mapper(this, schema);

 private sealed class Mapper : OneToOneMapperBase
 private sealed class Mapper : OneToOneMapperBase, ISaveAsOnnx
 {
 private readonly DataViewType[] _srcTypes;
 private readonly int[] _srcCols;
 private readonly DataViewType[] _types;
 private readonly LpNormNormalizingEstimatorBase.NormFunction[] _norms;
 private readonly bool[] _ensureZeroMeans;
 private readonly LpNormNormalizingTransformer _parent;

 public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
Expand All@@ -327,12 +330,16 @@ public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
 _types = new DataViewType[_parent.ColumnPairs.Length];
 _srcTypes = new DataViewType[_parent.ColumnPairs.Length];
 _srcCols = new int[_parent.ColumnPairs.Length];
 _norms = new LpNormNormalizingEstimatorBase.NormFunction[_parent.ColumnPairs.Length];
 _ensureZeroMeans = new bool[_parent.ColumnPairs.Length];
 for (int i = 0; i < _parent.ColumnPairs.Length; i++)
 {
 inputSchema.TryGetColumnIndex(_parent.ColumnPairs[i].inputColumnName, out _srcCols[i]);
 var srcCol = inputSchema[_srcCols[i]];
 _srcTypes[i] = srcCol.Type;
 _types[i] = srcCol.Type;
 _norms[i] = _parent._columns[i].Norm;
 _ensureZeroMeans[i] = _parent._columns[i].EnsureZeroMean;
 }
 }

Expand DownExpand Up@@ -594,6 +601,128 @@ private static float Mean(ReadOnlySpan<float> src, int length)
 return 0;
 return CpuMathUtils.Sum(src) / length;
 }

 public bool CanSaveOnnx(OnnxContext ctx) => true;

 public void SaveAsOnnx(OnnxContext ctx)
 {
 Host.CheckValue(ctx, nameof(ctx));

 for (int iinfo = 0; iinfo < _srcCols.Length; ++iinfo)
 {
 string inputColumnName = InputSchema[_srcCols[iinfo]].Name;
 if (!ctx.ContainsColumn(inputColumnName))
 {
 ctx.RemoveColumn(inputColumnName, false);
 continue;
 }

 if (!SaveAsOnnxCore(ctx, iinfo, ctx.GetVariableName(inputColumnName), ctx.AddIntermediateVariable(_srcTypes[iinfo], inputColumnName)))
 {
 ctx.RemoveColumn(inputColumnName, true);
 }
 }
 }

 private bool SaveAsOnnxCore(OnnxContext ctx, int iinfo, string srcVariableName, string dstVariableName)
 {
 string opType;

 if ((_norms[iinfo] != LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation) && (_ensureZeroMeans[iinfo] == false))
 {
 string strNorm;
 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 strNorm = "L1";
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 strNorm = "L2";
 else
 strNorm = "MAX";
 opType = "Normalizer";
 var node = ctx.CreateNode(opType, srcVariableName, dstVariableName, ctx.GetNodeName(opType));
 node.AddAttribute("norm", strNorm);
 return true;
 }

 opType = "ReduceMean";
 string meanOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MeanOfInput", true);
 var meanNode = ctx.CreateNode(opType, srcVariableName, meanOfInput, ctx.GetNodeName(opType), "");
 meanNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sub";
 string inputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "InputMinusMean");
 var subtractNode = ctx.CreateNode(opType, new[] { srcVariableName, meanOfInput }, new[] { inputMinusMean }, ctx.GetNodeName(opType), "");

 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 {
 opType = "Abs";
 string absOfInput = ctx.AddIntermediateVariable(_types[iinfo], "AbsOfInput");
 var absNode = ctx.CreateNode(opType, inputMinusMean, absOfInput, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfAbsOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SumOfAbsOfInput", true);
 var sumOfAbsNode = ctx.CreateNode(opType, absOfInput, sumOfAbsOfInput, ctx.GetNodeName(opType), "");
 sumOfAbsNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var l1Node = ctx.CreateNode(opType, new[] { inputMinusMean, sumOfAbsOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 {
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInput", true);
 var squareNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInput }, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfSquares = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInput, sumOfSquares, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string squareRoot = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var squareRootNode = ctx.CreateNode(opType, sumOfSquares, squareRoot, ctx.GetNodeName(opType), "");

 opType = "Div";
 var l2Node = ctx.CreateNode(opType, new[] { inputMinusMean, squareRoot }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.Infinity)
 {
 opType = "ReduceMax";
 string maxOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MaxOfInput", true);
 var maxNode = ctx.CreateNode(opType, inputMinusMean, maxOfInput, ctx.GetNodeName(opType), "");
 maxNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var lMaxNode = ctx.CreateNode(opType, new[] { inputMinusMean, maxOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation)
 {
 // first calculate the standard deviation
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInputMinusMean", true);
 var squareOfInputMinusMeanNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInputMinusMean }, ctx.GetNodeName(opType), "");

 opType = "ReduceMean";
 string average = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInputMinusMean, average, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string stdDev = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var stdDevNode = ctx.CreateNode(opType, average, stdDev, ctx.GetNodeName(opType), "");

 opType = "Div";
 string input = _ensureZeroMeans[iinfo] ? inputMinusMean : srcVariableName;
 var lStdDevNode = ctx.CreateNode(opType, new[] {input, stdDev }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else
 {
 Contracts.Assert(false);
 return false;
 }
 return true;
 }
 }
 }

Expand Down

62 changes: 62 additions & 0 deletions
test/Microsoft.ML.Tests/OnnxConversionTest.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -180,6 +180,68 @@ public void KmeansOnnxConversionTest()
 Done();
 }

 private class DataPoint
 {
 [VectorType(3)]
 public float[] Features { get; set; }
 }

 [Fact]
 void LpNormOnnxConversionTest()
 {
 var mlContext = new MLContext(seed: 1);

 var samples = new List<DataPoint>()
 {
 new DataPoint() { Features = new float[3] {0.01f, 0.02f, 0.03f} },
 new DataPoint() { Features = new float[3] {0.04f, 0.05f, 0.06f} },
 new DataPoint() { Features = new float[3] {0.07f, 0.08f, 0.09f} },
 new DataPoint() { Features = new float[3] {0.10f, 0.11f, 0.12f} },
 new DataPoint() { Features = new float[3] {0.13f, 0.14f, 0.15f} }
 };
 var dataView = mlContext.Data.LoadFromEnumerable(samples);

 LpNormNormalizingEstimatorBase.NormFunction[] norms =
 {
 LpNormNormalizingEstimatorBase.NormFunction.L1,
 LpNormNormalizingEstimatorBase.NormFunction.L2,
 LpNormNormalizingEstimatorBase.NormFunction.Infinity,
 LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation
 };

 bool[] ensureZeroMeans = { true, false};
 foreach (var ensureZeroMean in ensureZeroMeans)
 {
 foreach (var norm in norms)
 {
 var pipe = mlContext.Transforms.NormalizeLpNorm(nameof(DataPoint.Features), norm:norm, ensureZeroMean: ensureZeroMean);

 var model = pipe.Fit(dataView);
 var transformedData = model.Transform(dataView);
 var onnxModel = mlContext.Model.ConvertToOnnxProtobuf(model, dataView);

 var onnxFileName = $"LpNorm-{norm.ToString()}-{ensureZeroMean}.onnx";
 var onnxModelPath = GetOutputPath(onnxFileName);

 SaveOnnxModel(onnxModel, onnxModelPath, null);

 // Compare results produced by ML.NET and ONNX's runtime.
 if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows) && Environment.Is64BitProcess)
@ganikganikSep 6, 2019

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

RuntimeInformation.IsOSPlatform(OSPlatform.Windows) [](start = 24, length = 51)
Do you need this condition? If its a linux will results match?
@harishskharishskSep 6, 2019

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it is that the test will run only on Windows. The results should still match. It appears that OnnxRuntime doesn't support Linux and Mac yet.
 {
 // Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
 string[] inputNames = onnxModel.Graph.Input.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 string[] outputNames = onnxModel.Graph.Output.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(outputNames, inputNames, onnxModelPath);
 var onnxTransformer = onnxEstimator.Fit(dataView);
 var onnxResult = onnxTransformer.Transform(dataView);
 CompareSelectedR4VectorColumns(nameof(DataPoint.Features), outputNames[0], transformedData, onnxResult, 3);
 }
 }
 }

 Done();
 }

 [Fact]
 void CommandLineOnnxConversionTest()
 {
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Added onnx export functionality for LpNormNormalizingTransformer#4161

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

harishsk
merged 18 commits into

from

Sep 6, 2019
 Merged


Added onnx export functionality for LpNormNormalizingTransformer
#4161
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


18 commits


Select commit
Hold shift + click to select a range
8749a10

Merge pull request #1 from dotnet/master


harishsk Jun 20, 2019
fe25bf6

Fixed build errors resulting from upgrade to VS2019 compilers


harishsk Jun 21, 2019
cb446be

Added additional message describing the previous fix


harishsk Jun 21, 2019
b5ee220

Merge pull request #2 from dotnet/master


harishsk Jun 21, 2019
b9a7471

Merge pull request #3 from dotnet/master


harishsk Jun 24, 2019
80e238d

Merge pull request #4 from dotnet/master


harishsk Jun 27, 2019
2ef424d

Merge pull request #5 from dotnet/master


harishsk Jul 9, 2019
3958f01

Merge pull request #6 from dotnet/master


harishsk Aug 7, 2019
00bc7ef

Merge pull request #7 from dotnet/master


harishsk Aug 14, 2019
d0462f1

Merge pull request #8 from dotnet/master


harishsk Aug 16, 2019
c0a430a

Merge pull request #9 from dotnet/master


harishsk Aug 21, 2019
0b55903

Syncing upstream fork (#10)


harishsk Aug 30, 2019
798359a

Added export functionality for LpNormNormalizingTransformer


harishsk Aug 30, 2019
56983d5

Syncing upstream fork (#11)


harishsk Aug 30, 2019
fe44d4a

Merge branch 'master' into onnxexport


harishsk Aug 30, 2019
9c31984

Merge pull request #12 from dotnet/master


harishsk Aug 30, 2019
6e75d8a

Merge branch 'onnxexport' of ssh://github.com/harishsk/machinelearnin…


harishsk Aug 30, 2019
1308b4a

Replaced hardcoded Features column name


harishsk Sep 4, 2019

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


131 changes: 130 additions & 1 deletion
src/Microsoft.ML.Transforms/GcnTransform.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -12,6 +12,7 @@
using Microsoft.ML.EntryPoints;
using Microsoft.ML.Internal.CpuMath;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;

Expand DownExpand Up@@ -313,11 +314,13 @@ private protected override void SaveModel(ModelSaveContext ctx)

 private protected override IRowMapper MakeRowMapper(DataViewSchema schema) => new Mapper(this, schema);

 private sealed class Mapper : OneToOneMapperBase
 private sealed class Mapper : OneToOneMapperBase, ISaveAsOnnx
 {
 private readonly DataViewType[] _srcTypes;
 private readonly int[] _srcCols;
 private readonly DataViewType[] _types;
 private readonly LpNormNormalizingEstimatorBase.NormFunction[] _norms;
 private readonly bool[] _ensureZeroMeans;
 private readonly LpNormNormalizingTransformer _parent;

 public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
Expand All@@ -327,12 +330,16 @@ public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
 _types = new DataViewType[_parent.ColumnPairs.Length];
 _srcTypes = new DataViewType[_parent.ColumnPairs.Length];
 _srcCols = new int[_parent.ColumnPairs.Length];
 _norms = new LpNormNormalizingEstimatorBase.NormFunction[_parent.ColumnPairs.Length];
 _ensureZeroMeans = new bool[_parent.ColumnPairs.Length];
 for (int i = 0; i < _parent.ColumnPairs.Length; i++)
 {
 inputSchema.TryGetColumnIndex(_parent.ColumnPairs[i].inputColumnName, out _srcCols[i]);
 var srcCol = inputSchema[_srcCols[i]];
 _srcTypes[i] = srcCol.Type;
 _types[i] = srcCol.Type;
 _norms[i] = _parent._columns[i].Norm;
 _ensureZeroMeans[i] = _parent._columns[i].EnsureZeroMean;
 }
 }

Expand DownExpand Up@@ -594,6 +601,128 @@ private static float Mean(ReadOnlySpan<float> src, int length)
 return 0;
 return CpuMathUtils.Sum(src) / length;
 }

 public bool CanSaveOnnx(OnnxContext ctx) => true;

 public void SaveAsOnnx(OnnxContext ctx)
 {
 Host.CheckValue(ctx, nameof(ctx));

 for (int iinfo = 0; iinfo < _srcCols.Length; ++iinfo)
 {
 string inputColumnName = InputSchema[_srcCols[iinfo]].Name;
 if (!ctx.ContainsColumn(inputColumnName))
 {
 ctx.RemoveColumn(inputColumnName, false);
 continue;
 }

 if (!SaveAsOnnxCore(ctx, iinfo, ctx.GetVariableName(inputColumnName), ctx.AddIntermediateVariable(_srcTypes[iinfo], inputColumnName)))
 {
 ctx.RemoveColumn(inputColumnName, true);
 }
 }
 }

 private bool SaveAsOnnxCore(OnnxContext ctx, int iinfo, string srcVariableName, string dstVariableName)
 {
 string opType;

 if ((_norms[iinfo] != LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation) && (_ensureZeroMeans[iinfo] == false))
 {
 string strNorm;
 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 strNorm = "L1";
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 strNorm = "L2";
 else
 strNorm = "MAX";
 opType = "Normalizer";
 var node = ctx.CreateNode(opType, srcVariableName, dstVariableName, ctx.GetNodeName(opType));
 node.AddAttribute("norm", strNorm);
 return true;
 }

 opType = "ReduceMean";
 string meanOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MeanOfInput", true);
 var meanNode = ctx.CreateNode(opType, srcVariableName, meanOfInput, ctx.GetNodeName(opType), "");
 meanNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sub";
 string inputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "InputMinusMean");
 var subtractNode = ctx.CreateNode(opType, new[] { srcVariableName, meanOfInput }, new[] { inputMinusMean }, ctx.GetNodeName(opType), "");

 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 {
 opType = "Abs";
 string absOfInput = ctx.AddIntermediateVariable(_types[iinfo], "AbsOfInput");
 var absNode = ctx.CreateNode(opType, inputMinusMean, absOfInput, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfAbsOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SumOfAbsOfInput", true);
 var sumOfAbsNode = ctx.CreateNode(opType, absOfInput, sumOfAbsOfInput, ctx.GetNodeName(opType), "");
 sumOfAbsNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var l1Node = ctx.CreateNode(opType, new[] { inputMinusMean, sumOfAbsOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 {
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInput", true);
 var squareNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInput }, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfSquares = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInput, sumOfSquares, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string squareRoot = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var squareRootNode = ctx.CreateNode(opType, sumOfSquares, squareRoot, ctx.GetNodeName(opType), "");

 opType = "Div";
 var l2Node = ctx.CreateNode(opType, new[] { inputMinusMean, squareRoot }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.Infinity)
 {
 opType = "ReduceMax";
 string maxOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MaxOfInput", true);
 var maxNode = ctx.CreateNode(opType, inputMinusMean, maxOfInput, ctx.GetNodeName(opType), "");
 maxNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var lMaxNode = ctx.CreateNode(opType, new[] { inputMinusMean, maxOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation)
 {
 // first calculate the standard deviation
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInputMinusMean", true);
 var squareOfInputMinusMeanNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInputMinusMean }, ctx.GetNodeName(opType), "");

 opType = "ReduceMean";
 string average = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInputMinusMean, average, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string stdDev = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var stdDevNode = ctx.CreateNode(opType, average, stdDev, ctx.GetNodeName(opType), "");

 opType = "Div";
 string input = _ensureZeroMeans[iinfo] ? inputMinusMean : srcVariableName;
 var lStdDevNode = ctx.CreateNode(opType, new[] {input, stdDev }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else
 {
 Contracts.Assert(false);
 return false;
 }
 return true;
 }
 }
 }

Expand Down

62 changes: 62 additions & 0 deletions
test/Microsoft.ML.Tests/OnnxConversionTest.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -180,6 +180,68 @@ public void KmeansOnnxConversionTest()
 Done();
 }

 private class DataPoint
 {
 [VectorType(3)]
 public float[] Features { get; set; }
 }

 [Fact]
 void LpNormOnnxConversionTest()
 {
 var mlContext = new MLContext(seed: 1);

 var samples = new List<DataPoint>()
 {
 new DataPoint() { Features = new float[3] {0.01f, 0.02f, 0.03f} },
 new DataPoint() { Features = new float[3] {0.04f, 0.05f, 0.06f} },
 new DataPoint() { Features = new float[3] {0.07f, 0.08f, 0.09f} },
 new DataPoint() { Features = new float[3] {0.10f, 0.11f, 0.12f} },
 new DataPoint() { Features = new float[3] {0.13f, 0.14f, 0.15f} }
 };
 var dataView = mlContext.Data.LoadFromEnumerable(samples);

 LpNormNormalizingEstimatorBase.NormFunction[] norms =
 {
 LpNormNormalizingEstimatorBase.NormFunction.L1,
 LpNormNormalizingEstimatorBase.NormFunction.L2,
 LpNormNormalizingEstimatorBase.NormFunction.Infinity,
 LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation
 };

 bool[] ensureZeroMeans = { true, false};
 foreach (var ensureZeroMean in ensureZeroMeans)
 {
 foreach (var norm in norms)
 {
 var pipe = mlContext.Transforms.NormalizeLpNorm(nameof(DataPoint.Features), norm:norm, ensureZeroMean: ensureZeroMean);

 var model = pipe.Fit(dataView);
 var transformedData = model.Transform(dataView);
 var onnxModel = mlContext.Model.ConvertToOnnxProtobuf(model, dataView);

 var onnxFileName = $"LpNorm-{norm.ToString()}-{ensureZeroMean}.onnx";
 var onnxModelPath = GetOutputPath(onnxFileName);

 SaveOnnxModel(onnxModel, onnxModelPath, null);

 // Compare results produced by ML.NET and ONNX's runtime.
 if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows) && Environment.Is64BitProcess)
@ganikganikSep 6, 2019

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

RuntimeInformation.IsOSPlatform(OSPlatform.Windows) [](start = 24, length = 51)
Do you need this condition? If its a linux will results match?
@harishskharishskSep 6, 2019

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it is that the test will run only on Windows. The results should still match. It appears that OnnxRuntime doesn't support Linux and Mac yet.
 {
 // Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
 string[] inputNames = onnxModel.Graph.Input.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 string[] outputNames = onnxModel.Graph.Output.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(outputNames, inputNames, onnxModelPath);
 var onnxTransformer = onnxEstimator.Fit(dataView);
 var onnxResult = onnxTransformer.Transform(dataView);
 CompareSelectedR4VectorColumns(nameof(DataPoint.Features), outputNames[0], transformedData, onnxResult, 3);
 }
 }
 }

 Done();
 }

 [Fact]
 void CommandLineOnnxConversionTest()
 {
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Added onnx export functionality for LpNormNormalizingTransformer#4161

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

harishsk
merged 18 commits into

from

Sep 6, 2019
 Merged


Added onnx export functionality for LpNormNormalizingTransformer
#4161
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


18 commits


Select commit
Hold shift + click to select a range
8749a10

Merge pull request #1 from dotnet/master


harishsk Jun 20, 2019
fe25bf6

Fixed build errors resulting from upgrade to VS2019 compilers


harishsk Jun 21, 2019
cb446be

Added additional message describing the previous fix


harishsk Jun 21, 2019
b5ee220

Merge pull request #2 from dotnet/master


harishsk Jun 21, 2019
b9a7471

Merge pull request #3 from dotnet/master


harishsk Jun 24, 2019
80e238d

Merge pull request #4 from dotnet/master


harishsk Jun 27, 2019
2ef424d

Merge pull request #5 from dotnet/master


harishsk Jul 9, 2019
3958f01

Merge pull request #6 from dotnet/master


harishsk Aug 7, 2019
00bc7ef

Merge pull request #7 from dotnet/master


harishsk Aug 14, 2019
d0462f1

Merge pull request #8 from dotnet/master


harishsk Aug 16, 2019
c0a430a

Merge pull request #9 from dotnet/master


harishsk Aug 21, 2019
0b55903

Syncing upstream fork (#10)


harishsk Aug 30, 2019
798359a

Added export functionality for LpNormNormalizingTransformer


harishsk Aug 30, 2019
56983d5

Syncing upstream fork (#11)


harishsk Aug 30, 2019
fe44d4a

Merge branch 'master' into onnxexport


harishsk Aug 30, 2019
9c31984

Merge pull request #12 from dotnet/master


harishsk Aug 30, 2019
6e75d8a

Merge branch 'onnxexport' of ssh://github.com/harishsk/machinelearnin…


harishsk Aug 30, 2019
1308b4a

Replaced hardcoded Features column name


harishsk Sep 4, 2019

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


131 changes: 130 additions & 1 deletion
src/Microsoft.ML.Transforms/GcnTransform.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -12,6 +12,7 @@
using Microsoft.ML.EntryPoints;
using Microsoft.ML.Internal.CpuMath;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;

Expand DownExpand Up@@ -313,11 +314,13 @@ private protected override void SaveModel(ModelSaveContext ctx)

 private protected override IRowMapper MakeRowMapper(DataViewSchema schema) => new Mapper(this, schema);

 private sealed class Mapper : OneToOneMapperBase
 private sealed class Mapper : OneToOneMapperBase, ISaveAsOnnx
 {
 private readonly DataViewType[] _srcTypes;
 private readonly int[] _srcCols;
 private readonly DataViewType[] _types;
 private readonly LpNormNormalizingEstimatorBase.NormFunction[] _norms;
 private readonly bool[] _ensureZeroMeans;
 private readonly LpNormNormalizingTransformer _parent;

 public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
Expand All@@ -327,12 +330,16 @@ public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
 _types = new DataViewType[_parent.ColumnPairs.Length];
 _srcTypes = new DataViewType[_parent.ColumnPairs.Length];
 _srcCols = new int[_parent.ColumnPairs.Length];
 _norms = new LpNormNormalizingEstimatorBase.NormFunction[_parent.ColumnPairs.Length];
 _ensureZeroMeans = new bool[_parent.ColumnPairs.Length];
 for (int i = 0; i < _parent.ColumnPairs.Length; i++)
 {
 inputSchema.TryGetColumnIndex(_parent.ColumnPairs[i].inputColumnName, out _srcCols[i]);
 var srcCol = inputSchema[_srcCols[i]];
 _srcTypes[i] = srcCol.Type;
 _types[i] = srcCol.Type;
 _norms[i] = _parent._columns[i].Norm;
 _ensureZeroMeans[i] = _parent._columns[i].EnsureZeroMean;
 }
 }

Expand DownExpand Up@@ -594,6 +601,128 @@ private static float Mean(ReadOnlySpan<float> src, int length)
 return 0;
 return CpuMathUtils.Sum(src) / length;
 }

 public bool CanSaveOnnx(OnnxContext ctx) => true;

 public void SaveAsOnnx(OnnxContext ctx)
 {
 Host.CheckValue(ctx, nameof(ctx));

 for (int iinfo = 0; iinfo < _srcCols.Length; ++iinfo)
 {
 string inputColumnName = InputSchema[_srcCols[iinfo]].Name;
 if (!ctx.ContainsColumn(inputColumnName))
 {
 ctx.RemoveColumn(inputColumnName, false);
 continue;
 }

 if (!SaveAsOnnxCore(ctx, iinfo, ctx.GetVariableName(inputColumnName), ctx.AddIntermediateVariable(_srcTypes[iinfo], inputColumnName)))
 {
 ctx.RemoveColumn(inputColumnName, true);
 }
 }
 }

 private bool SaveAsOnnxCore(OnnxContext ctx, int iinfo, string srcVariableName, string dstVariableName)
 {
 string opType;

 if ((_norms[iinfo] != LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation) && (_ensureZeroMeans[iinfo] == false))
 {
 string strNorm;
 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 strNorm = "L1";
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 strNorm = "L2";
 else
 strNorm = "MAX";
 opType = "Normalizer";
 var node = ctx.CreateNode(opType, srcVariableName, dstVariableName, ctx.GetNodeName(opType));
 node.AddAttribute("norm", strNorm);
 return true;
 }

 opType = "ReduceMean";
 string meanOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MeanOfInput", true);
 var meanNode = ctx.CreateNode(opType, srcVariableName, meanOfInput, ctx.GetNodeName(opType), "");
 meanNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sub";
 string inputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "InputMinusMean");
 var subtractNode = ctx.CreateNode(opType, new[] { srcVariableName, meanOfInput }, new[] { inputMinusMean }, ctx.GetNodeName(opType), "");

 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 {
 opType = "Abs";
 string absOfInput = ctx.AddIntermediateVariable(_types[iinfo], "AbsOfInput");
 var absNode = ctx.CreateNode(opType, inputMinusMean, absOfInput, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfAbsOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SumOfAbsOfInput", true);
 var sumOfAbsNode = ctx.CreateNode(opType, absOfInput, sumOfAbsOfInput, ctx.GetNodeName(opType), "");
 sumOfAbsNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var l1Node = ctx.CreateNode(opType, new[] { inputMinusMean, sumOfAbsOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 {
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInput", true);
 var squareNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInput }, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfSquares = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInput, sumOfSquares, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string squareRoot = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var squareRootNode = ctx.CreateNode(opType, sumOfSquares, squareRoot, ctx.GetNodeName(opType), "");

 opType = "Div";
 var l2Node = ctx.CreateNode(opType, new[] { inputMinusMean, squareRoot }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.Infinity)
 {
 opType = "ReduceMax";
 string maxOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MaxOfInput", true);
 var maxNode = ctx.CreateNode(opType, inputMinusMean, maxOfInput, ctx.GetNodeName(opType), "");
 maxNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var lMaxNode = ctx.CreateNode(opType, new[] { inputMinusMean, maxOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation)
 {
 // first calculate the standard deviation
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInputMinusMean", true);
 var squareOfInputMinusMeanNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInputMinusMean }, ctx.GetNodeName(opType), "");

 opType = "ReduceMean";
 string average = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInputMinusMean, average, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string stdDev = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var stdDevNode = ctx.CreateNode(opType, average, stdDev, ctx.GetNodeName(opType), "");

 opType = "Div";
 string input = _ensureZeroMeans[iinfo] ? inputMinusMean : srcVariableName;
 var lStdDevNode = ctx.CreateNode(opType, new[] {input, stdDev }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else
 {
 Contracts.Assert(false);
 return false;
 }
 return true;
 }
 }
 }

Expand Down

62 changes: 62 additions & 0 deletions
test/Microsoft.ML.Tests/OnnxConversionTest.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -180,6 +180,68 @@ public void KmeansOnnxConversionTest()
 Done();
 }

 private class DataPoint
 {
 [VectorType(3)]
 public float[] Features { get; set; }
 }

 [Fact]
 void LpNormOnnxConversionTest()
 {
 var mlContext = new MLContext(seed: 1);

 var samples = new List<DataPoint>()
 {
 new DataPoint() { Features = new float[3] {0.01f, 0.02f, 0.03f} },
 new DataPoint() { Features = new float[3] {0.04f, 0.05f, 0.06f} },
 new DataPoint() { Features = new float[3] {0.07f, 0.08f, 0.09f} },
 new DataPoint() { Features = new float[3] {0.10f, 0.11f, 0.12f} },
 new DataPoint() { Features = new float[3] {0.13f, 0.14f, 0.15f} }
 };
 var dataView = mlContext.Data.LoadFromEnumerable(samples);

 LpNormNormalizingEstimatorBase.NormFunction[] norms =
 {
 LpNormNormalizingEstimatorBase.NormFunction.L1,
 LpNormNormalizingEstimatorBase.NormFunction.L2,
 LpNormNormalizingEstimatorBase.NormFunction.Infinity,
 LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation
 };

 bool[] ensureZeroMeans = { true, false};
 foreach (var ensureZeroMean in ensureZeroMeans)
 {
 foreach (var norm in norms)
 {
 var pipe = mlContext.Transforms.NormalizeLpNorm(nameof(DataPoint.Features), norm:norm, ensureZeroMean: ensureZeroMean);

 var model = pipe.Fit(dataView);
 var transformedData = model.Transform(dataView);
 var onnxModel = mlContext.Model.ConvertToOnnxProtobuf(model, dataView);

 var onnxFileName = $"LpNorm-{norm.ToString()}-{ensureZeroMean}.onnx";
 var onnxModelPath = GetOutputPath(onnxFileName);

 SaveOnnxModel(onnxModel, onnxModelPath, null);

 // Compare results produced by ML.NET and ONNX's runtime.
 if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows) && Environment.Is64BitProcess)
@ganikganikSep 6, 2019

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

RuntimeInformation.IsOSPlatform(OSPlatform.Windows) [](start = 24, length = 51)
Do you need this condition? If its a linux will results match?
@harishskharishskSep 6, 2019

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it is that the test will run only on Windows. The results should still match. It appears that OnnxRuntime doesn't support Linux and Mac yet.
 {
 // Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
 string[] inputNames = onnxModel.Graph.Input.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 string[] outputNames = onnxModel.Graph.Output.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(outputNames, inputNames, onnxModelPath);
 var onnxTransformer = onnxEstimator.Fit(dataView);
 var onnxResult = onnxTransformer.Transform(dataView);
 CompareSelectedR4VectorColumns(nameof(DataPoint.Features), outputNames[0], transformedData, onnxResult, 3);
 }
 }
 }

 Done();
 }

 [Fact]
 void CommandLineOnnxConversionTest()
 {
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Added onnx export functionality for LpNormNormalizingTransformer#4161

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

harishsk
merged 18 commits into

from

Sep 6, 2019
 Merged


Added onnx export functionality for LpNormNormalizingTransformer
#4161
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


18 commits


Select commit
Hold shift + click to select a range
8749a10

Merge pull request #1 from dotnet/master


harishsk Jun 20, 2019
fe25bf6

Fixed build errors resulting from upgrade to VS2019 compilers


harishsk Jun 21, 2019
cb446be

Added additional message describing the previous fix


harishsk Jun 21, 2019
b5ee220

Merge pull request #2 from dotnet/master


harishsk Jun 21, 2019
b9a7471

Merge pull request #3 from dotnet/master


harishsk Jun 24, 2019
80e238d

Merge pull request #4 from dotnet/master


harishsk Jun 27, 2019
2ef424d

Merge pull request #5 from dotnet/master


harishsk Jul 9, 2019
3958f01

Merge pull request #6 from dotnet/master


harishsk Aug 7, 2019
00bc7ef

Merge pull request #7 from dotnet/master


harishsk Aug 14, 2019
d0462f1

Merge pull request #8 from dotnet/master


harishsk Aug 16, 2019
c0a430a

Merge pull request #9 from dotnet/master


harishsk Aug 21, 2019
0b55903

Syncing upstream fork (#10)


harishsk Aug 30, 2019
798359a

Added export functionality for LpNormNormalizingTransformer


harishsk Aug 30, 2019
56983d5

Syncing upstream fork (#11)


harishsk Aug 30, 2019
fe44d4a

Merge branch 'master' into onnxexport


harishsk Aug 30, 2019
9c31984

Merge pull request #12 from dotnet/master


harishsk Aug 30, 2019
6e75d8a

Merge branch 'onnxexport' of ssh://github.com/harishsk/machinelearnin…


harishsk Aug 30, 2019
1308b4a

Replaced hardcoded Features column name


harishsk Sep 4, 2019

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


131 changes: 130 additions & 1 deletion
src/Microsoft.ML.Transforms/GcnTransform.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -12,6 +12,7 @@
using Microsoft.ML.EntryPoints;
using Microsoft.ML.Internal.CpuMath;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;

Expand DownExpand Up@@ -313,11 +314,13 @@ private protected override void SaveModel(ModelSaveContext ctx)

 private protected override IRowMapper MakeRowMapper(DataViewSchema schema) => new Mapper(this, schema);

 private sealed class Mapper : OneToOneMapperBase
 private sealed class Mapper : OneToOneMapperBase, ISaveAsOnnx
 {
 private readonly DataViewType[] _srcTypes;
 private readonly int[] _srcCols;
 private readonly DataViewType[] _types;
 private readonly LpNormNormalizingEstimatorBase.NormFunction[] _norms;
 private readonly bool[] _ensureZeroMeans;
 private readonly LpNormNormalizingTransformer _parent;

 public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
Expand All@@ -327,12 +330,16 @@ public Mapper(LpNormNormalizingTransformer parent, DataViewSchema inputSchema)
 _types = new DataViewType[_parent.ColumnPairs.Length];
 _srcTypes = new DataViewType[_parent.ColumnPairs.Length];
 _srcCols = new int[_parent.ColumnPairs.Length];
 _norms = new LpNormNormalizingEstimatorBase.NormFunction[_parent.ColumnPairs.Length];
 _ensureZeroMeans = new bool[_parent.ColumnPairs.Length];
 for (int i = 0; i < _parent.ColumnPairs.Length; i++)
 {
 inputSchema.TryGetColumnIndex(_parent.ColumnPairs[i].inputColumnName, out _srcCols[i]);
 var srcCol = inputSchema[_srcCols[i]];
 _srcTypes[i] = srcCol.Type;
 _types[i] = srcCol.Type;
 _norms[i] = _parent._columns[i].Norm;
 _ensureZeroMeans[i] = _parent._columns[i].EnsureZeroMean;
 }
 }

Expand DownExpand Up@@ -594,6 +601,128 @@ private static float Mean(ReadOnlySpan<float> src, int length)
 return 0;
 return CpuMathUtils.Sum(src) / length;
 }

 public bool CanSaveOnnx(OnnxContext ctx) => true;

 public void SaveAsOnnx(OnnxContext ctx)
 {
 Host.CheckValue(ctx, nameof(ctx));

 for (int iinfo = 0; iinfo < _srcCols.Length; ++iinfo)
 {
 string inputColumnName = InputSchema[_srcCols[iinfo]].Name;
 if (!ctx.ContainsColumn(inputColumnName))
 {
 ctx.RemoveColumn(inputColumnName, false);
 continue;
 }

 if (!SaveAsOnnxCore(ctx, iinfo, ctx.GetVariableName(inputColumnName), ctx.AddIntermediateVariable(_srcTypes[iinfo], inputColumnName)))
 {
 ctx.RemoveColumn(inputColumnName, true);
 }
 }
 }

 private bool SaveAsOnnxCore(OnnxContext ctx, int iinfo, string srcVariableName, string dstVariableName)
 {
 string opType;

 if ((_norms[iinfo] != LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation) && (_ensureZeroMeans[iinfo] == false))
 {
 string strNorm;
 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 strNorm = "L1";
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 strNorm = "L2";
 else
 strNorm = "MAX";
 opType = "Normalizer";
 var node = ctx.CreateNode(opType, srcVariableName, dstVariableName, ctx.GetNodeName(opType));
 node.AddAttribute("norm", strNorm);
 return true;
 }

 opType = "ReduceMean";
 string meanOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MeanOfInput", true);
 var meanNode = ctx.CreateNode(opType, srcVariableName, meanOfInput, ctx.GetNodeName(opType), "");
 meanNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sub";
 string inputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "InputMinusMean");
 var subtractNode = ctx.CreateNode(opType, new[] { srcVariableName, meanOfInput }, new[] { inputMinusMean }, ctx.GetNodeName(opType), "");

 if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L1)
 {
 opType = "Abs";
 string absOfInput = ctx.AddIntermediateVariable(_types[iinfo], "AbsOfInput");
 var absNode = ctx.CreateNode(opType, inputMinusMean, absOfInput, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfAbsOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SumOfAbsOfInput", true);
 var sumOfAbsNode = ctx.CreateNode(opType, absOfInput, sumOfAbsOfInput, ctx.GetNodeName(opType), "");
 sumOfAbsNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var l1Node = ctx.CreateNode(opType, new[] { inputMinusMean, sumOfAbsOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.L2)
 {
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInput = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInput", true);
 var squareNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInput }, ctx.GetNodeName(opType), "");

 opType = "ReduceSum";
 string sumOfSquares = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInput, sumOfSquares, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string squareRoot = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var squareRootNode = ctx.CreateNode(opType, sumOfSquares, squareRoot, ctx.GetNodeName(opType), "");

 opType = "Div";
 var l2Node = ctx.CreateNode(opType, new[] { inputMinusMean, squareRoot }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.Infinity)
 {
 opType = "ReduceMax";
 string maxOfInput = ctx.AddIntermediateVariable(_types[iinfo], "MaxOfInput", true);
 var maxNode = ctx.CreateNode(opType, inputMinusMean, maxOfInput, ctx.GetNodeName(opType), "");
 maxNode.AddAttribute("axes", new long[] { 1 });

 opType = "Div";
 var lMaxNode = ctx.CreateNode(opType, new[] { inputMinusMean, maxOfInput }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else if (_norms[iinfo] == LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation)
 {
 // first calculate the standard deviation
 opType = "Pow";
 string two = ctx.AddInitializer(2.0f);
 string squareOfInputMinusMean = ctx.AddIntermediateVariable(_types[iinfo], "SquareOfInputMinusMean", true);
 var squareOfInputMinusMeanNode = ctx.CreateNode(opType, new[] { inputMinusMean, two }, new[] { squareOfInputMinusMean }, ctx.GetNodeName(opType), "");

 opType = "ReduceMean";
 string average = ctx.AddIntermediateVariable(_types[iinfo], "SumOfSquares", true);
 var sumOfSquaresNode = ctx.CreateNode(opType, squareOfInputMinusMean, average, ctx.GetNodeName(opType), "");
 sumOfSquaresNode.AddAttribute("axes", new long[] { 1 });

 opType = "Sqrt";
 string stdDev = ctx.AddIntermediateVariable(_types[iinfo], "SquareRoot", true);
 var stdDevNode = ctx.CreateNode(opType, average, stdDev, ctx.GetNodeName(opType), "");

 opType = "Div";
 string input = _ensureZeroMeans[iinfo] ? inputMinusMean : srcVariableName;
 var lStdDevNode = ctx.CreateNode(opType, new[] {input, stdDev }, new[] { dstVariableName }, ctx.GetNodeName(opType), "");
 }
 else
 {
 Contracts.Assert(false);
 return false;
 }
 return true;
 }
 }
 }

Expand Down

62 changes: 62 additions & 0 deletions
test/Microsoft.ML.Tests/OnnxConversionTest.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -180,6 +180,68 @@ public void KmeansOnnxConversionTest()
 Done();
 }

 private class DataPoint
 {
 [VectorType(3)]
 public float[] Features { get; set; }
 }

 [Fact]
 void LpNormOnnxConversionTest()
 {
 var mlContext = new MLContext(seed: 1);

 var samples = new List<DataPoint>()
 {
 new DataPoint() { Features = new float[3] {0.01f, 0.02f, 0.03f} },
 new DataPoint() { Features = new float[3] {0.04f, 0.05f, 0.06f} },
 new DataPoint() { Features = new float[3] {0.07f, 0.08f, 0.09f} },
 new DataPoint() { Features = new float[3] {0.10f, 0.11f, 0.12f} },
 new DataPoint() { Features = new float[3] {0.13f, 0.14f, 0.15f} }
 };
 var dataView = mlContext.Data.LoadFromEnumerable(samples);

 LpNormNormalizingEstimatorBase.NormFunction[] norms =
 {
 LpNormNormalizingEstimatorBase.NormFunction.L1,
 LpNormNormalizingEstimatorBase.NormFunction.L2,
 LpNormNormalizingEstimatorBase.NormFunction.Infinity,
 LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation
 };

 bool[] ensureZeroMeans = { true, false};
 foreach (var ensureZeroMean in ensureZeroMeans)
 {
 foreach (var norm in norms)
 {
 var pipe = mlContext.Transforms.NormalizeLpNorm(nameof(DataPoint.Features), norm:norm, ensureZeroMean: ensureZeroMean);

 var model = pipe.Fit(dataView);
 var transformedData = model.Transform(dataView);
 var onnxModel = mlContext.Model.ConvertToOnnxProtobuf(model, dataView);

 var onnxFileName = $"LpNorm-{norm.ToString()}-{ensureZeroMean}.onnx";
 var onnxModelPath = GetOutputPath(onnxFileName);

 SaveOnnxModel(onnxModel, onnxModelPath, null);

 // Compare results produced by ML.NET and ONNX's runtime.
 if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows) && Environment.Is64BitProcess)
@ganikganikSep 6, 2019

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

RuntimeInformation.IsOSPlatform(OSPlatform.Windows) [](start = 24, length = 51)
Do you need this condition? If its a linux will results match?
@harishskharishskSep 6, 2019

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it is that the test will run only on Windows. The results should still match. It appears that OnnxRuntime doesn't support Linux and Mac yet.
 {
 // Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
 string[] inputNames = onnxModel.Graph.Input.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 string[] outputNames = onnxModel.Graph.Output.Select(valueInfoProto => valueInfoProto.Name).ToArray();
 var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(outputNames, inputNames, onnxModelPath);
 var onnxTransformer = onnxEstimator.Fit(dataView);
 var onnxResult = onnxTransformer.Transform(dataView);
 CompareSelectedR4VectorColumns(nameof(DataPoint.Features), outputNames[0], transformedData, onnxResult, 3);
 }
 }
 }

 Done();
 }

 [Fact]
 void CommandLineOnnxConversionTest()
 {
Expand Down