Added onnx export support for KeyToValueMappingTransformer#4455

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 1 commit into from
Nov 14, 2019
Merged

Added onnx export support for KeyToValueMappingTransformer #4455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
62 changes: 61 additions & 1 deletion src/Microsoft.ML.Data/Transforms/KeyToValue.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,7 @@
using Microsoft.ML.CommandLine;
using Microsoft.ML.Data;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Model.Pfa;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;
Expand DownExpand Up@@ -152,7 +153,7 @@ private protected override void SaveModel(ModelSaveContext ctx)

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

private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa
private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa, ISaveAsOnnx
{
private readonly KeyToValueMappingTransformer _parent;
private readonly DataViewType[] _types;
Expand DownExpand Up@@ -298,6 +299,8 @@ protected KeyToValueMap(Mapper mapper, PrimitiveDataViewType typeVal, int iinfo)
public abstract Delegate GetMappingGetter(DataViewRow input);

public abstract JToken SavePfa(BoundPfaContext ctx, JToken srcToken);

public abstract bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName);
}

private class KeyToValueMap<TKey, TValue> : KeyToValueMap
Expand DownExpand Up@@ -494,8 +497,65 @@ public override JToken SavePfa(BoundPfaContext ctx, JToken srcToken)
}
return PfaUtils.If(PfaUtils.Call("<", srcToken, 0), defaultToken, PfaUtils.Index(cellRef, srcToken));
}

public override bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName)
{
string opType;

// Onnx expects the input keys to be int64s. But the input data can come from an ML.NET node that
// may output a uint32. So cast it here to ensure that the data is treated correctly
opType = "Cast";
var castNodeOutput = ctx.AddIntermediateVariable(TypeOutput, "CastNodeOutput", true);
var castNode = ctx.CreateNode(opType, srcVariableName, castNodeOutput, ctx.GetNodeName(opType), "");
var t = InternalDataKindExtensions.ToInternalDataKind(DataKind.Int64).ToType();
castNode.AddAttribute("to", t);

opType = "LabelEncoder";
var node = ctx.CreateNode(opType, castNodeOutput, dstVariableName, ctx.GetNodeName(opType));
var keys = Array.ConvertAll<int, long>(Enumerable.Range(1, _values.Length).ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("keys_int64s", keys);

if (TypeOutput == NumberDataViewType.Int64)
{
long[] values = Array.ConvertAll<TValue, long>(_values.GetValues().ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("values_int64s", values);
}
else if (TypeOutput == NumberDataViewType.Single)
{
float[] values = Array.ConvertAll<TValue, float>(_values.GetValues().ToArray(), item => Convert.ToSingle(item));
node.AddAttribute("values_floats", values);
}
else if (TypeOutput == TextDataViewType.Instance)
{
string[] values = Array.ConvertAll<TValue, string>(_values.GetValues().ToArray(), item => Convert.ToString(item));
node.AddAttribute("values_strings", values);
}
else
return false;

return true;
}
}

public bool CanSaveOnnx(OnnxContext ctx) => true;

public void SaveAsOnnx(OnnxContext ctx)
{
for (int iinfo = 0; iinfo < _parent.ColumnPairs.Length; ++iinfo)
{
var info = _parent.ColumnPairs[iinfo];
var inputColumnName = info.inputColumnName;

if (!ctx.ContainsColumn(inputColumnName))
continue;

var dstVariableName = ctx.AddIntermediateVariable(_types[iinfo], info.outputColumnName, true);
if (!_kvMaps[iinfo].SaveOnnx(ctx, inputColumnName, dstVariableName))
{
ctx.RemoveColumn(inputColumnName, true);
}
}
}
}
}

Expand Down
64 changes: 64 additions & 0 deletions test/Microsoft.ML.Tests/OnnxConversionTest.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1040,6 +1040,42 @@ public void OptionalColumnOnnxTest()
Done();
}

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

string dataPath = GetDataPath("breast-cancer.txt");
var dataView = mlContext.Data.LoadFromTextFile<BreastCancerMulticlassExample>(dataPath,
separatorChar: '\t',
hasHeader: true);

var pipeline = mlContext.Transforms.Conversion.MapValueToKey("LabelKey", "Label").
Append(mlContext.Transforms.Conversion.MapKeyToValue("LabelValue", "LabelKey"));

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

var onnxFileName = "KeyToValue.onnx";
var onnxModelPath = GetOutputPath(onnxFileName);

SaveOnnxModel(onnxModel, onnxModelPath, null);

if (IsOnnxRuntimeSupported())
{
// 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);
CompareSelectedScalarColumns<ReadOnlyMemory<Char>>(transformedData.Schema[3].Name, outputNames[3], transformedData, onnxResult);
}

Done();
}

private void CreateDummyExamplesToMakeComplierHappy()
{
var dummyExample = new BreastCancerFeatureVector() { Features = null };
Expand DownExpand Up@@ -1105,6 +1141,34 @@ private void CompareSelectedVectorColumns<T>(string leftColumnName, string right
}
}

private void CompareSelectedScalarColumns<T>(string leftColumnName, string rightColumnName, IDataView left, IDataView right)
{
var leftColumn = left.Schema[leftColumnName];
var rightColumn = right.Schema[rightColumnName];

using (var expectedCursor = left.GetRowCursor(leftColumn))
using (var actualCursor = right.GetRowCursor(rightColumn))
{
T expected = default;
VBuffer<T> actual = default;
var expectedGetter = expectedCursor.GetGetter<T>(leftColumn);
var actualGetter = actualCursor.GetGetter<VBuffer<T>>(rightColumn);
while (expectedCursor.MoveNext() && actualCursor.MoveNext())
{
expectedGetter(ref expected);
actualGetter(ref actual);
var actualVal = actual.GetItemOrDefault(0);

Assert.Equal(1, actual.Length);

if (typeof(T) == typeof(ReadOnlyMemory<Char>))
Assert.Equal(expected.ToString(), actualVal.ToString());
else
Assert.Equal(expected, actualVal);
}
}
}

private void CompareSelectedR8VectorColumns(string leftColumnName, string rightColumnName, IDataView left, IDataView right, int precision = 6)
{
var leftColumn = left.Schema[leftColumnName];
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all \u003cpre\u003e\u003ccode\u003e 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 support for KeyToValueMappingTransformer#4455

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 1 commit into from
Nov 14, 2019
Merged

Added onnx export support for KeyToValueMappingTransformer #4455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
62 changes: 61 additions & 1 deletion src/Microsoft.ML.Data/Transforms/KeyToValue.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,7 @@
using Microsoft.ML.CommandLine;
using Microsoft.ML.Data;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Model.Pfa;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;
Expand DownExpand Up@@ -152,7 +153,7 @@ private protected override void SaveModel(ModelSaveContext ctx)

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

private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa
private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa, ISaveAsOnnx
{
private readonly KeyToValueMappingTransformer _parent;
private readonly DataViewType[] _types;
Expand DownExpand Up@@ -298,6 +299,8 @@ protected KeyToValueMap(Mapper mapper, PrimitiveDataViewType typeVal, int iinfo)
public abstract Delegate GetMappingGetter(DataViewRow input);

public abstract JToken SavePfa(BoundPfaContext ctx, JToken srcToken);

public abstract bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName);
}

private class KeyToValueMap<TKey, TValue> : KeyToValueMap
Expand DownExpand Up@@ -494,8 +497,65 @@ public override JToken SavePfa(BoundPfaContext ctx, JToken srcToken)
}
return PfaUtils.If(PfaUtils.Call("<", srcToken, 0), defaultToken, PfaUtils.Index(cellRef, srcToken));
}

public override bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName)
{
string opType;

// Onnx expects the input keys to be int64s. But the input data can come from an ML.NET node that
// may output a uint32. So cast it here to ensure that the data is treated correctly
opType = "Cast";
var castNodeOutput = ctx.AddIntermediateVariable(TypeOutput, "CastNodeOutput", true);
var castNode = ctx.CreateNode(opType, srcVariableName, castNodeOutput, ctx.GetNodeName(opType), "");
var t = InternalDataKindExtensions.ToInternalDataKind(DataKind.Int64).ToType();
castNode.AddAttribute("to", t);

opType = "LabelEncoder";
var node = ctx.CreateNode(opType, castNodeOutput, dstVariableName, ctx.GetNodeName(opType));
var keys = Array.ConvertAll<int, long>(Enumerable.Range(1, _values.Length).ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("keys_int64s", keys);

if (TypeOutput == NumberDataViewType.Int64)
{
long[] values = Array.ConvertAll<TValue, long>(_values.GetValues().ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("values_int64s", values);
}
else if (TypeOutput == NumberDataViewType.Single)
{
float[] values = Array.ConvertAll<TValue, float>(_values.GetValues().ToArray(), item => Convert.ToSingle(item));
node.AddAttribute("values_floats", values);
}
else if (TypeOutput == TextDataViewType.Instance)
{
string[] values = Array.ConvertAll<TValue, string>(_values.GetValues().ToArray(), item => Convert.ToString(item));
node.AddAttribute("values_strings", values);
}
else
return false;

return true;
}
}

public bool CanSaveOnnx(OnnxContext ctx) => true;

public void SaveAsOnnx(OnnxContext ctx)
{
for (int iinfo = 0; iinfo < _parent.ColumnPairs.Length; ++iinfo)
{
var info = _parent.ColumnPairs[iinfo];
var inputColumnName = info.inputColumnName;

if (!ctx.ContainsColumn(inputColumnName))
continue;

var dstVariableName = ctx.AddIntermediateVariable(_types[iinfo], info.outputColumnName, true);
if (!_kvMaps[iinfo].SaveOnnx(ctx, inputColumnName, dstVariableName))
{
ctx.RemoveColumn(inputColumnName, true);
}
}
}
}
}

Expand Down
64 changes: 64 additions & 0 deletions test/Microsoft.ML.Tests/OnnxConversionTest.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1040,6 +1040,42 @@ public void OptionalColumnOnnxTest()
Done();
}

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

string dataPath = GetDataPath("breast-cancer.txt");
var dataView = mlContext.Data.LoadFromTextFile<BreastCancerMulticlassExample>(dataPath,
separatorChar: '\t',
hasHeader: true);

var pipeline = mlContext.Transforms.Conversion.MapValueToKey("LabelKey", "Label").
Append(mlContext.Transforms.Conversion.MapKeyToValue("LabelValue", "LabelKey"));

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

var onnxFileName = "KeyToValue.onnx";
var onnxModelPath = GetOutputPath(onnxFileName);

SaveOnnxModel(onnxModel, onnxModelPath, null);

if (IsOnnxRuntimeSupported())
{
// 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);
CompareSelectedScalarColumns<ReadOnlyMemory<Char>>(transformedData.Schema[3].Name, outputNames[3], transformedData, onnxResult);
}

Done();
}

private void CreateDummyExamplesToMakeComplierHappy()
{
var dummyExample = new BreastCancerFeatureVector() { Features = null };
Expand DownExpand Up@@ -1105,6 +1141,34 @@ private void CompareSelectedVectorColumns<T>(string leftColumnName, string right
}
}

private void CompareSelectedScalarColumns<T>(string leftColumnName, string rightColumnName, IDataView left, IDataView right)
{
var leftColumn = left.Schema[leftColumnName];
var rightColumn = right.Schema[rightColumnName];

using (var expectedCursor = left.GetRowCursor(leftColumn))
using (var actualCursor = right.GetRowCursor(rightColumn))
{
T expected = default;
VBuffer<T> actual = default;
var expectedGetter = expectedCursor.GetGetter<T>(leftColumn);
var actualGetter = actualCursor.GetGetter<VBuffer<T>>(rightColumn);
while (expectedCursor.MoveNext() && actualCursor.MoveNext())
{
expectedGetter(ref expected);
actualGetter(ref actual);
var actualVal = actual.GetItemOrDefault(0);

Assert.Equal(1, actual.Length);

if (typeof(T) == typeof(ReadOnlyMemory<Char>))
Assert.Equal(expected.ToString(), actualVal.ToString());
else
Assert.Equal(expected, actualVal);
}
}
}

private void CompareSelectedR8VectorColumns(string leftColumnName, string rightColumnName, IDataView left, IDataView right, int precision = 6)
{
var leftColumn = left.Schema[leftColumnName];
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 support for KeyToValueMappingTransformer#4455

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 1 commit into from
Nov 14, 2019
Merged

Added onnx export support for KeyToValueMappingTransformer #4455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
62 changes: 61 additions & 1 deletion src/Microsoft.ML.Data/Transforms/KeyToValue.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,7 @@
using Microsoft.ML.CommandLine;
using Microsoft.ML.Data;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Model.Pfa;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;
Expand DownExpand Up@@ -152,7 +153,7 @@ private protected override void SaveModel(ModelSaveContext ctx)

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

private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa
private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa, ISaveAsOnnx
{
private readonly KeyToValueMappingTransformer _parent;
private readonly DataViewType[] _types;
Expand DownExpand Up@@ -298,6 +299,8 @@ protected KeyToValueMap(Mapper mapper, PrimitiveDataViewType typeVal, int iinfo)
public abstract Delegate GetMappingGetter(DataViewRow input);

public abstract JToken SavePfa(BoundPfaContext ctx, JToken srcToken);

public abstract bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName);
}

private class KeyToValueMap<TKey, TValue> : KeyToValueMap
Expand DownExpand Up@@ -494,8 +497,65 @@ public override JToken SavePfa(BoundPfaContext ctx, JToken srcToken)
}
return PfaUtils.If(PfaUtils.Call("<", srcToken, 0), defaultToken, PfaUtils.Index(cellRef, srcToken));
}

public override bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName)
{
string opType;

// Onnx expects the input keys to be int64s. But the input data can come from an ML.NET node that
// may output a uint32. So cast it here to ensure that the data is treated correctly
opType = "Cast";
var castNodeOutput = ctx.AddIntermediateVariable(TypeOutput, "CastNodeOutput", true);
var castNode = ctx.CreateNode(opType, srcVariableName, castNodeOutput, ctx.GetNodeName(opType), "");
var t = InternalDataKindExtensions.ToInternalDataKind(DataKind.Int64).ToType();
castNode.AddAttribute("to", t);

opType = "LabelEncoder";
var node = ctx.CreateNode(opType, castNodeOutput, dstVariableName, ctx.GetNodeName(opType));
var keys = Array.ConvertAll<int, long>(Enumerable.Range(1, _values.Length).ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("keys_int64s", keys);

if (TypeOutput == NumberDataViewType.Int64)
{
long[] values = Array.ConvertAll<TValue, long>(_values.GetValues().ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("values_int64s", values);
}
else if (TypeOutput == NumberDataViewType.Single)
{
float[] values = Array.ConvertAll<TValue, float>(_values.GetValues().ToArray(), item => Convert.ToSingle(item));
node.AddAttribute("values_floats", values);
}
else if (TypeOutput == TextDataViewType.Instance)
{
string[] values = Array.ConvertAll<TValue, string>(_values.GetValues().ToArray(), item => Convert.ToString(item));
node.AddAttribute("values_strings", values);
}
else
return false;

return true;
}
}

public bool CanSaveOnnx(OnnxContext ctx) => true;

public void SaveAsOnnx(OnnxContext ctx)
{
for (int iinfo = 0; iinfo < _parent.ColumnPairs.Length; ++iinfo)
{
var info = _parent.ColumnPairs[iinfo];
var inputColumnName = info.inputColumnName;

if (!ctx.ContainsColumn(inputColumnName))
continue;

var dstVariableName = ctx.AddIntermediateVariable(_types[iinfo], info.outputColumnName, true);
if (!_kvMaps[iinfo].SaveOnnx(ctx, inputColumnName, dstVariableName))
{
ctx.RemoveColumn(inputColumnName, true);
}
}
}
}
}

Expand Down
64 changes: 64 additions & 0 deletions test/Microsoft.ML.Tests/OnnxConversionTest.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1040,6 +1040,42 @@ public void OptionalColumnOnnxTest()
Done();
}

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

string dataPath = GetDataPath("breast-cancer.txt");
var dataView = mlContext.Data.LoadFromTextFile<BreastCancerMulticlassExample>(dataPath,
separatorChar: '\t',
hasHeader: true);

var pipeline = mlContext.Transforms.Conversion.MapValueToKey("LabelKey", "Label").
Append(mlContext.Transforms.Conversion.MapKeyToValue("LabelValue", "LabelKey"));

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

var onnxFileName = "KeyToValue.onnx";
var onnxModelPath = GetOutputPath(onnxFileName);

SaveOnnxModel(onnxModel, onnxModelPath, null);

if (IsOnnxRuntimeSupported())
{
// 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);
CompareSelectedScalarColumns<ReadOnlyMemory<Char>>(transformedData.Schema[3].Name, outputNames[3], transformedData, onnxResult);
}

Done();
}

private void CreateDummyExamplesToMakeComplierHappy()
{
var dummyExample = new BreastCancerFeatureVector() { Features = null };
Expand DownExpand Up@@ -1105,6 +1141,34 @@ private void CompareSelectedVectorColumns<T>(string leftColumnName, string right
}
}

private void CompareSelectedScalarColumns<T>(string leftColumnName, string rightColumnName, IDataView left, IDataView right)
{
var leftColumn = left.Schema[leftColumnName];
var rightColumn = right.Schema[rightColumnName];

using (var expectedCursor = left.GetRowCursor(leftColumn))
using (var actualCursor = right.GetRowCursor(rightColumn))
{
T expected = default;
VBuffer<T> actual = default;
var expectedGetter = expectedCursor.GetGetter<T>(leftColumn);
var actualGetter = actualCursor.GetGetter<VBuffer<T>>(rightColumn);
while (expectedCursor.MoveNext() && actualCursor.MoveNext())
{
expectedGetter(ref expected);
actualGetter(ref actual);
var actualVal = actual.GetItemOrDefault(0);

Assert.Equal(1, actual.Length);

if (typeof(T) == typeof(ReadOnlyMemory<Char>))
Assert.Equal(expected.ToString(), actualVal.ToString());
else
Assert.Equal(expected, actualVal);
}
}
}

private void CompareSelectedR8VectorColumns(string leftColumnName, string rightColumnName, IDataView left, IDataView right, int precision = 6)
{
var leftColumn = left.Schema[leftColumnName];
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 \u003e 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 support for KeyToValueMappingTransformer#4455

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 1 commit into from
Nov 14, 2019
Merged

Added onnx export support for KeyToValueMappingTransformer #4455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
62 changes: 61 additions & 1 deletion src/Microsoft.ML.Data/Transforms/KeyToValue.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,7 @@
using Microsoft.ML.CommandLine;
using Microsoft.ML.Data;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Model.Pfa;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;
Expand DownExpand Up@@ -152,7 +153,7 @@ private protected override void SaveModel(ModelSaveContext ctx)

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

private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa
private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa, ISaveAsOnnx
{
private readonly KeyToValueMappingTransformer _parent;
private readonly DataViewType[] _types;
Expand DownExpand Up@@ -298,6 +299,8 @@ protected KeyToValueMap(Mapper mapper, PrimitiveDataViewType typeVal, int iinfo)
public abstract Delegate GetMappingGetter(DataViewRow input);

public abstract JToken SavePfa(BoundPfaContext ctx, JToken srcToken);

public abstract bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName);
}

private class KeyToValueMap<TKey, TValue> : KeyToValueMap
Expand DownExpand Up@@ -494,8 +497,65 @@ public override JToken SavePfa(BoundPfaContext ctx, JToken srcToken)
}
return PfaUtils.If(PfaUtils.Call("<", srcToken, 0), defaultToken, PfaUtils.Index(cellRef, srcToken));
}

public override bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName)
{
string opType;

// Onnx expects the input keys to be int64s. But the input data can come from an ML.NET node that
// may output a uint32. So cast it here to ensure that the data is treated correctly
opType = "Cast";
var castNodeOutput = ctx.AddIntermediateVariable(TypeOutput, "CastNodeOutput", true);
var castNode = ctx.CreateNode(opType, srcVariableName, castNodeOutput, ctx.GetNodeName(opType), "");
var t = InternalDataKindExtensions.ToInternalDataKind(DataKind.Int64).ToType();
castNode.AddAttribute("to", t);

opType = "LabelEncoder";
var node = ctx.CreateNode(opType, castNodeOutput, dstVariableName, ctx.GetNodeName(opType));
var keys = Array.ConvertAll<int, long>(Enumerable.Range(1, _values.Length).ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("keys_int64s", keys);

if (TypeOutput == NumberDataViewType.Int64)
{
long[] values = Array.ConvertAll<TValue, long>(_values.GetValues().ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("values_int64s", values);
}
else if (TypeOutput == NumberDataViewType.Single)
{
float[] values = Array.ConvertAll<TValue, float>(_values.GetValues().ToArray(), item => Convert.ToSingle(item));
node.AddAttribute("values_floats", values);
}
else if (TypeOutput == TextDataViewType.Instance)
{
string[] values = Array.ConvertAll<TValue, string>(_values.GetValues().ToArray(), item => Convert.ToString(item));
node.AddAttribute("values_strings", values);
}
else
return false;

return true;
}
}

public bool CanSaveOnnx(OnnxContext ctx) => true;

public void SaveAsOnnx(OnnxContext ctx)
{
for (int iinfo = 0; iinfo < _parent.ColumnPairs.Length; ++iinfo)
{
var info = _parent.ColumnPairs[iinfo];
var inputColumnName = info.inputColumnName;

if (!ctx.ContainsColumn(inputColumnName))
continue;

var dstVariableName = ctx.AddIntermediateVariable(_types[iinfo], info.outputColumnName, true);
if (!_kvMaps[iinfo].SaveOnnx(ctx, inputColumnName, dstVariableName))
{
ctx.RemoveColumn(inputColumnName, true);
}
}
}
}
}

Expand Down
64 changes: 64 additions & 0 deletions test/Microsoft.ML.Tests/OnnxConversionTest.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1040,6 +1040,42 @@ public void OptionalColumnOnnxTest()
Done();
}

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

string dataPath = GetDataPath("breast-cancer.txt");
var dataView = mlContext.Data.LoadFromTextFile<BreastCancerMulticlassExample>(dataPath,
separatorChar: '\t',
hasHeader: true);

var pipeline = mlContext.Transforms.Conversion.MapValueToKey("LabelKey", "Label").
Append(mlContext.Transforms.Conversion.MapKeyToValue("LabelValue", "LabelKey"));

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

var onnxFileName = "KeyToValue.onnx";
var onnxModelPath = GetOutputPath(onnxFileName);

SaveOnnxModel(onnxModel, onnxModelPath, null);

if (IsOnnxRuntimeSupported())
{
// 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);
CompareSelectedScalarColumns<ReadOnlyMemory<Char>>(transformedData.Schema[3].Name, outputNames[3], transformedData, onnxResult);
}

Done();
}

private void CreateDummyExamplesToMakeComplierHappy()
{
var dummyExample = new BreastCancerFeatureVector() { Features = null };
Expand DownExpand Up@@ -1105,6 +1141,34 @@ private void CompareSelectedVectorColumns<T>(string leftColumnName, string right
}
}

private void CompareSelectedScalarColumns<T>(string leftColumnName, string rightColumnName, IDataView left, IDataView right)
{
var leftColumn = left.Schema[leftColumnName];
var rightColumn = right.Schema[rightColumnName];

using (var expectedCursor = left.GetRowCursor(leftColumn))
using (var actualCursor = right.GetRowCursor(rightColumn))
{
T expected = default;
VBuffer<T> actual = default;
var expectedGetter = expectedCursor.GetGetter<T>(leftColumn);
var actualGetter = actualCursor.GetGetter<VBuffer<T>>(rightColumn);
while (expectedCursor.MoveNext() && actualCursor.MoveNext())
{
expectedGetter(ref expected);
actualGetter(ref actual);
var actualVal = actual.GetItemOrDefault(0);

Assert.Equal(1, actual.Length);

if (typeof(T) == typeof(ReadOnlyMemory<Char>))
Assert.Equal(expected.ToString(), actualVal.ToString());
else
Assert.Equal(expected, actualVal);
}
}
}

private void CompareSelectedR8VectorColumns(string leftColumnName, string rightColumnName, IDataView left, IDataView right, int precision = 6)
{
var leftColumn = left.Schema[leftColumnName];
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 support for KeyToValueMappingTransformer#4455

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 1 commit into from
Nov 14, 2019
Merged

Added onnx export support for KeyToValueMappingTransformer #4455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
62 changes: 61 additions & 1 deletion src/Microsoft.ML.Data/Transforms/KeyToValue.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,7 @@
using Microsoft.ML.CommandLine;
using Microsoft.ML.Data;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Model.Pfa;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;
Expand DownExpand Up@@ -152,7 +153,7 @@ private protected override void SaveModel(ModelSaveContext ctx)

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

private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa
private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa, ISaveAsOnnx
{
private readonly KeyToValueMappingTransformer _parent;
private readonly DataViewType[] _types;
Expand DownExpand Up@@ -298,6 +299,8 @@ protected KeyToValueMap(Mapper mapper, PrimitiveDataViewType typeVal, int iinfo)
public abstract Delegate GetMappingGetter(DataViewRow input);

public abstract JToken SavePfa(BoundPfaContext ctx, JToken srcToken);

public abstract bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName);
}

private class KeyToValueMap<TKey, TValue> : KeyToValueMap
Expand DownExpand Up@@ -494,8 +497,65 @@ public override JToken SavePfa(BoundPfaContext ctx, JToken srcToken)
}
return PfaUtils.If(PfaUtils.Call("<", srcToken, 0), defaultToken, PfaUtils.Index(cellRef, srcToken));
}

public override bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName)
{
string opType;

// Onnx expects the input keys to be int64s. But the input data can come from an ML.NET node that
// may output a uint32. So cast it here to ensure that the data is treated correctly
opType = "Cast";
var castNodeOutput = ctx.AddIntermediateVariable(TypeOutput, "CastNodeOutput", true);
var castNode = ctx.CreateNode(opType, srcVariableName, castNodeOutput, ctx.GetNodeName(opType), "");
var t = InternalDataKindExtensions.ToInternalDataKind(DataKind.Int64).ToType();
castNode.AddAttribute("to", t);

opType = "LabelEncoder";
var node = ctx.CreateNode(opType, castNodeOutput, dstVariableName, ctx.GetNodeName(opType));
var keys = Array.ConvertAll<int, long>(Enumerable.Range(1, _values.Length).ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("keys_int64s", keys);

if (TypeOutput == NumberDataViewType.Int64)
{
long[] values = Array.ConvertAll<TValue, long>(_values.GetValues().ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("values_int64s", values);
}
else if (TypeOutput == NumberDataViewType.Single)
{
float[] values = Array.ConvertAll<TValue, float>(_values.GetValues().ToArray(), item => Convert.ToSingle(item));
node.AddAttribute("values_floats", values);
}
else if (TypeOutput == TextDataViewType.Instance)
{
string[] values = Array.ConvertAll<TValue, string>(_values.GetValues().ToArray(), item => Convert.ToString(item));
node.AddAttribute("values_strings", values);
}
else
return false;

return true;
}
}

public bool CanSaveOnnx(OnnxContext ctx) => true;

public void SaveAsOnnx(OnnxContext ctx)
{
for (int iinfo = 0; iinfo < _parent.ColumnPairs.Length; ++iinfo)
{
var info = _parent.ColumnPairs[iinfo];
var inputColumnName = info.inputColumnName;

if (!ctx.ContainsColumn(inputColumnName))
continue;

var dstVariableName = ctx.AddIntermediateVariable(_types[iinfo], info.outputColumnName, true);
if (!_kvMaps[iinfo].SaveOnnx(ctx, inputColumnName, dstVariableName))
{
ctx.RemoveColumn(inputColumnName, true);
}
}
}
}
}

Expand Down
64 changes: 64 additions & 0 deletions test/Microsoft.ML.Tests/OnnxConversionTest.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1040,6 +1040,42 @@ public void OptionalColumnOnnxTest()
Done();
}

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

string dataPath = GetDataPath("breast-cancer.txt");
var dataView = mlContext.Data.LoadFromTextFile<BreastCancerMulticlassExample>(dataPath,
separatorChar: '\t',
hasHeader: true);

var pipeline = mlContext.Transforms.Conversion.MapValueToKey("LabelKey", "Label").
Append(mlContext.Transforms.Conversion.MapKeyToValue("LabelValue", "LabelKey"));

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

var onnxFileName = "KeyToValue.onnx";
var onnxModelPath = GetOutputPath(onnxFileName);

SaveOnnxModel(onnxModel, onnxModelPath, null);

if (IsOnnxRuntimeSupported())
{
// 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);
CompareSelectedScalarColumns<ReadOnlyMemory<Char>>(transformedData.Schema[3].Name, outputNames[3], transformedData, onnxResult);
}

Done();
}

private void CreateDummyExamplesToMakeComplierHappy()
{
var dummyExample = new BreastCancerFeatureVector() { Features = null };
Expand DownExpand Up@@ -1105,6 +1141,34 @@ private void CompareSelectedVectorColumns<T>(string leftColumnName, string right
}
}

private void CompareSelectedScalarColumns<T>(string leftColumnName, string rightColumnName, IDataView left, IDataView right)
{
var leftColumn = left.Schema[leftColumnName];
var rightColumn = right.Schema[rightColumnName];

using (var expectedCursor = left.GetRowCursor(leftColumn))
using (var actualCursor = right.GetRowCursor(rightColumn))
{
T expected = default;
VBuffer<T> actual = default;
var expectedGetter = expectedCursor.GetGetter<T>(leftColumn);
var actualGetter = actualCursor.GetGetter<VBuffer<T>>(rightColumn);
while (expectedCursor.MoveNext() && actualCursor.MoveNext())
{
expectedGetter(ref expected);
actualGetter(ref actual);
var actualVal = actual.GetItemOrDefault(0);

Assert.Equal(1, actual.Length);

if (typeof(T) == typeof(ReadOnlyMemory<Char>))
Assert.Equal(expected.ToString(), actualVal.ToString());
else
Assert.Equal(expected, actualVal);
}
}
}

private void CompareSelectedR8VectorColumns(string leftColumnName, string rightColumnName, IDataView left, IDataView right, int precision = 6)
{
var leftColumn = left.Schema[leftColumnName];
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 support for KeyToValueMappingTransformer#4455

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 1 commit into from
Nov 14, 2019
Merged

Added onnx export support for KeyToValueMappingTransformer #4455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
62 changes: 61 additions & 1 deletion src/Microsoft.ML.Data/Transforms/KeyToValue.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,7 @@
using Microsoft.ML.CommandLine;
using Microsoft.ML.Data;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Model.Pfa;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;
Expand DownExpand Up@@ -152,7 +153,7 @@ private protected override void SaveModel(ModelSaveContext ctx)

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

private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa
private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa, ISaveAsOnnx
{
private readonly KeyToValueMappingTransformer _parent;
private readonly DataViewType[] _types;
Expand DownExpand Up@@ -298,6 +299,8 @@ protected KeyToValueMap(Mapper mapper, PrimitiveDataViewType typeVal, int iinfo)
public abstract Delegate GetMappingGetter(DataViewRow input);

public abstract JToken SavePfa(BoundPfaContext ctx, JToken srcToken);

public abstract bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName);
}

private class KeyToValueMap<TKey, TValue> : KeyToValueMap
Expand DownExpand Up@@ -494,8 +497,65 @@ public override JToken SavePfa(BoundPfaContext ctx, JToken srcToken)
}
return PfaUtils.If(PfaUtils.Call("<", srcToken, 0), defaultToken, PfaUtils.Index(cellRef, srcToken));
}

public override bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName)
{
string opType;

// Onnx expects the input keys to be int64s. But the input data can come from an ML.NET node that
// may output a uint32. So cast it here to ensure that the data is treated correctly
opType = "Cast";
var castNodeOutput = ctx.AddIntermediateVariable(TypeOutput, "CastNodeOutput", true);
var castNode = ctx.CreateNode(opType, srcVariableName, castNodeOutput, ctx.GetNodeName(opType), "");
var t = InternalDataKindExtensions.ToInternalDataKind(DataKind.Int64).ToType();
castNode.AddAttribute("to", t);

opType = "LabelEncoder";
var node = ctx.CreateNode(opType, castNodeOutput, dstVariableName, ctx.GetNodeName(opType));
var keys = Array.ConvertAll<int, long>(Enumerable.Range(1, _values.Length).ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("keys_int64s", keys);

if (TypeOutput == NumberDataViewType.Int64)
{
long[] values = Array.ConvertAll<TValue, long>(_values.GetValues().ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("values_int64s", values);
}
else if (TypeOutput == NumberDataViewType.Single)
{
float[] values = Array.ConvertAll<TValue, float>(_values.GetValues().ToArray(), item => Convert.ToSingle(item));
node.AddAttribute("values_floats", values);
}
else if (TypeOutput == TextDataViewType.Instance)
{
string[] values = Array.ConvertAll<TValue, string>(_values.GetValues().ToArray(), item => Convert.ToString(item));
node.AddAttribute("values_strings", values);
}
else
return false;

return true;
}
}

public bool CanSaveOnnx(OnnxContext ctx) => true;

public void SaveAsOnnx(OnnxContext ctx)
{
for (int iinfo = 0; iinfo < _parent.ColumnPairs.Length; ++iinfo)
{
var info = _parent.ColumnPairs[iinfo];
var inputColumnName = info.inputColumnName;

if (!ctx.ContainsColumn(inputColumnName))
continue;

var dstVariableName = ctx.AddIntermediateVariable(_types[iinfo], info.outputColumnName, true);
if (!_kvMaps[iinfo].SaveOnnx(ctx, inputColumnName, dstVariableName))
{
ctx.RemoveColumn(inputColumnName, true);
}
}
}
}
}

Expand Down
64 changes: 64 additions & 0 deletions test/Microsoft.ML.Tests/OnnxConversionTest.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1040,6 +1040,42 @@ public void OptionalColumnOnnxTest()
Done();
}

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

string dataPath = GetDataPath("breast-cancer.txt");
var dataView = mlContext.Data.LoadFromTextFile<BreastCancerMulticlassExample>(dataPath,
separatorChar: '\t',
hasHeader: true);

var pipeline = mlContext.Transforms.Conversion.MapValueToKey("LabelKey", "Label").
Append(mlContext.Transforms.Conversion.MapKeyToValue("LabelValue", "LabelKey"));

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

var onnxFileName = "KeyToValue.onnx";
var onnxModelPath = GetOutputPath(onnxFileName);

SaveOnnxModel(onnxModel, onnxModelPath, null);

if (IsOnnxRuntimeSupported())
{
// 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);
CompareSelectedScalarColumns<ReadOnlyMemory<Char>>(transformedData.Schema[3].Name, outputNames[3], transformedData, onnxResult);
}

Done();
}

private void CreateDummyExamplesToMakeComplierHappy()
{
var dummyExample = new BreastCancerFeatureVector() { Features = null };
Expand DownExpand Up@@ -1105,6 +1141,34 @@ private void CompareSelectedVectorColumns<T>(string leftColumnName, string right
}
}

private void CompareSelectedScalarColumns<T>(string leftColumnName, string rightColumnName, IDataView left, IDataView right)
{
var leftColumn = left.Schema[leftColumnName];
var rightColumn = right.Schema[rightColumnName];

using (var expectedCursor = left.GetRowCursor(leftColumn))
using (var actualCursor = right.GetRowCursor(rightColumn))
{
T expected = default;
VBuffer<T> actual = default;
var expectedGetter = expectedCursor.GetGetter<T>(leftColumn);
var actualGetter = actualCursor.GetGetter<VBuffer<T>>(rightColumn);
while (expectedCursor.MoveNext() && actualCursor.MoveNext())
{
expectedGetter(ref expected);
actualGetter(ref actual);
var actualVal = actual.GetItemOrDefault(0);

Assert.Equal(1, actual.Length);

if (typeof(T) == typeof(ReadOnlyMemory<Char>))
Assert.Equal(expected.ToString(), actualVal.ToString());
else
Assert.Equal(expected, actualVal);
}
}
}

private void CompareSelectedR8VectorColumns(string leftColumnName, string rightColumnName, IDataView left, IDataView right, int precision = 6)
{
var leftColumn = left.Schema[leftColumnName];
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 support for KeyToValueMappingTransformer#4455

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 1 commit into from
Nov 14, 2019
Merged

Added onnx export support for KeyToValueMappingTransformer #4455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
62 changes: 61 additions & 1 deletion src/Microsoft.ML.Data/Transforms/KeyToValue.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,7 @@
using Microsoft.ML.CommandLine;
using Microsoft.ML.Data;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Model.Pfa;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;
Expand DownExpand Up@@ -152,7 +153,7 @@ private protected override void SaveModel(ModelSaveContext ctx)

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

private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa
private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa, ISaveAsOnnx
{
private readonly KeyToValueMappingTransformer _parent;
private readonly DataViewType[] _types;
Expand DownExpand Up@@ -298,6 +299,8 @@ protected KeyToValueMap(Mapper mapper, PrimitiveDataViewType typeVal, int iinfo)
public abstract Delegate GetMappingGetter(DataViewRow input);

public abstract JToken SavePfa(BoundPfaContext ctx, JToken srcToken);

public abstract bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName);
}

private class KeyToValueMap<TKey, TValue> : KeyToValueMap
Expand DownExpand Up@@ -494,8 +497,65 @@ public override JToken SavePfa(BoundPfaContext ctx, JToken srcToken)
}
return PfaUtils.If(PfaUtils.Call("<", srcToken, 0), defaultToken, PfaUtils.Index(cellRef, srcToken));
}

public override bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName)
{
string opType;

// Onnx expects the input keys to be int64s. But the input data can come from an ML.NET node that
// may output a uint32. So cast it here to ensure that the data is treated correctly
opType = "Cast";
var castNodeOutput = ctx.AddIntermediateVariable(TypeOutput, "CastNodeOutput", true);
var castNode = ctx.CreateNode(opType, srcVariableName, castNodeOutput, ctx.GetNodeName(opType), "");
var t = InternalDataKindExtensions.ToInternalDataKind(DataKind.Int64).ToType();
castNode.AddAttribute("to", t);

opType = "LabelEncoder";
var node = ctx.CreateNode(opType, castNodeOutput, dstVariableName, ctx.GetNodeName(opType));
var keys = Array.ConvertAll<int, long>(Enumerable.Range(1, _values.Length).ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("keys_int64s", keys);

if (TypeOutput == NumberDataViewType.Int64)
{
long[] values = Array.ConvertAll<TValue, long>(_values.GetValues().ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("values_int64s", values);
}
else if (TypeOutput == NumberDataViewType.Single)
{
float[] values = Array.ConvertAll<TValue, float>(_values.GetValues().ToArray(), item => Convert.ToSingle(item));
node.AddAttribute("values_floats", values);
}
else if (TypeOutput == TextDataViewType.Instance)
{
string[] values = Array.ConvertAll<TValue, string>(_values.GetValues().ToArray(), item => Convert.ToString(item));
node.AddAttribute("values_strings", values);
}
else
return false;

return true;
}
}

public bool CanSaveOnnx(OnnxContext ctx) => true;

public void SaveAsOnnx(OnnxContext ctx)
{
for (int iinfo = 0; iinfo < _parent.ColumnPairs.Length; ++iinfo)
{
var info = _parent.ColumnPairs[iinfo];
var inputColumnName = info.inputColumnName;

if (!ctx.ContainsColumn(inputColumnName))
continue;

var dstVariableName = ctx.AddIntermediateVariable(_types[iinfo], info.outputColumnName, true);
if (!_kvMaps[iinfo].SaveOnnx(ctx, inputColumnName, dstVariableName))
{
ctx.RemoveColumn(inputColumnName, true);
}
}
}
}
}

Expand Down
64 changes: 64 additions & 0 deletions test/Microsoft.ML.Tests/OnnxConversionTest.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1040,6 +1040,42 @@ public void OptionalColumnOnnxTest()
Done();
}

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

string dataPath = GetDataPath("breast-cancer.txt");
var dataView = mlContext.Data.LoadFromTextFile<BreastCancerMulticlassExample>(dataPath,
separatorChar: '\t',
hasHeader: true);

var pipeline = mlContext.Transforms.Conversion.MapValueToKey("LabelKey", "Label").
Append(mlContext.Transforms.Conversion.MapKeyToValue("LabelValue", "LabelKey"));

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

var onnxFileName = "KeyToValue.onnx";
var onnxModelPath = GetOutputPath(onnxFileName);

SaveOnnxModel(onnxModel, onnxModelPath, null);

if (IsOnnxRuntimeSupported())
{
// 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);
CompareSelectedScalarColumns<ReadOnlyMemory<Char>>(transformedData.Schema[3].Name, outputNames[3], transformedData, onnxResult);
}

Done();
}

private void CreateDummyExamplesToMakeComplierHappy()
{
var dummyExample = new BreastCancerFeatureVector() { Features = null };
Expand DownExpand Up@@ -1105,6 +1141,34 @@ private void CompareSelectedVectorColumns<T>(string leftColumnName, string right
}
}

private void CompareSelectedScalarColumns<T>(string leftColumnName, string rightColumnName, IDataView left, IDataView right)
{
var leftColumn = left.Schema[leftColumnName];
var rightColumn = right.Schema[rightColumnName];

using (var expectedCursor = left.GetRowCursor(leftColumn))
using (var actualCursor = right.GetRowCursor(rightColumn))
{
T expected = default;
VBuffer<T> actual = default;
var expectedGetter = expectedCursor.GetGetter<T>(leftColumn);
var actualGetter = actualCursor.GetGetter<VBuffer<T>>(rightColumn);
while (expectedCursor.MoveNext() && actualCursor.MoveNext())
{
expectedGetter(ref expected);
actualGetter(ref actual);
var actualVal = actual.GetItemOrDefault(0);

Assert.Equal(1, actual.Length);

if (typeof(T) == typeof(ReadOnlyMemory<Char>))
Assert.Equal(expected.ToString(), actualVal.ToString());
else
Assert.Equal(expected, actualVal);
}
}
}

private void CompareSelectedR8VectorColumns(string leftColumnName, string rightColumnName, IDataView left, IDataView right, int precision = 6)
{
var leftColumn = left.Schema[leftColumnName];
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 support for KeyToValueMappingTransformer#4455

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 1 commit into from
Nov 14, 2019
Merged

Added onnx export support for KeyToValueMappingTransformer #4455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
62 changes: 61 additions & 1 deletion src/Microsoft.ML.Data/Transforms/KeyToValue.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,7 @@
using Microsoft.ML.CommandLine;
using Microsoft.ML.Data;
using Microsoft.ML.Internal.Utilities;
using Microsoft.ML.Model.OnnxConverter;
using Microsoft.ML.Model.Pfa;
using Microsoft.ML.Runtime;
using Microsoft.ML.Transforms;
Expand DownExpand Up@@ -152,7 +153,7 @@ private protected override void SaveModel(ModelSaveContext ctx)

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

private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa
private sealed class Mapper : OneToOneMapperBase, ISaveAsPfa, ISaveAsOnnx
{
private readonly KeyToValueMappingTransformer _parent;
private readonly DataViewType[] _types;
Expand DownExpand Up@@ -298,6 +299,8 @@ protected KeyToValueMap(Mapper mapper, PrimitiveDataViewType typeVal, int iinfo)
public abstract Delegate GetMappingGetter(DataViewRow input);

public abstract JToken SavePfa(BoundPfaContext ctx, JToken srcToken);

public abstract bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName);
}

private class KeyToValueMap<TKey, TValue> : KeyToValueMap
Expand DownExpand Up@@ -494,8 +497,65 @@ public override JToken SavePfa(BoundPfaContext ctx, JToken srcToken)
}
return PfaUtils.If(PfaUtils.Call("<", srcToken, 0), defaultToken, PfaUtils.Index(cellRef, srcToken));
}

public override bool SaveOnnx(OnnxContext ctx, string srcVariableName, string dstVariableName)
{
string opType;

// Onnx expects the input keys to be int64s. But the input data can come from an ML.NET node that
// may output a uint32. So cast it here to ensure that the data is treated correctly
opType = "Cast";
var castNodeOutput = ctx.AddIntermediateVariable(TypeOutput, "CastNodeOutput", true);
var castNode = ctx.CreateNode(opType, srcVariableName, castNodeOutput, ctx.GetNodeName(opType), "");
var t = InternalDataKindExtensions.ToInternalDataKind(DataKind.Int64).ToType();
castNode.AddAttribute("to", t);

opType = "LabelEncoder";
var node = ctx.CreateNode(opType, castNodeOutput, dstVariableName, ctx.GetNodeName(opType));
var keys = Array.ConvertAll<int, long>(Enumerable.Range(1, _values.Length).ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("keys_int64s", keys);

if (TypeOutput == NumberDataViewType.Int64)
{
long[] values = Array.ConvertAll<TValue, long>(_values.GetValues().ToArray(), item => Convert.ToInt64(item));
node.AddAttribute("values_int64s", values);
}
else if (TypeOutput == NumberDataViewType.Single)
{
float[] values = Array.ConvertAll<TValue, float>(_values.GetValues().ToArray(), item => Convert.ToSingle(item));
node.AddAttribute("values_floats", values);
}
else if (TypeOutput == TextDataViewType.Instance)
{
string[] values = Array.ConvertAll<TValue, string>(_values.GetValues().ToArray(), item => Convert.ToString(item));
node.AddAttribute("values_strings", values);
}
else
return false;

return true;
}
}

public bool CanSaveOnnx(OnnxContext ctx) => true;

public void SaveAsOnnx(OnnxContext ctx)
{
for (int iinfo = 0; iinfo < _parent.ColumnPairs.Length; ++iinfo)
{
var info = _parent.ColumnPairs[iinfo];
var inputColumnName = info.inputColumnName;

if (!ctx.ContainsColumn(inputColumnName))
continue;

var dstVariableName = ctx.AddIntermediateVariable(_types[iinfo], info.outputColumnName, true);
if (!_kvMaps[iinfo].SaveOnnx(ctx, inputColumnName, dstVariableName))
{
ctx.RemoveColumn(inputColumnName, true);
}
}
}
}
}

Expand Down
64 changes: 64 additions & 0 deletions test/Microsoft.ML.Tests/OnnxConversionTest.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1040,6 +1040,42 @@ public void OptionalColumnOnnxTest()
Done();
}

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

string dataPath = GetDataPath("breast-cancer.txt");
var dataView = mlContext.Data.LoadFromTextFile<BreastCancerMulticlassExample>(dataPath,
separatorChar: '\t',
hasHeader: true);

var pipeline = mlContext.Transforms.Conversion.MapValueToKey("LabelKey", "Label").
Append(mlContext.Transforms.Conversion.MapKeyToValue("LabelValue", "LabelKey"));

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

var onnxFileName = "KeyToValue.onnx";
var onnxModelPath = GetOutputPath(onnxFileName);

SaveOnnxModel(onnxModel, onnxModelPath, null);

if (IsOnnxRuntimeSupported())
{
// 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);
CompareSelectedScalarColumns<ReadOnlyMemory<Char>>(transformedData.Schema[3].Name, outputNames[3], transformedData, onnxResult);
}

Done();
}

private void CreateDummyExamplesToMakeComplierHappy()
{
var dummyExample = new BreastCancerFeatureVector() { Features = null };
Expand DownExpand Up@@ -1105,6 +1141,34 @@ private void CompareSelectedVectorColumns<T>(string leftColumnName, string right
}
}

private void CompareSelectedScalarColumns<T>(string leftColumnName, string rightColumnName, IDataView left, IDataView right)
{
var leftColumn = left.Schema[leftColumnName];
var rightColumn = right.Schema[rightColumnName];

using (var expectedCursor = left.GetRowCursor(leftColumn))
using (var actualCursor = right.GetRowCursor(rightColumn))
{
T expected = default;
VBuffer<T> actual = default;
var expectedGetter = expectedCursor.GetGetter<T>(leftColumn);
var actualGetter = actualCursor.GetGetter<VBuffer<T>>(rightColumn);
while (expectedCursor.MoveNext() && actualCursor.MoveNext())
{
expectedGetter(ref expected);
actualGetter(ref actual);
var actualVal = actual.GetItemOrDefault(0);

Assert.Equal(1, actual.Length);

if (typeof(T) == typeof(ReadOnlyMemory<Char>))
Assert.Equal(expected.ToString(), actualVal.ToString());
else
Assert.Equal(expected, actualVal);
}
}
}

private void CompareSelectedR8VectorColumns(string leftColumnName, string rightColumnName, IDataView left, IDataView right, int precision = 6)
{
var leftColumn = left.Schema[leftColumnName];
Expand Down