public void TestSaveAndLoadTreeFeaturizer()
{
int dataPointCount = 200;
var data = SamplesUtils.DatasetUtils.GenerateFloatLabelFloatFeatureVectorSamples(dataPointCount).ToList();
var dataView = ML.Data.LoadFromEnumerable(data);
dataView = ML.Data.Cache(dataView);
var trainerOptions = new FastForestRegressionTrainer.Options
{
NumberOfThreads = 1,
NumberOfTrees = 10,
NumberOfLeaves = 4,
MinimumExampleCountPerLeaf = 10,
FeatureColumnName = "Features",
LabelColumnName = "Label"
};
var options = new FastForestRegressionFeaturizationEstimator.Options()
{
InputColumnName = "Features",
TreesColumnName = "Trees",
LeavesColumnName = "Leaves",
PathsColumnName = "Paths",
TrainerOptions = trainerOptions
};
var pipeline = ML.Transforms.FeaturizeByFastForestRegression(options)
.Append(ML.Transforms.Concatenate("CombinedFeatures", "Features", "Trees", "Leaves", "Paths"))
.Append(ML.Regression.Trainers.Sdca("Label", "CombinedFeatures"));
var model = pipeline.Fit(dataView);
var prediction = model.Transform(dataView);
var metrics = ML.Regression.Evaluate(prediction);
Assert.True(metrics.MeanAbsoluteError < 0.25);
Assert.True(metrics.MeanSquaredError < 0.1);
// Save the trained model into file.
ITransformer loadedModel = null;
var tempPath = Path.GetTempFileName();
using (var file = new SimpleFileHandle(Env, tempPath, true, true))
{
using (var fs = file.CreateWriteStream())
ML.Model.Save(model, null, fs);
using (var fs = file.OpenReadStream())
loadedModel = ML.Model.Load(fs, out var schema);
}
var loadedPrediction = loadedModel.Transform(dataView);
var loadedMetrics = ML.Regression.Evaluate(loadedPrediction);
Assert.Equal(metrics.MeanAbsoluteError, loadedMetrics.MeanAbsoluteError);
Assert.Equal(metrics.MeanSquaredError, loadedMetrics.MeanSquaredError);
}
public void TestEstimatorSaveLoad()
{
IHostEnvironment env = new MLContext(1);
var dataFile = GetDataPath("images/images.tsv");
var imageFolder = Path.GetDirectoryName(dataFile);
var data = TextLoader.Create(env, new TextLoader.Options()
{
Columns = new[]
{
new TextLoader.Column("ImagePath", DataKind.String, 0),
new TextLoader.Column("Name", DataKind.String, 1),
}
}, new MultiFileSource(dataFile));
var pipe = new ImageLoadingEstimator(env, imageFolder, ("ImageReal", "ImagePath"))
.Append(new ImageResizingEstimator(env, "ImageReal", 100, 100, "ImageReal"))
.Append(new ImagePixelExtractingEstimator(env, "ImagePixels", "ImageReal"))
.Append(new ImageGrayscalingEstimator(env, ("ImageGray", "ImageReal")));
pipe.GetOutputSchema(SchemaShape.Create(data.Schema));
var model = pipe.Fit(data);
var tempPath = Path.GetTempFileName();
using (var file = new SimpleFileHandle(env, tempPath, true, true))
{
using (var fs = file.CreateWriteStream())
ML.Model.Save(model, null, fs);
ITransformer model2;
using (var fs = file.OpenReadStream())
model2 = ML.Model.Load(fs, out var schema);
var transformerChain = model2 as TransformerChain <ITransformer>;
Assert.NotNull(transformerChain);
var newCols = ((ImageLoadingTransformer)transformerChain.First()).Columns;
var oldCols = ((ImageLoadingTransformer)model.First()).Columns;
Assert.True(newCols
.Zip(oldCols, (x, y) => x == y)
.All(x => x));
}
Done();
}
public void TestEstimatorSaveLoad()
{
IHostEnvironment env = new MLContext();
var dataFile = GetDataPath("images/images.tsv");
var imageFolder = Path.GetDirectoryName(dataFile);
var data = TextLoader.Create(env, new TextLoader.Arguments()
{
Column = new[]
{
new TextLoader.Column("ImagePath", DataKind.TX, 0),
new TextLoader.Column("Name", DataKind.TX, 1),
}
}, new MultiFileSource(dataFile));
var pipe = new ImageLoadingEstimator(env, imageFolder, ("ImagePath", "ImageReal"))
.Append(new ImageResizingEstimator(env, "ImageReal", "ImageReal", 100, 100))
.Append(new ImagePixelExtractingEstimator(env, "ImageReal", "ImagePixels"))
.Append(new ImageGrayscalingEstimator(env, ("ImageReal", "ImageGray")));
pipe.GetOutputSchema(Core.Data.SchemaShape.Create(data.Schema));
var model = pipe.Fit(data);
var tempPath = Path.GetTempFileName();
using (var file = new SimpleFileHandle(env, tempPath, true, true))
{
using (var fs = file.CreateWriteStream())
model.SaveTo(env, fs);
var model2 = TransformerChain.LoadFrom(env, file.OpenReadStream());
var newCols = ((ImageLoaderTransform)model2.First()).Columns;
var oldCols = ((ImageLoaderTransform)model.First()).Columns;
Assert.True(newCols
.Zip(oldCols, (x, y) => x == y)
.All(x => x));
}
Done();
}
public void TestOnnxTransformSaveAndLoadWithCustomShapes()
{
// The loaded model has input shape [-1, 3] and output shape [-1].
var modelFile = Path.Combine(Directory.GetCurrentDirectory(), "unknowndimensions", "test_unknowndimensions_float.onnx");
var dataPoints = new InputWithCustomShape[]
{
// It's a flattened 3-by-3 tensor.
// [1.1, 1.3, 1.2]
// |1.9, 1.3, 1.2|
// [1.1, 1.3, 1.8]
new InputWithCustomShape()
{
input = new float[] { 1.1f, 1.3f, 1.2f, 1.9f, 1.3f, 1.2f, 1.1f, 1.3f, 1.8f }
},
// It's a flattened 3-by-3 tensor.
// [0, 0, 1]
// |1, 0, 0|
// [1, 0, 0]
new InputWithCustomShape()
{
input = new float[] { 0f, 0f, 1f, 1f, 0f, 0f, 1f, 0f, 0f }
}
};
var shapeDictionary = new Dictionary <string, int[]>()
{
{ nameof(InputWithCustomShape.input), new int[] { 3, 3 } }
};
var dataView = ML.Data.LoadFromEnumerable(dataPoints);
var pipeline = ML.Transforms.ApplyOnnxModel(nameof(PredictionWithCustomShape.argmax),
nameof(InputWithCustomShape.input), modelFile, shapeDictionary);
var model = pipeline.Fit(dataView);
// Save the trained ONNX transformer into file and then load it back.
ITransformer loadedModel = null;
var tempPath = Path.GetTempFileName();
using (var file = new SimpleFileHandle(Env, tempPath, true, true))
{
// Save.
using (var fs = file.CreateWriteStream())
ML.Model.Save(model, null, fs);
// Load.
using (var fs = file.OpenReadStream())
loadedModel = ML.Model.Load(fs, out var schema);
}
var transformedDataView = loadedModel.Transform(dataView);
// Conduct the same check for all the 3 called public APIs.
var transformedDataPoints = ML.Data.CreateEnumerable <PredictionWithCustomShape>(transformedDataView, false).ToList();
// One data point generates one transformed data point.
Assert.Equal(dataPoints.Count(), transformedDataPoints.Count);
// Check result numbers. They are results of applying ONNX argmax along the second axis; for example
// [1.1, 1.3, 1.2] ---> [1] because 1.3 (indexed by 1) is the largest element.
// |1.9, 1.3, 1.2| ---> |0| 1.9 0
// [1.1, 1.3, 1.8] ---> [2] 1.8 2
var expectedResults = new long[][]
{
new long[] { 1, 0, 2 },
new long[] { 2, 0, 0 }
};
for (int i = 0; i < transformedDataPoints.Count; ++i)
{
Assert.Equal(transformedDataPoints[i].argmax, expectedResults[i]);
}
(model as IDisposable)?.Dispose();
(loadedModel as IDisposable)?.Dispose();
}
public void TestSaveAndLoadDoubleTreeFeaturizer()
{
int dataPointCount = 200;
var data = SamplesUtils.DatasetUtils.GenerateFloatLabelFloatFeatureVectorSamples(dataPointCount).ToList();
var dataView = ML.Data.LoadFromEnumerable(data);
dataView = ML.Data.Cache(dataView);
var trainerOptions = new FastForestRegressionTrainer.Options
{
NumberOfThreads = 1,
NumberOfTrees = 10,
NumberOfLeaves = 4,
MinimumExampleCountPerLeaf = 10,
FeatureColumnName = "Features",
LabelColumnName = "Label"
};
// Trains tree featurization on "Features" and applies on "CopiedFeatures".
var options = new FastForestRegressionFeaturizationEstimator.Options()
{
InputColumnName = "CopiedFeatures",
TrainerOptions = trainerOptions,
TreesColumnName = "OhMyTrees",
LeavesColumnName = "OhMyLeaves",
PathsColumnName = "OhMyPaths"
};
var pipeline = ML.Transforms.CopyColumns("CopiedFeatures", "Features")
.Append(ML.Transforms.FeaturizeByFastForestRegression(options))
.Append(ML.Transforms.Concatenate("CombinedFeatures", "Features", "OhMyTrees", "OhMyLeaves", "OhMyPaths"))
.Append(ML.Regression.Trainers.Sdca("Label", "CombinedFeatures"));
var model = pipeline.Fit(dataView);
var prediction = model.Transform(dataView);
var metrics = ML.Regression.Evaluate(prediction);
Assert.True(metrics.MeanAbsoluteError < 0.25);
Assert.True(metrics.MeanSquaredError < 0.1);
// Save the trained model into file and then load it back.
ITransformer loadedModel = null;
var tempPath = Path.GetTempFileName();
using (var file = new SimpleFileHandle(Env, tempPath, true, true))
{
using (var fs = file.CreateWriteStream())
ML.Model.Save(model, null, fs);
using (var fs = file.OpenReadStream())
loadedModel = ML.Model.Load(fs, out var schema);
}
// Compute prediction using the loaded model.
var loadedPrediction = loadedModel.Transform(dataView);
var loadedMetrics = ML.Regression.Evaluate(loadedPrediction);
// Check if the loaded model produces the same result as the trained model.
Assert.Equal(metrics.MeanAbsoluteError, loadedMetrics.MeanAbsoluteError);
Assert.Equal(metrics.MeanSquaredError, loadedMetrics.MeanSquaredError);
var secondPipeline = ML.Transforms.CopyColumns("CopiedFeatures", "Features")
.Append(ML.Transforms.NormalizeBinning("CopiedFeatures"))
.Append(ML.Transforms.FeaturizeByFastForestRegression(options))
.Append(ML.Transforms.Concatenate("CombinedFeatures", "Features", "OhMyTrees", "OhMyLeaves", "OhMyPaths"))
.Append(ML.Regression.Trainers.Sdca("Label", "CombinedFeatures"));
var secondModel = secondPipeline.Fit(dataView);
var secondPrediction = secondModel.Transform(dataView);
var secondMetrics = ML.Regression.Evaluate(secondPrediction);
// The second pipeline trains a tree featurizer on a bin-based normalized feature, so the second pipeline
// is different from the first pipeline.
Assert.NotEqual(metrics.MeanAbsoluteError, secondMetrics.MeanAbsoluteError);
Assert.NotEqual(metrics.MeanSquaredError, secondMetrics.MeanSquaredError);
}
private void RunCore(IChannel ch, string cmd)
{
Host.AssertValue(ch);
Host.AssertNonEmpty(cmd);
ch.Trace("Constructing trainer");
ITrainer trainer = Args.Trainer.CreateComponent(Host);
IPredictor inputPredictor = null;
if (Args.ContinueTrain && !TrainUtils.TryLoadPredictor(ch, Host, Args.InputModelFile, out inputPredictor))
{
ch.Warning("No input model file specified or model file did not contain a predictor. The model state cannot be initialized.");
}
ch.Trace("Constructing the training pipeline");
IDataView trainPipe = CreateLoader();
ISchema schema = trainPipe.Schema;
string label = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.LabelColumn),
Args.LabelColumn, DefaultColumnNames.Label);
string features = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.FeatureColumn),
Args.FeatureColumn, DefaultColumnNames.Features);
string group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.GroupColumn),
Args.GroupColumn, DefaultColumnNames.GroupId);
string weight = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.WeightColumn),
Args.WeightColumn, DefaultColumnNames.Weight);
string name = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.NameColumn),
Args.NameColumn, DefaultColumnNames.Name);
TrainUtils.AddNormalizerIfNeeded(Host, ch, trainer, ref trainPipe, features, Args.NormalizeFeatures);
ch.Trace("Binding columns");
var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, Args.CustomColumn);
var data = new RoleMappedData(trainPipe, label, features, group, weight, name, customCols);
RoleMappedData validData = null;
if (!string.IsNullOrWhiteSpace(Args.ValidationFile))
{
if (!trainer.Info.SupportsValidation)
{
ch.Warning("Ignoring validationFile: Trainer does not accept validation dataset.");
}
else
{
ch.Trace("Constructing the validation pipeline");
IDataView validPipe = CreateRawLoader(dataFile: Args.ValidationFile);
validPipe = ApplyTransformUtils.ApplyAllTransformsToData(Host, trainPipe, validPipe);
validData = new RoleMappedData(validPipe, data.Schema.GetColumnRoleNames());
}
}
// In addition to the training set, some trainers can accept two data sets, validation set and test set,
// in training phase. The major difference between validation set and test set is that training process may
// indirectly use validation set to improve the model but the learned model should totally independent of test set.
// Similar to validation set, the trainer can report the scores computed using test set.
RoleMappedData testDataUsedInTrainer = null;
if (!string.IsNullOrWhiteSpace(Args.TestFile))
{
// In contrast to the if-else block for validation above, we do not throw a warning if test file is provided
// because this is TrainTest command.
if (trainer.Info.SupportsTest)
{
ch.Trace("Constructing the test pipeline");
IDataView testPipeUsedInTrainer = CreateRawLoader(dataFile: Args.TestFile);
testPipeUsedInTrainer = ApplyTransformUtils.ApplyAllTransformsToData(Host, trainPipe, testPipeUsedInTrainer);
testDataUsedInTrainer = new RoleMappedData(testPipeUsedInTrainer, data.Schema.GetColumnRoleNames());
}
}
var predictor = TrainUtils.Train(Host, ch, data, trainer, validData,
Args.Calibrator, Args.MaxCalibrationExamples, Args.CacheData, inputPredictor, testDataUsedInTrainer);
IDataLoader testPipe;
bool hasOutfile = !string.IsNullOrEmpty(Args.OutputModelFile);
var tempFilePath = hasOutfile ? null : Path.GetTempFileName();
using (var file = new SimpleFileHandle(ch, hasOutfile ? Args.OutputModelFile : tempFilePath, true, !hasOutfile))
{
TrainUtils.SaveModel(Host, ch, file, predictor, data, cmd);
ch.Trace("Constructing the testing pipeline");
using (var stream = file.OpenReadStream())
using (var rep = RepositoryReader.Open(stream, ch))
testPipe = LoadLoader(rep, Args.TestFile, true);
}
// Score.
ch.Trace("Scoring and evaluating");
ch.Assert(Args.Scorer == null || Args.Scorer is ICommandLineComponentFactory, "TrainTestCommand should only be used from the command line.");
IDataScorerTransform scorePipe = ScoreUtils.GetScorer(Args.Scorer, predictor, testPipe, features, group, customCols, Host, data.Schema);
// Evaluate.
var evaluator = Args.Evaluator?.CreateComponent(Host) ??
EvaluateUtils.GetEvaluator(Host, scorePipe.Schema);
var dataEval = new RoleMappedData(scorePipe, label, features,
group, weight, name, customCols, opt: true);
var metrics = evaluator.Evaluate(dataEval);
MetricWriter.PrintWarnings(ch, metrics);
evaluator.PrintFoldResults(ch, metrics);
if (!metrics.TryGetValue(MetricKinds.OverallMetrics, out var overall))
{
throw ch.Except("No overall metrics found");
}
overall = evaluator.GetOverallResults(overall);
MetricWriter.PrintOverallMetrics(Host, ch, Args.SummaryFilename, overall, 1);
evaluator.PrintAdditionalMetrics(ch, metrics);
Dictionary <string, IDataView>[] metricValues = { metrics };
SendTelemetryMetric(metricValues);
if (!string.IsNullOrWhiteSpace(Args.OutputDataFile))
{
var perInst = evaluator.GetPerInstanceMetrics(dataEval);
var perInstData = new RoleMappedData(perInst, label, null, group, weight, name, customCols);
var idv = evaluator.GetPerInstanceDataViewToSave(perInstData);
MetricWriter.SavePerInstance(Host, ch, Args.OutputDataFile, idv);
}
}