public void AutoFitImageClassificationTrainTest()
{
var context = new MLContext();
var datasetPath = DatasetUtil.GetFlowersDataset();
var columnInference = context.Auto().InferColumns(datasetPath, "Label");
var textLoader = context.Data.CreateTextLoader(columnInference.TextLoaderOptions);
var trainData = context.Data.ShuffleRows(textLoader.Load(datasetPath), seed: 1);
var originalColumnNames = trainData.Schema.Select(c => c.Name);
TrainTestData trainTestData = context.Data.TrainTestSplit(trainData, testFraction: 0.2, seed: 1);
IDataView trainDataset = SplitUtil.DropAllColumnsExcept(context, trainTestData.TrainSet, originalColumnNames);
IDataView testDataset = SplitUtil.DropAllColumnsExcept(context, trainTestData.TestSet, originalColumnNames);
var result = context.Auto()
.CreateMulticlassClassificationExperiment(0)
.Execute(trainDataset, testDataset, columnInference.ColumnInformation);
//Known issue, where on Ubuntu there is degradation in accuracy.
if (!(RuntimeInformation.IsOSPlatform(OSPlatform.Windows) ||
RuntimeInformation.IsOSPlatform(OSPlatform.OSX)))
{
Assert.Equal(0.778, result.BestRun.ValidationMetrics.MicroAccuracy, 3);
}
else
{
Assert.Equal(1, result.BestRun.ValidationMetrics.MicroAccuracy, 3);
}
var scoredData = result.BestRun.Model.Transform(trainData);
Assert.Equal(TextDataViewType.Instance, scoredData.Schema[DefaultColumnNames.PredictedLabel].Type);
}
public void AutoFitContextLogTest()
{
// This test confirms that logs produced from contexts made during AutoML experiment
// runs are correctly relayed to the main Experiment MLContext.
_markerAutoFitContextLogTest = false;
var context = new MLContext(1);
context.Log += MlContextLog;
var datasetPath = DatasetUtil.GetFlowersDataset();
var columnInference = context.Auto().InferColumns(datasetPath, "Label");
var textLoader = context.Data.CreateTextLoader(columnInference.TextLoaderOptions);
var trainData = textLoader.Load(datasetPath);
var result = context.Auto()
.CreateMulticlassClassificationExperiment(15)
.Execute(trainData, columnInference.ColumnInformation);
Assert.True(_markerAutoFitContextLogTest, "Image classification trainer logs from Experiment's sub contexts" +
"were not relayed to the main MLContext.");
}
public void AutoFitImageClassification()
{
// This test executes the code path that model builder code will take to get a model using image
// classification API.
var context = new MLContext(1);
context.Log += Context_Log;
var datasetPath = DatasetUtil.GetFlowersDataset();
var columnInference = context.Auto().InferColumns(datasetPath, "Label");
var textLoader = context.Data.CreateTextLoader(columnInference.TextLoaderOptions);
var trainData = textLoader.Load(datasetPath);
var result = context.Auto()
.CreateMulticlassClassificationExperiment(0)
.Execute(trainData, columnInference.ColumnInformation);
Assert.InRange(result.BestRun.ValidationMetrics.MicroAccuracy, 0.80, 0.9);
var scoredData = result.BestRun.Model.Transform(trainData);
Assert.Equal(TextDataViewType.Instance, scoredData.Schema[DefaultColumnNames.PredictedLabel].Type);
}
