/// <summary>
/// 学習開始
/// </summary>
/// <param name="batchSize"></param>
/// <param name="epoch"></param>
/// <param name="architecture"></param>
/// <returns></returns>
public Task Run(string batchSize, string epoch, string architecture)
{
var task = Task.Factory.StartNew(() =>
{
ImageClassificationTrainer.Architecture arch = GetArchitecture(architecture);
var classifierOptions = new ImageClassificationTrainer.Options()
{
FeatureColumnName = "Image",
LabelColumnName = "LabelAsKey",
ValidationSet = validationSet,
Arch = arch,
MetricsCallback = (metrics) => LearningCallBack(metrics),
TestOnTrainSet = false,
WorkspacePath = workspaceRelativePath
};
var trainingPipeline = mlContext.MulticlassClassification.Trainers.ImageClassification(classifierOptions)
.Append(mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
ITransformer trainedModel = trainingPipeline.Fit(trainSet);
});
return(task);
}
public static IEstimator <ITransformer> BuildTrainingPipeline(MLContext mlContext, ImageClassificationTrainer.Architecture architecture)
{
// Data process configuration with pipeline data transformations
var dataProcessPipeline = mlContext.Transforms.Conversion.MapValueToKey("Label", "Label")
.Append(mlContext.Transforms.LoadRawImageBytes("ImageSourceTemp", null, "ImageSource"))
.Append(mlContext.Transforms.CopyColumns("Features", "ImageSourceTemp"));
// Set the training algorithm
var trainer = mlContext.MulticlassClassification.Trainers.ImageClassification(
new ImageClassificationTrainer.Options()
{
Arch = architecture,
LabelColumnName = "Label",
FeatureColumnName = "Features"
}).Append(mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel", "PredictedLabel"));
var trainingPipeline = dataProcessPipeline.Append(trainer);
return(trainingPipeline);
}
public static void CreateModel(string savePath, string modelName, IEnumerable <ModelInput> images, ImageClassificationTrainer.Architecture architecture)
{
// Load Data
IDataView trainingDataView = mlContext.Data.LoadFromEnumerable(images);
// Build training pipeline
IEstimator <ITransformer> trainingPipeline = BuildTrainingPipeline(mlContext, architecture);
// Train Model
ITransformer mlModel = TrainModel(mlContext, trainingDataView, trainingPipeline);
// Evaluate quality of Model
Evaluate(mlContext, trainingDataView, trainingPipeline, savePath + $"\\{modelName}_log.txt");
// Save model
SaveModel(mlContext, mlModel, savePath + $"\\{modelName}.zip", trainingDataView.Schema);
}
private static ITransformer TrainModel(MLContext mlContext, IDataView dataView, string dataSetDir, ImageClassificationTrainer.Architecture architecture, int epochs, double testFraction)
{
IDataView shuffledData = mlContext.Data.ShuffleRows(dataView);
var preprocessingPipeline = mlContext.Transforms.Conversion.MapValueToKey(inputColumnName: "Label",
outputColumnName: "LabelKey")
.Append(mlContext.Transforms.LoadRawImageBytes(outputColumnName: "Img",
imageFolder: dataSetDir,
inputColumnName: "ImgPath")); // > InputData.cs
IDataView preProcData = preprocessingPipeline.Fit(shuffledData).Transform(shuffledData);
DataOperationsCatalog.TrainTestData trainSplit = mlContext.Data.TrainTestSplit(data: preProcData, testFraction: testFraction);
DataOperationsCatalog.TrainTestData validationTestSplit = mlContext.Data.TrainTestSplit(trainSplit.TestSet);
IDataView trainSet = trainSplit.TrainSet;
IDataView validationSet = validationTestSplit.TrainSet;
IDataView testSet = validationTestSplit.TestSet;
var classifierOptions = new ImageClassificationTrainer.Options
{
FeatureColumnName = "Img",
LabelColumnName = "LabelKey",
ValidationSet = validationSet,
Arch = architecture,
MetricsCallback = metrics => Console.WriteLine(metrics),
TestOnTrainSet = false,
ReuseTrainSetBottleneckCachedValues = true,
ReuseValidationSetBottleneckCachedValues = true,
Epoch = epochs,
};
var trainingPipeline = mlContext.MulticlassClassification.Trainers.ImageClassification(classifierOptions)
.Append(mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
return(trainingPipeline.Fit(trainSet));
}
public GpuSupportedModelRetrainStrategy(ImageClassificationTrainer.Architecture architecture, ILogger logger)
{
_architecture = architecture;
_logger = logger;
}
static (ITransformer mlModel, IReadOnlyList <TrainCatalogBase.CrossValidationResult <MulticlassClassificationMetrics> > evaluation) TrainModel(ImageClassificationTrainer.Architecture architecture, int epoch)
{
// To suppress errors from the TensorFlow library, set $env:TF_CPP_MIN_LOG_LEVEL = 2
var inputs = new List <ModelInput>();
foreach (var subDir in Directory.GetDirectories(inputDataDirectoryPath))
{
foreach (var file in Directory.GetFiles(subDir))
{
inputs.Add(new ModelInput()
{
Label = subDir.Split("\\").Last(), ImageSource = file
});
}
}
var trainingDataView = mlContext.Data.LoadFromEnumerable <ModelInput>(inputs);
var dataProcessPipeline = mlContext.Transforms.Conversion.MapValueToKey("Label", "Label")
.Append(mlContext.Transforms.LoadRawImageBytes("ImageSource_featurized", null, "ImageSource"))
.Append(mlContext.Transforms.CopyColumns("Features", "ImageSource_featurized"));
var trainer = mlContext.MulticlassClassification.Trainers.ImageClassification(
new ImageClassificationTrainer.Options()
{
Arch = architecture,
Epoch = epoch,
FeatureColumnName = "Features",
LabelColumnName = "Label",
})
.Append(mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel", "PredictedLabel"));
IEstimator <ITransformer> trainingPipeline = dataProcessPipeline.Append(trainer);
var mlModel = trainingPipeline.Fit(trainingDataView);
var evaluation = mlContext.MulticlassClassification.CrossValidate(trainingDataView, trainingPipeline, numberOfFolds: 5, labelColumnName: "Label");
return(mlModel, evaluation);
}
