/// <summary>
/// Performs image classification using transfer learning.
/// usage of this API requires additional NuGet dependencies on TensorFlow redist, see linked document for more information.
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </summary>
/// <param name="catalog"></param>
/// <param name="featuresColumnName">The name of the input features column.</param>
/// <param name="labelColumnName">The name of the labels column.</param>
/// <param name="scoreColumnName">The name of the output score column.</param>
/// <param name="predictedLabelColumnName">The name of the output predicted label columns.</param>
/// <param name="validationSet">Validation set.</param>
public static ImageClassificationEstimator ImageClassification(
this ModelOperationsCatalog catalog,
string featuresColumnName,
string labelColumnName,
string scoreColumnName = "Score",
string predictedLabelColumnName = "PredictedLabel",
IDataView validationSet = null
)
{
var options = new ImageClassificationEstimator.Options()
{
FeaturesColumnName = featuresColumnName,
LabelColumnName = labelColumnName,
ScoreColumnName = scoreColumnName,
PredictedLabelColumnName = predictedLabelColumnName,
ValidationSet = validationSet
};
return(ImageClassification(catalog, options));
}
public TransformerChain <KeyToValueMappingTransformer> TrainResnetV250()
{
var options = new ImageClassificationEstimator.Options()
{
FeaturesColumnName = "Image",
LabelColumnName = "Label",
Arch = ImageClassificationEstimator.Architecture.ResnetV250,
Epoch = 50,
BatchSize = 10,
LearningRate = 0.01f,
EarlyStoppingCriteria = new ImageClassificationEstimator.EarlyStopping(minDelta: 0.001f, patience: 20, metric: ImageClassificationEstimator.EarlyStoppingMetric.Loss),
ValidationSet = testDataset,
ModelSavePath = assetsPath,
DisableEarlyStopping = true
};
var pipeline = mlContext.Model.ImageClassification(options)
.Append(mlContext.Transforms.Conversion.MapKeyToValue(
outputColumnName: "PredictedLabel",
inputColumnName: "PredictedLabel"));
return(pipeline.Fit(trainDataset));
}
public static void Example()
{
string assetsRelativePath = @"../../../assets";
string assetsPath = GetAbsolutePath(assetsRelativePath);
var outputMlNetModelFilePath = Path.Combine(assetsPath, "outputs",
"imageClassifier.zip");
string imagesDownloadFolderPath = Path.Combine(assetsPath, "inputs",
"images");
//Download the image set and unzip
string finalImagesFolderName = DownloadImageSet(
imagesDownloadFolderPath);
string fullImagesetFolderPath = Path.Combine(
imagesDownloadFolderPath, finalImagesFolderName);
try
{
MLContext mlContext = new MLContext(seed: 1);
//Load all the original images info
IEnumerable <ImageData> images = LoadImagesFromDirectory(
folder: fullImagesetFolderPath, useFolderNameAsLabel: true);
IDataView shuffledFullImagesDataset = mlContext.Data.ShuffleRows(
mlContext.Data.LoadFromEnumerable(images));
shuffledFullImagesDataset = mlContext.Transforms.Conversion
.MapValueToKey("Label")
.Append(mlContext.Transforms.LoadImages("Image",
fullImagesetFolderPath, false, "ImagePath"))
.Fit(shuffledFullImagesDataset)
.Transform(shuffledFullImagesDataset);
// Split the data 90:10 into train and test sets, train and
// evaluate.
TrainTestData trainTestData = mlContext.Data.TrainTestSplit(
shuffledFullImagesDataset, testFraction: 0.1, seed: 1);
IDataView trainDataset = trainTestData.TrainSet;
IDataView testDataset = trainTestData.TestSet;
var options = new ImageClassificationEstimator.Options()
{
FeaturesColumnName = "Image",
LabelColumnName = "Label",
// Just by changing/selecting InceptionV3/MobilenetV2/ResnetV250 here instead of
// ResnetV2101 you can try a different architecture/
// pre-trained model.
Arch = ImageClassificationEstimator.Architecture.ResnetV2101,
Epoch = 50,
BatchSize = 10,
LearningRate = 0.01f,
MetricsCallback = (metrics) => Console.WriteLine(metrics),
ValidationSet = testDataset,
DisableEarlyStopping = true
};
var pipeline = mlContext.Model.ImageClassification(options)
.Append(mlContext.Transforms.Conversion.MapKeyToValue(
outputColumnName: "PredictedLabel",
inputColumnName: "PredictedLabel"));
Console.WriteLine("*** Training the image classification model " +
"with DNN Transfer Learning on top of the selected " +
"pre-trained model/architecture ***");
// Measuring training time
var watch = System.Diagnostics.Stopwatch.StartNew();
var trainedModel = pipeline.Fit(trainDataset);
watch.Stop();
long elapsedMs = watch.ElapsedMilliseconds;
Console.WriteLine("Training with transfer learning took: " +
(elapsedMs / 1000).ToString() + " seconds");
mlContext.Model.Save(trainedModel, shuffledFullImagesDataset.Schema,
"model.zip");
ITransformer loadedModel;
DataViewSchema schema;
using (var file = File.OpenRead("model.zip"))
loadedModel = mlContext.Model.Load(file, out schema);
EvaluateModel(mlContext, testDataset, loadedModel);
watch = System.Diagnostics.Stopwatch.StartNew();
// Predict image class using an in-memory image.
TrySinglePrediction(fullImagesetFolderPath, mlContext, loadedModel);
watch.Stop();
elapsedMs = watch.ElapsedMilliseconds;
Console.WriteLine("Prediction engine took: " +
(elapsedMs / 1000).ToString() + " seconds");
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
Console.WriteLine("Press any key to finish");
Console.ReadKey();
}
public static void Example()
{
string assetsRelativePath = @"../../../assets";
string assetsPath = GetAbsolutePath(assetsRelativePath);
var outputMlNetModelFilePath = Path.Combine(assetsPath, "outputs",
"imageClassifier.zip");
string imagesDownloadFolderPath = Path.Combine(assetsPath, "inputs",
"images");
// Download Cifar Dataset.
string finalImagesFolderName = DownloadImageSet(
imagesDownloadFolderPath);
string finalImagesFolderNameTrain = "cifar\\train";
string fullImagesetFolderPathTrain = Path.Combine(
imagesDownloadFolderPath, finalImagesFolderNameTrain);
string finalImagesFolderNameTest = "cifar\\test";
string fullImagesetFolderPathTest = Path.Combine(
imagesDownloadFolderPath, finalImagesFolderNameTest);
try
{
MLContext mlContext = new MLContext(seed: 1);
//Load all the original train images info
IEnumerable <ImageData> train_images = LoadImagesFromDirectory(
folder: fullImagesetFolderPathTrain, useFolderNameAsLabel: true);
IDataView trainDataset = mlContext.Data.LoadFromEnumerable(train_images);
trainDataset = mlContext.Transforms.Conversion
.MapValueToKey("Label")
.Append(mlContext.Transforms.LoadImages("Image",
fullImagesetFolderPathTrain, false, "ImagePath"))
.Fit(trainDataset)
.Transform(trainDataset);
//Load all the original test images info
IEnumerable <ImageData> test_images = LoadImagesFromDirectory(
folder: fullImagesetFolderPathTest, useFolderNameAsLabel: true);
IDataView testDataset = mlContext.Data.LoadFromEnumerable(test_images);
testDataset = mlContext.Transforms.Conversion
.MapValueToKey("Label")
.Append(mlContext.Transforms.LoadImages("Image",
fullImagesetFolderPathTest, false, "ImagePath"))
.Fit(testDataset)
.Transform(testDataset);
var options = new ImageClassificationEstimator.Options()
{
FeaturesColumnName = "Image",
LabelColumnName = "Label",
// Just by changing/selecting InceptionV3/MobilenetV2 here instead of
// ResnetV2101 you can try a different architecture/
// pre-trained model.
Arch = ImageClassificationEstimator.Architecture.ResnetV2101,
Epoch = 182,
BatchSize = 128,
LearningRate = 0.01f,
MetricsCallback = (metrics) => Console.WriteLine(metrics),
ValidationSet = testDataset,
DisableEarlyStopping = true,
ReuseValidationSetBottleneckCachedValues = false,
ReuseTrainSetBottleneckCachedValues = false,
// Use linear scaling rule and Learning rate decay as an option
// This is known to do well for Cifar dataset and Resnet models
// You can also try other types of Learning rate scheduling methods
// available in LearningRateScheduler.cs
LearningRateScheduler = new LsrDecay()
};
var pipeline = mlContext.Model.ImageClassification(options)
.Append(mlContext.Transforms.Conversion.MapKeyToValue(
outputColumnName: "PredictedLabel",
inputColumnName: "PredictedLabel"));
Console.WriteLine("*** Training the image classification model " +
"with DNN Transfer Learning on top of the selected " +
"pre-trained model/architecture ***");
// Measuring training time
var watch = System.Diagnostics.Stopwatch.StartNew();
var trainedModel = pipeline.Fit(trainDataset);
watch.Stop();
long elapsedMs = watch.ElapsedMilliseconds;
Console.WriteLine("Training with transfer learning took: " +
(elapsedMs / 1000).ToString() + " seconds");
mlContext.Model.Save(trainedModel, testDataset.Schema,
"model.zip");
ITransformer loadedModel;
DataViewSchema schema;
using (var file = File.OpenRead("model.zip"))
loadedModel = mlContext.Model.Load(file, out schema);
EvaluateModel(mlContext, testDataset, loadedModel);
watch = System.Diagnostics.Stopwatch.StartNew();
// Predict image class using an in-memory image.
TrySinglePrediction(fullImagesetFolderPathTest, mlContext, loadedModel);
watch.Stop();
elapsedMs = watch.ElapsedMilliseconds;
Console.WriteLine("Prediction engine took: " +
(elapsedMs / 1000).ToString() + " seconds");
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
Console.WriteLine("Press any key to finish");
Console.ReadKey();
}
