/// <summary>
/// The main applicaton entry point.
/// </summary>
/// <param name="args">The command line arguments.</param>
public static void Main(string[] args)
{
// set up a machine learning context
var context = new MLContext();
// load training and test data
Console.WriteLine("Loading data...");
var data = context.Data.LoadFromTextFile <HeartData>(dataPath, hasHeader: false, separatorChar: ',');
// split the data into a training and test partition
var partitions = context.Data.TrainTestSplit(data, testFraction: 0.4);
// load training and testing data
var training = context.Data.CreateEnumerable <HeartData>(partitions.TrainSet, reuseRowObject: false);
var testing = context.Data.CreateEnumerable <HeartData>(partitions.TestSet, reuseRowObject: false);
// set up data arrays
var training_data = training.Select(v => v.GetFeatures()).ToArray();
var training_labels = training.Select(v => v.GetLabel()).ToArray();
var testing_data = testing.Select(v => v.GetFeatures()).ToArray();
var testing_labels = testing.Select(v => v.GetLabel()).ToArray();
// build features and labels
var features = NetUtil.Var(new int[] { 7 }, DataType.Float);
var labels = NetUtil.Var(new int[] { 1 }, DataType.Float);
// build the network
var network = features
.Dense(16, CNTKLib.ReLU)
.Dense(128, CNTKLib.ReLU)
.Dense(1, CNTKLib.Sigmoid)
.ToNetwork();
Console.WriteLine("Model architecture:");
Console.WriteLine(network.ToSummary());
// set up the loss function and the classification error function
var lossFunc = CNTKLib.BinaryCrossEntropy(network.Output, labels);
var errorFunc = NetUtil.BinaryClassificationError(network.Output, labels);
// use the Adam learning algorithm
var learner = network.GetAdamLearner(
learningRateSchedule: (0.001, 1),
momentumSchedule: (0.9, 1),
unitGain: true);
// set up a trainer and an evaluator
var trainer = network.GetTrainer(learner, lossFunc, errorFunc);
var evaluator = network.GetEvaluator(errorFunc);
// train the model
Console.WriteLine("Epoch\tTrain\tTrain\tTest");
Console.WriteLine("\tLoss\tError\tError");
Console.WriteLine("-----------------------------");
var maxEpochs = 100;
var batchSize = 1;
var loss = new double[maxEpochs];
var trainingError = new double[maxEpochs];
var testingError = new double[maxEpochs];
var batchCount = 0;
for (int epoch = 0; epoch < maxEpochs; epoch++)
{
// train one epoch on batches
loss[epoch] = 0.0;
trainingError[epoch] = 0.0;
batchCount = 0;
training_data.Index().Shuffle().Batch(batchSize, (indices, begin, end) =>
{
// get the current batch
var featureBatch = features.GetBatch(training_data, indices, begin, end);
var labelBatch = labels.GetBatch(training_labels, indices, begin, end);
// train the network on the batch
var result = trainer.TrainBatch(
new[] {
(features, featureBatch),
(labels, labelBatch)
},
/// <summary>
/// The main program entry point.
/// </summary>
/// <param name="args">The command line parameters.</param>
static void Main(string[] args)
{
// check the compute device
Console.WriteLine("Checking compute device...");
Console.WriteLine($" Using: {NetUtil.CurrentDevice.AsString()}");
// unpack archive
Console.WriteLine("Unpacking archive...");
if (!File.Exists("x_train_imdb.bin"))
{
ZipFile.ExtractToDirectory("imdb_data.zip", ".");
}
// load training and test data
Console.WriteLine("Loading data files...");
var sequenceLength = 500;
var training_data = DataUtil.LoadBinary <float>("x_train_imdb.bin", 25000, sequenceLength);
var training_labels = DataUtil.LoadBinary <float>("y_train_imdb.bin", 25000);
var testing_data = DataUtil.LoadBinary <float>("x_test_imdb.bin", 25000, sequenceLength);
var testing_labels = DataUtil.LoadBinary <float>("y_test_imdb.bin", 25000);
Console.WriteLine($" Records for training: {training_data.Length}");
Console.WriteLine($" Records for testing: {testing_data.Length}");
// build features and labels
var features = NetUtil.Var(new int[] { 1 }, CNTK.DataType.Float);
var labels = NetUtil.Var(new int[] { 1 }, CNTK.DataType.Float,
dynamicAxes: new List <CNTK.Axis>()
{
CNTK.Axis.DefaultBatchAxis()
});
// build the network
var lstmUnits = 32;
var network = features
.OneHotOp(10000, true)
.Embedding(32)
.LSTM(lstmUnits, lstmUnits)
.Dense(1, CNTKLib.Sigmoid)
.ToNetwork();
Console.WriteLine("Model architecture:");
Console.WriteLine(network.ToSummary());
// set up the loss function and the classification error function
var lossFunc = CNTKLib.BinaryCrossEntropy(network.Output, labels);
var errorFunc = NetUtil.BinaryClassificationError(network.Output, labels);
// use the Adam learning algorithm
var learner = network.GetAdamLearner(
learningRateSchedule: (0.001, 1),
momentumSchedule: (0.9, 1),
unitGain: true);
// set up a trainer and an evaluator
var trainer = network.GetTrainer(learner, lossFunc, errorFunc);
var evaluator = network.GetEvaluator(errorFunc);
// train the model
Console.WriteLine("Epoch\tTrain\tTrain\tTest");
Console.WriteLine("\tLoss\tError\tError");
Console.WriteLine("-----------------------------");
var maxEpochs = 10;
var batchSize = 128;
var loss = new double[maxEpochs];
var trainingError = new double[maxEpochs];
var testingError = new double[maxEpochs];
var batchCount = 0;
for (int epoch = 0; epoch < maxEpochs; epoch++)
{
// train one epoch on batches
loss[epoch] = 0.0;
trainingError[epoch] = 0.0;
batchCount = 0;
training_data.Batch(batchSize, (data, begin, end) =>
{
// get the current batch
var featureBatch = features.GetSequenceBatch(sequenceLength, training_data, begin, end);
var labelBatch = labels.GetBatch(training_labels, begin, end);
// train the network on the batch
var result = trainer.TrainBatch(
new[] {
(features, featureBatch),
(labels, labelBatch)
},
/// <summary>
/// The main program entry point.
/// </summary>
/// <param name="args">The command line parameters.</param>
static void Main(string[] args)
{
// set up a machine learning context
var context = new MLContext();
// load the spam dataset in memory
Console.WriteLine("Loading data...");
var data = context.Data.LoadFromTextFile <SpamData>(
path: dataPath,
hasHeader: true,
separatorChar: '\t');
// use 80% for training and 20% for testing
var partitions = context.Data.TrainTestSplit(data, testFraction: 0.3);
// set up a pipeline to featurize the text
Console.WriteLine("Featurizing text...");
var pipeline = context.Transforms.Text.FeaturizeText(
outputColumnName: "Features",
inputColumnName: nameof(SpamData.Message));
// create a model
var model = pipeline.Fit(partitions.TrainSet);
// create training and testing datasets
var trainingData = model.Transform(partitions.TrainSet);
var testingData = model.Transform(partitions.TestSet);
// create training and testing enumerations
var training = context.Data.CreateEnumerable <ProcessedData>(trainingData, reuseRowObject: false);
var testing = context.Data.CreateEnumerable <ProcessedData>(testingData, reuseRowObject: false);
// set up data arrays
var training_data = training.Select(v => v.GetFeatures()).ToArray();
var training_labels = training.Select(v => v.GetLabel()).ToArray();
var testing_data = testing.Select(v => v.GetFeatures()).ToArray();
var testing_labels = testing.Select(v => v.GetLabel()).ToArray();
// report shape of dataset
var nodeCount = training_data.First().Length;
Console.WriteLine($" Embedded text data in {nodeCount} dimensions");
// build features and labels
var features = NetUtil.Var(new int[] { nodeCount }, DataType.Float);
var labels = NetUtil.Var(new int[] { 1 }, DataType.Float);
// build the network
var network = features
.Dense(16, CNTKLib.ReLU)
.Dense(16, CNTKLib.ReLU)
.Dense(1, CNTKLib.Sigmoid)
.ToNetwork();
Console.WriteLine("Model architecture:");
Console.WriteLine(network.ToSummary());
// set up the loss function and the classification error function
var lossFunc = CNTKLib.BinaryCrossEntropy(network.Output, labels);
var errorFunc = NetUtil.BinaryClassificationError(network.Output, labels);
// use the Adam learning algorithm
var learner = network.GetAdamLearner(
learningRateSchedule: (0.001, 1),
momentumSchedule: (0.9, 1),
unitGain: true);
// set up a trainer and an evaluator
var trainer = network.GetTrainer(learner, lossFunc, errorFunc);
var evaluator = network.GetEvaluator(errorFunc);
// train the model
Console.WriteLine("Epoch\tTrain\tTrain\tTest");
Console.WriteLine("\tLoss\tError\tError");
Console.WriteLine("-----------------------------");
var maxEpochs = 10;
var batchSize = 64;
var loss = new double[maxEpochs];
var trainingError = new double[maxEpochs];
var testingError = new double[maxEpochs];
var batchCount = 0;
for (int epoch = 0; epoch < maxEpochs; epoch++)
{
// train one epoch on batches
loss[epoch] = 0.0;
trainingError[epoch] = 0.0;
batchCount = 0;
training_data.Index().Shuffle().Batch(batchSize, (indices, begin, end) =>
{
// get the current batch
var featureBatch = features.GetBatch(training_data, indices, begin, end);
var labelBatch = labels.GetBatch(training_labels, indices, begin, end);
// train the network on the batch
var result = trainer.TrainBatch(
new[] {
(features, featureBatch),
(labels, labelBatch)
},