/// <summary>
/// Create a MNIST trainer (writing recognition) will be added to an environemnt.
/// </summary>
/// <param name="sigma">The sigma environemnt this trainer will be assigned to.</param>
/// <returns>The newly created trainer.</returns>
private static ITrainer CreateMnistTrainer(SigmaEnvironment sigma)
{
ByteRecordReader mnistImageReader = new ByteRecordReader(headerLengthBytes: 16, recordSizeBytes: 28 * 28, source: new CompressedSource(new MultiSource(new FileSource("train-images-idx3-ubyte.gz"), new UrlSource("http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz"))));
IRecordExtractor mnistImageExtractor = mnistImageReader.Extractor("inputs", new[] { 0L, 0L }, new[] { 28L, 28L }).Preprocess(new NormalisingPreprocessor(0, 255));
ByteRecordReader mnistTargetReader = new ByteRecordReader(headerLengthBytes: 8, recordSizeBytes: 1, source: new CompressedSource(new MultiSource(new FileSource("train-labels-idx1-ubyte.gz"), new UrlSource("http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz"))));
IRecordExtractor mnistTargetExtractor = mnistTargetReader.Extractor("targets", new[] { 0L }, new[] { 1L }).Preprocess(new OneHotPreprocessor(minValue: 0, maxValue: 9));
IDataset dataset = new Dataset("mnist-training", Dataset.BlockSizeAuto, mnistImageExtractor, mnistTargetExtractor);
ITrainer trainer = sigma.CreateTrainer("test");
trainer.Network = new Network
{
Architecture = InputLayer.Construct(28, 28)
+ 2 * FullyConnectedLayer.Construct(28 * 28)
+ FullyConnectedLayer.Construct(10)
+ OutputLayer.Construct(10)
+ SoftMaxCrossEntropyCostLayer.Construct()
};
trainer.TrainingDataIterator = new MinibatchIterator(8, dataset);
trainer.Optimiser = new AdagradOptimiser(baseLearningRate: 0.02);
trainer.Operator = new CpuSinglethreadedOperator();
trainer.AddInitialiser("*.weights", new GaussianInitialiser(standardDeviation: 0.05f));
trainer.AddInitialiser("*.bias*", new GaussianInitialiser(standardDeviation: 0.01f, mean: 0.03f));
trainer.AddGlobalHook(new CurrentEpochIterationReporter(TimeStep.Every(1, TimeScale.Iteration)));
return(trainer);
}
private static void SampleLoadExtractIterate()
{
SigmaEnvironment sigma = SigmaEnvironment.Create("test");
sigma.Prepare();
//var irisReader = new CsvRecordReader(new MultiSource(new FileSource("iris.data"), new UrlSource("http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data")));
//IRecordExtractor irisExtractor = irisReader.Extractor("inputs2", new[] { 0, 3 }, "targets2", 4).AddValueMapping(4, "Iris-setosa", "Iris-versicolor", "Iris-virginica");
//irisExtractor = irisExtractor.Preprocess(new OneHotPreprocessor(sectionName: "targets2", minValue: 0, maxValue: 2), new NormalisingPreprocessor(sectionNames: "inputs2", minInputValue: 0, maxInputValue: 6));
ByteRecordReader mnistImageReader = new ByteRecordReader(headerLengthBytes: 16, recordSizeBytes: 28 * 28, source: new CompressedSource(new MultiSource(new FileSource("train-images-idx3-ubyte.gz"), new UrlSource("http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz"))));
IRecordExtractor mnistImageExtractor = mnistImageReader.Extractor("inputs", new[] { 0L, 0L }, new[] { 28L, 28L }).Preprocess(new NormalisingPreprocessor(0, 255));
ByteRecordReader mnistTargetReader = new ByteRecordReader(headerLengthBytes: 8, recordSizeBytes: 1, source: new CompressedSource(new MultiSource(new FileSource("train-labels-idx1-ubyte.gz"), new UrlSource("http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz"))));
IRecordExtractor mnistTargetExtractor = mnistTargetReader.Extractor("targets", new[] { 0L }, new[] { 1L }).Preprocess(new OneHotPreprocessor(minValue: 0, maxValue: 9));
IComputationHandler handler = new CpuFloat32Handler();
ExtractedDataset dataset = new ExtractedDataset("mnist-training", ExtractedDataset.BlockSizeAuto, mnistImageExtractor, mnistTargetExtractor);
IDataset[] slices = dataset.SplitRecordwise(0.8, 0.2);
IDataset trainingData = slices[0];
IDataset validationData = slices[1];
MinibatchIterator trainingIterator = new MinibatchIterator(1, trainingData);
MinibatchIterator validationIterator = new MinibatchIterator(1, validationData);
while (true)
{
foreach (var block in trainingIterator.Yield(handler, sigma))
{
Thread.Sleep(100);
PrintFormattedBlock(block, PrintUtils.AsciiGreyscalePalette);
Thread.Sleep(1000);
}
}
//Random random = new Random();
//INDArray array = new ADNDArray<float>(3, 1, 2, 2);
//new GaussianInitialiser(0.05, 0.05).Initialise(array, Handler, random);
//Console.WriteLine(array);
//new ConstantValueInitialiser(1).Initialise(array, Handler, random);
//Console.WriteLine(array);
//dataset.InvalidateAndClearCaches();
}
public IRecordExtractor Extractor(params IRecordExtractor[] extractors)
{
IRecordExtractor firstExtractor = extractors[0];
firstExtractor.Reader = Reader;
firstExtractor.ParentExtractor = this;
firstExtractor.SectionNames = MergeSectionNames(firstExtractor);
if (extractors.Length > 1)
{
return(firstExtractor.Extractor(extractors.SubArray(1, extractors.Length - 1)));
}
return(firstExtractor);
}
private string[] MergeSectionNames(IRecordExtractor otherExtractor)
{
ISet <string> allSectionNames = new HashSet <string>();
foreach (string section in SectionNames)
{
allSectionNames.Add(section);
}
if (otherExtractor.SectionNames != null)
{
foreach (string section in otherExtractor.SectionNames)
{
allSectionNames.Add(section);
}
}
return(allSectionNames.ToArray());
}
private static void SampleCachedFastIteration()
{
SigmaEnvironment sigma = SigmaEnvironment.Create("test");
IDataSource dataSource = new CompressedSource(new MultiSource(new FileSource("train-images-idx3-ubyte.gz"), new UrlSource("http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz")));
ByteRecordReader mnistImageReader = new ByteRecordReader(headerLengthBytes: 16, recordSizeBytes: 28 * 28, source: dataSource);
IRecordExtractor mnistImageExtractor = mnistImageReader.Extractor("inputs", new[] { 0L, 0L }, new[] { 28L, 28L }).Preprocess(new NormalisingPreprocessor(0, 255));
IDataset dataset = new ExtractedDataset("mnist-training", ExtractedDataset.BlockSizeAuto, mnistImageExtractor);
IDataset[] slices = dataset.SplitRecordwise(0.8, 0.2);
IDataset trainingData = slices[0];
Stopwatch stopwatch = Stopwatch.StartNew();
IDataIterator iterator = new MinibatchIterator(10, trainingData);
foreach (var block in iterator.Yield(new CpuFloat32Handler(), sigma))
{
//PrintFormattedBlock(block, PrintUtils.AsciiGreyscalePalette);
}
Console.Write("\nFirst iteration took " + stopwatch.Elapsed + "\n+=+ Iterating over dataset again +=+ Dramatic pause...");
ArrayUtils.Range(1, 10).ToList().ForEach(i =>
{
Thread.Sleep(500);
Console.Write(".");
});
stopwatch.Restart();
foreach (var block in iterator.Yield(new CpuFloat32Handler(), sigma))
{
//PrintFormattedBlock(block, PrintUtils.AsciiGreyscalePalette);
}
Console.WriteLine("Second iteration took " + stopwatch.Elapsed);
}
/// <summary>
/// Create an IRIS trainer that observers the current epoch and iteration
/// </summary>
/// <param name="sigma">The sigma environemnt.</param>
/// <returns>The newly created trainer that can be added to the environemnt.</returns>
private static ITrainer CreateIrisTrainer(SigmaEnvironment sigma)
{
CsvRecordReader irisReader = new CsvRecordReader(new MultiSource(new FileSource("iris.data"), new UrlSource("http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data")));
IRecordExtractor irisExtractor = irisReader.Extractor("inputs", new[] { 0, 3 }, "targets", 4).AddValueMapping(4, "Iris-setosa", "Iris-versicolor", "Iris-virginica");
irisExtractor = irisExtractor.Preprocess(new OneHotPreprocessor(sectionName: "targets", minValue: 0, maxValue: 2));
irisExtractor = irisExtractor.Preprocess(new PerIndexNormalisingPreprocessor(0, 1, "inputs", 0, 4.3, 7.9, 1, 2.0, 4.4, 2, 1.0, 6.9, 3, 0.1, 2.5));
Dataset dataset = new Dataset("iris", Dataset.BlockSizeAuto, irisExtractor);
IDataset trainingDataset = dataset;
IDataset validationDataset = dataset;
ITrainer trainer = sigma.CreateTrainer("test");
trainer.Network = new Network
{
Architecture = InputLayer.Construct(4)
+ FullyConnectedLayer.Construct(10)
+ FullyConnectedLayer.Construct(20)
+ FullyConnectedLayer.Construct(10)
+ FullyConnectedLayer.Construct(3)
+ OutputLayer.Construct(3)
+ SquaredDifferenceCostLayer.Construct()
};
trainer.TrainingDataIterator = new MinibatchIterator(4, trainingDataset);
trainer.AddNamedDataIterator("validation", new UndividedIterator(validationDataset));
trainer.Optimiser = new GradientDescentOptimiser(learningRate: 0.002);
trainer.Operator = new CpuSinglethreadedOperator();
trainer.AddInitialiser("*.weights", new GaussianInitialiser(standardDeviation: 0.4));
trainer.AddInitialiser("*.bias*", new GaussianInitialiser(standardDeviation: 0.01, mean: 0.05));
trainer.AddHook(new ValueReporterHook("optimiser.cost_total", TimeStep.Every(1, TimeScale.Epoch)));
trainer.AddHook(new ValidationAccuracyReporter("validation", TimeStep.Every(1, TimeScale.Epoch), tops: 1));
trainer.AddLocalHook(new CurrentEpochIterationReporter(TimeStep.Every(1, TimeScale.Epoch)));
return(trainer);
}
/// <summary>
/// Attach a certain record extractor to this record reader.
/// </summary>
/// <param name="extractor">The extractor to attach this reader to.</param>
/// <returns>The given extractor (for convenience).</returns>
public IRecordExtractor Extractor(IRecordExtractor extractor)
{
extractor.Reader = this;
return(extractor);
}
public IRecordExtractor Extractor(IRecordExtractor extractor)
{
throw new NotImplementedException();
}
