private static BPTTTeacher GetTeacher(int weightsCount, NeuralTuringMachine machine) { RMSPropWeightUpdater rmsPropWeightUpdater = new RMSPropWeightUpdater(weightsCount, 0.95, 0.5, 0.001, 0.001); BPTTTeacher teacher = new BPTTTeacher(machine, rmsPropWeightUpdater); return(teacher); }
private static void ClassicIterations(int controllerSize, int headCount, int memoryN, int memoryM, Random rand, List <double[][]> inputs, List <double[][]> outputs) { int weightsCount; var machine = GetRandomMachine(out weightsCount, controllerSize, headCount, memoryN, memoryM, rand); RMSPropWeightUpdater rmsPropWeightUpdater = new RMSPropWeightUpdater(weightsCount, 0.95, 0.5, 0.001); BPTTTeacher teacher = new BPTTTeacher(machine, rmsPropWeightUpdater); double[][] errors = new double[100][]; long[] times = new long[100]; for (int i = 0; i < 100; i++) { errors[i] = new double[4]; for (int j = 0; j < 4; j++) { errors[i][j] = 1; } } int count = inputs.Count; for (int i = 1; i < 10000000; i++) { int index = rand.Next(count); double[][] input = inputs[index]; double[][] output = outputs[index]; Stopwatch stopwatch = new Stopwatch(); stopwatch.Start(); double[][] machinesOutput = teacher.Train(input, output); stopwatch.Stop(); times[i % 100] = stopwatch.ElapsedMilliseconds; double[] error = CalculateLoss(output, machinesOutput); errors[i % 100][0] = error[0]; errors[i % 100][1] = error[1]; errors[i % 100][2] = error[2]; errors[i % 100][3] = error[3]; double averageError = errors.Average(doubles => doubles.Average()); if (i % 100 == 0) { WriteExample(i, times, errors, averageError, output, machinesOutput); } if (i % 2500 == 0) { string directoryName = string.Format("{0}_{1}_{2}_{3}", controllerSize, headCount, memoryM, memoryN); if (!Directory.Exists(directoryName)) { Directory.CreateDirectory(directoryName); } string filename = string.Format("NTM_{0}_{1}_{2}.ntm", i, DateTime.Now.ToString("s").Replace(":", ""), averageError); machine.Save(Path.Combine(directoryName, filename)); } } }
public LearningTask(NeuralTuringMachine machine, RMSPropWeightUpdater weightUpdater, int id) { _iterations = 0; _machine = machine; _weightUpdater = weightUpdater; _id = id; _teacher = new BPTTTeacher(_machine, weightUpdater); _longTermAverageErrors = new List <double>(); Priority = 10; }
public void CopyFrom(LearningTask task, int weightsCount) { CopyMachine copyMachine = new CopyMachine(weightsCount, task._machine); _machine.UpdateWeights(copyMachine); _weightUpdater = task._weightUpdater.Clone(); _teacher = new BPTTTeacher(_machine, _weightUpdater); _iterations = task._iterations; _longTermAverageErrors = new List <double>(task._longTermAverageErrors); Priority = task.Priority; }
public LearningTask(NeuralTuringMachine machine, RMSPropWeightUpdater weightUpdater, Func <Tuple <double[][], double[][]> > exampleGenerator, string directoryName, int id) { _iterations = 0; _machine = machine; _weightUpdater = weightUpdater; _exampleGenerator = exampleGenerator; _directoryName = directoryName; _id = id; _teacher = new BPTTTeacher(_machine, weightUpdater); _longTermAverageErrors = new List <double>(); Priority = 100 / 32; }
private static void Iterate(BPTTTeacher teacher, double[] errors, long[] times, int id) { const int vectorSize = 8; const int minSeqLen = 1; const int maxSeqLen = 20; //double savingThreshold = 0.0005; Random rand = new Random(DateTime.Now.Millisecond); for (int i = 1; i <= 100; i++) { var sequence = SequenceGenerator.GenerateSequence(rand.Next(minSeqLen, maxSeqLen), vectorSize); Stopwatch stopwatch = new Stopwatch(); stopwatch.Start(); double[][] machinesOutput = teacher.Train(sequence.Item1, sequence.Item2); stopwatch.Stop(); times[i % 100] = stopwatch.ElapsedMilliseconds; double error = CalculateLoss(sequence.Item2, machinesOutput); errors[i % 100] = error; if (i % 100 == 0) { double averageError2 = errors.Average(); Console.WriteLine("Iteration: {0}, error: {1}, id: {2}", i, averageError2, id); //if (averageError2 < savingThreshold) //{ // savingThreshold /= 2; // machine.Save("NTM_" + averageError2 + "_" + DateTime.Now.ToString("s").Replace(":", "")); // maxSeqLen++; // minSeqLen++; //} } //if (i % 100000 == 0) //{ // machine.Save("NTM_" + i + DateTime.Now.ToString("s").Replace(":", "")); //} } }
private static void StandardCopyTask(DataStream reportStream) { double[] errors = new double[100]; long[] times = new long[100]; for (int i = 0; i < 100; i++) { errors[i] = 1; } const int seed = 32702; Console.WriteLine(seed); //TODO args parsing shit Random rand = new Random(seed); const int vectorSize = 8; const int controllerSize = 100; const int headsCount = 1; const int memoryN = 128; const int memoryM = 20; const int inputSize = vectorSize + 2; const int outputSize = vectorSize; //TODO remove rand NeuralTuringMachine machine = new NeuralTuringMachine(vectorSize + 2, vectorSize, controllerSize, headsCount, memoryN, memoryM, new RandomWeightInitializer(rand)); //TODO extract weight count calculation int headUnitSize = Head.GetUnitSize(memoryM); var weightsCount = (headsCount * memoryN) + (memoryN * memoryM) + (controllerSize * headsCount * memoryM) + (controllerSize * inputSize) + (controllerSize) + (outputSize * (controllerSize + 1)) + (headsCount * headUnitSize * (controllerSize + 1)); Console.WriteLine(weightsCount); RMSPropWeightUpdater rmsPropWeightUpdater = new RMSPropWeightUpdater(weightsCount, 0.95, 0.5, 0.001, 0.001); //NeuralTuringMachine machine = NeuralTuringMachine.Load(@"NTM_0.000583637804331003_2015-04-18T223455"); BPTTTeacher teacher = new BPTTTeacher(machine, rmsPropWeightUpdater); //for (int i = 1; i < 256; i++) //{ // var sequence = SequenceGenerator.GenerateSequence(i, vectorSize); // double[][] machineOutput = teacher.Train(sequence.Item1, sequence.Item2); // double error = CalculateLoss(sequence.Item2, machineOutput); // Console.WriteLine("{0},{1}", i, error); //} int minSeqLen = 200; int maxSeqLen = 200; double savingThreshold = 0.0005; for (int i = 1; i < 10000000; i++) { //var sequence = SequenceGenerator.GenerateSequence(rand.Next(20) + 1, vectorSize); var sequence = SequenceGenerator.GenerateSequence(rand.Next(minSeqLen, maxSeqLen), vectorSize); Stopwatch stopwatch = new Stopwatch(); stopwatch.Start(); double[][] headAddressings; double[][] machinesOutput = teacher.TrainVerbose(sequence.Item1, sequence.Item2, out headAddressings); stopwatch.Stop(); times[i % 100] = stopwatch.ElapsedMilliseconds; double error = CalculateLoss(sequence.Item2, machinesOutput); double averageError = error / (sequence.Item2.Length * sequence.Item2[0].Length); errors[i % 100] = error; if (reportStream != null) { reportStream.Set("Iteration", i); reportStream.Set("Average data loss", averageError); reportStream.Set("Training time", stopwatch.ElapsedMilliseconds); reportStream.Set("Sequence length", (sequence.Item1.Length - 2) / 2); reportStream.Set("Input", sequence.Item1); reportStream.Set("Known output", sequence.Item2); reportStream.Set("Real output", machinesOutput); reportStream.Set("Head addressings", headAddressings); reportStream.SendData(); } if (i % 100 == 0) { double averageError2 = errors.Average(); Console.WriteLine( "Iteration: {0}, error: {1}, iterations per second: {2:0.0} MinSeqLen: {3} MaxSeqLen: {4}", i, averageError2, 1000 / times.Average(), minSeqLen, maxSeqLen); if (averageError2 < savingThreshold) { savingThreshold /= 2; machine.Save("NTM_" + averageError2 + "_" + DateTime.Now.ToString("s").Replace(":", "")); maxSeqLen++; minSeqLen++; } } if (i % 100000 == 0) { machine.Save("NTM_" + i + DateTime.Now.ToString("s").Replace(":", "")); } } }
private static void MultipleSimultaniousAvgCopyTasks() { const int numberOfThreads = 1; const int numberOfParallelTasks = 16; bool end = false; BlockingCollection <Tuple <Action <int>, int> > work = new BlockingCollection <Tuple <Action <int>, int> >(); Thread[] threads = new Thread[numberOfThreads]; SemaphoreSlim[] semaphores = new SemaphoreSlim[numberOfParallelTasks]; for (int i = 0; i < numberOfParallelTasks; i++) { semaphores[i] = new SemaphoreSlim(0); } for (int i = 0; i < numberOfThreads; i++) { threads[i] = new Thread( () => { while (!end) { var action = work.Take(); action.Item1(action.Item2); semaphores[action.Item2].Release(); } }); threads[i].Start(); } double[][] errorss = new double[numberOfParallelTasks][]; long[][] timess = new long[numberOfParallelTasks][]; NeuralTuringMachine[] machines = new NeuralTuringMachine[numberOfParallelTasks]; BPTTTeacher[] teachers = new BPTTTeacher[numberOfParallelTasks]; int weightsCount = 0; for (int i = 0; i < numberOfParallelTasks; i++) { errorss[i] = new double[100]; timess[i] = new long[100]; for (int j = 0; j < 100; j++) { errorss[i][j] = 1; } machines[i] = GetRandomMachine(out weightsCount); teachers[i] = GetTeacher(weightsCount, machines[i]); } int k = 1; while (!end) { Stopwatch stopwatch = new Stopwatch(); stopwatch.Start(); for (int i = 0; i < numberOfParallelTasks; i++) { var index = i; work.Add(new Tuple <Action <int>, int>(id => Iterate(teachers[index], errorss[index], timess[index], id), index)); } for (int i = 0; i < numberOfParallelTasks; i++) { semaphores[i].Wait(); } Console.WriteLine("Average NTMs"); double[] errors = errorss.Select(doubles => doubles.Average()).ToArray(); AverageMachineWeightUpdater averageWeightUpdater = new AverageMachineWeightUpdater(weightsCount, machines); foreach (NeuralTuringMachine machine in machines) { machine.UpdateWeights(averageWeightUpdater); averageWeightUpdater.Reset(); } for (int i = 0; i < numberOfParallelTasks; i++) { teachers[i] = GetTeacher(weightsCount, machines[i]); } Console.WriteLine("Iteration: {0}", k); Console.WriteLine("Average error: {0}", errors.Average()); Console.WriteLine("Best error: {0}", errors.Min()); k++; stopwatch.Stop(); double seconds = stopwatch.ElapsedMilliseconds / (double)1000; Console.WriteLine("Time: {0}[s] per task: {1}[s]", seconds, seconds / numberOfParallelTasks); } }
static void Main() { DataStream reportStream = null; try { YoVisionClientHelper yoVisionClientHelper = new YoVisionClientHelper(); yoVisionClientHelper.Connect(EndpointType.NetTcp, 8081, "localhost", "YoVisionServer"); reportStream = yoVisionClientHelper.RegisterDataStream("NGram task training", new Int32DataType("Iteration"), new DoubleDataType("Average data loss"), new Double2DArrayType("Input"), new Double2DArrayType("Known output"), new Double2DArrayType("Real output"), new Double2DArrayType("Head addressings")); } catch (Exception ex) { Console.WriteLine(ex.Message); } const int controllerSize = 100; const int headsCount = 1; const int memoryN = 128; const int memoryM = 20; const int inputSize = 1; const int outputSize = 1; Random rand = new Random(42); NeuralTuringMachine machine = new NeuralTuringMachine(inputSize, outputSize, controllerSize, headsCount, memoryN, memoryM, new RandomWeightInitializer(rand)); int headUnitSize = Head.GetUnitSize(memoryM); var weightsCount = (headsCount * memoryN) + (memoryN * memoryM) + (controllerSize * headsCount * memoryM) + (controllerSize * inputSize) + (controllerSize) + (outputSize * (controllerSize + 1)) + (headsCount * headUnitSize * (controllerSize + 1)); Console.WriteLine(weightsCount); RMSPropWeightUpdater rmsPropWeightUpdater = new RMSPropWeightUpdater(weightsCount, 0.95, 0.5, 0.001, 0.001); BPTTTeacher teacher = new BPTTTeacher(machine, rmsPropWeightUpdater); long[] times = new long[100]; for (int i = 1; i < 10000000; i++) { Tuple<double[][], double[][]> data = SequenceGenerator.GenerateSequence(SequenceGenerator.GeneratePropabilities()); Stopwatch stopwatch = new Stopwatch(); stopwatch.Start(); double[][] headAddressings; double[][] output = teacher.TrainVerbose(data.Item1, data.Item2, out headAddressings); stopwatch.Stop(); times[i % 100] = stopwatch.ElapsedMilliseconds; if (i%10 == 0) { double loss = CalculateLogLoss(output, data.Item2); if (reportStream != null) { reportStream.Set("Iteration", i); reportStream.Set("Average data loss", loss); reportStream.Set("Input", data.Item1); reportStream.Set("Known output", data.Item2); reportStream.Set("Real output", output); reportStream.Set("Head addressings", headAddressings); reportStream.SendData(); } } if (i%100 == 0) { Console.WriteLine("Iteration: {0}, iterations per second: {1:0.0}", i, 1000 / times.Average()); } if (i%1000 == 0) { double[] props = SequenceGenerator.GeneratePropabilities(); const int sampleCount = 100; double[] losses = new double[sampleCount]; for (int j = 0; j < sampleCount; j++) { Tuple<double[][], double[][]> sequence = SequenceGenerator.GenerateSequence(props); var machineOutput = teacher.Train(sequence.Item1, sequence.Item2); double[][] knownOutput = sequence.Item2; double loss = CalculateLogLoss(machineOutput, knownOutput); losses[j] = -loss; } Console.WriteLine("Loss [bits per sequence]: {0}", losses.Average()); } if (i % 1000 == 0) { machine.Save("NTM_" + i + DateTime.Now.ToString("s").Replace(":", "")); } } }