public Seq2Seq() { trainer = new TrainerCPU(TrainType.MiniBatch, new Adamax()); trainer.BatchSize = 7; trainer.GradientClipValue = 5; network = new NeuralNetwork(random, 0.02); network.AddNewLayer(new Shape(11), new GruLayer(20)); // Энкодер network.AddNewLayer(new FeedForwardLayer(7, new RectifiedLinearUnit(0.3))); // Компрессор network.AddNewLayer(new GruLayer(20)); //Декодер network.AddNewLayer(new FeedForwardLayer(10, new SoftmaxUnit())); //Декодер Console.WriteLine("\n\tseq2seq\n\n" + network + "\n\n"); network.ResetState(); }
static void Main(string[] args) { Random random = new Random(13); NeuralNetwork cNN = new NeuralNetwork(random, 0.2); var conv = new ConvolutionLayer(new RectifiedLinearUnit(0.01), 8, 3, 3); conv.IsSame = true; cNN.AddNewLayer(new Shape(28, 28), conv); cNN.AddNewLayer(new MaxPooling(2, 2)); cNN.AddNewLayer(new ConvolutionLayer(new RectifiedLinearUnit(0.01), 16, 3, 3)); cNN.AddNewLayer(new MaxPooling(2, 2)); cNN.AddNewLayer(new ConvolutionLayer(new RectifiedLinearUnit(0.01), 32, 3, 3)); cNN.AddNewLayer(new UnPooling(2, 2)); cNN.AddNewLayer(new ConvolutionLayer(new RectifiedLinearUnit(0.01), 16, 3, 3)); cNN.AddNewLayer(new MaxPooling(2, 2)); cNN.AddNewLayer(new Flatten()); cNN.AddNewLayer(new FeedForwardLayer(20, new RectifiedLinearUnit(0.01))); cNN.AddNewLayer(new FeedForwardLayer(2, new SoftmaxUnit())); Console.WriteLine(cNN); GraphCPU graph = new GraphCPU(false); NNValue nValue = NNValue.Random(28, 28, 2, random); NNValue nValue1 = NNValue.Random(28, 28, 2, random); NNValue outp = new NNValue(new double[] { 0, 1 }); NNValue outp1 = new NNValue(new double[] { 1, 0 }); DataSetNoReccurent data = new DataSetNoReccurent(new NNValue[] { nValue, nValue1 }, new NNValue[] { outp, outp1 }, new CrossEntropyWithSoftmax()); TrainerCPU trainer = new TrainerCPU(TrainType.MiniBatch, new Adam()); trainer.BatchSize = 2; trainer.Train(10000, 0.001, cNN, data, 2, 0.0001); double[] dbs = cNN.Activate(nValue, graph).DataInTensor; double[] dbs1 = cNN.Activate(nValue1, graph).DataInTensor; }