public void ExecuteTest()
{
float max_err = 0;
Random rd = new Random(1234);
foreach (int batch in new int[] { 1, 2 })
{
foreach (int channels in new int[] { 1, 2, 3, 4, 5, 6, 7, 8 })
{
foreach (int stride in new int[] { 2, 3, 4 })
{
foreach (int inwidth in new int[] { 5, 7, 11 })
{
foreach (int inheight in new int[] { 5, 7, 11 })
{
int outwidth = inwidth / stride, outheight = inheight / stride;
float[] xval = (new float[inwidth * inheight * channels * batch]).Select((_) => (float)rd.NextDouble()).ToArray();
float[] gyval = (new float[outwidth * outheight * channels * batch]).Select((_) => (float)rd.NextDouble()).ToArray();
Map2D x = new Map2D(channels, inwidth, inheight, batch, xval);
Map2D gy = new Map2D(channels, outwidth, outheight, batch, gyval);
Map2D gx = Reference(x, gy, stride);
OverflowCheckedTensor x_tensor = new OverflowCheckedTensor(Shape.Map2D(channels, inwidth, inheight, batch), xval);
OverflowCheckedTensor y_tensor = new OverflowCheckedTensor(Shape.Map2D(channels, outwidth, outheight, batch));
OverflowCheckedTensor gy_tensor = new OverflowCheckedTensor(Shape.Map2D(channels, outwidth, outheight, batch), gyval);
OverflowCheckedTensor gx_tensor = new OverflowCheckedTensor(Shape.Map2D(channels, inwidth, inheight, batch));
MaxPooling ope_pool = new MaxPooling(inwidth, inheight, channels, stride, batch);
ope_pool.Execute(x_tensor, y_tensor);
MaxUnpooling ope_unpool = new MaxUnpooling(inwidth, inheight, channels, stride, batch);
ope_unpool.Execute(gy_tensor, x_tensor, y_tensor, gx_tensor);
float[] gx_expect = gx.ToArray();
float[] gx_actual = gx_tensor.State;
int gx_expect_nonzero = gx_expect.Count((v) => v != 0);
int gx_actual_nonzero = gx_expect.Count((v) => v != 0);
CollectionAssert.AreEqual(xval, x_tensor.State);
CollectionAssert.AreEqual(gyval, gy_tensor.State);
Assert.AreEqual(y_tensor.Length, gx_expect_nonzero);
Assert.AreEqual(y_tensor.Length, gx_actual_nonzero);
AssertError.Tolerance(gx_expect, gx_actual, 1e-7f, 1e-5f, ref max_err, $"mismatch value {channels},{stride},{inwidth},{inheight},{batch}");
Console.WriteLine($"pass: {channels},{stride},{inwidth},{inheight},{batch}");
}
}
}
}
}
Console.WriteLine($"maxerr:{max_err}");
}
public void MaxPoolingStorageTest()
{
var max = new MaxPooling(2, 2);
var doc = new XmlDocument();
var el = XmlStorage.SaveToEl(doc, max);
var test = XmlStorage.LoadFromNode <MaxPooling>(el);
Assert.True(test is MaxPooling);
Assert.Equal(max.Rows, test.Rows);
Assert.Equal(max.Columns, test.Columns);
Assert.Equal(max.RowStride, test.RowStride);
Assert.Equal(max.ColumnStride, test.ColumnStride);
}
public static void Run()
{
sw = new Stopwatch();
Console.WriteLine("Generating Test Data...");
NdArray input = new NdArray(BenchDataMaker.GetRealArray(INPUT_SIZE));
NdArray inputImage = new NdArray(BenchDataMaker.GetRealArray(3 * 256 * 256 * 5), new[] { 3, 256, 256 }, 5);
Console.WriteLine("Generated Test Data");
Console.WriteLine("Init Linear");
Linear linear = new Linear(INPUT_SIZE, OUTPUT_SIZE);
Console.WriteLine("Init Tanh");
Tanh tanh = new Tanh();
Console.WriteLine("Init Sigmoid");
Sigmoid sigmoid = new Sigmoid();
Console.WriteLine("Init ReLU");
ReLU relu = new ReLU();
Console.WriteLine("Init LeakyReLU");
LeakyReLU leakyRelu = new LeakyReLU();
Console.WriteLine("Init MaxPooling");
MaxPooling maxPooling = new MaxPooling(2);
Console.WriteLine("Init Convolution2D");
Convolution2D conv2d = new Convolution2D(3, 32, 3);
Console.WriteLine("Init Deconvolution2D");
Deconvolution2D deconv2d = new Deconvolution2D(32, 3, 3);
Dropout dropout = new Dropout();
TestLayer(linear, input);
Console.WriteLine("aaaaaaaaaaaa");
Console.ReadLine();
TestLayer(tanh, input);
TestLayer(sigmoid, input);
TestLayer(relu, input);
TestLayer(leakyRelu, input);
TestLayer(maxPooling, inputImage);
TestLayer(conv2d, inputImage);
TestLayer(deconv2d, inputImage);
TestLayer(dropout, input);
}
public void ExecuteTest()
{
float max_err = 0;
foreach (int batch in new int[] { 1, 2 })
{
foreach (int channels in new int[] { 3, 5 })
{
foreach (int stride in new int[] { 2, 3, 4 })
{
foreach (int inwidth in new int[] { 5, 7, 11 })
{
foreach (int inheight in new int[] { 5, 7, 11 })
{
foreach (int indepth in new int[] { 5, 7, 11 })
{
int outwidth = inwidth / stride, outheight = inheight / stride, outdepth = indepth / stride;
float[] xval = (new float[inwidth * inheight * indepth * channels * batch]).Select((_, idx) => idx * 1e-3f).ToArray();
Map3D x = new Map3D(channels, inwidth, inheight, indepth, batch, xval);
Map3D y = Reference(x, stride);
OverflowCheckedTensor x_tensor = new OverflowCheckedTensor(Shape.Map3D(channels, inwidth, inheight, indepth, batch), xval);
OverflowCheckedTensor y_tensor = new OverflowCheckedTensor(Shape.Map3D(channels, outwidth, outheight, outdepth, batch));
MaxPooling ope = new MaxPooling(inwidth, inheight, indepth, channels, stride, batch);
ope.Execute(x_tensor, y_tensor);
float[] y_expect = y.ToArray();
float[] y_actual = y_tensor.State;
CollectionAssert.AreEqual(xval, x_tensor.State);
AssertError.Tolerance(y_expect, y_actual, 1e-7f, 1e-5f, ref max_err, $"mismatch value {channels},{stride},{inwidth},{inheight},{indepth},{batch}");
Console.WriteLine($"pass: {channels},{stride},{inwidth},{inheight},{batch}");
}
}
}
}
}
}
Console.WriteLine($"maxerr:{max_err}");
}
public void ForwardBackwardTest()
{
var data = new double[]
{
3, 2, 1, 5,
4, 2, 6, 1,
8, 2, 6, 3,
6, 3, 9, 5
};
var input = new TensorOld(data, 1, 1, 4, 4);
var pooling = new MaxPooling(2);
pooling.PrepareTrain(input);
var forward = pooling.Forward(input);
var expected = new TensorOld(new double[]
{
4, 6,
8, 9
}, 1, 1, 2, 2);
Assert.Equal(expected, forward);
var error = new TensorOld(new double[]
{
0.5, 0.7,
-0.3, 1.2
}, 1, 1, 2, 2);
var backward = pooling.Backward(error);
var backExpected = new TensorOld(new double[]
{
0, 0, 0, 0,
0.5, 0, 0.7, 0,
-0.3, 0, 0, 0,
0, 0, 1.2, 0
}, 1, 1, 4, 4);
Assert.Equal(backExpected, backward);
}
public void SpeedTest()
{
int inwidth = 512, inheight = 512, channels = 32, stride = 2;
int outwidth = inwidth / stride, outheight = inheight / stride;
OverflowCheckedTensor x_tensor = new OverflowCheckedTensor(Shape.Map2D(channels, inwidth, inheight));
OverflowCheckedTensor y_tensor = new OverflowCheckedTensor(Shape.Map2D(channels, outwidth, outheight));
MaxPooling ope = new MaxPooling(inwidth, inheight, channels, stride);
Stopwatch sw = new Stopwatch();
sw.Start();
ope.Execute(x_tensor, y_tensor);
ope.Execute(x_tensor, y_tensor);
ope.Execute(x_tensor, y_tensor);
ope.Execute(x_tensor, y_tensor);
sw.Stop();
Console.WriteLine($"{sw.ElapsedMilliseconds / 4} msec");
}
static void Main(string[] args)
{
Console.WriteLine("MNIST Test");
int seed;
using (var rng = new RNGCryptoServiceProvider())
{
var buffer = new byte[sizeof(int)];
rng.GetBytes(buffer);
seed = BitConverter.ToInt32(buffer, 0);
}
RandomProvider.SetSeed(seed);
var assembly = Assembly.GetExecutingAssembly();
var filename = "CNN.xml";
var serializer = new DataContractSerializer(typeof(IEnumerable <Layer>), new Type[] { typeof(Convolution), typeof(BatchNormalization), typeof(Activation), typeof(ReLU), typeof(MaxPooling), typeof(FullyConnected), typeof(Softmax) });
var random = RandomProvider.GetRandom();
var trainingList = new List <Tuple <double[], double[]> >();
var testList = new List <Tuple <double[], double[]> >();
var accuracyList = new List <double>();
var lossList = new List <double>();
var logPath = "Log.csv";
var channels = 1;
var imageWidth = 28;
var imageHeight = 28;
var filters = 30;
var filterWidth = 5;
var filterHeight = 5;
var poolWidth = 2;
var poolHeight = 2;
var activationMapWidth = Convolution.GetActivationMapLength(imageWidth, filterWidth);
var activationMapHeight = Convolution.GetActivationMapLength(imageHeight, filterHeight);
var outputWidth = MaxPooling.GetOutputLength(activationMapWidth, poolWidth);
var outputHeight = MaxPooling.GetOutputLength(activationMapHeight, poolHeight);
Model model;
using (Stream
imagesStream = assembly.GetManifestResourceStream("MNISTTest.train-images.idx3-ubyte"),
labelsStream = assembly.GetManifestResourceStream("MNISTTest.train-labels.idx1-ubyte"))
{
foreach (var image in MnistImage.Load(imagesStream, labelsStream).Take(1000))
{
var t = new double[10];
for (int i = 0; i < 10; i++)
{
if (i == image.Label)
{
t[i] = 1.0;
}
else
{
t[i] = 0.0;
}
}
trainingList.Add(Tuple.Create <double[], double[]>(image.Normalize(), t));
}
}
using (Stream
imagesStream = assembly.GetManifestResourceStream("MNISTTest.t10k-images.idx3-ubyte"),
labelsStream = assembly.GetManifestResourceStream("MNISTTest.t10k-labels.idx1-ubyte"))
{
foreach (var image in MnistImage.Load(imagesStream, labelsStream).Take(1000))
{
var t = new double[10];
for (int i = 0; i < 10; i++)
{
if (i == image.Label)
{
t[i] = 1.0;
}
else
{
t[i] = 0.0;
}
}
testList.Add(Tuple.Create <double[], double[]>(image.Normalize(), t));
}
}
if (File.Exists(filename))
{
using (XmlReader xmlReader = XmlReader.Create(filename))
{
model = new Model((IEnumerable <Layer>)serializer.ReadObject(xmlReader), new Adam(), new SoftmaxCrossEntropy());
}
}
else
{
/*model = new Model(new Layer[] {
* new Convolutional(channels, imageWidth, imageHeight, filters, filterWidth, filterHeight, (fanIn, fanOut) => Initializers.HeNormal(fanIn)),
* new Activation(filters * activationMapWidth * activationMapHeight, new ReLU()),
* new MaxPooling(filters, activationMapWidth, activationMapHeight, poolWidth, poolHeight),
* new FullyConnected(filters * outputWidth * outputHeight, 100, (fanIn, fanOut) => Initializers.HeNormal(fanIn)),
* new Activation(100, new ReLU()),
* new Softmax(100, 10, (fanIn, fanOut) => Initializers.GlorotNormal(fanIn, fanOut))
* }, new Adam(), new SoftmaxCrossEntropy());*/
/*var inputLayer = new Convolutional(channels, imageWidth, imageHeight, filters, filterWidth, filterHeight, (fanIn, fanOut) => Initializers.HeNormal(fanIn));
*
* new Softmax(
* new Activation(
* new FullyConnected(
* new MaxPooling(
* new Activation(inputLayer, new ReLU()),
* filters, inputLayer.ActivationMapWidth, inputLayer.ActivationMapHeight, poolWidth, poolHeight),
* 100, (fanIn, fanOut) => Initializers.HeNormal(fanIn)),
* new ReLU()),
* 10, (fanIn, fanOut) => Initializers.GlorotNormal(fanIn, fanOut));
*
* model = new Model(inputLayer, new Adam(), new SoftmaxCrossEntropy());*/
model = new Model(
new Convolution(channels, imageWidth, imageHeight, filters, filterWidth, filterHeight, (fanIn, fanOut) => Initializers.HeNormal(fanIn),
new Activation(new ReLU(),
new MaxPooling(filters, activationMapWidth, activationMapHeight, poolWidth, poolHeight,
new FullyConnected(filters * outputWidth * outputHeight, (fanIn, fanOut) => Initializers.HeNormal(fanIn),
new Activation(new ReLU(),
new Softmax(100, 10, (fanIn, fanOut) => Initializers.GlorotNormal(fanIn, fanOut))))))),
new Adam(), new SoftmaxCrossEntropy());
int epochs = 50;
int iterations = 1;
model.Stepped += (sender, e) =>
{
double tptn = 0.0;
trainingList.ForEach(x =>
{
var vector = model.Predicate(x.Item1);
var i = ArgMax(vector);
var j = ArgMax(x.Item2);
if (i == j && Math.Round(vector[i]) == x.Item2[j])
{
tptn += 1.0;
}
});
var accuracy = tptn / trainingList.Count;
accuracyList.Add(accuracy);
lossList.Add(model.Loss);
Console.WriteLine("Epoch {0}/{1}", iterations, epochs);
Console.WriteLine("Accuracy: {0}, Loss: {1}", accuracy, model.Loss);
iterations++;
};
Console.WriteLine("Training...");
var stopwatch = Stopwatch.StartNew();
model.Fit(trainingList, epochs, 100);
stopwatch.Stop();
Console.WriteLine("Done ({0}).", stopwatch.Elapsed.ToString());
}
double testTptn = 0.0;
testList.ForEach(x =>
{
var vector = model.Predicate(x.Item1);
var i = ArgMax(vector);
var j = ArgMax(x.Item2);
if (i == j && Math.Round(vector[i]) == x.Item2[j])
{
testTptn += 1.0;
}
});
Console.WriteLine("Accuracy: {0}", testTptn / testList.Count);
if (accuracyList.Count > 0)
{
var logDictionary = new Dictionary <string, IEnumerable <double> >();
logDictionary.Add("Accuracy", accuracyList);
logDictionary.Add("Loss", lossList);
ToCsv(logPath, logDictionary);
Console.WriteLine("Saved log to {0}...", logPath);
}
XmlWriterSettings settings = new XmlWriterSettings();
settings.Indent = true;
settings.Encoding = new System.Text.UTF8Encoding(false);
using (XmlWriter xmlWriter = XmlWriter.Create(filename, settings))
{
serializer.WriteObject(xmlWriter, model.Layers);
xmlWriter.Flush();
}
}
public static void Run()
{
Stopwatch sw = new Stopwatch();
NdArray inputArrayCpu = new NdArray(Initializer.GetRealArray(INPUT_SIZE));
NdArray inputArrayGpu = new NdArray(Initializer.GetRealArray(INPUT_SIZE));
//Linear
Linear linear = new Linear(INPUT_SIZE, OUTPUT_SIZE);
Console.WriteLine("◆" + linear.Name);
sw.Restart();
NdArray[] gradArrayCpu = linear.Forward(inputArrayCpu);
sw.Stop();
Console.WriteLine("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data; //DataをGradとして使用
sw.Restart();
linear.Backward(gradArrayCpu);
sw.Stop();
Console.WriteLine("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (linear.SetGpuEnable(true))
{
sw.Restart();
NdArray[] gradArrayGpu = linear.Forward(inputArrayGpu);
sw.Stop();
Console.WriteLine("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayGpu[0].Grad = gradArrayGpu[0].Data;
sw.Restart();
linear.Backward(gradArrayGpu);
sw.Stop();
Console.WriteLine("Backward[Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
//Tanh
TanhActivation tanh = new TanhActivation();
Console.WriteLine("\n◆" + tanh.Name);
sw.Restart();
gradArrayCpu = tanh.Forward(inputArrayCpu);
sw.Stop();
Console.WriteLine("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
tanh.Backward(gradArrayCpu);
sw.Stop();
Console.WriteLine("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (tanh.SetGpuEnable(true))
{
sw.Restart();
NdArray[] gradArrayGpu = tanh.Forward(inputArrayGpu);
sw.Stop();
Console.WriteLine("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayGpu[0].Grad = gradArrayGpu[0].Data;
sw.Restart();
tanh.Backward(gradArrayGpu);
sw.Stop();
Console.WriteLine("Backward[Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
//Sigmoid
Sigmoid sigmoid = new Sigmoid();
Console.WriteLine("\n◆" + sigmoid.Name);
sw.Restart();
gradArrayCpu = sigmoid.Forward(inputArrayCpu);
sw.Stop();
Console.WriteLine("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
sigmoid.Backward(gradArrayCpu);
sw.Stop();
Console.WriteLine("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (sigmoid.SetGpuEnable(true))
{
sw.Restart();
NdArray[] gradArrayGpu = sigmoid.Forward(inputArrayGpu);
sw.Stop();
Console.WriteLine("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayGpu[0].Grad = gradArrayGpu[0].Data;
sw.Restart();
sigmoid.Backward(gradArrayGpu);
sw.Stop();
Console.WriteLine("Backward[Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
//ReLU
ReLU relu = new ReLU();
Console.WriteLine("\n◆" + relu.Name);
sw.Restart();
gradArrayCpu = relu.Forward(inputArrayCpu);
sw.Stop();
Console.WriteLine("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
relu.Backward(gradArrayCpu);
sw.Stop();
Console.WriteLine("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (relu.SetGpuEnable(true))
{
sw.Restart();
NdArray[] gradArrayGpu = relu.Forward(inputArrayGpu);
sw.Stop();
Console.WriteLine("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayGpu[0].Grad = gradArrayGpu[0].Data;
sw.Restart();
relu.Backward(gradArrayGpu);
sw.Stop();
Console.WriteLine("Backward[Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
//LeakyReLU
LeakyReLU leakyRelu = new LeakyReLU();
Console.WriteLine("\n◆" + leakyRelu.Name);
sw.Restart();
gradArrayCpu = leakyRelu.Forward(inputArrayCpu);
sw.Stop();
Console.WriteLine("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
leakyRelu.Backward(gradArrayCpu);
sw.Stop();
Console.WriteLine("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (leakyRelu.SetGpuEnable(true))
{
sw.Restart();
NdArray[] gradArrayGpu = leakyRelu.Forward(inputArrayGpu);
sw.Stop();
Console.WriteLine("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayGpu[0].Grad = gradArrayGpu[0].Data;
sw.Restart();
leakyRelu.Backward(gradArrayGpu);
sw.Stop();
Console.WriteLine("Backward[Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
NdArray inputImageArrayGpu = new NdArray(Initializer.GetRealArray(3 * 256 * 256 * 5), new[] { 3, 256, 256 }, 5);
NdArray inputImageArrayCpu = new NdArray(Initializer.GetRealArray(3 * 256 * 256 * 5), new[] { 3, 256, 256 }, 5);
//MaxPooling
MaxPooling maxPooling = new MaxPooling(3);
Console.WriteLine("\n◆" + maxPooling.Name);
sw.Restart();
NdArray[] gradImageArrayCpu = maxPooling.Forward(inputImageArrayCpu);
sw.Stop();
Console.WriteLine("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradImageArrayCpu[0].Grad = gradImageArrayCpu[0].Data;
sw.Restart();
maxPooling.Backward(gradImageArrayCpu);
sw.Stop();
Console.WriteLine("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (maxPooling.SetGpuEnable(true))
{
sw.Restart();
maxPooling.Forward(inputImageArrayGpu);
sw.Stop();
Console.WriteLine("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
//メモリ転送のみのため実装がない
Console.WriteLine("Backward[Gpu] : None");
}
//Conv2D
Convolution2D conv2d = new Convolution2D(3, 3, 3);
Console.WriteLine("\n◆" + conv2d.Name);
sw.Restart();
gradImageArrayCpu = conv2d.Forward(inputImageArrayCpu);
sw.Stop();
Console.WriteLine("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradImageArrayCpu[0].Grad = gradImageArrayCpu[0].Data;
sw.Restart();
conv2d.Backward(gradImageArrayCpu);
sw.Stop();
Console.WriteLine("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (conv2d.SetGpuEnable(true))
{
sw.Restart();
NdArray[] gradImageArrayGpu = conv2d.Forward(inputImageArrayGpu);
sw.Stop();
Console.WriteLine("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradImageArrayGpu[0].Grad = gradImageArrayGpu[0].Data;
sw.Restart();
conv2d.Backward(gradImageArrayGpu);
sw.Stop();
Console.WriteLine("Backward[Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
//Deconv2D
Deconvolution2D deconv2d = new Deconvolution2D(3, 3, 3);
Console.WriteLine("\n◆" + deconv2d.Name);
sw.Restart();
gradImageArrayCpu = deconv2d.Forward(inputImageArrayCpu);
sw.Stop();
Console.WriteLine("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradImageArrayCpu[0].Grad = gradImageArrayCpu[0].Data;
sw.Restart();
deconv2d.Backward(gradImageArrayCpu);
sw.Stop();
Console.WriteLine("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (deconv2d.SetGpuEnable(true))
{
sw.Restart();
NdArray[] gradImageArrayGpu = deconv2d.Forward(inputImageArrayGpu);
sw.Stop();
Console.WriteLine("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradImageArrayGpu[0].Grad = gradImageArrayGpu[0].Data;
sw.Restart();
deconv2d.Backward(gradImageArrayGpu);
sw.Stop();
Console.WriteLine("Backward[Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
//Dropout
Dropout dropout = new Dropout();
Console.WriteLine("\n◆" + dropout.Name);
sw.Restart();
gradArrayCpu = dropout.Forward(inputArrayCpu);
sw.Stop();
Console.WriteLine("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
dropout.Backward(gradArrayCpu);
sw.Stop();
Console.WriteLine("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (dropout.SetGpuEnable(true))
{
sw.Restart();
NdArray[] gradArrayGpu = dropout.Forward(inputArrayGpu);
sw.Stop();
Console.WriteLine("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayGpu[0].Grad = gradArrayGpu[0].Data;
sw.Restart();
dropout.Backward(gradArrayGpu);
sw.Stop();
Console.WriteLine("Backward[Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
}
public static void Run(bool verbose)
{
Stopwatch sw = new Stopwatch();
NdArray inputArrayCpu = new NdArray(BenchDataMaker.GetRealArray(INPUT_SIZE));
NdArray inputArrayGpu = new NdArray(BenchDataMaker.GetRealArray(INPUT_SIZE));
Ensure.Argument(inputArrayGpu).NotNull();
Ensure.Argument(inputArrayCpu).NotNull();
//Linear
Linear linear = new Linear(verbose, INPUT_SIZE, OUTPUT_SIZE);
if (verbose)
{
RILogManager.Default?.EnterMethod(linear.Name);
}
sw.Restart();
NdArray[] gradArrayCpu = linear.Forward(verbose, inputArrayCpu);
sw.Stop();
if (verbose)
{
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
Ensure.Argument(gradArrayCpu).NotNull();
gradArrayCpu[0].Grad = gradArrayCpu[0].Data; // Use Data as Grad
sw.Restart();
linear.Backward(verbose, gradArrayCpu);
sw.Stop();
if (verbose)
{
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
if (linear.SetGpuEnable(true))
{
sw.Restart();
NdArray[] gradArrayGpu = linear.Forward(verbose, inputArrayGpu);
sw.Stop();
if (verbose)
{
RILogManager.Default?.SendDebug("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
gradArrayGpu[0].Grad = gradArrayGpu[0].Data;
sw.Restart();
linear.Backward(verbose, gradArrayGpu);
sw.Stop();
if (verbose)
{
RILogManager.Default?.SendDebug("Backward[Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
}
if (verbose)
{
RILogManager.Default?.ExitMethod(linear.Name);
}
//Tanh
Tanh tanh = new Tanh();
if (verbose)
{
RILogManager.Default?.EnterMethod(tanh.Name);
}
sw.Restart();
gradArrayCpu = tanh.Forward(verbose, inputArrayCpu);
sw.Stop();
if (verbose)
{
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
tanh.Backward(verbose, gradArrayCpu);
sw.Stop();
if (verbose)
{
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
if (tanh.SetGpuEnable(true))
{
HandleGPU(verbose, sw, tanh, inputArrayGpu);
}
if (verbose)
{
RILogManager.Default?.ExitMethod(tanh.Name);
}
//Sigmoid
Sigmoid sigmoid = new Sigmoid();
if (verbose)
{
RILogManager.Default?.EnterMethod(sigmoid.Name);
}
sw.Restart();
gradArrayCpu = sigmoid.Forward(verbose, inputArrayCpu);
sw.Stop();
if (verbose)
{
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
sigmoid.Backward(verbose, gradArrayCpu);
sw.Stop();
if (verbose)
{
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
if (sigmoid.SetGpuEnable(true))
{
HandleGPU(verbose, sw, sigmoid, inputArrayGpu);
}
if (verbose)
{
RILogManager.Default?.ExitMethod(tanh.Name);
}
//Softmax
Softmax sm = new Softmax();
RILogManager.Default?.EnterMethod(sm.Name);
sw.Restart();
gradArrayCpu = sm.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
sm.Backward(verbose, gradArrayCpu);
sw.Stop();
if (verbose)
{
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
if (verbose)
{
RILogManager.Default?.ExitMethod(sm.Name);
}
//Softplus
Softplus sp = new Softplus();
if (verbose)
{
RILogManager.Default?.EnterMethod(sp.Name);
}
sw.Restart();
gradArrayCpu = sp.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
sp.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
RILogManager.Default?.ExitMethod(sp.Name);
//ReLU
ReLU relu = new ReLU();
RILogManager.Default?.EnterMethod(relu.Name);
sw.Restart();
gradArrayCpu = relu.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
relu.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (relu.SetGpuEnable(true))
{
HandleGPU(verbose, sw, relu, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(relu.Name);
//LeakyReLU
LeakyReLU leakyRelu = new LeakyReLU();
RILogManager.Default?.EnterMethod(leakyRelu.Name);
sw.Restart();
gradArrayCpu = leakyRelu.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
leakyRelu.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (leakyRelu.SetGpuEnable(true))
{
HandleGPU(verbose, sw, leakyRelu, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(leakyRelu.Name);
//ReLuTanh
ReLuTanh rth = new ReLuTanh();
RILogManager.Default?.EnterMethod(rth.Name);
sw.Restart();
gradArrayCpu = rth.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
rth.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (rth.SetGpuEnable(true))
{
HandleGPU(verbose, sw, rth, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(rth.Name);
////Swish
//Swish swi = new Swish();
//RILogManager.Default?.SendDebug(swi.Name);
//sw.Restart();
//gradArrayCpu = swi.Forward(inputArrayCpu);
//sw.Stop();
//RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
//gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
//sw.Restart();
//swi.Backward(gradArrayCpu);
//sw.Stop();
//RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
NdArray inputImageArrayGpu = new NdArray(BenchDataMaker.GetRealArray(3 * 256 * 256 * 5), new[] { 3, 256, 256 }, 5);
NdArray inputImageArrayCpu = new NdArray(BenchDataMaker.GetRealArray(3 * 256 * 256 * 5), new[] { 3, 256, 256 }, 5);
//MaxPooling
MaxPooling maxPooling = new MaxPooling(3);
RILogManager.Default?.EnterMethod(maxPooling.Name);
sw.Restart();
NdArray[] gradImageArrayCpu = maxPooling.Forward(verbose, inputImageArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradImageArrayCpu[0].Grad = gradImageArrayCpu[0].Data;
sw.Restart();
maxPooling.Backward(verbose, gradImageArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (maxPooling.SetGpuEnable(true))
{
sw.Restart();
maxPooling.Forward(verbose, inputImageArrayGpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
// There is no implementation for memory transfer only
RILogManager.Default?.SendDebug("Backward[Gpu] : None");
}
RILogManager.Default?.ExitMethod(maxPooling.Name);
//AvgPooling
AveragePooling avgPooling = new AveragePooling(3);
RILogManager.Default?.EnterMethod(avgPooling.Name);
sw.Restart();
gradImageArrayCpu = avgPooling.Forward(verbose, inputImageArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradImageArrayCpu[0].Grad = gradImageArrayCpu[0].Data;
sw.Restart();
avgPooling.Backward(verbose, gradImageArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
RILogManager.Default?.ExitMethod(avgPooling.Name);
//Conv2D
Convolution2D conv2d = new Convolution2D(verbose, 3, 3, 3);
RILogManager.Default?.EnterMethod(conv2d.Name);
sw.Restart();
gradImageArrayCpu = conv2d.Forward(verbose, inputImageArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradImageArrayCpu[0].Grad = gradImageArrayCpu[0].Data;
sw.Restart();
conv2d.Backward(verbose, gradImageArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (conv2d.SetGpuEnable(true))
{
HandleGPU(verbose, sw, conv2d, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(conv2d.Name);
//Deconv2D
Deconvolution2D deconv2d = new Deconvolution2D(verbose, 3, 3, 3);
RILogManager.Default?.EnterMethod(deconv2d.Name);
sw.Restart();
gradImageArrayCpu = deconv2d.Forward(verbose, inputImageArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradImageArrayCpu[0].Grad = gradImageArrayCpu[0].Data;
sw.Restart();
deconv2d.Backward(verbose, gradImageArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (deconv2d.SetGpuEnable(true))
{
HandleGPU(verbose, sw, deconv2d, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(deconv2d.Name);
//Dropout
Dropout dropout = new Dropout();
RILogManager.Default?.EnterMethod(dropout.Name);
sw.Restart();
gradArrayCpu = dropout.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
dropout.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (dropout.SetGpuEnable(true))
{
sw.Restart();
NdArray[] gradArrayGpu = dropout.Forward(verbose, inputArrayGpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayGpu[0].Grad = gradArrayGpu[0].Data;
sw.Restart();
dropout.Backward(verbose, gradArrayGpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Gpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
}
RILogManager.Default?.ExitMethod(dropout.Name);
//ArcSinH
ArcSinH a = new ArcSinH();
RILogManager.Default?.EnterMethod(a.Name);
sw.Restart();
gradArrayCpu = a.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
a.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (a.SetGpuEnable(true))
{
HandleGPU(verbose, sw, a, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(a.Name);
//ELU
ELU e = new ELU();
RILogManager.Default?.EnterMethod(e.Name);
sw.Restart();
gradArrayCpu = e.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
e.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
RILogManager.Default?.ExitMethod(e.Name);
//LeakyReluShifted
LeakyReLUShifted lrs = new LeakyReLUShifted();
RILogManager.Default?.EnterMethod(lrs.Name);
sw.Restart();
gradArrayCpu = lrs.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
lrs.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (lrs.SetGpuEnable(true))
{
HandleGPU(verbose, sw, lrs, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(lrs.Name);
//Logistic
LogisticFunction lf = new LogisticFunction();
RILogManager.Default?.EnterMethod(lf.Name);
sw.Restart();
gradArrayCpu = lf.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
lf.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (lf.SetGpuEnable(true))
{
HandleGPU(verbose, sw, lf, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(lf.Name);
//MaxMinusOne
MaxMinusOne mmo = new MaxMinusOne();
RILogManager.Default?.EnterMethod(mmo.Name);
sw.Restart();
gradArrayCpu = mmo.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
mmo.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (mmo.SetGpuEnable(true))
{
HandleGPU(verbose, sw, mmo, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(mmo.Name);
//ScaledELU
ScaledELU se = new ScaledELU();
RILogManager.Default?.EnterMethod(se.Name);
sw.Restart();
gradArrayCpu = se.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
se.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (se.SetGpuEnable(true))
{
HandleGPU(verbose, sw, se, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(se.Name);
//Sine
Sine s = new Sine();
RILogManager.Default?.EnterMethod(s.Name);
sw.Restart();
gradArrayCpu = s.Forward(verbose, inputArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Forward [Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
gradArrayCpu[0].Grad = gradArrayCpu[0].Data;
sw.Restart();
s.Backward(verbose, gradArrayCpu);
sw.Stop();
RILogManager.Default?.SendDebug("Backward[Cpu] : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μｓ");
if (s.SetGpuEnable(true))
{
HandleGPU(verbose, sw, s, inputArrayGpu);
}
RILogManager.Default?.ExitMethod(s.Name);
}
public bool CreateLayer(int nCount, ELayerType type, ActivationSettings activationSettings)
{
Layer.Utility.Layer layer;
switch (type)
{
case ELayerType.Invalid:
throw new ArgumentException("Invalid \"type\" argument.");
case ELayerType.AveragePooling:
layer = new AveragePooling(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
case ELayerType.AverageUnpooling:
layer = new AverageUnpooling(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
case ELayerType.Convolutional:
layer = new Convolutional(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
case ELayerType.Deconvolutional:
layer = new Deconvolutional(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
case ELayerType.Dropout:
layer = new Dropout(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
case ELayerType.FullyConnected:
layer = new FullyConnected(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
case ELayerType.GatedRecurrent:
layer = new GatedRecurrent(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
case ELayerType.LSTM:
layer = new LSTM(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
case ELayerType.MaxPooling:
layer = new MaxPooling(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
case ELayerType.MaxUnpooling:
layer = new MaxUnpooling(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
case ELayerType.Recurrent:
layer = new Recurrent(nCount, Layers.Count, activationSettings);
Layers.Add(layer);
return(true);
default:
throw new ArgumentException("Invalid \"type\" argument.");
}
}
public void ForwardBackwardTest3()
{
var data = new double[]
{
3, 2, 1, 5,
4, 2, 6, 1,
8, 2, 6, 3,
6, 3, 9, 5,
3, 2, 1, 5,
4, 2, 6, 1,
8, 2, 6, 3,
6, 3, 9, 5,
3, 2, 1, 5,
4, 2, 6, 1,
8, 2, 6, 3,
6, 3, 9, 5,
3, 2, 1, 5,
4, 2, 6, 1,
8, 2, 6, 3,
6, 3, 9, 5,
3, 2, 1, 5,
4, 2, 6, 1,
8, 2, 6, 3,
6, 3, 9, 5,
3, 2, 1, 5,
4, 2, 6, 1,
8, 2, 6, 3,
6, 3, 9, 5,
};
var input = new TensorOld(data, 2, 3, 4, 4);
var pooling = new MaxPooling(1, 3, 1, 3);
pooling.PrepareTrain(input);
var actual = pooling.Forward(input);
var expected = new TensorOld(new double[]
{
3, 6, 8, 9,
3, 6, 8, 9,
3, 6, 8, 9,
3, 6, 8, 9,
3, 6, 8, 9,
3, 6, 8, 9,
}, 2, 3, 4, 1);
Assert.Equal(expected, actual);
var error = new TensorOld(new double[]
{
0.8, 0.7, -1.5, 0.4,
0.8, 0.7, -1.5, 0.4,
0.8, 0.7, -1.5, 0.4,
0.8, 0.7, -1.5, 0.4,
0.8, 0.7, -1.5, 0.4,
0.8, 0.7, -1.5, 0.4,
}, 2, 3, 4, 1);
var backward = pooling.Backward(error);
var backData = new double[]
{
0.8, 0, 0, 0,
0, 0, 0.7, 0,
-1.5, 0, 0, 0,
0, 0, 0.4, 0,
0.8, 0, 0, 0,
0, 0, 0.7, 0,
-1.5, 0, 0, 0,
0, 0, 0.4, 0,
0.8, 0, 0, 0,
0, 0, 0.7, 0,
-1.5, 0, 0, 0,
0, 0, 0.4, 0,
0.8, 0, 0, 0,
0, 0, 0.7, 0,
-1.5, 0, 0, 0,
0, 0, 0.4, 0,
0.8, 0, 0, 0,
0, 0, 0.7, 0,
-1.5, 0, 0, 0,
0, 0, 0.4, 0,
0.8, 0, 0, 0,
0, 0, 0.7, 0,
-1.5, 0, 0, 0,
0, 0, 0.4, 0,
};
var backExpected = new TensorOld(backData, 2, 3, 4, 4);
Assert.Equal(backExpected, backward);
}
