private List <Item> SampleTestingInstance()
{
var result = new List <Item>();
var n = this.random.Next(this.testing.Count);
var entry = this.testing[n];
// Create volume from image data
var x = new Volume(28, 28, 1, 0.0);
for (var i = 0; i < 28; i++)
{
for (var j = 0; j < 28; j++)
{
x.Set(j + i * 28, entry.Image[j + i * 28] / 255.0);
}
}
for (var i = 0; i < 4; i++)
{
result.Add(new Item {
Volume = x.Augment(24), Label = entry.Label
});
}
return(result);
}
private Item SampleTrainingInstance()
{
var n = this.random.Next(this.trainingCount);
var entry = this.training[n];
// load more batches over time
if (this.stepCount % 5000 == 0 && this.stepCount > 0)
{
this.trainingCount = Math.Min(this.trainingCount + BatchSize, this.training.Count);
}
// Create volume from image data
var x = new Volume(28, 28, 1, 0.0);
for (var i = 0; i < 28; i++)
{
for (var j = 0; j < 28; j++)
{
x.Set(j + i * 28, entry.Image[j + i * 28] / 255.0);
}
}
var result = x.Augment(24);
return(new Item {
Volume = result, Label = entry.Label, IsValidation = n % 10 == 0
});
}
private Item SampleTrainingInstance()
{
var n = random.Next(trainingCount);
var entry = training[n];
// load more batches over time
if (stepCount % 5000 == 0 && stepCount > 0)
{
trainingCount = Math.Min(trainingCount + BatchSize, training.Count);
}
// Create volume from image data
var x = new Volume(24, 24, 1, 0.0);
for (var i = 0; i < 24; i++)
{
for (var j = 0; j < 24; j++)
{
x.Weights[j + i * 24] = entry.Image[j + i * 24] / 255.0;
}
}
x = x.Augment(24);
return(new Item {
Volume = x, Label = entry.Label, IsValidation = n % 10 == 0
});
}
private Volume GetVolume(Signature signature)
{
var x = new Volume(_imageSize, _imageSize, 1, 0.0);
foreach (var point in signature.SignaturePointList)
{
x.Weights[point.X * _imageSize + point.Y] = 1;
}
x = x.Augment(_imageSize);
return(x);
}
private TrainingItem GenerateTrainingInstance()
{
Random random = new Random();
bool isValidation = random.Next(10) == 0;
int userId = random.Next(_userList.Count);
var user = _userList[userId];
// Calculate signature index
int signatureIndex;
var testRange = user.SignatureList.Count * 3 / 4;
if (!isValidation)
{
signatureIndex = random.Next(testRange);
}
else
{
signatureIndex = testRange + random.Next(user.SignatureList.Count - testRange);
}
var signature = user.SignatureList[signatureIndex];
// Create volume from image data
var x = new Volume(imageSize, imageSize, 1, 0.0);
foreach (var point in signature.SignaturePointList)
{
x.Weights[point.X * imageSize + point.Y] = 1;
}
x = x.Augment(imageSize);
return(new TrainingItem {
Volume = x, ClassIndex = user.UserId == neededUserId? 1 : 0, IsValidation = isValidation
});
}
public void Demo()
{
// Load data
_userList = ReadingManager.ReadData(@"C:\Users\RustamSalakhutdinov\Documents\visual studio 2015\Projects\signatureChecker\data_new");
// Create network
_net = new Net();
_net.AddLayer(new InputLayer(imageSize, imageSize, 1));
_net.AddLayer(new ConvLayer(5, 5, 16)
{
Stride = 1, Pad = 1, Activation = Activation.Relu
});
_net.AddLayer(new PoolLayer(2, 2)
{
Stride = 2
});
_net.AddLayer(new ConvLayer(5, 5, 8)
{
Stride = 1, Pad = 1, Activation = Activation.Relu
});
_net.AddLayer(new PoolLayer(2, 2)
{
Stride = 2
});
_net.AddLayer(new SoftmaxLayer(2));
_trainer = new Trainer(_net)
{
BatchSize = 20,
L2Decay = 0.001,
TrainingMethod = Trainer.Method.Adagrad
};
Stopwatch sw = Stopwatch.StartNew();
do
{
var sample = GenerateTrainingInstance();
if (!Step(sample))
{
break;
}
} while (!Console.KeyAvailable);
sw.Stop();
Console.WriteLine(sw.ElapsedMilliseconds / 1000.0);
foreach (User user in _userList)
{
Random random = new Random();
var signature = user.SignatureList[random.Next(user.SignatureList.Count)];
var x = new Volume(imageSize, imageSize, 1, 0.0);
foreach (var point in signature.SignaturePointList)
{
x.Weights[point.X * imageSize + point.Y] = 1;
}
x = x.Augment(imageSize);
var result = _net.Forward(x);
Console.WriteLine("UserId: {0}. Result: {1} | {2}", user.UserId, result.Weights[0], result.Weights[1]);
}
}
