public async Task Test(string dataset, string filename)
{
ModelSerializer modelSerializer = new ModelSerializer();
model = modelSerializer.DeserializeCNN(filename);
fDataSet testdataset = new fDataSet();
testdataset.Deserializer(dataset);
int index = random.Next(0, testdataset.fData.Count);
AI.Core.fDataSet dataSet = new AI.Core.fDataSet();
dataSet.fData = testdataset.fData;
pixel = testdataset.fData[index].Pixel;
label = testdataset.fData[index].DecodeLabel;
//model.predict
probs = model.Predict(dataSet.fData[index]);
AI.ML.CNN.Trainers.ADAM adam = new AI.ML.CNN.Trainers.ADAM();
softmaxOutput = adam.Softmax(probs);
double maxValue = softmaxOutput.Max();
predict = softmaxOutput.ToList().IndexOf(maxValue);
//int lindex = random.Next(0, 5);
//predict = lindex == 2 ? random.Next(0, 9) : label;
result[0] = label;
result[1] = predict;
await Clients.All.SendAsync("ReceiveMessage", pixel);
await Clients.All.SendAsync("ReceiveLabel", result);
}
public virtual Trainer Configure <T>(Model model, int?epochs, fDataSet dataSet, double?learningRate, double?momentum)
where T : CNN.Loss, new()
{
base.Configure(model, epochs, dataSet);
// 0. assert learningRate and momentum
if ((learningRate == null) || (momentum == null))
{
throw new Exception();
}
this.learningRate = learningRate;
this.momentum = momentum;
this.lossfunc = new T();
return(this);
}
partial void test_ai_uByteLoaderToolStripMenuItem_Click(object sender, EventArgs e)
{
//string dataFileName = @"C:\Users\ogban\Documents\mnist\train-images.idx3-ubyte";
//string labelFileName = @"C:\Users\ogban\Documents\mnist\train-labels.idx1-ubyte";
//string log = "";
//IList<fData> dataList = AI.Core.UByteLoader.ReadGrayImage(dataFileName, null, -2.0, 2.0, labelFileName, -1.0, 1.0);
//fDataSet dataSet = new fDataSet();
//dataSet.fData = dataList;
//Random random = new Random();
//int rand = 0;
//for (int i=0; i<20; i++)
//{
// rand = random.Next(0, 60000);
// log += dataList[rand].ToImageString();
// log += dataList[rand].DecodeLabel.ToString();
//}
string dataFileName = @"C:\Users\ogban\Documents\mnist\cifar\cifar-10-batches-bin\data_batch_1.bin";
string[] classes = new string[] { "airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "horse", "ship", "truck" };
string log = "";
IList <fData> dataList = AI.Core.UByteLoader.ReadColorImage(dataFileName, 1, -2.0, 2.0, -1.0, 1.0);
fDataSet dataSet = new fDataSet();
dataSet.fData = dataList;
int size = (int)System.Math.Sqrt(dataSet.fData[0].Pixel.Length / 3);
int[] pixel = null;
pixel = dataSet.fData[0].Pixel;
log += classes[dataSet.fData[0].DecodeLabel];
Mat matImg = new Mat(size, size, DepthType.Cv8U, 3);
Image <Bgr, Byte> img = matImg.ToImage <Bgr, Byte>();
Image <Bgr, Byte> image = setColorPixels(img, size, pixel);
int[] input_size = new int[] { 256, 256 };
int[] resizedPixel = Resize_Color(image, input_size);
//Random random = new Random();
//int rand = 0;
//for (int i = 0; i < 20; i++)
//{
// rand = random.Next(0, 60000);
// log += dataList[rand].ToImageString();
// log += dataList[rand].DecodeLabel.ToString();
//}
richTextBox.Text = log;
}
