public static void LoadData()
{
Downloader.DownloadSample(SampleDataset.MNIST);
var samplePath = Downloader.GetSamplePath(SampleDataset.MNIST);
train = new DataFrameList <float>(DataFrame <float> .LoadBinary(samplePath.TrainX, 60000, imgDim), DataFrame <float> .LoadBinary(samplePath.TrainY, 60000, labelDim));
test = new DataFrameList <float>(DataFrame <float> .LoadBinary(samplePath.TestX, 10000, imgDim), DataFrame <float> .LoadBinary(samplePath.TestY, 10000, labelDim));
}
protected override void AgentReplay(
int batchSize,
OptimizerBase optimizer,
MetricFunction lossMetric,
bool shuffle)
{
var batch = shuffle ? ReplayMemory.ToShuffledBatch(batchSize) : ReplayMemory.ToRandomBatch(batchSize);
var states = new DataFrame <float>(StateShape);
var statesTarget = new DataFrame <float>(StateShape);
foreach (var sample in batch)
{
states.Add(sample.Item1);
statesTarget.Add(sample.Item4 ?? new float[StateShape.TotalSize]);
}
var prediction = Model.Predict(states);
var predictionOfTargetStates = Model.Predict(statesTarget);
var predictionTarget = TargetModel.Predict(statesTarget);
var data = new DataFrameList <float>(StateShape, ActionShape);
for (var i = 0; i < batch.Length; i++)
{
var sample = batch[i];
var t = prediction[i];
if (sample.Item4 == null)
{
t[sample.Item2] = sample.Item3;
}
else
{
var lastValue = float.MinValue;
var valueIndex = 0;
for (var j = 0; j < predictionOfTargetStates[i].Length; j++)
{
if (predictionOfTargetStates[i][j] > lastValue)
{
lastValue = predictionOfTargetStates[i][j];
valueIndex = j;
}
}
t[sample.Item2] = (float)(sample.Item3 + DiscountFactor * predictionTarget[i][valueIndex]);
}
data.AddFrame(sample.Item1, t);
}
Model.Fit(data, 1, batch.Length, optimizer, lossMetric);
}
public static void LoadData()
{
CsvDataFrame <float> frame = new CsvDataFrame <float>();
Downloader.DownloadSample(SampleDataset.HousingRegression);
var samplePath = Downloader.GetSamplePath(SampleDataset.HousingRegression);
frame.ReadCsv(samplePath.Train, true);
DataFrame <float> trainX = frame[1, 13];
DataFrame <float> trainY = frame[14, 1];
trainData = new DataFrameList <float>(trainX, trainY);
}
public static void LoadData()
{
featureShape = new Shape(2);
labelShape = new Shape(1);
DataFrame frameX = new DataFrame(featureShape);
DataFrame frameY = new DataFrame(labelShape);
/*
* //One approach of building dataset
* trainData.Add(new List<float>() { 0, 0 }, 0);
* trainData.Add(new List<float>() { 0, 1 }, 1);
* trainData.Add(new List<float>() { 1, 0 }, 1);
* trainData.Add(new List<float>() { 1, 1 }, 0);
* trainData.YFrame.OneHotEncode();
*/
//Second approach
frameX.Add(0, 0); frameY.Add(0);
frameX.Add(0, 1); frameY.Add(1);
frameX.Add(1, 0); frameY.Add(1);
frameX.Add(1, 1); frameY.Add(0);
trainData = new DataFrameList(frameX, frameY);
}
