private static WeightsAndBias AddWeights(WeightsAndBias wb1, WeightsAndBias wb2)
{
wb1.Weights.InplaceAdd(wb2.Weights);
wb1.Bias += wb2.Bias;
return(wb1);
}
static void Main(string[] args)
{
Arguments arg;
if ((arg = Arguments.Parse(args)) == null)
{
return;
}
var sw = System.Diagnostics.Stopwatch.StartNew();
Console.Write("Initializing/Connecting to cluster... ");
Logger.ParseArgs(new string[] { "-log", "DistributedSGD.log" });
Prajna.Core.Environment.Init();
var cluster = new Cluster(arg.Cluster);
Console.WriteLine($"done. (took: {sw.Elapsed})");
sw.Restart();
Console.Write("Loading dataset(s)... ");
DSet <Example> trainSet = LoadDSet(cluster, arg.TrainFile, arg.NumPartitions, arg.NumTrain > 0 ? arg.NumTrain : int.MaxValue, 0);
DSet <Example> testSet = arg.TestFile == null ? null : LoadDSet(cluster, arg.TestFile, arg.NumPartitions, arg.NumTest > 0 ? arg.NumTest : int.MaxValue, 0);
Func <DSet <Example>, int> getDimension = ds => ds.Fold((max, ex) => Math.Max(ex.Features.Indices.Max(), max), Math.Max, 0) + 1;
var dimension = Math.Max(getDimension(trainSet), arg.TestFile == null ? 0 : getDimension(testSet));
Console.WriteLine($"done. (took: {sw.Elapsed})");
SetDimension(trainSet, dimension);
Console.WriteLine($"Train Count: {trainSet.Count()}");
float trainPrior = GetPrior(trainSet);
Console.WriteLine($"Train Prior: {trainPrior}");
if (arg.TestFile != null)
{
SetDimension(testSet, dimension);
Console.WriteLine($"Test Count: {testSet.Count()}");
float testPrior = GetPrior(testSet);
Console.WriteLine($"Test Prior: {testPrior}");
}
ILossFunction loss;
switch (arg.Loss.ToLower())
{
case "logistic":
loss = new LogisticLoss();
break;
case "hinge":
loss = new HingeLoss();
break;
default:
Console.WriteLine($"Unrecognized loss function: {arg.Loss}. Supported values: Hinge, Logistic.");
return;
}
if (arg.ModelOut != null)
{
if (!Directory.Exists(Path.GetDirectoryName(arg.ModelOut)))
{
Console.WriteLine($"Directory {Path.GetDirectoryName(arg.ModelOut)} not found.");
return;
}
}
var model = new LinearModel(new HingeLoss(), arg.LearningRate, arg.L2, arg.L1);
var initialParams = new WeightsAndBias(new float[dimension], 0.0f);
WeightsAndBias finalParams = RunSGD(trainSet, testSet, model, initialParams, DistributedSGD <WeightsAndBias> .Instance, arg.NumEpochs);
if (arg.ModelOut != null)
{
Console.WriteLine();
Console.Write("Done training. Saving model... ");
sw.Restart();
using (var writer = new StreamWriter(arg.ModelOut))
{
writer.WriteLine("Dimension:");
writer.WriteLine(finalParams.Weights.Length);
writer.WriteLine("Weights:");
foreach (var w in finalParams.Weights)
{
writer.WriteLine(w);
}
writer.WriteLine("Bias:");
writer.WriteLine(finalParams.Bias);
}
Console.WriteLine($"done. (took: {sw.Elapsed})");
}
}
