/// <summary>
/// Add a new set of data.
/// </summary>
/// <param name="mcm"></param>
/// <param name="timeTaken"></param>
public void AddData(MulticlassClassificationMetrics mcm, double timeTaken)
{
MacroAccuracy.AddValue(mcm.MacroAccuracy);
MicroAccuracy.AddValue(mcm.MicroAccuracy);
LogLoss.AddValue(mcm.LogLoss);
LogLossReduction.AddValue(mcm.LogLossReduction);
TimeTakenMiliSeconds.AddValue(timeTaken);
StatConfusionMatrix.AddConfusionMatrix(mcm.ConfusionMatrix);
}
public void LogLoss_Loss()
{
var sut = new LogLoss();
var targets = Matrix <float> .Build.Dense(3, 2, new float[] { 1f, 1f, 0f, 0f, 0f, 1, });
var predictions = Matrix <float> .Build.Dense(3, 2, new float[] { 0.9f, 0.9f, 0.1f, .1f, .1f, .9f });
var actual = sut.Loss(targets, predictions);
Assert.AreEqual(0.105360545, actual, 0.001);
}
/// <summary>
/// Add a set of evaluation metrics to the set of observations.
/// </summary>
/// <param name="metrics">The observed binary classification evaluation metric</param>
void IMetricsStatistics <MultiClassClassifierMetrics> .Add(MultiClassClassifierMetrics metrics)
{
MacroAccuracy.Add(metrics.MacroAccuracy);
MicroAccuracy.Add(metrics.MicroAccuracy);
LogLoss.Add(metrics.LogLoss);
LogLossReduction.Add(metrics.LogLossReduction);
TopKAccuracy.Add(metrics.TopKAccuracy);
if (PerClassLogLoss == null)
{
PerClassLogLoss = MetricsStatisticsUtils.InitializeArray(metrics.PerClassLogLoss.Count);
}
MetricsStatisticsUtils.AddToEach(metrics.PerClassLogLoss, PerClassLogLoss);
}
public static double Train()
{
var startTime = System.Diagnostics.Stopwatch.StartNew();
Data data = allData.Take(trainDataSize);
int inputSize = 28 * 28, outputSize = 10, deep;
deep = width.Count + 1;
//double[] init = new double[5] { 1, 1, 1, 1, 1 }, bias = new double[5] { 1, 1, 1, 1, 1 };
ILossFunction <double> loss = new LogLoss();
Model m = new Model(deep, width.ToArray(), 1, 1, inputSize, outputSize, true, trainMatrixRandomCenter, trainMatrixRandomOffset, trainReLUCoef, trainSigmoidCoef);
m.LogEpoch = logEpoch;
m.LogBatch = logBatch;
m.Train(data, trainEpoch, trainBatch, trainTeachRate, loss);
m.Save(modelPath);
startTime.Stop();
return(startTime.ElapsedMilliseconds);
}
private static void Main()
{
/*basic config*/
const int batchSize = 256;
const int maxEpo = 100;
const float learningRate = 1e-4f;
const float weightDecay = 1e-4f;
/*context and net symbol*/
var ctx = Context.Gpu();
var net = AlexnetSymbol(2);
/*args_map and aux_map is used for parameters' saving*/
var argsMap = new Dictionary <string, NDArray>();
var auxMap = new Dictionary <string, NDArray>();
/*we should tell mxnet the shape of data and label*/
argsMap["data"] = new NDArray(new Shape(batchSize, 3, 256, 256), ctx);
argsMap["label"] = new NDArray(new Shape(batchSize), ctx);
/*with data and label, executor can be generated varmatically*/
using (var exec = net.SimpleBind(ctx, argsMap))
{
var argNames = net.ListArguments();
var auxiliaryDictionary = exec.AuxiliaryDictionary();
var argmentDictionary = exec.ArgmentDictionary();
/*if fine tune from some pre-trained model, we should load the parameters*/
// NDArray.Load("./model/alex_params_3", nullptr, &args_map);
/*else, we should use initializer Xavier to init the params*/
var xavier = new Xavier(RandType.Gaussian, FactorType.In, 2.34f);
foreach (var arg in argmentDictionary)
{
/*be careful here, the arg's name must has some specific ends or starts for
* initializer to call*/
xavier.Operator(arg.Key, arg.Value);
}
/*print out to check the shape of the net*/
foreach (var s in net.ListArguments())
{
Logging.LG(s);
var sb = new StringBuilder();
var k = argmentDictionary[s].GetShape();
foreach (var i in k)
{
sb.Append($"{i} ");
}
Logging.LG(sb.ToString());
}
/*these binary files should be generated using im2rc tools, which can be found
* in mxnet/bin*/
var trainIter = new MXDataIter("ImageRecordIter")
.SetParam("path_imglist", "./data/train.lst")
.SetParam("path_imgrec", "./data/train.rec")
.SetParam("data_shape", new Shape(3, 256, 256))
.SetParam("batch_size", batchSize)
.SetParam("shuffle", 1)
.CreateDataIter();
var valIter = new MXDataIter("ImageRecordIter")
.SetParam("path_imglist", "./data/val.lst")
.SetParam("path_imgrec", "./data/val.rec")
.SetParam("data_shape", new Shape(3, 256, 256))
.SetParam("batch_size", batchSize)
.CreateDataIter();
var opt = OptimizerRegistry.Find("ccsgd");
opt.SetParam("momentum", 0.9)
.SetParam("rescale_grad", 1.0 / batchSize)
.SetParam("clip_gradient", 10)
.SetParam("lr", learningRate)
.SetParam("wd", weightDecay);
var accuracyTrain = new Accuracy();
var accuracyVal = new Accuracy();
var loglossVal = new LogLoss();
for (var iter = 0; iter < maxEpo; ++iter)
{
Logging.LG($"Train Epoch: {iter}");
/*reset the metric every epoch*/
accuracyTrain.Reset();
/*reset the data iter every epoch*/
trainIter.Reset();
while (trainIter.Next())
{
var batch = trainIter.GetDataBatch();
Logging.LG($"{trainIter.GetDataBatch().Index.Length}");
/*use copyto to feed new data and label to the executor*/
batch.Data.CopyTo(argmentDictionary["data"]);
batch.Label.CopyTo(argmentDictionary["label"]);
exec.Forward(true);
exec.Backward();
for (var i = 0; i < argNames.Count; ++i)
{
if (argNames[i] == "data" || argNames[i] == "label")
{
continue;
}
opt.Update(i, exec.ArgmentArrays[i], exec.GradientArrays[i]);
}
NDArray.WaitAll();
accuracyTrain.Update(batch.Label, exec.Outputs[0]);
}
Logging.LG($"ITER: {iter} Train Accuracy: {accuracyTrain.Get()}");
Logging.LG($"Val Epoch: {iter}");
accuracyVal.Reset();
valIter.Reset();
loglossVal.Reset();
while (valIter.Next())
{
var batch = valIter.GetDataBatch();
Logging.LG($"{valIter.GetDataBatch().Index.Length}");
batch.Data.CopyTo(argmentDictionary["data"]);
batch.Label.CopyTo(argmentDictionary["label"]);
exec.Forward(false);
NDArray.WaitAll();
accuracyVal.Update(batch.Label, exec.Outputs[0]);
loglossVal.Update(batch.Label, exec.Outputs[0]);
}
Logging.LG($"ITER: {iter} Val Accuracy: {accuracyVal.Get()}");
Logging.LG($"ITER: {iter} Val LogLoss: {loglossVal.Get()}");
/*save the parameters*/
var savePathParam = $"./model/alex_param_{iter}";
var saveArgs = argmentDictionary;
/*we do not want to save the data and label*/
if (saveArgs.ContainsKey("data"))
{
saveArgs.Remove("data");
}
if (saveArgs.ContainsKey("label"))
{
saveArgs.Remove("label");
}
/*the alexnet does not get any aux array, so we do not need to save
* aux_map*/
Logging.LG($"ITER: {iter} Saving to...{savePathParam}");
NDArray.Save(savePathParam, saveArgs);
}
/*don't foget to release the executor*/
}
MXNet.MXNotifyShutdown();
}
