/// <summary>
/// Main methods for model training
/// </summary>
/// <param name="mlconfigPath"></param>
/// <param name="token"></param>
/// <param name="trainingProgress"></param>
/// <param name="pdevice"></param>
/// <returns></returns>
public static TrainResult TrainModel(string mlconfigPath, CancellationToken token, TrainingProgress trainingProgress, ProcessDevice pdevice)
{
try
{
//device definition
DeviceDescriptor device = MLFactory.GetDevice(pdevice);
//LOad ML configuration file
var dicMParameters = MLFactory.LoadMLConfiguration(mlconfigPath);
//add path of model folder
dicMParameters.Add("root", Project.GetMLConfigFolder(mlconfigPath));
//prepare NN data
var retVal = MLFactory.PrepareNNData(dicMParameters, CustomNNModels.CustomModelCallEntryPoint, device);
//create trainer
var tr = new MLTrainer(retVal.f.StreamConfigurations, retVal.f.InputVariables, retVal.f.OutputVariables);
//setup model checkpoint
string modelCheckPoint = null;
if (dicMParameters.ContainsKey("configid"))
{
modelCheckPoint = MLFactory.GetModelCheckPointPath(mlconfigPath, dicMParameters["configid"].Trim(' '));
}
//setup model checkpoint
string historyPath = null;
if (dicMParameters.ContainsKey("configid"))
{
historyPath = MLFactory.GetTrainingHistoryPath(mlconfigPath, dicMParameters["configid"].Trim(' '));
}
//create trainer
var trainer = tr.CreateTrainer(retVal.nnModel, retVal.lrData, retVal.trData, modelCheckPoint, historyPath);
//perform training
var result = tr.Train(trainer, retVal.nnModel, retVal.trData, retVal.mbs, device, token, trainingProgress, modelCheckPoint, historyPath);
return(result);
}
catch (Exception)
{
throw;
}
}
public void RunModel(string mlconfigName, CancellationToken token, TrainingProgress trainingProgress, ProcessDevice pdevice)
{
Project.TrainModel(mlconfigName, token, trainingProgress, pdevice);
}
protected virtual ProgressData progressTraining(TrainingParameters trParams, Trainer trainer,
Function network, MinibatchSourceEx mbs, int epoch, TrainingProgress progress, DeviceDescriptor device)
{
//calculate average training loss and evaluation
var mbAvgLoss = trainer.PreviousMinibatchLossAverage();
var mbAvgEval = trainer.PreviousMinibatchEvaluationAverage();
//get training dataset
double trainEval = mbAvgEval;
//sometimes when the data set is huge validation model against
// full training dataset could take time, so we can skip it by setting parameter 'FullTrainingSetEval'
if (trParams.FullTrainingSetEval)
{
var evParams = new EvaluationParameters()
{
MinibatchSize = trParams.BatchSize,
MBSource = new MinibatchSourceEx(mbs.Type, this.StreamConfigurations.ToArray(), this.InputVariables, this.OutputVariables, mbs.TrainingDataFile, null, MinibatchSource.FullDataSweep, false, 0),
Ouptut = OutputVariables,
Input = InputVariables,
};
var result = MLEvaluator.EvaluateFunction(trainer.Model(), evParams, device);
trainEval = MLEvaluator.CalculateMetrics(trainer.EvaluationFunction().Name, result.actual, result.predicted, device);
}
string bestModelPath = m_bestModelPath;
double validEval = 0;
//in case validation data set is empty don't perform test-minibatch
if (!string.IsNullOrEmpty(mbs.ValidationDataFile))
{
var evParams = new EvaluationParameters()
{
MinibatchSize = trParams.BatchSize,
//StrmsConfig = StreamConfigurations.ToArray(),
MBSource = new MinibatchSourceEx(mbs.Type, this.StreamConfigurations.ToArray(), this.InputVariables, this.OutputVariables, mbs.ValidationDataFile, null, MinibatchSource.FullDataSweep, false, 0),
Ouptut = OutputVariables,
Input = InputVariables,
};
//
var result = MLEvaluator.EvaluateFunction(trainer.Model(), evParams, device);
validEval = MLEvaluator.CalculateMetrics(trainer.EvaluationFunction().Name, result.actual, result.predicted, device);
}
//here we should decide if the current model worth to be saved into temp location
// depending of the Evaluation function which sometimes can be better if it is greater that previous (e.g. ClassificationAccuracy)
if (isBetterThanPrevious(trainEval, validEval, StatMetrics.IsGoalToMinimize(trainer.EvaluationFunction())) && trParams.SaveModelWhileTraining)
{
//save model
var strFilePath = $"{trParams.ModelTempLocation}\\model_at_{epoch}of{trParams.Epochs}_epochs_TimeSpan_{DateTime.Now.Ticks}";
if (!Directory.Exists(trParams.ModelTempLocation))
{
Directory.CreateDirectory(trParams.ModelTempLocation);
}
//save temp model
network.Save(strFilePath);
//set training and validation evaluation to previous state
m_PrevTrainingEval = trainEval;
m_PrevValidationEval = validEval;
bestModelPath = strFilePath;
var tpl = Tuple.Create <double, double, string>(trainEval, validEval, strFilePath);
m_ModelEvaluations.Add(tpl);
}
m_bestModelPath = bestModelPath;
//create progressData object
var prData = new ProgressData();
prData.EpochTotal = trParams.Epochs;
prData.EpochCurrent = epoch;
prData.EvaluationFunName = trainer.EvaluationFunction().Name;
prData.TrainEval = trainEval;
prData.ValidationEval = validEval;
prData.MinibatchAverageEval = mbAvgEval;
prData.MinibatchAverageLoss = mbAvgLoss;
//prData.BestModel = bestModelPath;
//the progress is only reported if satisfied the following condition
if (progress != null && (epoch % trParams.ProgressFrequency == 0 || epoch == 1 || epoch == trParams.Epochs))
{
//add info to the history
m_trainingHistory.Add(new Tuple <int, float, float, float, float>(epoch, (float)mbAvgLoss, (float)mbAvgEval,
(float)trainEval, (float)validEval));
//send progress
progress(prData);
//
//Console.WriteLine($"Epoch={epoch} of {trParams.Epochs} processed.");
}
//return progress data
return(prData);
}
/// <summary>
/// Main method for training
/// </summary>
/// <param name="trainer"></param>
/// <param name="network"></param>
/// <param name="trParams"></param>
/// <param name="miniBatchSource"></param>
/// <param name="device"></param>
/// <param name="token"></param>
/// <param name="progress"></param>
/// <param name="modelCheckPoint"></param>
/// <returns></returns>
public override TrainResult Train(Trainer trainer, Function network, TrainingParameters trParams,
MinibatchSourceEx miniBatchSource, DeviceDescriptor device, CancellationToken token, TrainingProgress progress, string modelCheckPoint, string historyPath)
{
try
{
//create trainer result.
// the variable indicate how training process is ended
// completed, stopped, crashed,
var trainResult = new TrainResult();
var historyFile = "";
//create training process evaluation collection
//for each iteration it is stored evaluationValue for training, and validation set with the model
m_ModelEvaluations = new List <Tuple <double, double, string> >();
//check what is the optimization (Minimization (error) or maximization (accuracy))
bool isMinimize = StatMetrics.IsGoalToMinimize(trainer.EvaluationFunction());
//setup first iteration
if (m_trainingHistory == null)
{
m_trainingHistory = new List <Tuple <int, float, float, float, float> >();
}
//in case of continuation of training iteration must start with the last of path previous training process
int epoch = (m_trainingHistory.Count > 0)? m_trainingHistory.Last().Item1 + 1:1;
//define progressData
ProgressData prData = null;
//define helper variable collection
var vars = InputVariables.Union(OutputVariables).ToList();
//training process
while (true)
{
//get next mini batch data
var args = miniBatchSource.GetNextMinibatch(trParams.BatchSize, device);
var isSweepEnd = args.Any(a => a.Value.sweepEnd);
//prepare the data for trainer
var arguments = MinibatchSourceEx.ToMinibatchValueData(args, vars);
trainer.TrainMinibatch(arguments, isSweepEnd, device);
//make progress
if (isSweepEnd)
{
//check the progress of the training process
prData = progressTraining(trParams, trainer, network, miniBatchSource, epoch, progress, device);
//check if training process ends
if (epoch >= trParams.Epochs)
{
//save training checkpoint state
if (!string.IsNullOrEmpty(modelCheckPoint))
{
trainer.SaveCheckpoint(modelCheckPoint);
}
//save training history
if (!string.IsNullOrEmpty(historyPath))
{
string header = $"{trainer.LossFunction().Name};{trainer.EvaluationFunction().Name};";
MLFactory.SaveTrainingHistory(m_trainingHistory, header, historyPath);
}
//save best or last trained model and send report last time before trainer completes
var bestModelPath = saveBestModel(trParams, trainer.Model(), epoch, isMinimize);
//
if (progress != null)
{
progress(prData);
}
//
trainResult.Iteration = epoch;
trainResult.ProcessState = ProcessState.Compleated;
trainResult.BestModelFile = bestModelPath;
trainResult.TrainingHistoryFile = historyFile;
break;
}
else
{
epoch++;
}
}
//stop in case user request it
if (token.IsCancellationRequested)
{
if (!string.IsNullOrEmpty(modelCheckPoint))
{
trainer.SaveCheckpoint(modelCheckPoint);
}
//save training history
if (!string.IsNullOrEmpty(historyPath))
{
string header = $"{trainer.LossFunction().Name};{trainer.EvaluationFunction().Name};";
MLFactory.SaveTrainingHistory(m_trainingHistory, header, historyPath);
}
//sometime stopping training process can be before first epoch passed so make a incomplete progress
if (prData == null)//check the progress of the training process
{
prData = progressTraining(trParams, trainer, network, miniBatchSource, epoch, progress, device);
}
//save best or last trained model and send report last time before trainer terminates
var bestModelPath = saveBestModel(trParams, trainer.Model(), epoch, isMinimize);
//
if (progress != null)
{
progress(prData);
}
//setup training result
trainResult.Iteration = prData.EpochCurrent;
trainResult.ProcessState = ProcessState.Stopped;
trainResult.BestModelFile = bestModelPath;
trainResult.TrainingHistoryFile = historyFile;
break;
}
}
return(trainResult);
}
catch (Exception ex)
{
var ee = ex;
throw;
}
finally
{
}
}
/// <summary>
/// Calback from the training in order to inform user about trining progress
/// </summary>
/// <param name="trParams"></param>
/// <param name="trainer"></param>
/// <param name="network"></param>
/// <param name="mbs"></param>
/// <param name="epoch"></param>
/// <param name="progress"></param>
/// <param name="device"></param>
/// <returns></returns>
protected virtual ProgressData progressTraining(TrainingParameters trParams, Trainer trainer,
Function network, MinibatchSourceEx mbs, int epoch, TrainingProgress progress, DeviceDescriptor device)
{
//calculate average training loss and evaluation
var mbAvgLoss = trainer.PreviousMinibatchLossAverage();
var mbAvgEval = trainer.PreviousMinibatchEvaluationAverage();
var vars = InputVariables.Union(OutputVariables).ToList();
//get training dataset
double trainEval = mbAvgEval;
//sometimes when the data set is huge validation model against
// full training dataset could take time, so we can skip it by setting parameter 'FullTrainingSetEval'
if (trParams.FullTrainingSetEval)
{
if (m_TrainData == null || m_TrainData.Values.Any(x => x.data.IsValid == false))
{
using (var streamDatat = MinibatchSourceEx.GetFullBatch(mbs.Type, mbs.TrainingDataFile, mbs.StreamConfigurations, device))
{
//get full training dataset
m_TrainData = MinibatchSourceEx.ToMinibatchData(streamDatat, vars, mbs.Type);
}
//perform evaluation of the current model on whole training dataset
trainEval = trainer.TestMinibatch(m_TrainData, device);
}
}
string bestModelPath = m_bestModelPath;
double validEval = 0;
//in case validation data set is empty don't perform test-minibatch
if (!string.IsNullOrEmpty(mbs.ValidationDataFile))
{
if (m_ValidationData == null || m_ValidationData.Values.Any(x => x.data.IsValid == false))
{
//get validation dataset
using (var streamData = MinibatchSourceEx.GetFullBatch(mbs.Type, mbs.ValidationDataFile, mbs.StreamConfigurations, device))
{
//store validation data for future testing
m_ValidationData = MinibatchSourceEx.ToMinibatchData(streamData, vars, mbs.Type);
}
}
//perform evaluation of the current model with validation dataset
validEval = trainer.TestMinibatch(m_ValidationData, device);
}
//here we should decide if the current model worth to be saved into temp location
// depending of the Evaluation function which sometimes can be better if it is greater that previous (e.g. ClassificationAccuracy)
if (isBetterThanPrevious(trainEval, validEval, StatMetrics.IsGoalToMinimize(trainer.EvaluationFunction())) && trParams.SaveModelWhileTraining)
{
//save model
var strFilePath = $"{trParams.ModelTempLocation}\\model_at_{epoch}of{trParams.Epochs}_epochs_TimeSpan_{DateTime.Now.Ticks}";
if (!Directory.Exists(trParams.ModelTempLocation))
{
Directory.CreateDirectory(trParams.ModelTempLocation);
}
//save temp model
network.Save(strFilePath);
//set training and validation evaluation to previous state
m_PrevTrainingEval = trainEval;
m_PrevValidationEval = validEval;
bestModelPath = strFilePath;
var tpl = Tuple.Create <double, double, string>(trainEval, validEval, strFilePath);
m_ModelEvaluations.Add(tpl);
}
m_bestModelPath = bestModelPath;
//create progressData object
var prData = new ProgressData();
prData.EpochTotal = trParams.Epochs;
prData.EpochCurrent = epoch;
prData.EvaluationFunName = trainer.EvaluationFunction().Name;
prData.TrainEval = trainEval;
prData.ValidationEval = validEval;
prData.MinibatchAverageEval = mbAvgEval;
prData.MinibatchAverageLoss = mbAvgLoss;
//the progress is only reported if satisfied the following condition
if (progress != null && (epoch % trParams.ProgressFrequency == 0 || epoch == 1 || epoch == trParams.Epochs))
{
//add info to the history
m_trainingHistory.Add(new Tuple <int, float, float, float, float>(epoch, (float)mbAvgLoss, (float)mbAvgEval,
(float)trainEval, (float)validEval));
//send progress
progress(prData);
//
//Console.WriteLine($"Epoch={epoch} of {trParams.Epochs} processed.");
}
//return progress data
return(prData);
}
public bool Stop(TrainingProgress progress) => progress.Loss <= SmallestRequiredLoss ? true : false;
