/// <summary>
/// The constructor.
/// </summary>
/// <param name="mycaffe">Specifies the instance of MyCaffe assoiated with the open project - when using more than one Brain, this is the master project.</param>
/// <param name="properties">Specifies the properties passed into the trainer.</param>
/// <param name="random">Specifies the random number generator used.</param>
/// <param name="phase">Specifies the phase under which to run.</param>
public Brain(MyCaffeControl <T> mycaffe, PropertySet properties, CryptoRandom random, Phase phase)
{
m_mycaffe = mycaffe;
m_solver = mycaffe.GetInternalSolver();
m_netOutput = mycaffe.GetInternalNet(phase);
m_netTarget = new Net <T>(m_mycaffe.Cuda, m_mycaffe.Log, m_netOutput.net_param, m_mycaffe.CancelEvent, null, phase);
m_properties = properties;
m_random = random;
Blob <T> data = m_netOutput.blob_by_name("data");
if (data == null)
{
m_mycaffe.Log.FAIL("Missing the expected input 'data' blob!");
}
m_nBatchSize = data.num;
Blob <T> logits = m_netOutput.blob_by_name("logits");
if (logits == null)
{
m_mycaffe.Log.FAIL("Missing the expected input 'logits' blob!");
}
m_nActionCount = logits.channels;
m_transformer = m_mycaffe.DataTransformer;
m_blobActions = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log, false);
m_blobQValue = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log);
m_blobNextQValue = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log);
m_blobExpectedQValue = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log);
m_blobDone = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log, false);
m_blobLoss = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log);
m_blobWeights = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log, false);
m_fGamma = (float)properties.GetPropertyAsDouble("Gamma", m_fGamma);
m_memLoss = m_netOutput.FindLastLayer(LayerParameter.LayerType.MEMORY_LOSS) as MemoryLossLayer <T>;
if (m_memLoss == null)
{
m_mycaffe.Log.FAIL("Missing the expected MEMORY_LOSS layer!");
}
double?dfRate = mycaffe.CurrentProject.GetSolverSettingAsNumeric("base_lr");
if (dfRate.HasValue)
{
m_dfLearningRate = dfRate.Value;
}
m_nMiniBatch = m_properties.GetPropertyAsInt("MiniBatch", m_nMiniBatch);
m_bUseAcceleratedTraining = properties.GetPropertyAsBool("UseAcceleratedTraining", false);
if (m_nMiniBatch > 1)
{
m_colAccumulatedGradients = m_netOutput.learnable_parameters.Clone();
m_colAccumulatedGradients.SetDiff(0);
}
}
public Brain(MyCaffeControl <T> mycaffe, PropertySet properties, CryptoRandom random, Phase phase)
{
m_mycaffe = mycaffe;
m_net = mycaffe.GetInternalNet(phase);
m_solver = mycaffe.GetInternalSolver();
m_properties = properties;
m_random = random;
m_memData = m_net.FindLayer(LayerParameter.LayerType.MEMORYDATA, null) as MemoryDataLayer <T>;
m_memLoss = m_net.FindLayer(LayerParameter.LayerType.MEMORY_LOSS, null) as MemoryLossLayer <T>;
SoftmaxLayer <T> softmax = m_net.FindLayer(LayerParameter.LayerType.SOFTMAX, null) as SoftmaxLayer <T>;
if (softmax != null)
{
throw new Exception("The PG.SIMPLE trainer does not support the Softmax layer, use the 'PG.ST' or 'PG.MT' trainer instead.");
}
if (m_memData == null)
{
throw new Exception("Could not find the MemoryData Layer!");
}
if (m_memLoss == null)
{
throw new Exception("Could not find the MemoryLoss Layer!");
}
m_memLoss.OnGetLoss += memLoss_OnGetLoss;
m_blobDiscountedR = new Blob <T>(mycaffe.Cuda, mycaffe.Log);
m_blobPolicyGradient = new Blob <T>(mycaffe.Cuda, mycaffe.Log);
m_nMiniBatch = mycaffe.CurrentProject.GetBatchSize(phase);
}
public Brain(MyCaffeControl <T> mycaffe, PropertySet properties, CryptoRandom random, Phase phase)
{
m_mycaffe = mycaffe;
m_net = mycaffe.GetInternalNet(phase);
m_solver = mycaffe.GetInternalSolver();
m_properties = properties;
m_random = random;
m_memData = m_net.FindLayer(LayerParameter.LayerType.MEMORYDATA, null) as MemoryDataLayer <T>;
m_memLoss = m_net.FindLayer(LayerParameter.LayerType.MEMORY_LOSS, null) as MemoryLossLayer <T>;
m_softmax = m_net.FindLayer(LayerParameter.LayerType.SOFTMAX, null) as SoftmaxLayer <T>;
if (m_memData == null)
{
throw new Exception("Could not find the MemoryData Layer!");
}
if (m_memLoss == null)
{
throw new Exception("Could not find the MemoryLoss Layer!");
}
m_memData.OnDataPack += memData_OnDataPack;
m_memLoss.OnGetLoss += memLoss_OnGetLoss;
m_blobDiscountedR = new Blob <T>(mycaffe.Cuda, mycaffe.Log);
m_blobPolicyGradient = new Blob <T>(mycaffe.Cuda, mycaffe.Log);
m_blobActionOneHot = new Blob <T>(mycaffe.Cuda, mycaffe.Log);
m_blobDiscountedR1 = new Blob <T>(mycaffe.Cuda, mycaffe.Log);
m_blobPolicyGradient1 = new Blob <T>(mycaffe.Cuda, mycaffe.Log);
m_blobActionOneHot1 = new Blob <T>(mycaffe.Cuda, mycaffe.Log);
m_blobLoss = new Blob <T>(mycaffe.Cuda, mycaffe.Log);
m_blobAprobLogit = new Blob <T>(mycaffe.Cuda, mycaffe.Log);
if (m_softmax != null)
{
LayerParameter p = new LayerParameter(LayerParameter.LayerType.SOFTMAXCROSSENTROPY_LOSS);
p.loss_weight.Add(1);
p.loss_weight.Add(0);
p.loss_param.normalization = LossParameter.NormalizationMode.NONE;
m_softmaxCe = new SoftmaxCrossEntropyLossLayer <T>(mycaffe.Cuda, mycaffe.Log, p);
}
m_colAccumulatedGradients = m_net.learnable_parameters.Clone();
m_colAccumulatedGradients.SetDiff(0);
int nMiniBatch = mycaffe.CurrentProject.GetBatchSize(phase);
if (nMiniBatch != 0)
{
m_nMiniBatch = nMiniBatch;
}
m_nMiniBatch = m_properties.GetPropertyAsInt("MiniBatch", m_nMiniBatch);
}
/// <summary>
/// The DoWork thread is the main tread used to train or run the model depending on the operation selected.
/// </summary>
/// <param name="sender">Specifies the sender</param>
/// <param name="e">specifies the arguments.</param>
private void m_bw_DoWork(object sender, DoWorkEventArgs e)
{
BackgroundWorker bw = sender as BackgroundWorker;
m_input = e.Argument as InputData;
SettingsCaffe s = new SettingsCaffe();
s.ImageDbLoadMethod = IMAGEDB_LOAD_METHOD.LOAD_ALL;
try
{
m_model.Batch = m_input.Batch;
m_mycaffe = new MyCaffeControl <float>(s, m_log, m_evtCancel);
// Train the model.
if (m_input.Operation == InputData.OPERATION.TRAIN)
{
m_model.Iterations = (int)((m_input.Epochs * 7000) / m_model.Batch);
m_log.WriteLine("Training for " + m_input.Epochs.ToString() + " epochs (" + m_model.Iterations.ToString("N0") + " iterations).", true);
m_log.WriteLine("INFO: " + m_model.Iterations.ToString("N0") + " iterations.", true);
m_log.WriteLine("Using hidden = " + m_input.HiddenSize.ToString() + ", and word size = " + m_input.WordSize.ToString() + ".", true);
// Load the Seq2Seq training model.
NetParameter netParam = m_model.CreateModel(m_input.InputFileName, m_input.TargetFileName, m_input.HiddenSize, m_input.WordSize, m_input.UseSoftmax, m_input.UseExternalIp);
string strModel = netParam.ToProto("root").ToString();
SolverParameter solverParam = m_model.CreateSolver(m_input.LearningRate);
string strSolver = solverParam.ToProto("root").ToString();
byte[] rgWts = loadWeights("sequence");
m_strModel = strModel;
m_strSolver = strSolver;
m_mycaffe.OnTrainingIteration += m_mycaffe_OnTrainingIteration;
m_mycaffe.OnTestingIteration += m_mycaffe_OnTestingIteration;
m_mycaffe.LoadLite(Phase.TRAIN, strSolver, strModel, rgWts, false, false);
if (!m_input.UseSoftmax)
{
MemoryLossLayer <float> lossLayerTraining = m_mycaffe.GetInternalNet(Phase.TRAIN).FindLayer(LayerParameter.LayerType.MEMORY_LOSS, "loss") as MemoryLossLayer <float>;
if (lossLayerTraining != null)
{
lossLayerTraining.OnGetLoss += LossLayer_OnGetLossTraining;
}
MemoryLossLayer <float> lossLayerTesting = m_mycaffe.GetInternalNet(Phase.TEST).FindLayer(LayerParameter.LayerType.MEMORY_LOSS, "loss") as MemoryLossLayer <float>;
if (lossLayerTesting != null)
{
lossLayerTesting.OnGetLoss += LossLayer_OnGetLossTesting;
}
}
m_blobProbs = new Blob <float>(m_mycaffe.Cuda, m_mycaffe.Log);
m_blobScale = new Blob <float>(m_mycaffe.Cuda, m_mycaffe.Log);
TextDataLayer <float> dataLayerTraining = m_mycaffe.GetInternalNet(Phase.TRAIN).FindLayer(LayerParameter.LayerType.TEXT_DATA, "data") as TextDataLayer <float>;
if (dataLayerTraining != null)
{
dataLayerTraining.OnGetData += DataLayerTraining_OnGetDataTraining;
}
// Train the Seq2Seq model.
m_plotsSequenceLoss = new PlotCollection("Sequence Loss");
m_plotsSequenceAccuracyTest = new PlotCollection("Sequence Accuracy Test");
m_plotsSequenceAccuracyTrain = new PlotCollection("Sequence Accuracy Train");
m_mycaffe.Train(m_model.Iterations);
saveWeights("sequence", m_mycaffe);
}
// Run a trained model.
else
{
NetParameter netParam = m_model.CreateModel(m_input.InputFileName, m_input.TargetFileName, m_input.HiddenSize, m_input.WordSize, m_input.UseSoftmax, m_input.UseExternalIp, Phase.RUN);
string strModel = netParam.ToProto("root").ToString();
byte[] rgWts = loadWeights("sequence");
strModel = m_model.PrependInput(strModel);
m_strModelRun = strModel;
int nN = m_model.TimeSteps;
m_mycaffe.LoadToRun(strModel, rgWts, new BlobShape(new List <int>()
{
nN, 1, 1, 1
}), null, null, false, false);
m_blobProbs = new Blob <float>(m_mycaffe.Cuda, m_mycaffe.Log);
m_blobScale = new Blob <float>(m_mycaffe.Cuda, m_mycaffe.Log);
runModel(m_mycaffe, bw, m_input.InputText);
}
}
catch (Exception excpt)
{
throw excpt;
}
finally
{
// Cleanup.
if (m_mycaffe != null)
{
m_mycaffe.Dispose();
m_mycaffe = null;
}
}
}
/// <summary>
/// The constructor.
/// </summary>
/// <param name="mycaffe">Specifies the instance of MyCaffe assoiated with the open project - when using more than one Brain, this is the master project.</param>
/// <param name="properties">Specifies the properties passed into the trainer.</param>
/// <param name="random">Specifies the random number generator used.</param>
/// <param name="phase">Specifies the phase under which to run.</param>
public Brain(MyCaffeControl <T> mycaffe, PropertySet properties, CryptoRandom random, Phase phase)
{
m_mycaffe = mycaffe;
m_solver = mycaffe.GetInternalSolver();
m_netOutput = mycaffe.GetInternalNet(phase);
m_netTarget = new Net <T>(m_mycaffe.Cuda, m_mycaffe.Log, m_netOutput.net_param, m_mycaffe.CancelEvent, null, phase);
m_properties = properties;
m_random = random;
Blob <T> data = m_netOutput.blob_by_name("data");
if (data == null)
{
m_mycaffe.Log.FAIL("Missing the expected input 'data' blob!");
}
m_nFramesPerX = data.channels;
m_nBatchSize = data.num;
Blob <T> logits = m_netOutput.blob_by_name("logits");
if (logits == null)
{
m_mycaffe.Log.FAIL("Missing the expected input 'logits' blob!");
}
m_nActionCount = logits.channels;
m_transformer = m_mycaffe.DataTransformer;
if (m_transformer == null)
{
TransformationParameter trans_param = new TransformationParameter();
int nC = m_mycaffe.CurrentProject.Dataset.TrainingSource.ImageChannels;
int nH = m_mycaffe.CurrentProject.Dataset.TrainingSource.ImageHeight;
int nW = m_mycaffe.CurrentProject.Dataset.TrainingSource.ImageWidth;
m_transformer = new DataTransformer <T>(m_mycaffe.Cuda, m_mycaffe.Log, trans_param, phase, nC, nH, nW);
}
for (int i = 0; i < m_nFramesPerX; i++)
{
m_transformer.param.mean_value.Add(255 / 2); // center each frame
}
m_transformer.param.scale = 1.0 / 255; // normalize
m_transformer.Update();
m_blobActions = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log, false);
m_blobQValue = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log);
m_blobNextQValue = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log);
m_blobExpectedQValue = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log);
m_blobDone = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log, false);
m_blobLoss = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log);
m_blobWeights = new Blob <T>(m_mycaffe.Cuda, m_mycaffe.Log, false);
m_fGamma = (float)properties.GetPropertyAsDouble("Gamma", m_fGamma);
m_memLoss = m_netOutput.FindLastLayer(LayerParameter.LayerType.MEMORY_LOSS) as MemoryLossLayer <T>;
if (m_memLoss == null)
{
m_mycaffe.Log.FAIL("Missing the expected MEMORY_LOSS layer!");
}
double?dfRate = mycaffe.CurrentProject.GetSolverSettingAsNumeric("base_lr");
if (dfRate.HasValue)
{
m_dfLearningRate = dfRate.Value;
}
m_nMiniBatch = m_properties.GetPropertyAsInt("MiniBatch", m_nMiniBatch);
m_bUseAcceleratedTraining = properties.GetPropertyAsBool("UseAcceleratedTraining", false);
if (m_nMiniBatch > 1)
{
m_colAccumulatedGradients = m_netOutput.learnable_parameters.Clone();
m_colAccumulatedGradients.SetDiff(0);
}
}
