/// <summary>
/// Generates output predictions for the input samples. Computation is done in batches.
/// </summary>
/// <param name="x">The input data frame to run prediction.</param>
/// <param name="batch_size">Size of the batch.</param>
/// <returns></returns>
public DataFrame Predict(DataFrame x, int batch_size)
{
DataFrameIter dataFrameIter = new DataFrameIter(x);
List <float> predictions = new List <float>();
dataFrameIter.SetBatchSize(batch_size);
while (dataFrameIter.Next())
{
var data = dataFrameIter.GetBatchX();
SuperArray output = data;
foreach (var layer in Layers)
{
if (layer.SkipPred)
{
continue;
}
layer.Forward(output);
output = layer.Output;
}
predictions.AddRange(output.List <float>());
}
DataFrame result = new DataFrame();
result.Load(predictions.ToArray());
return(result);
}
/// <summary>
/// Generates output predictions for the input samples. Computation is done in batches.
/// </summary>
/// <param name="x">The input data frame to run prediction.</param>
/// <param name="batch_size">Size of the batch.</param>
/// <returns></returns>
public Tensor Predict(DataFrame x, int batch_size)
{
DataFrameIter dataFrameIter = new DataFrameIter(x);
List <float> predictions = new List <float>();
dataFrameIter.SetBatchSize(batch_size);
long[] outshape = null;
while (dataFrameIter.Next())
{
var data = dataFrameIter.GetBatchX();
Tensor output = data;
foreach (var layer in Layers)
{
if (layer.SkipPred)
{
continue;
}
layer.Forward(output);
output = layer.Output;
}
predictions.AddRange(output.ToArray().Cast <float>());
}
return(K.CreateVariable(predictions.ToArray(), outshape));
}
/// <summary>
/// Trains the model for a given number of epochs (iterations on a dataset).
/// </summary>
/// <param name="train">The train dataset which is an instance of DataFrame Iter.</param>
/// <param name="epochs">Integer. Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided. Note that in conjunction with initial_epoch, epochs is to be understood as "final epoch". The model is not trained for a number of iterations given by epochs, but merely until the epoch of index epochs is reached.</param>
/// <param name="batchSize">Integer or None. Number of samples per gradient update. If unspecified, batch_size will default to 32.</param>
/// <param name="val">The validation set of data to evaluate the model at every epoch.</param>
public void Train(DataFrameIter train, int epochs, int batchSize, DataFrameIter val = null)
{
LearningHistory = new History();
Stopwatch trainWatch = new Stopwatch();
try
{
Stopwatch batchWatch = new Stopwatch();
long n = train.DataSize;
trainWatch.Start();
train.SetBatchSize(batchSize);
if (val != null)
{
val.SetBatchSize(batchSize);
}
for (int iteration = 1; iteration <= epochs; iteration++)
{
batchWatch.Restart();
OnEpochStart(iteration);
RunEpoch(iteration, train, val);
batchWatch.Stop();
long samplesSeen = n * 1000 / (batchWatch.ElapsedMilliseconds + 1);
if (val == null)
{
OnEpochEnd(iteration, samplesSeen, train_losses.Average(), 0, train_metrics.Average(), 0, batchWatch.ElapsedMilliseconds);
}
else
{
OnEpochEnd(iteration, samplesSeen, train_losses.Average(), val_losses.Average(), train_metrics.Average(), val_metrics.Average(), batchWatch.ElapsedMilliseconds);
}
LearningHistory.Add(train_losses, train_metrics, val_losses, val_metrics);
}
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
trainWatch.Stop();
OnTrainingEnd(LearningHistory, trainWatch.ElapsedMilliseconds);
}
