RowShuffle<T>
Models & Types · AiDotNet.Augmentation.Tabular
Shuffles rows within a batch of tabular data.
Inheritance: AugmentationBase<T, Matrix<T>> → TabularAugmenterBase<T> → RowShuffle<T>
For Beginners
Row shuffling randomly reorders the samples in your data. While this doesn’t create new data, it ensures the model doesn’t learn from the order of samples, which is especially important when data has natural ordering.
How It Works
When to use:
- When data has natural temporal or sequential ordering
- As part of mini-batch training to randomize batch composition
- When consecutive samples might be correlated
Constructors
| Constructor | Summary |
|---|---|
RowShuffle(double probability) |
Creates a new row shuffle augmentation. |
Methods
| Method | Summary |
|---|---|
ValueTuple<Matrix<T>, Vector<T>> ShuffleWithLabels(Matrix<T> data, Vector<T> labels, AugmentationContext<T> context) |
Shuffles data and labels together, maintaining row correspondence. |