MNIST
classin packageklyn.math.datasets
public class MNIST
MNIST

Loads handwritten-digit data as four statically typed, independent NDArrays. Images have shape [samples, 28, 28], normalized to [0, 1] and stored in the requested floating type (Float by default). Labels are one-dimensional Int arrays, never one-hot encoded.

Example

xTrain, yTrain, xTest, yTest = MNIST.load(Path("mnist"))

Methods
Modifier and Type Member Description
public static load
load<T>(folder as Path = null, trainLimit as Long = 0l, testLimit as Long = 0l, download as Boolean = true) as Tuple<NDArray<T>, NDArray<Int>, NDArray<T>, NDArray<Int>>
Loads the train and t10k IDX image/label files, downloading missing files.