FashionMnistDataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads the Fashion-MNIST clothing classification dataset (60k train / 10k test, 28x28 grayscale).

Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → FashionMnistDataLoader<T>

How It Works

Fashion-MNIST is a drop-in replacement for MNIST with clothing images (t-shirt, trouser, pullover, etc.). Same format (28x28 grayscale, 10 classes) but more challenging.

Constructors

Constructor Summary
FashionMnistDataLoader(FashionMnistDataLoaderOptions options) Creates a new Fashion-MNIST data loader.

Properties

Property Summary
IReadOnlyList<string> ClassNames { get; } Gets the human-readable class names.
int FeatureCount { get; }
int OutputDimension { get; }
int TotalCount { get; }
string Description { get; }
string Name { get; }

Methods

Method Summary
ValueTuple<IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>> Split(double trainRatio, double validationRatio, int? seed)