ImageNet1kDataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads the ImageNet-1K (ILSVRC 2012) image classification dataset (~1.28M train / 50K val, 1000 classes).

Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → ImageNet1kDataLoader<T>

How It Works

ImageNet-1K expects a directory structure of:

Images are loaded as RGB, resized to ImageSize x ImageSize, and optionally normalized to [0,1]. Labels are one-hot encoded across 1000 classes, ordered by synset ID alphabetically.

Constructors

Constructor Summary
ImageNet1kDataLoader(ImageNet1kDataLoaderOptions options) Creates a new ImageNet-1K data loader.

Properties

Property Summary
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)