Caltech101DataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads the Caltech-101 image classification dataset (Fei-Fei et al. 2004).

Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → Caltech101DataLoader<T>

How It Works

Expects:

or the directory layout extracted directly under {DataPath}. Auto-download fetches the canonical Caltech.edu zip. Standard split: first TrainImagesPerClass images per class go to train, the rest go to test/validation (split == Validation gets the same set as Test since Caltech-101 has no canonical val split).

Constructors

Constructor Summary
Caltech101DataLoader(Caltech101DataLoaderOptions options)

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)