FMoWDataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads the Functional Map of the World (fMoW) satellite imagery dataset (1M+ images, 62 categories).

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

How It Works

fMoW expects:

Each category has sequenced image folders with RGB images and JSON metadata. Labels are one-hot encoded as Tensor[N, 62].

Constructors

Constructor Summary
FMoWDataLoader(FMoWDataLoaderOptions options) Creates a new fMoW data loader.

Properties

Property Summary
IReadOnlyList<string> ClassNames { get; } Gets the 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)