Stl10DataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads the STL-10 image classification dataset (Coates et al. 2011) at native 96×96 resolution.

Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → Stl10DataLoader<T>

How It Works

Expects the canonical Stanford binary release:

Auto-downloads the canonical tarball. Pixel data is stored channel-major (R·R·…G·G·…B·B·…) and column-major within a channel — this loader transposes to standard row-major HWC during decoding.

Constructors

Constructor Summary
Stl10DataLoader(Stl10DataLoaderOptions 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)