SkinLesionDataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads the ISIC Skin Lesion classification dataset (~25K images, 8 diagnostic categories).

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

How It Works

Skin Lesion expects:

The ground truth CSV has columns: image, MEL, NV, BCC, AK, BKL, DF, VASC, SCC. Each column is 0.0 or 1.0, with exactly one positive per row (one-hot). Labels are stored as Tensor[N, 8].

Constructors

Constructor Summary
SkinLesionDataLoader(SkinLesionDataLoaderOptions options) Creates a new Skin Lesion data loader.

Properties

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