RetinalFundusDataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads retinal fundus photography datasets for diabetic retinopathy detection (5-class grading).

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

How It Works

Retinal Fundus expects:

The CSV has columns: image (filename without extension), level (0-4 severity grade). Labels are one-hot encoded as Tensor[N, 5] for the 5 DR severity levels.

Constructors

Constructor Summary
RetinalFundusDataLoader(RetinalFundusDataLoaderOptions options) Creates a new Retinal Fundus data loader.

Properties

Property Summary
IReadOnlyList<string> SeverityNames { get; } Gets the severity level 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)