ChestXray14DataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads the NIH Chest X-ray 14 multi-label classification dataset (112K images, 14 disease labels).

Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → ChestXray14DataLoader<T>

How It Works

Chest X-ray 14 expects:

The CSV contains columns: Image Index, Finding Labels, Follow-up #, Patient ID, Patient Age, etc. Finding Labels is a pipe-separated list of disease names (e.g., “Atelectasis|Effusion”). Labels are multi-hot encoded as Tensor[N, 14] where each dimension corresponds to a disease.

Constructors

Constructor Summary
ChestXray14DataLoader(ChestXray14DataLoaderOptions options) Creates a new ChestX-ray14 data loader.

Properties

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