ChestXray14DataLoaderOptions

Options & Configuration · AiDotNet.Data.Vision.Benchmarks

Configuration options for the NIH Chest X-ray 14 data loader.

How It Works

NIH Chest X-ray 14 contains 112,120 frontal-view chest X-ray images from 30,805 unique patients with 14 disease labels mined from radiology reports using NLP. This is a multi-label classification task where each image can have zero or more of the 14 disease labels.

Constructors

Constructor Summary
ChestXray14DataLoaderOptions()

Properties

Property Summary
DatasetSplit Split { get; set; } Dataset split to load.
bool AutoDownload { get; set; } Automatically download if not present.
bool Normalize { get; set; } Normalize pixel values to [0, 1].
int ImageSize { get; set; } Target image size.
int? MaxSamples { get; set; } Optional maximum number of samples to load.
string DataPath { get; set; } Root data path.