OxfordPetsDataLoaderOptions

Options & Configuration ยท AiDotNet.Data.Vision.Benchmarks

Configuration options for the Oxford-IIIT Pet dataset loader (Parkhi et al. 2012).

How It Works

Oxford-IIIT Pets โ€” 37 dog/cat breeds, ~200 images per breed (7,349 total). Standard fine-grained classification benchmark with both species (binary) and breed (37-way) labels. Filenames encode breeds: e.g. Abyssinian_100.jpg.

Constructors

Constructor Summary
OxfordPetsDataLoaderOptions()

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 byte pixel values to [0, 1] when true (default), or keep raw 0..255 when false.
int ImageSize { get; set; } Target square image edge in pixels.
int? MaxSamples { get; set; } Optional maximum number of samples to load (for fast iteration / smoke testing).
string DataPath { get; set; } Root data path.

Methods

Method Summary
void Validate() Validates that all option values are within acceptable ranges.