StanfordCarsDataLoaderOptions

Options & Configuration · AiDotNet.Data.Vision.Benchmarks

Configuration for the Stanford Cars dataset loader (Krause et al. 2013).

How It Works

Stanford Cars — 196 fine-grained car-model classes, 16,185 images. Standard fine-grained classification benchmark. Original Stanford URLs have been intermittent over the years, so AutoDownload defaults to false; download manually from the various community mirrors or HuggingFace and extract under DataPath.

Constructors

Constructor Summary
StanfordCarsDataLoaderOptions()

Properties

Property Summary
DatasetSplit Split { get; set; } Gets or sets which split of the dataset is loaded.
bool AutoDownload { get; set; } Auto-download is OFF by default — Stanford URLs are unstable.
bool Normalize { get; set; } Gets or sets whether pixel values are scaled to [0, 1].
int ImageSize { get; set; } Gets or sets the side length, in pixels, images are resized to.
int? MaxSamples { get; set; } Gets or sets the most samples loaded; null loads the whole split.
string DataPath { get; set; } Gets or sets the dataset root directory; null uses the default data directory for this dataset.

Methods

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