DtdDataLoaderOptions

Options & Configuration · AiDotNet.Data.Vision.Benchmarks

Configuration options for the Describable Textures Dataset (DTD) loader (Cimpoi et al. 2014).

How It Works

DTD — 47 texture classes × 120 images each (5,640 total). The canonical texture-classification benchmark. Ten predefined train/val/test splits; this loader uses split #1 by default (matches the standard reporting convention). Image-list-based labels via labels/{train,val,test}1.txt.

Constructors

Constructor Summary
DtdDataLoaderOptions()

Properties

Property Summary
DatasetSplit Split { get; set; } Gets or sets which split of the dataset is loaded.
bool AutoDownload { get; set; } Gets or sets whether the dataset is downloaded into the data directory when it is not there.
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 SplitIndex { get; set; } Predefined split index (1..10).
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.