Caltech101DataLoaderOptions

Options & Configuration · AiDotNet.Data.Vision.Benchmarks

Configuration options for the Caltech-101 image classification data loader (Fei-Fei et al. 2004).

How It Works

Caltech-101 contains ≈ 9,000 images across 101 object categories plus a background “BACKGROUND_Google” class (102 total). Image counts per category vary from 40 to 800. Pre-CNN era benchmark, still used for few-shot studies. Standard practice samples ≤ 30 images/class for training and uses the rest for testing.

Constructors

Constructor Summary
Caltech101DataLoaderOptions()

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 TrainImagesPerClass { get; set; } Per-class images for the training split.
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.