Food101DataLoaderOptions
Options & Configuration · AiDotNet.Data.Vision.Benchmarks
Configuration options for the Food-101 image classification data loader.
How It Works
Food-101 (Bossard et al. 2014) — 101 food categories, 101,000 images total (750 train + 250 test per class). Standard fine-grained classification benchmark. Auto-downloads from the ETH Zürich mirror.
Constructors
| Constructor | Summary |
|---|---|
Food101DataLoaderOptions() |
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? 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. |