Places365DataLoaderOptions
Options & Configuration · AiDotNet.Data.Vision.Benchmarks
Configuration options for the Places365 data loader.
How It Works
Places365 is a scene recognition dataset with 1.8M training images across 365 scene categories (e.g., bedroom, kitchen, forest, highway). Available in standard (256x256) and challenge (high-res) versions.
Constructors
| Constructor | Summary |
|---|---|
Places365DataLoaderOptions() |
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 pixel values to [0, 1]. |
int ImageSize { get; set; } |
Target image size. |
int? MaxSamples { get; set; } |
Optional maximum number of samples to load. |
string DataPath { get; set; } |
Root data path. |