PascalVocDataLoaderOptions
Options & Configuration · AiDotNet.Data.Vision.Benchmarks
Configuration options for the Pascal VOC data loader.
How It Works
Pascal VOC (Visual Object Classes) is a classic object detection benchmark with 20 categories. VOC2007 has 5K train/val + 5K test images. VOC2012 has 11.5K train/val images. Annotations are in XML format (one per image).
Constructors
| Constructor | Summary |
|---|---|
PascalVocDataLoaderOptions() |
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 MaxDetections { get; set; } |
Maximum number of detections per image. |
int? MaxSamples { get; set; } |
Optional maximum number of samples to load. |
string DataPath { get; set; } |
Root data path. |
string Year { get; set; } |
VOC year version. |