CocoDetectionDataLoaderOptions
Options & Configuration · AiDotNet.Data.Vision.Benchmarks
Configuration options for the COCO Detection data loader.
How It Works
COCO (Common Objects in Context) 2017 Detection contains 118K training and 5K validation images with 80 object categories. Annotations include bounding boxes, segmentation masks, and captions. This loader focuses on the object detection task (bounding boxes + class labels).
Constructors
| Constructor | Summary |
|---|---|
CocoDetectionDataLoaderOptions() |
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. |
Methods
| Method | Summary |
|---|---|
void Validate() |
Validates that all option values are within acceptable ranges. |