DocVqaDataLoaderOptions
Options & Configuration · AiDotNet.Data.Vision.Benchmarks
Configuration options for the DocVQA (Document Visual Question Answering) data loader.
How It Works
DocVQA contains document images with questions and answers. Standard benchmark for document understanding models combining OCR and visual reasoning.
Constructors
| Constructor | Summary |
|---|---|
DocVqaDataLoaderOptions() |
Properties
| Property | Summary |
|---|---|
DatasetSplit Split { get; set; } |
Dataset split to load. |
bool AutoDownload { get; set; } |
Automatically download if not present. |
int ImageHeight { get; set; } |
Image height after resizing. |
int ImageWidth { get; set; } |
Image width after resizing. |
int MaxAnswerLength { get; set; } |
Maximum answer character length for text encoding. |
int MaxQuestionLength { get; set; } |
Maximum question token length. |
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. |