PubLayNetDataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads the PubLayNet document layout analysis dataset.

Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → PubLayNetDataLoader<T>

How It Works

PubLayNet expects:

Features are flattened image pixels Tensor[N, H * W * 3]. Labels are layout region count per class Tensor[N, NumClasses].

Constructors

Constructor Summary
PubLayNetDataLoader(PubLayNetDataLoaderOptions options)

Properties

Property Summary
int FeatureCount { get; }
int OutputDimension { get; }
int TotalCount { get; }
string Description { get; }
string Name { get; }

Methods

Method Summary
ValueTuple<IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>> Split(double trainRatio, double validationRatio, int? seed)