Places365DataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads the Places365 scene recognition dataset (1.8M train / 36.5K val, 256x256 RGB, 365 scene categories).

Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → Places365DataLoader<T>

How It Works

Places365 expects a directory structure where each scene category is a subfolder:

Alternatively, expects a categories file (categories_places365.txt) and image list files (places365_train_standard.txt, places365_val.txt) for label mapping.

Constructors

Constructor Summary
Places365DataLoader(Places365DataLoaderOptions options) Creates a new Places365 data loader.

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)