TinyImageNetDataLoader<T>
Models & Types · AiDotNet.Data.Vision.Benchmarks
Loads the Tiny ImageNet 200-class image-classification dataset (500 train + 50 val + 50 test per class at 64×64).
Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → TinyImageNetDataLoader<T>
How It Works
Expects the canonical Stanford CS231n directory layout:
Auto-download fetches the canonical zip from cs231n.stanford.edu.
Validation labels are mapped via val_annotations.txt; test
labels are zeroed since they’re hidden upstream.
Constructors
| Constructor | Summary |
|---|---|
TinyImageNetDataLoader(TinyImageNetDataLoaderOptions options) |
Creates a new Tiny ImageNet 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) |