ImageNet21kDataLoader<T>
Models & Types · AiDotNet.Data.Vision.Benchmarks
Loads the ImageNet-21K dataset (~14.2M images, 21,841 categories from the full WordNet hierarchy).
Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → ImageNet21kDataLoader<T>
How It Works
ImageNet-21K uses the same directory structure as ImageNet-1K (synset folders), but with 21K+ categories.
The dataset must be downloaded manually from https://image-net.org/.
Use MaxClasses and MaxSamples to load manageable subsets.
Constructors
| Constructor | Summary |
|---|---|
ImageNet21kDataLoader(ImageNet21kDataLoaderOptions options) |
Creates a new ImageNet-21K 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) |