Kinetics400DataLoader<T>
Models & Types · AiDotNet.Data.Video.Benchmarks
Loads the Kinetics-400 human action recognition dataset (~300K clips, 400 classes).
Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → Kinetics400DataLoader<T>
How It Works
Kinetics-400 expects pre-extracted frames:
Features are frame tensors Tensor[N, FramesPerVideo * FrameHeight * FrameWidth * 3]. Labels are one-hot Tensor[N, 400].
Constructors
| Constructor | Summary |
|---|---|
Kinetics400DataLoader(Kinetics400DataLoaderOptions options) |
Creates a new Kinetics-400 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) |