Fsd50kDataLoader<T>
Models & Types · AiDotNet.Data.Audio.Benchmarks
Loads the FSD50K audio event dataset (51,197 clips, 200 sound event classes).
Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → Fsd50kDataLoader<T>
How It Works
FSD50K expects:
CSV columns: fname, labels (comma-separated class names), mids, split. Features are raw waveform Tensor[N, MaxSamples]. Labels are multi-hot Tensor[N, 200].
Constructors
| Constructor | Summary |
|---|---|
Fsd50kDataLoader(Fsd50kDataLoaderOptions options) |
Creates a new FSD50K 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) |