MaestroDataLoader<T>
Models & Types · AiDotNet.Data.Audio.Benchmarks
Loads the MAESTRO piano performance dataset (~200 hours, aligned MIDI and audio).
Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → MaestroDataLoader<T>
How It Works
MAESTRO expects:
CSV columns: canonical_composer, canonical_title, split, year, midi_filename, audio_filename, duration. Features are raw waveform Tensor[N, MaxSamples]. Labels are MIDI note activations Tensor[N, 128] (one per MIDI note).
Constructors
| Constructor | Summary |
|---|---|
MaestroDataLoader(MaestroDataLoaderOptions options) |
Creates a new MAESTRO 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) |