EpisodicDataLoaderTaskSamplerAdapter<T, TInput, TOutput>
Models & Types · AiDotNet.MetaLearning.Data
Adapter that wraps an existing IEpisodicDataLoader
to implement the ITaskSampler interface.
This provides backward compatibility so that legacy data loaders can be used
with the new task-sampler-based infrastructure.
Implements: ITaskSampler<T, TInput, TOutput>
Constructors
| Constructor | Summary |
|---|---|
EpisodicDataLoaderTaskSamplerAdapter(IEpisodicDataLoader<T, TInput, TOutput> loader) |
Creates an adapter wrapping the given episodic data loader. |
Properties
| Property | Summary |
|---|---|
int NumQueryPerClass { get; } |
|
int NumShots { get; } |
|
int NumWays { get; } |
Methods
| Method | Summary |
|---|---|
IEpisode<T, TInput, TOutput> SampleOne() |
|
TaskBatch<T, TInput, TOutput> SampleBatch(int batchSize) |
|
void SetSeed(int seed) |
|
void UpdateWithFeedback(IReadOnlyList<IEpisode<T, TInput, TOutput>> episodes, IReadOnlyList<double> losses) |