IEpisodicDataset<T, TInput, TOutput>

Interfaces · AiDotNet.Interfaces

Interface for episodic datasets used in meta-learning.

Properties

Property Summary
bool HasMoreEpisodes { get; } Gets whether the dataset has more episodes.
int ClassesPerEpisode { get; } Gets the number of classes per episode (N-way).
int EpisodeCount { get; } Gets the total number of episodes in the dataset.
int ExamplesPerClass { get; } Gets the number of examples per class (K-shot).
int QueryExamplesPerClass { get; } Gets the number of query examples per class.

Methods

Method Summary
IMetaLearningTask<T, TInput, TOutput> GetEpisode(int episodeIndex) Gets a specific episode from the dataset.
List<IMetaLearningTask<T, TInput, TOutput>> GetEpisodeBatch(int batchSize, bool shuffle) Gets a batch of episodes from the dataset.
List<IMetaLearningTask<T, TInput, TOutput>> SampleTasks(int numTasks, int? episodeIndex) Samples a batch of tasks from the dataset.
void Reset() Resets the dataset to the beginning.
void SetRandomSeed(int seed) Sets the random seed for reproducible sampling.
void Shuffle() Shuffles the dataset.