Namespace AiDotNet.Data.Sampling
Classes
- ActiveLearningSampler<T>
A sampler for active learning that selects the most informative samples for labeling.
- CurriculumSampler<T>
A sampler that implements curriculum learning by progressively introducing harder samples.
- DataSamplerBase
Base class for all data samplers providing common functionality.
- EpochAdaptiveSamplerBase<T>
Base class for epoch-adaptive samplers that change behavior over training epochs.
- ImportanceSampler<T>
A sampler that implements importance sampling for variance reduction.
- RandomSampler
A sampler that randomly shuffles the dataset indices each epoch.
- Samplers
Static factory class for creating data samplers with beginner-friendly methods.
- SelfPacedSampler<T>
A sampler that implements self-paced learning with automatic difficulty adjustment.
- SequentialSampler
A sampler that returns indices in sequential order without shuffling.
- StratifiedBatchSampler
A batch sampler that ensures each batch contains samples from all classes.
- StratifiedSampler
A sampler that ensures each class is represented proportionally in each epoch.
- SubsetSampler
A sampler that returns a subset of indices.
- WeightedSamplerBase<T>
Base class for weighted samplers providing common weight-based functionality.
- WeightedSampler<T>
A sampler that samples indices based on their weights.
Enums
- ActiveLearningStrategy
Active learning selection strategies.
- CurriculumStrategy
Defines how the curriculum progresses over epochs.