WeightedSampler<T>
Models & Types · AiDotNet.Data.Sampling
A sampler that samples indices based on their weights.
Inheritance: DataSamplerBase → WeightedSamplerBase<T> → WeightedSampler<T>
For Beginners
This sampler lets you control how often each sample appears:
- Higher weight = more likely to be selected
- Lower weight = less likely to be selected
Common uses:
- Class imbalance: Give higher weights to underrepresented classes
- Hard example mining: Give higher weights to samples the model struggles with
- Curriculum learning: Adjust weights during training based on difficulty
Example:
How It Works
WeightedSampler selects samples with probability proportional to their weights. This is useful for handling class imbalance, importance sampling, or focusing training on harder examples.
Constructors
| Constructor | Summary |
|---|---|
WeightedSampler(IEnumerable<T> weights, int? numSamples, bool replacement, int? seed) |
Initializes a new instance of the WeightedSampler class. |
Methods
| Method | Summary |
|---|---|
T[] CreateBalancedWeights(IReadOnlyList<int> labels, int numClasses) |
Creates weights that balance class frequencies. |