SelfTeacherModel<T>
Models & Types · AiDotNet.KnowledgeDistillation.Teachers
Self teacher model that uses the student’s own predictions from earlier training.
Inheritance: TeacherModelBase<Vector<T>, Vector<T>, T> → SelfTeacherModel<T>
For Beginners
Self-distillation is a technique where a model learns from its own
earlier predictions. This teacher stores pre-computed predictions from earlier epochs and
returns them by index via GetCachedPrediction.
Constructors
| Constructor | Summary |
|---|---|
SelfTeacherModel(int outputDimension) |
Initializes a new instance of SelfTeacherModel for cached predictions mode. |
Properties
| Property | Summary |
|---|---|
int OutputDimension { get; } |
Gets the output dimension of the teacher model. |
Methods
| Method | Summary |
|---|---|
Vector<T> GetCachedPrediction(int index) |
Gets a cached prediction by index. |
Vector<T> GetLogits(Vector<T> input) |
Not supported for SelfTeacherModel — always throws. |
void CachePredictions(Vector<T>[] predictions) |