MultiModalTeacherModel<T>

Models & Types ยท AiDotNet.KnowledgeDistillation.Teachers

Multi-modal teacher that combines multiple input modalities (vision, text, audio).

Inheritance: TeacherModelBase<Vector<T>, Vector<T>, T> โ†’ MultiModalTeacherModel<T>

Constructors

Constructor Summary
MultiModalTeacherModel(ITeacherModel<Vector<T>, Vector<T>>[] modalityTeachers, double[] modalityWeights)

Properties

Property Summary
int OutputDimension { get; }

Methods

Method Summary
Vector<T> GetLogits(Vector<T> input) Gets combined logits from all modality teachers.