ddu¶
- probly.method.ddu(base: Predictor[In, Out], sn_coeff: float = 3.0) DDUPredictor[In, Out][source]¶
Apply spectral normalization and add a Gaussian-mixture density head.
Based on [MKvA+23].
- Parameters:
base – Base classification model to be transformed.
sn_coeff – Lipschitz coefficient for spectral normalization.
- Returns:
The transformed DDU predictor.
