Keras 3 API documentation
Models API The Model class The Sequential class Model training APIs Saving & serialization Knowledge distillation Layers API Callbacks API Ops API Optimizers Metrics Losses Data loading Built-in small datasets Keras Applications Mixed precision Multi-device distribution RNG API Rematerialization Utilities
Keras 2 API documentation
► Keras 3 API documentation / Models API / Knowledge distillation / Base distillation loss

Base distillation loss

[source]

DistillationLoss class

keras.distillation.DistillationLoss()

Base class for distillation loss computation.

Distillation losses define how to compute the distillation loss between teacher and student outputs. Each loss implements a specific approach to knowledge transfer, from simple logits matching to feature-based distillation.

To create custom distillation losses, subclass this class and override the compute_loss method.

Base distillation loss
DistillationLoss class