Usage of constraints
Functions from the
constraints module allow setting constraints (eg. non-negativity) on network parameters during optimization.
The penalties are applied on a per-layer basis. The exact API will depend on the layer, but the layers
Conv3D have a unified API.
These layers expose 2 keyword arguments:
kernel_constraintfor the main weights matrix
bias_constraintfor the bias.
from keras.constraints import maxnorm model.add(Dense(64, kernel_constraint=max_norm(2.)))
- max_norm(max_value=2, axis=0): maximum-norm constraint
- non_neg(): non-negativity constraint
- unit_norm(): unit-norm constraint, enforces the matrix to have unit norm along the last axis