Constraints¶
Linear Weight Constraints¶
These should be used for linear accumulators.
-
class
libspn_keras.constraints.
GreaterEqualEpsilonNormalized
(epsilon=1e-10, axis=- 2)¶ Constraints the weight to be greater than or equal to epsilon and then normalizes.
- Parameters
epsilon (
float
) – Constant, usually small non-zero
-
class
libspn_keras.constraints.
GreaterEqualEpsilon
(epsilon=1e-10)¶ Constraints the weight to be greater than or equal to epsilon.
- Parameters
epsilon (
float
) – Constant, usually small non-zero
Log Weight Constraints¶
These should be used for log accumulators.
-
class
libspn_keras.constraints.
LogNormalized
(axis=- 2)¶ Normalizes log-space weights.
- Parameters
axis (int) – Axis along whichto normalize
Scale Constraints¶
The following constraint is useful for ensuring stable scale parameters in location-scale leaf layers.
-
class
libspn_keras.constraints.
Clip
(min, max=None)¶ Constraints the weights to be between
min
andmax
.- Parameters
min (
float
) – Minimum clip valuemax (
Optional
[float
]) – Maximum clip value