tf.keras.constraints.Constraint

Base class for weight constraints.

A Constraint instance works like a stateless function. Users who subclass this class should override the __call__() method, which takes a single weight parameter and return a projected version of that parameter (e.g. normalized or clipped). Constraints can be used with various Keras layers via the kernel_constraint or bias_constraint arguments.

Here's a simple example of a non-negative weight constraint:

class NonNegative(keras.constraints.Constraint):

 def __call__(self, w):
   return w * ops.cast(ops.greater_equal(w, 0.), dtype=w.dtype)

weight = ops.convert_to_tensor((-1.0, 1.0))
NonNegative()(weight)
[0.,  1.]

Usage in a layer:

keras.layers.Dense(4, kernel_constraint=NonNegative())

Methods

from_config

View source

@classmethod
from_config(
    config
)

Instantiates a weight constraint from a configuration dictionary.

Example:

constraint = UnitNorm()
config = constraint.get_config()
constraint = UnitNorm.from_config(config)

get_config

View source

get_config()

Returns a Python dict of the object config.

A constraint config is a Python dictionary (JSON-serializable) that can be used to reinstantiate the same object.

__call__

View source

__call__(
    w
)

Applies the constraint to the input weight variable.

By default, the inputs weight variable is not modified. Users should override this method to implement their own projection function.