tfl.linear_lib.project

Applies constraints to weights.

tfl.linear_lib.project(
    weights,
    monotonicities,
    monotonic_dominances=None,
    range_dominances=None,
    input_min=None,
    input_max=None,
    normalization_order=None
)

weights Tensor which represents weights of TFL linear layer. Must have shape [len(monotonicities), units].
monotonicities List or tuple of same length as number of elements in 'weights' of {-1, 0, 1} which represent monotonicity constraints per dimension. -1 stands for decreasing, 0 for no constraints, 1 for increasing.
monotonic_dominances List of two-element tuples. First element is the index of the dominant feature. Second element is the index of the weak feature.
range_dominances List of two-element tuples. First element is the index of the dominant feature. Second element is the index of the weak feature.
input_min List or tuple of length same length as number of elements in 'weights' of either None or float to compute input range for range dominance projection.
input_max List or tuple of length same length as number of elements in 'weights' of either None or float to compute input range for range dominance projection.
normalization_order If specified weights will be adjusted to have norm 1. Norm will be computed by: tf.norm(tensor, ord=normalization_order).

ValueError If shape of weights is not (len(monotonicities), units).

'weights' with monotonicity constraints and normalization applied to it.