tfl.linear_lib.verify_hyperparameters

Verifies that all given hyperparameters are consistent.

tfl.linear_lib.verify_hyperparameters(
    num_input_dims=None,
    units=None,
    input_shape=None,
    monotonicities=None,
    monotonic_dominances=None,
    range_dominances=None,
    input_min=None,
    input_max=None,
    weights_shape=None
)

This function does not inspect weights themselves. Only their shape. Use assert_constraints() to assert actual weights against constraints.

Unlike linear layer itself this function requires monotonicites to be specified via list or tuple rather than via single element because that's how monotonicites are stored internaly.

See tfl.layers.Linear Layer class level comment for detailed description of arguments.

num_input_dims None or number of input dimensions.
units Units hyperparameter of Linear layer.
input_shape Shape of layer input.
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 which specifies the minimum value to clip by.
input_max List or tuple of length same length as number of elements in 'weights' of either None or float which specifies the maximum value to clip by.
weights_shape None or shape of tensor which represents weights of Linear layer.

ValueError If something is inconsistent.