Attend the Women in ML Symposium on December 7 Register now

Module: tfl.pwl_calibration_lib

Stay organized with collections Save and categorize content based on your preferences.

Implementation of algorithms required for PWL calibration layer.

Classes

class BoundConstraintsType: Type of bound constraints for PWL calibration.

Functions

assert_constraints(...): Asserts that 'outputs' satisfiy constraints.

compute_interpolation_weights(...): Computes weights for PWL calibration.

convert_all_constraints(...): Converts parameters of PWL calibration layer to internal format.

linear_initializer(...): Initializes PWL calibration layer to represent linear function.

project_all_constraints(...): Jointly projects into all supported constraints.

verify_hyperparameters(...): Verifies that all given hyperparameters are consistent.

absolute_import Instance of __future__._Feature
division Instance of __future__._Feature
print_function Instance of __future__._Feature