Module: tfl.conditional_pwl_calibration

Implements PWLCalibration with derived parameters (kernels).

pwl_calibration_fn is similar to tfl.layers.PWLCalibration with the key difference that the keypoints are decided by the given parameters instead of learnable weights belonging to a layer. These parameters can be one of:

  • constants,
  • trainable variables,
  • outputs from other TF modules.

For inputs of shape (batch_size, units), two sets of parameters are required to configure the piece-wise linear calibrator in terms of its x and y values:

  • keypoint_input_parameters for configuring the x values,
  • keypoint_output_parameters for configuring the y values.

This function is a general form of conditional calibration, that one input variable is calibrated based on free form parameters coming from other variables and their transformations.

Shapes:

The last dimension sizes of keypoint_input_parameters (input_param_size) and keypoint_output_parameters (output_param_size) depend on the number of keypoints used by the calibrator. We follow the relationships that

  • input_param_size = # keypoints - 2, as the leftmost and rightmost keypoints are given.
  • output_param_size = # keypoints initially, and we then modify it by

    1. if cyclic calibrator: output_param_size -= 1,
    2. if clamp_min: output_param_size -= 1,
    3. if clamp_max: output_param_size -= 1,
    4. if need to learn how to impute missing: output_param_size += 1.

The final shapes need to be broadcast friendly with (batch_size, units, 1):

  • keypoint_input_parameters: (1 or batch_size, 1 or units, input_param_size).
  • keypoint_output_parameters: (1 or batch_size, 1 or units, output_param_size).

Functions

default_keypoint_input_parameters(...): Helper creating default keypoint_input_parameters.

default_keypoint_output_parameters(...): Helper creating default keypoint_output_parameters.

pwl_calibration_fn(...): Calibrates inputs using derived parameters (kernels).