:py:mod:`orcanet_contrib.custom_objects`
========================================

.. py:module:: orcanet_contrib.custom_objects


Module Contents
---------------


Functions
~~~~~~~~~

.. autoapisummary::

   orcanet_contrib.custom_objects.get_custom_objects
   orcanet_contrib.custom_objects.loss_mean_relative_error_energy
   orcanet_contrib.custom_objects.loss_uncertainty_mae
   orcanet_contrib.custom_objects.loss_uncertainty_mse
   orcanet_contrib.custom_objects.loss_uncertainty_gaussian_likelihood
   orcanet_contrib.custom_objects.loss_uncertainty_gaussian_likelihood_dir
   orcanet_contrib.custom_objects.loss_direction
   orcanet_contrib.custom_objects.loss_direction_grad
   orcanet_contrib.custom_objects.mean_absolute_error



Attributes
~~~~~~~~~~

.. autoapisummary::

   orcanet_contrib.custom_objects.dir_y_true


.. py:function:: get_custom_objects()

   
   Functions that returns a dict with all relevant loss functions in this file.
















   ..
       !! processed by numpydoc !!

.. py:function:: loss_mean_relative_error_energy(y_true, y_pred)

   
   Loss function that calculates the mean relative error.
   y_true & y_pred are expected to be e_true & e_pred.
   L = (e_reco - e_true) / e_true



   :Returns:

       **mre** : Mean relative (energy) error loss
           ..













   ..
       !! processed by numpydoc !!

.. py:function:: loss_uncertainty_mae(y_true, y_pred)

   
   Mean absolute error loss for the uncertainty estimation.
   L = sigma_pred / abs(label_true - label_reco).



   :Returns:

       **loss** : Mean absolute error for uncertainty estimations.
           ..













   ..
       !! processed by numpydoc !!

.. py:function:: loss_uncertainty_mse(y_true, y_pred)

   
   Mean squared error loss for the uncertainty estimation.
   L = sigma_pred / abs(label_true - label_reco)**2.



   :Returns:

       **loss** : Mean squared error for uncertainty estimations.
           ..













   ..
       !! processed by numpydoc !!

.. py:function:: loss_uncertainty_gaussian_likelihood(y_true, y_pred)

   
   Loss function that calculates something similar to a Gaussian Likelihood.
   Requires that y_pred contains only one predicted value (label).
   y_true & y_pred are expected to contain the predicted/true label and
   the predicted std for the label.
   L = ln(std ** 2) + (y_label_pred - y_label_true) / (std ** 2)



   :Returns:

       **loss** : Gaussian Likelihood loss
           ..













   ..
       !! processed by numpydoc !!

.. py:function:: loss_uncertainty_gaussian_likelihood_dir(y_true, y_pred)

   
   Loss function that calculates something similar to a Gaussian
   Likelihood for predicted directions. Requires that y_pred contains
   three predicted values (labels): dir_x, dir_y, dir_z.
   y_true & y_pred are expected to contain the predicted/true label and
   the predicted std for the label.
   L = ln(std ** 2) + (y_label_pred - y_label_true) / (std ** 2)



   :Returns:

       **loss** : Gaussian Likelihood loss for the directional error
           ..













   ..
       !! processed by numpydoc !!

.. py:function:: loss_direction(y_true, y_pred)

   
   Loss function that calculates the space angle between the predicted
   and the true direction.
   Not used anymore, can lead to inf gradients due to tf.acos(space_angle_inner_value)!
   Converts cartesian dirs to spherical coordinate system and then
   calculates the space angle between the two vectors.



   :Returns:

       **total_loss** : Space angle loss
           ..













   ..
       !! processed by numpydoc !!

.. py:function:: loss_direction_grad()

   
   Similar loss function as in loss_direction, but here it is just used
   for manually calculating the gradient in the  main function. Done in
   order to protect the loss_direction function from inf gradients.
















   ..
       !! processed by numpydoc !!

.. py:function:: mean_absolute_error(y_true, y_pred)

   
   Copy of the Keras mean absolute error function for testing purposes.
















   ..
       !! processed by numpydoc !!

.. py:data:: dir_y_true