emmi.utils.running_moments
==========================

.. py:module:: emmi.utils.running_moments


Classes
-------

.. autoapisummary::

   emmi.utils.running_moments.RunningMoments


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

.. py:class:: RunningMoments

   Calculates running moments of data (mean and variance) for data normalization purposes.


   .. py:method:: push_tensor(x, dim=1)

      Add a tensor to the moment calculation. Calculations are carried out in float64 to avoid numerical
      imprecisions.
      :param x: Tensor to push. Shape should be (num_points, dim). The statistics are averaged over the num_points
      :param dim: Which dim (i.e., axis) contains the feature dimension. For example, in a pointcloud dim=1 calculates
                  the mean/std of the x, y and z positions. In an RGB image (batch_size, num_channels, height, width),
                  dim=1 calculates the per-channel mean/std.



   .. py:method:: push_scalar(x)

      Add a scalar to the moment calculation. Calculations are carried out in float64 to avoid numerical
      imprecisions.
      :param x: Scalar to add to the moment calculations.



   .. py:method:: mean()


   .. py:method:: var()


   .. py:method:: std()