foscat.SphereUpGeo
==================

.. py:module:: foscat.SphereUpGeo


Classes
-------

.. autoapisummary::

   foscat.SphereUpGeo.SphereUpGeo


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

.. py:class:: SphereUpGeo(nside_out: int, cell_ids_out, radius_deg: float | None = None, sigma_deg: float | None = None, weight_norm: str = 'l1', up_norm: str = 'col_l1', eps: float = 1e-12, device=None, dtype=torch.float32)

   Bases: :py:obj:`torch.nn.Module`


   Geometric HEALPix upsampling operator using the transpose of SphereDownGeo.

   `cell_ids_out` (coarse pixels at nside_out, NESTED) is mandatory.
   Forward expects x of shape [B, C, K_out] aligned with that order.
   Output is a full fine-grid map [B, C, N_in] at nside_in = 2*nside_out.

   Normalization (diagonal corrections):
     - up_norm='adjoint': x_up = M^T x
     - up_norm='col_l1':  x_up = (M^T x) / col_sum, col_sum[i] = sum_k M[k,i]
     - up_norm='diag_l2': x_up = (M^T x) / col_l2,  col_l2[i]  = sum_k M[k,i]^2


   .. py:attribute:: device
      :value: None



   .. py:attribute:: dtype
      :value: Ellipsis



   .. py:attribute:: nside_out


   .. py:attribute:: nside_in


   .. py:attribute:: N_out


   .. py:attribute:: N_in


   .. py:attribute:: up_norm
      :value: ''



   .. py:attribute:: eps


   .. py:attribute:: cell_ids_out_np


   .. py:attribute:: K_out


   .. py:attribute:: M_size


   .. py:attribute:: M_T


   .. py:method:: forward(x: torch.Tensor)

      x: [B, C, K_out] -> x_up: [B, C, N_in].