ggt.data.dataset
================

.. py:module:: ggt.data.dataset


Classes
-------

.. autoapisummary::

   ggt.data.dataset.FITSDataset


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

.. py:class:: FITSDataset(data_dir, slug=None, split=None, channels=1, cutout_size=167, label_col='bt_g', normalize=True, transform=None, expand_factor=1, repeat_dims=False, label_scaling=None, scaling_data_dir=None, scaling_slug=None, load_labels=True)

   Bases: :py:obj:`torch.utils.data.Dataset`


   Dataset from FITS files. Pre-caches FITS files as PyTorch tensors to
   improve data load speed.


   .. py:attribute:: data_dir


   .. py:attribute:: cutout_shape


   .. py:attribute:: normalize
      :value: True



   .. py:attribute:: transform
      :value: None



   .. py:attribute:: repeat_dims
      :value: False



   .. py:attribute:: expand_factor
      :value: 1



   .. py:attribute:: data_info
      :value: None



   .. py:attribute:: cutouts_path


   .. py:attribute:: tensors_path


   .. py:attribute:: filenames


   .. py:attribute:: observations


   .. py:method:: __getitem__(index)

      Magic method to index into the dataset.



   .. py:method:: __len__()

      Return the effective length of the dataset.



   .. py:method:: load_fits_as_tensor(filename)
      :staticmethod:


      Open a FITS file and convert it to a Torch tensor.