coco_pipe.decoding.foundation_models.validation
===============================================

.. py:module:: coco_pipe.decoding.foundation_models.validation

.. autoapi-nested-parse::

   Opt-in real-checkpoint validation for foundation-model registry entries.



Attributes
----------

.. autoapisummary::

   coco_pipe.decoding.foundation_models.validation.DEFAULT_CHANNELS


Functions
---------

.. autoapisummary::

   coco_pipe.decoding.foundation_models.validation.validate_real_checkpoints
   coco_pipe.decoding.foundation_models.validation.validate_real_training
   coco_pipe.decoding.foundation_models.validation.main


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

.. py:data:: DEFAULT_CHANNELS
   :value: ['Fp1', 'Fp2', 'F7', 'F3', 'Fz', 'F4', 'F8', 'T7', 'C3', 'Cz', 'C4', 'T8', 'P7', 'P3', 'Pz',...


.. py:function:: validate_real_checkpoints(model_keys = ('cbramod', 'labram', 'reve', 'luna'), device = 'cpu', token = None, ch_names = None)

   Download each checkpoint and run one headless forward pass.

   :param ch_names: Montage to validate against. Defaults to :data:`DEFAULT_CHANNELS`
                    (a representative 19-channel 10-20 set). Pass the study's actual
                    channel list to exercise the exact channel adaptation (e.g. the real
                    ``128 x N`` LaBraM interpolation) the cohort run will use.
   :type ch_names: sequence of str, optional


.. py:function:: validate_real_training(model_keys = ('cbramod', 'labram', 'reve', 'luna'), train_modes = ('linear_probe', 'full', 'lora'), device = 'cpu', token = None, max_epochs = 1, ch_names = None)

   Run tiny grouped training and checkpoint-reload smoke tests.

   ``ch_names`` defaults to :data:`DEFAULT_CHANNELS`; pass the study montage
   to train against the exact channel adaptation used in cohort runs.


.. py:function:: main()