protosleepnet.baselines.test_seq_1ch
====================================

.. py:module:: protosleepnet.baselines.test_seq_1ch

.. autoapi-nested-parse::

   Evaluate single-channel SeqSleepNet-Phan on MASS (in-domain).

   Loads the pretrained model from HuggingFace and evaluates on the MASS
   test split using per-subject voting (L=20). Saves per-subject predictions
   and aggregated metrics.

   Usage:
       python -m protosleepnet.baselines.test_seq_1ch --gpu_id 0



Attributes
----------

.. autoapisummary::

   protosleepnet.baselines.test_seq_1ch.CHANNELS
   protosleepnet.baselines.test_seq_1ch.CLASS_NAMES
   protosleepnet.baselines.test_seq_1ch.MODEL_NAME
   protosleepnet.baselines.test_seq_1ch.PIPELINE
   protosleepnet.baselines.test_seq_1ch.SEQ_LEN


Functions
---------

.. autoapisummary::

   protosleepnet.baselines.test_seq_1ch.compute_metrics
   protosleepnet.baselines.test_seq_1ch.evaluate_subject
   protosleepnet.baselines.test_seq_1ch.main


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

.. py:function:: compute_metrics(all_proba, all_targets, ignore_index=-1)

   Compute metrics from aggregated probabilities and targets.


.. py:function:: evaluate_subject(model, inputs, L, device)

   Sliding-window voting evaluation for a single subject.


.. py:function:: main()

.. py:data:: CHANNELS
   :value: ['EEG']


.. py:data:: CLASS_NAMES
   :value: ['W', 'N1', 'N2', 'N3', 'REM']


.. py:data:: MODEL_NAME
   :value: 'seqsleepnet-phan'


.. py:data:: PIPELINE
   :value: 'seqsleepnet'


.. py:data:: SEQ_LEN
   :value: 20