braindecode 1.6.0.dev1024__tar.gz → 1.6.1.dev1034__tar.gz

{braindecode-1.6.0.dev1024/braindecode.egg-info → braindecode-1.6.1.dev1034}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.6.0.dev1024
+Version: 1.6.1.dev1034
 Summary: Deep learning software to decode EEG, ECG or MEG signals
 Author-email: Robin Tibor Schirrmeister <robintibor@gmail.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Alexandre Gramfort <agramfort@meta.com>
 Maintainer-email: Alexandre Gramfort <agramfort@meta.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Robin Tibor Schirrmeister <robintibor@gmail.com>

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/braindecode/datasets/bids/hub.py

@@ -466,6 +466,7 @@ class HubDatasetMixin:
         token: Optional[str] = None,
         cache_dir: Optional[Union[str, Path]] = None,
         force_download: bool = False,
+        revision: str | None = None,
         **kwargs,
     ):
         """
@@ -485,6 +486,9 @@ class HubDatasetMixin:
             cache directory (~/.cache/huggingface/datasets).
         force_download : bool, default=False
             Whether to force re-download even if cached.
+        revision : str | None, default=None
+            Specific branch, tag, or commit to download. If None, uses the
+            repository's default revision.
         **kwargs
             Additional arguments (currently unused).
 
@@ -526,6 +530,7 @@ class HubDatasetMixin:
                 token=token,
                 cache_dir=cache_dir,
                 force_download=force_download,
+                revision=revision,
             )
 
             # Load format info

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/braindecode/models/__init__.py

@@ -21,7 +21,7 @@ from .eegitnet import EEGITNet
 from .eegminer import EEGMiner
 from .eegnet import EEGNet, EEGNetv4
 from .eegnex import EEGNeX
-from .eegpt import EEGPT
+from .eegpt import EEGPT, InterpolatedEEGPT
 from .eegsimpleconv import EEGSimpleConv
 from .eegsym import EEGSym
 from .eegtcnet import EEGTCNet
@@ -85,6 +85,7 @@ __all__ = [
     "BrainModule",
     "EEGConformer",
     "EEGPT",
+    "InterpolatedEEGPT",
     "EEGInceptionERP",
     "EEGInceptionMI",
     "EEGITNet",

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/braindecode/models/contrawr.py

@@ -5,6 +5,7 @@ import torch.nn as nn
 from mne.utils import warn
 
 from braindecode.models.base import EEGModuleMixin
+from braindecode.models.util import _disable_batch_norm_training_if_batch_size_one
 
 
 class ContraWR(EEGModuleMixin, nn.Module):
@@ -122,6 +123,7 @@ class ContraWR(EEGModuleMixin, nn.Module):
         self.activation_layer = activation()
         self.final_layer = nn.Linear(emb_size, self.n_outputs)
 
+    @_disable_batch_norm_training_if_batch_size_one
     def forward(self, X: torch.Tensor) -> torch.Tensor:
         """
         Forward pass.

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/braindecode/models/deepsleepnet.py

@@ -7,6 +7,7 @@ import torch.nn as nn
 from einops.layers.torch import Rearrange
 
 from braindecode.models.base import EEGModuleMixin
+from braindecode.models.util import _disable_batch_norm_training_if_batch_size_one
 
 
 class DeepSleepNet(EEGModuleMixin, nn.Module):
@@ -289,6 +290,7 @@ class DeepSleepNet(EEGModuleMixin, nn.Module):
             else nn.Linear(fc_out_features, self.n_outputs)
         )
 
+    @_disable_batch_norm_training_if_batch_size_one
     def forward(self, x):
         if x.ndim == 3:
             x = x.unsqueeze(1)

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/braindecode/models/eegminer.py

@@ -13,6 +13,7 @@ from torch import nn
 
 import braindecode.functional as F
 from braindecode.models.base import EEGModuleMixin
+from braindecode.models.util import _disable_batch_norm_training_if_batch_size_one
 from braindecode.modules import GeneralizedGaussianFilter
 
 _eeg_miner_methods = ["mag", "corr", "plv"]
@@ -191,6 +192,7 @@ class EEGMiner(EEGModuleMixin, nn.Module):
         self.final_layer = nn.Linear(self.n_features, self.n_outputs)
         nn.init.zeros_(self.final_layer.bias)
 
+    @_disable_batch_norm_training_if_batch_size_one
     def forward(self, x):
         """x: (batch, electrodes, time)"""
         batch = x.shape[0]

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/braindecode/models/eegpt.py

@@ -1435,3 +1435,32 @@ class _EEGTransformer(nn.Module):
         )
 
         return x
+
+
+# -----------------------------------------------------------------------------
+# InterpolatedEEGPT — experimental channel-interpolation variant of EEGPT
+# -----------------------------------------------------------------------------
+# A :func:`~braindecode.models.interpolated.InterpolatedModel` wrapper around
+# :class:`EEGPT` whose target channel set is the canonical ``EEGPT_CHANNELS``.
+# Accepts arbitrary user ``chs_info``; projects to the canonical channels via an
+# MNE-backed (frozen by default) interpolation matrix.
+
+from mne.channels import make_standard_montage  # noqa: E402
+
+from braindecode.models.interpolated import InterpolatedModel  # noqa: E402
+
+montage = make_standard_montage("standard_1020")
+ch_pos = {
+    ch.upper(): (ch, loc) for ch, loc in montage.get_positions()["ch_pos"].items()
+}
+_EEGPT_TARGET_CHS_INFO = [
+    {
+        "ch_name": ch_pos[ch.upper()][0],
+        "kind": "eeg",
+        "loc": ch_pos[ch.upper()][1],
+    }
+    for ch in EEGPT_CHANNELS
+]
+InterpolatedEEGPT = InterpolatedModel(
+    EEGPT, _EEGPT_TARGET_CHS_INFO, name="InterpolatedEEGPT"
+)

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/braindecode/models/eegsym.py

@@ -11,6 +11,7 @@ from braindecode.datautil.channel_utils import (
     match_hemisphere_chans,
 )
 from braindecode.models.base import EEGModuleMixin
+from braindecode.models.util import _disable_batch_norm_training_if_batch_size_one
 
 
 class EEGSym(EEGModuleMixin, nn.Module):
@@ -363,6 +364,7 @@ class EEGSym(EEGModuleMixin, nn.Module):
             out_features=self.n_outputs,
         )
 
+    @_disable_batch_norm_training_if_batch_size_one
     def forward(self, x):
         """Forward pass.
 

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/braindecode/models/summary.csv

@@ -53,5 +53,6 @@ REVE,General,Classification,200,"n_outputs, n_times, n_chans",69481476,"REVE(n_t
 DGCNN,Emotion Recognition,Classification,128,"n_chans, n_outputs, n_times, chs_info",1037385,"DGCNN(n_chans=62, n_outputs=4, n_times=128)","Graph Neural Network,Channel"
 InterpolatedBENDR,General,"Classification,Embedding",250,"chs_info, n_outputs, n_times",157143101,"InterpolatedBENDR(chs_info=<user>, n_outputs=4, n_times=1000)","Foundation Model,Convolution,Channel"
 InterpolatedBIOT,"Sleep Staging, Epilepsy",Classification,200,"chs_info, n_outputs, n_times, sfreq",3184101,"InterpolatedBIOT(chs_info=<user>, n_outputs=5, sfreq=200, n_times=6000)","Foundation Model,Channel"
+InterpolatedEEGPT,General,Classification,256,"chs_info, n_outputs, n_times",25323137,"InterpolatedEEGPT(chs_info=<user>, n_outputs=4, n_times=1024)","Foundation Model,Attention/Transformer,Channel"
 InterpolatedLaBraM,General,"Classification, Embedding",200,"chs_info, n_outputs, n_times",5866196,"InterpolatedLaBraM(chs_info=<user>, n_outputs=4, n_times=1000)","Convolution,Foundation Model,Channel"
 InterpolatedSignalJEPA,"Motor Imagery, ERP, SSVEP",Embedding,128,"chs_info",3456882,"InterpolatedSignalJEPA(chs_info=<user>)","Convolution,Channel,Foundation Model"

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/braindecode/models/usleep.py

@@ -9,6 +9,7 @@ import torch
 from torch import nn
 
 from braindecode.models.base import EEGModuleMixin
+from braindecode.models.util import _disable_batch_norm_training_if_batch_size_one
 
 
 class USleep(EEGModuleMixin, nn.Module):
@@ -295,6 +296,7 @@ class USleep(EEGModuleMixin, nn.Module):
             # output is (B, n_classes, S)
         )
 
+    @_disable_batch_norm_training_if_batch_size_one
     def forward(self, x: torch.Tensor) -> torch.Tensor:
         """If input x has shape (B, S, C, T), return y_pred of shape (B, n_classes, S).
         If input x has shape (B, C, T), return y_pred of shape (B, n_classes).

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/braindecode/models/util.py

@@ -12,6 +12,8 @@ from typing import Any, Dict, Literal, Optional, Sequence
 import numpy as np
 import pandas as pd
 import pydantic
+import torch  # noqa: F401  # exposed so TorchScript can resolve ``torch`` through the BatchNorm-guard wrapper's __globals__
+from torch import nn
 
 models_dict = {}
 
@@ -23,6 +25,38 @@ _EEG_PARAMS = frozenset(
 )
 
 _JSON_SAFE = (int, float, str, bool, type(None))
+_BATCH_NORM_MODULES = (
+    nn.BatchNorm1d,
+    nn.BatchNorm2d,
+    nn.BatchNorm3d,
+    nn.SyncBatchNorm,
+)
+
+
+def _disable_batch_norm_training_if_batch_size_one(forward):
+    """Temporarily set BatchNorm layers to train(False) for batch size one."""
+    forward_signature = inspect.signature(forward)
+
+    @wraps(forward)
+    def wrapped(self, *args, **kwargs):
+        bound = forward_signature.bind(self, *args, **kwargs)
+        x = next(value for name, value in bound.arguments.items() if name != "self")
+        batch_norms = []
+        if self.training and x.shape[0] == 1:
+            batch_norms = [
+                layer
+                for layer in self.modules()
+                if isinstance(layer, _BATCH_NORM_MODULES) and layer.training
+            ]
+            for batch_norm in batch_norms:
+                batch_norm.train(False)
+        try:
+            return forward(self, *args, **kwargs)
+        finally:
+            for batch_norm in batch_norms:
+                batch_norm.train(True)
+
+    return wrapped
 
 
 def _is_jsonable(val):
@@ -275,6 +309,11 @@ models_mandatory_parameters: list[
     ("EEGITNet", ["n_chans", "n_outputs", "n_times"], None),
     ("EEGNet", ["n_chans", "n_outputs", "n_times"], None),
     ("EEGPT", ["n_chans", "n_outputs", "n_times", "chs_info"], None),
+    (
+        "InterpolatedEEGPT",
+        ["chs_info", "n_outputs", "n_times"],
+        {"chs_info": _chs_info_4ch},  # MNE interpolation needs >=4 channels
+    ),
     ("ShallowFBCSPNet", ["n_chans", "n_outputs", "n_times"], None),
     (
         "SleepStagerBlanco2020",

braindecode-1.6.1.dev1034/braindecode/version.py

@@ -0,0 +1 @@
+__version__ = "1.6.1.dev1034"

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034/braindecode.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.6.0.dev1024
+Version: 1.6.1.dev1034
 Summary: Deep learning software to decode EEG, ECG or MEG signals
 Author-email: Robin Tibor Schirrmeister <robintibor@gmail.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Alexandre Gramfort <agramfort@meta.com>
 Maintainer-email: Alexandre Gramfort <agramfort@meta.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Robin Tibor Schirrmeister <robintibor@gmail.com>

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/docs/api.rst

@@ -160,6 +160,7 @@ interface for all EEG models and can derive variable names when needed.
      IFNet
      InterpolatedBENDR
      InterpolatedBIOT
+     InterpolatedEEGPT
      InterpolatedLaBraM
      InterpolatedModel
      InterpolatedSignalJEPA

{braindecode-1.6.0.dev1024 → braindecode-1.6.1.dev1034}/docs/whats_new.rst

@@ -22,12 +22,21 @@
 .. _current:
 
 
-Current 1.6.0 (GitHub)
+Current 1.6.1 (GitHub)
 ===============================
 
 Enhancements
 ============
 
+- Add a ``revision`` keyword argument to
+  :meth:`braindecode.datasets.BaseConcatDataset.pull_from_hub` so callers can
+  pin dataset downloads to a specific branch, tag, or commit on the Hugging
+  Face Hub.
+- Add :class:`braindecode.models.InterpolatedEEGPT`, a channel-interpolation
+  variant of :class:`braindecode.models.EEGPT` built with
+  :func:`~braindecode.models.interpolated.InterpolatedModel`.
+  By `Pierre Guetschel`_.
+
 API and behavior changes
 ========================
 
@@ -41,12 +50,27 @@ Requirements
 Bug fixes
 ==========
 
-- None yet
+- Fix :class:`~braindecode.models.ContraWR`,
+  :class:`~braindecode.models.DeepSleepNet`, and
+  :class:`~braindecode.models.EEGMiner` raising a confusing
+  :class:`ValueError` on ``batch_size=1`` forward passes in train mode due to
+  :class:`~torch.nn.BatchNorm1d` (and its 2D/3D variants) requiring more than
+  one sample per channel during training.  The affected BatchNorm layers now
+  use running statistics when ``batch_size == 1`` in train mode.
+  By `Bruno Aristimunha`_.
+
+- Fix incorrect import path in CONTRIBUTING.md by `Yiheng Li`_
 
 Code health
 ============
 
-- None yet
+- Add a monthly scheduled workflow that cuts a stable PyPI release on
+  the 1st of every month, complementing the existing per-push ``.devN``
+  pipeline. (:gh:`1030` by `Bruno Aristimunha`_)
+
+- Make the monthly release workflow push only the release tag and open a
+  pull request for the version bump, so it never needs to push to the
+  protected ``master`` branch. (:gh:`1031` by `Bruno Aristimunha`_)
 
 
 Current 1.5.1 (stable)
@@ -1217,3 +1241,5 @@ Authors
 .. _Sarthak Tayal: https://github.com/tayal-sarthak
 .. _Vandit Shah: https://github.com/ShahVandit
 .. _Léo Burgund: https://github.com/leob000
+.. _Adam Mounir: https://github.com/adammounir
+.. _Yiheng Li: https://github.com/YihengLi-1

braindecode-1.6.0.dev1024/braindecode/version.py

@@ -1 +0,0 @@
-__version__ = "1.6.0.dev1024"