braindecode 1.6.1.dev1065__tar.gz → 1.6.1.dev1079__tar.gz

{braindecode-1.6.1.dev1065/braindecode.egg-info → braindecode-1.6.1.dev1079}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.6.1.dev1065
+Version: 1.6.1.dev1079
 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-1.6.1.dev1065 → braindecode-1.6.1.dev1079}/braindecode/augmentation/base.py

@@ -105,7 +105,15 @@ class Transform(torch.nn.Module):
         mask = self._get_mask(out_X.shape[0], out_X.device)
         num_valid = mask.sum().long()
 
-        if num_valid > 0:
+        if num_valid == out_X.shape[0]:
+            # Fast path: every sample is augmented (e.g. ``probability=1.0``,
+            # the common case). Operate on the whole batch and skip the boolean
+            # gather/scatter (``out_X[mask]`` then ``out_X[mask] = ...``), which
+            # would otherwise copy the batch twice.
+            out_X, out_y = self.operation(
+                out_X, out_y, **self.get_augmentation_params(out_X, out_y)
+            )
+        elif num_valid > 0:
             # Uses the mask to define the output
             out_X[mask, ...], tr_y = self.operation(
                 out_X[mask, ...],
@@ -168,23 +176,47 @@ class Compose(Transform):
         return X, y
 
 
-def _make_collateable(transform, device=None):
-    """Wraps a transform to make it collateable.
-
-    with device control.
-    """
+class _AugmentationCollate:
+    """Collate that applies a transform to each batch, with optional expansion.
 
-    def _collate_fn(batch):
-        collated_batch = default_collate(batch)
-        X, y = collated_batch[:2]
+    A picklable callable (so it works with ``num_workers > 0``, unlike a
+    closure) that collates the batch once and then either augments it in place
+    or grows it.
 
-        if device is not None:
-            X = X.to(device)
-            y = y.to(device)
-
-        return (*transform(X, y), *collated_batch[2:])
+    Parameters
+    ----------
+    transform : Transform
+        Transform applied to the collated ``(X, y)``.
+    device : str | torch.device | None, optional
+        Device the batch is moved to before transforming. Defaults to None.
+    n_augmentation : int, optional
+        ``0`` (default) applies the transform in place (batch size unchanged).
+        ``> 0`` keeps the clean originals and appends ``n_augmentation``
+        independently transformed copies, returning ``(X, y)`` of
+        ``(1 + n_augmentation)`` times the original size.
+    """
 
-    return _collate_fn
+    def __init__(self, transform, device=None, n_augmentation=0):
+        self.transform = transform
+        self.device = device
+        self.n_augmentation = n_augmentation
+
+    def __call__(self, batch):
+        collated = default_collate(batch)
+        X, y = collated[:2]
+        if self.device is not None:
+            X = X.to(self.device)
+            y = y.to(self.device)
+        if self.n_augmentation == 0:
+            return (*self.transform(X, y), *collated[2:])
+        # Fixed expansion: keep the clean originals, then append
+        # ``n_augmentation`` independently transformed copies.
+        xs, ys = [X], [y]
+        for _ in range(self.n_augmentation):
+            aug_X, aug_y = self.transform(X, y)
+            xs.append(aug_X)
+            ys.append(aug_y)
+        return torch.cat(xs), torch.cat(ys)
 
 
 class AugmentedDataLoader(DataLoader):
@@ -198,28 +230,44 @@ class AugmentedDataLoader(DataLoader):
         Transform or sequence of Transform to be applied to each batch.
     device : str | torch.device | None, optional
         Device on which to transform the data. Defaults to None.
+    n_augmentation : int, optional
+        Number of augmented copies to append to each batch (fixed expansion).
+        When ``0`` (default) the transforms are applied in place and the batch
+        keeps its size (stochastic-per-epoch augmentation, backwards-compatible).
+        When ``> 0`` each batch becomes ``(1 + n_augmentation)`` times larger:
+        the clean originals are kept and ``n_augmentation`` independently
+        transformed copies are appended. This expresses augmentations defined as
+        a fixed set-expansion (e.g. the EEG-Inception MI 6x training set,
+        ``n_augmentation=5``). In this mode batches are returned as ``(X, y)``.
     **kwargs : dict, optional
         keyword arguments to pass to standard DataLoader class.
     """
 
-    def __init__(self, dataset, transforms=None, device=None, **kwargs):
+    def __init__(
+        self, dataset, transforms=None, device=None, n_augmentation=0, **kwargs
+    ):
         if "collate_fn" in kwargs:
             raise ValueError(
                 "collate_fn cannot be used in this context because it is used "
                 "to pass transform"
             )
+        if n_augmentation < 0:
+            raise ValueError("n_augmentation must be a non-negative integer.")
         if transforms is None or (
             isinstance(transforms, list) and len(transforms) == 0
         ):
-            self.collated_tr = _make_collateable(IdentityTransform(), device=device)
+            transform = IdentityTransform()
         elif isinstance(transforms, (Transform, nn.Module)):
-            self.collated_tr = _make_collateable(transforms, device=device)
+            transform = transforms
         elif isinstance(transforms, list):
-            self.collated_tr = _make_collateable(Compose(transforms), device=device)
+            transform = Compose(transforms)
         else:
             raise TypeError(
                 "transforms can be either a Transform object "
                 "or a list of Transform objects."
             )
 
+        self.collated_tr = _AugmentationCollate(
+            transform, device=device, n_augmentation=n_augmentation
+        )
         super().__init__(dataset, collate_fn=self.collated_tr, **kwargs)

{braindecode-1.6.1.dev1065 → braindecode-1.6.1.dev1079}/braindecode/augmentation/functional.py

@@ -18,7 +18,7 @@ from mne.filter import notch_filter
 from scipy.interpolate import Rbf
 from sklearn.utils import check_random_state
 from torch.fft import fft, ifft
-from torch.nn.functional import one_hot, pad
+from torch.nn.functional import pad
 
 
 def identity(X: torch.Tensor, y: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
@@ -253,25 +253,34 @@ def channels_dropout(
     return X * mask.unsqueeze(-1), y
 
 
-def _make_permutation_matrix(
+def _make_channel_permutation(
     X: torch.Tensor, mask: torch.Tensor, random_state: int | np.random.Generator | None
 ) -> torch.Tensor:
+    """Per-sample channel permutation that shuffles only the masked channels.
+
+    Returns a ``(batch, n_channels)`` index permutation: output channel ``i`` is
+    taken from input channel ``perm[b, i]``. Masked channels are permuted among
+    their own positions; unmasked channels keep their place.
+
+    The per-sample ``rng.permutation`` is kept (rather than a vectorized random
+    draw) so the output is bit-for-bit identical to the previous one-hot/matmul
+    implementation — vectorizing the draw would change seeded results. The win
+    is downstream: the caller gathers with this index instead of building
+    ``(batch, n_channels, n_channels)`` one-hot matrices and a matmul.
+    """
     rng = check_random_state(random_state)
     batch_size, n_channels, _ = X.shape
-    hard_mask = mask.round()
-    batch_permutations = torch.empty(
-        batch_size, n_channels, n_channels, device=X.device
-    )
-    for b, mask in enumerate(hard_mask):
-        channels_to_shuffle = torch.arange(n_channels, device=X.device)
-        channels_to_shuffle = channels_to_shuffle[mask.bool()]
-        reordered_channels = torch.tensor(
-            rng.permutation(channels_to_shuffle.cpu()), device=X.device
+    hard_mask = mask.round().bool()
+    channels = torch.arange(n_channels, device=X.device)
+    perm = channels.repeat(batch_size, 1)
+    for b in range(batch_size):
+        channels_to_shuffle = channels[hard_mask[b]]
+        perm[b, channels_to_shuffle] = torch.tensor(
+            rng.permutation(channels_to_shuffle.cpu()),
+            device=X.device,
+            dtype=perm.dtype,
         )
-        channels_permutation = torch.arange(n_channels, device=X.device)
-        channels_permutation[channels_to_shuffle] = reordered_channels
-        batch_permutations[b, ...] = one_hot(channels_permutation)
-    return batch_permutations
+    return perm
 
 
 def channels_shuffle(
@@ -314,8 +323,11 @@ def channels_shuffle(
     if p_shuffle == 0:
         return X, y
     mask = _pick_channels_randomly(X, 1 - p_shuffle, random_state)
-    batch_permutations = _make_permutation_matrix(X, mask, random_state)
-    return torch.matmul(batch_permutations, X), y
+    perm = _make_channel_permutation(X, mask, random_state)
+    # Gather channels (output[b, i] = X[b, perm[b, i]]) instead of building
+    # one-hot permutation matrices and a (batch, C, C) @ (batch, C, T) matmul.
+    perm = perm.unsqueeze(-1).expand(-1, -1, X.shape[-1])
+    return torch.gather(X, 1, perm), y
 
 
 def gaussian_noise(
@@ -1188,19 +1200,21 @@ def mask_encoding(
        32 (2024): 875-886.
     """
 
-    batch_indices = torch.arange(X.shape[0]).repeat_interleave(n_segments)
-    start_indices = time_start.flatten()
-    mask_indices = start_indices[:, None] + torch.arange(segment_length)
-
-    # Create a boolean mask with the same shape as X
-    mask = torch.zeros_like(X, dtype=torch.bool)
-    for batch_index, grouped_mask_indices in zip(batch_indices, mask_indices):
-        mask[batch_index, :, grouped_mask_indices] = True
-
-    # Apply the mask to set the values to 0
-    X[mask] = 0
-
-    return X, y  # Return the masked tensor and labels
+    # All channels are zeroed at the same time positions, so build a single
+    # (batch, n_times) time-mask and broadcast it over channels, vectorized
+    # (no Python loop over batch * n_segments).
+    device = X.device
+    batch_indices = torch.arange(X.shape[0], device=device).repeat_interleave(
+        n_segments * segment_length
+    )
+    seg_indices = (
+        time_start.flatten().to(device)[:, None]
+        + torch.arange(segment_length, device=device)
+    ).flatten()
+    time_mask = torch.zeros(X.shape[0], X.shape[-1], dtype=torch.bool, device=device)
+    time_mask[batch_indices, seg_indices] = True
+
+    return X.masked_fill(time_mask.unsqueeze(1), 0), y
 
 
 def channels_rereference(

{braindecode-1.6.1.dev1065 → braindecode-1.6.1.dev1079}/braindecode/datasets/__init__.py

@@ -10,6 +10,7 @@ from .base import (
 from .bcicomp import BCICompetitionIVDataset4
 from .bids import BIDSDataset, BIDSEpochsDataset
 from .chb_mit import CHBMIT
+from .collate import pad_channels_collate
 from .mne import create_from_mne_epochs, create_from_mne_raw
 from .moabb import BNCI2014_001, HGD, MOABBDataset
 from .nmt import NMT
@@ -42,4 +43,5 @@ __all__ = [
     "SleepPhysionetChallenge2018",
     "create_from_X_y",
     "BCICompetitionIVDataset4",
+    "pad_channels_collate",
 ]

{braindecode-1.6.1.dev1065 → braindecode-1.6.1.dev1079}/braindecode/datasets/base.py

@@ -192,6 +192,31 @@ def _channel_info(mne_obj):
     return n_ch, type_str, sfreq
 
 
+def _compute_ch_pos(info, targets_from):
+    """Return ``(n_ch, 3)`` float32 electrode positions aligned to ``X``'s rows.
+
+    Positions are the MNE head-frame coordinates ``info["chs"][i]["loc"][:3]``
+    (meters) -- the same representation braindecode models already consume (see
+    e.g. ``signal_jepa``/``REVE``). When ``targets_from != "metadata"`` the
+    window's misc channels are dropped from ``X`` in ``__getitem__``, so the
+    matching misc rows are dropped here too. Emits a one-time ``UserWarning`` if
+    no channel carries a real position (no montage set).
+    """
+    pos = np.asarray([ch["loc"][:3] for ch in info["chs"]], dtype="float32")
+    if targets_from != "metadata":
+        misc_mask = np.asarray(info.get_channel_types()) == "misc"
+        pos = pos[~misc_mask]
+    has_pos = np.isfinite(pos).all(axis=1) & np.any(pos != 0, axis=1)
+    if pos.size and not has_pos.any():
+        warnings.warn(
+            "Returning channel positions but no montage is set: all positions "
+            "are zero/non-finite. Call ``raw.set_montage(...)`` (or set a "
+            "montage during preprocessing) before enabling ``return_ch_pos``.",
+            UserWarning,
+        )
+    return pos
+
+
 def _window_info(crop_inds, sfreq):
     """Extract window size from crop indices.
 
@@ -448,6 +473,10 @@ class RecordDataset(Dataset[tuple[np.ndarray, int | str, tuple[int, int, int]]])
     ):
         self._description = _create_description(description)
         self.transform = transform
+        # Opt-in: when True, ``__getitem__`` appends channel positions (n_ch, 3).
+        # Default off keeps the public ``(X, y, crop_inds)`` contract intact.
+        self.return_ch_pos = False
+        self._ch_pos = None
 
     @abstractmethod
     def __len__(self) -> int:
@@ -750,6 +779,20 @@ class EEGWindowsDataset(_ZarrMixin, RecordDataset):
     @raw.setter
     def raw(self, value):
         self._raw = value
+        self._ch_pos = None  # invalidate cached positions
+
+    @property
+    def ch_pos(self):
+        """Electrode positions ``(n_ch, 3)`` (x, y, z) aligned to ``X``'s channels.
+
+        Cached MNE head-frame coordinates in meters. Rows match the channels
+        returned by :meth:`__getitem__` (misc target channels excluded when
+        ``targets_from="channels"``). All-zero/NaN when no montage is set.
+        """
+        if self._ch_pos is None:
+            info = self._raw.info if self._raw is not None else self._make_mne_info()
+            self._ch_pos = _compute_ch_pos(info, self.targets_from)
+        return self._ch_pos
 
     def __getitem__(self, index: int):
         """Get a window and its target.
@@ -793,6 +836,8 @@ class EEGWindowsDataset(_ZarrMixin, RecordDataset):
                 y = X[misc_mask, :]
             y = y.copy()
             X = X[~misc_mask, :]
+        if self.return_ch_pos:
+            return X, y, crop_inds, self.ch_pos
         return X, y, crop_inds
 
     def __len__(self):
@@ -1016,6 +1061,24 @@ class WindowsDataset(_ZarrMixin, RecordDataset):
     @windows.setter
     def windows(self, value):
         self._windows = value
+        self._ch_pos = None  # invalidate cached positions
+
+    @property
+    def ch_pos(self):
+        """Electrode positions ``(n_ch, 3)`` (x, y, z) aligned to ``X``'s channels.
+
+        Cached MNE head-frame coordinates in meters. Rows match the channels
+        returned by :meth:`__getitem__` (misc target channels excluded when
+        ``targets_from="channels"``). All-zero/NaN when no montage is set.
+        """
+        if self._ch_pos is None:
+            info = (
+                self._windows.info
+                if self._windows is not None
+                else self._make_mne_info()
+            )
+            self._ch_pos = _compute_ch_pos(info, self.targets_from)
+        return self._ch_pos
 
     @staticmethod
     def _can_use_fast_get_epoch_from_raw(epochs: mne.BaseEpochs) -> bool:
@@ -1068,6 +1131,8 @@ class WindowsDataset(_ZarrMixin, RecordDataset):
         # necessary to cast as list to get list of three tensors from batch,
         # otherwise get single 2d-tensor...
         crop_inds = self.crop_inds[index].tolist()
+        if self.return_ch_pos:
+            return X, y, crop_inds, self.ch_pos
         return X, y, crop_inds
 
     def __len__(self) -> int:
@@ -1458,6 +1523,50 @@ class BaseConcatDataset(ConcatDataset, HubDatasetMixin, Generic[T]):
                 )
         return self
 
+    def set_return_ch_pos(self, value: bool = True) -> "BaseConcatDataset":
+        """Toggle returning electrode positions from every subdataset.
+
+        When enabled, each windowed subdataset's ``__getitem__`` appends a
+        ``(n_ch, 3)`` array of electrode positions (x, y, z), so a batch yields
+        ``(X, y, crop_inds, ch_pos)``. Heterogeneous (variable-channel)
+        collections additionally need
+        :func:`braindecode.datasets.pad_channels_collate` as the DataLoader
+        ``collate_fn``. Default-off: leaves the ``(X, y, crop_inds)`` contract
+        untouched.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to return channel positions (default ``True``).
+
+        Returns
+        -------
+        self : BaseConcatDataset
+        """
+        for ds in self.datasets:
+            ds.return_ch_pos = value
+        return self
+
+    @property
+    def ch_pos(self):
+        """Electrode positions ``(n_ch, 3)`` from the first recording.
+
+        Convenience accessor mirroring how the repr reports channel info "from
+        first recording". For per-sample positions in a heterogeneous
+        collection, enable :meth:`set_return_ch_pos` and read them from the
+        batch instead.
+        """
+        if not self.datasets:
+            raise ValueError("Empty BaseConcatDataset has no channel positions.")
+        first = self.datasets[0]
+        if not hasattr(first, "ch_pos"):
+            raise AttributeError(
+                f"{type(first).__name__} does not expose channel positions; "
+                "ch_pos is available on windowed datasets (EEGWindowsDataset / "
+                "WindowsDataset)."
+            )
+        return first.ch_pos
+
     def _outdated_save(self, path, overwrite=False):
         """This is a copy of the old saving function, that had inconsistent.
 

{braindecode-1.6.1.dev1065 → braindecode-1.6.1.dev1079}/braindecode/datasets/bids/hub.py

@@ -327,6 +327,7 @@ class HubDatasetMixin:
 
         n_recordings = len(self.datasets)
         first_ds = self.datasets[0]
+        descriptions = [ds.description for ds in self.datasets]
 
         # Get dataset-specific info based on type using registry
         dataset_type = get_dataset_type(first_ds)
@@ -358,6 +359,9 @@ class HubDatasetMixin:
             raise TypeError(f"Unsupported dataset type: {dataset_type}")
 
         # Create README content and save
+        license_value, license_needs_update = _infer_license_from_descriptions(
+            descriptions
+        )
         readme_content = _generate_readme_content(
             format_info=format_info,
             n_recordings=n_recordings,
@@ -366,6 +370,8 @@ class HubDatasetMixin:
             data_type=data_type,
             n_windows=n_windows,
             total_duration=total_duration,
+            license=license_value,
+            license_needs_update=license_needs_update,
         )
 
         # Save README
@@ -967,6 +973,8 @@ def _generate_readme_content(
     n_windows: int,
     total_duration: float | None = None,
     format: str = "zarr",
+    license: str = "please-specify",
+    license_needs_update: bool = True,
 ):
     """Generate README.md content for a dataset uploaded to the Hub.
 
@@ -988,6 +996,10 @@ def _generate_readme_content(
         Total duration in seconds across all recordings.
     format : str
         Storage format (default: "zarr").
+    license : str
+        Dataset license string to write in YAML front matter.
+    license_needs_update : bool
+        Whether to append a reminder comment next to the license field.
 
     Returns
     -------
@@ -1003,6 +1015,10 @@ def _generate_readme_content(
         str(timedelta(seconds=int(total_duration))) if total_duration else "N/A"
     )
 
+    license_line = f"license: {license}"
+    if license_needs_update:
+        license_line += "  # Please update this field to reflect your dataset's license"
+
     return f"""---
 tags:
 - braindecode
@@ -1010,7 +1026,7 @@ tags:
 - neuroscience
 - brain-computer-interface
 - deep-learning
-license: unknown
+{license_line}
 ---
 
 # EEG Dataset
@@ -1106,3 +1122,27 @@ if hasattr(dataset.datasets[0], "bids_channels"):
 
 *Created with [braindecode](https://braindecode.org)*
 """
+
+
+def _infer_license_from_descriptions(
+    descriptions: list[pd.Series | None],
+) -> tuple[str, bool]:
+    """Infer a single dataset license from descriptions.
+
+    Returns inferred license and whether a manual update reminder is needed.
+    """
+    licenses = set()
+    for description in descriptions:
+        if description is None:
+            continue
+        raw_license = description.get("license", None)
+        if raw_license is None:
+            continue
+        normalized = str(raw_license).strip()
+        if normalized and normalized.lower() != "nan":
+            licenses.add(normalized)
+
+    if len(licenses) == 1:
+        return next(iter(licenses)), False
+
+    return "please-specify", True

braindecode-1.6.1.dev1079/braindecode/datasets/collate.py

@@ -0,0 +1,105 @@
+"""Collate functions for braindecode datasets.
+
+:func:`pad_channels_collate` makes a :class:`~braindecode.datasets.BaseConcatDataset`
+that mixes recordings with *different channel sets* (heterogeneous montages)
+batchable: it pads every sample's channels to the batch maximum and emits a
+boolean channel mask. Pair it with ``set_return_ch_pos(True)`` so each sample
+carries its electrode positions -- channel identity is then encoded by the
+positions, not by row index, which is exactly what position-aware models
+(e.g. ``REVE``) consume.
+"""
+
+# Authors: The braindecode developers
+#
+# License: BSD (3-clause)
+
+from __future__ import annotations
+
+import numpy as np
+import torch
+from torch.utils.data._utils.collate import default_collate
+
+__all__ = ["pad_channels_collate"]
+
+
+def pad_channels_collate(batch, pad_value: float = 0.0, pos_pad_value: float = 0.0):
+    """Collate variable-channel windows by padding channels to the batch maximum.
+
+    Each item of ``batch`` is the tuple returned by a windowed dataset's
+    ``__getitem__``: either ``(X, y, crop_inds)`` or, when
+    ``return_ch_pos=True`` (see
+    :meth:`braindecode.datasets.BaseConcatDataset.set_return_ch_pos`),
+    ``(X, y, crop_inds, ch_pos)``. Signals with different numbers of channels
+    are zero-padded along the channel axis to ``max_ch`` (the largest channel
+    count in the batch) so they can be stacked into a single tensor, and a
+    boolean ``ch_mask`` marks the real (non-padded) channels.
+
+    The time dimension is assumed uniform (fixed-length windows); a
+    :class:`ValueError` is raised otherwise.
+
+    This makes a heterogeneous collection **batchable**. *Consuming* the result
+    (so a model ignores padded channels) requires a position/channel-aware
+    model; fixed-geometry models (e.g. ``ShallowFBCSPNet``) structurally need a
+    constant channel count and cannot use variable batches.
+
+    Parameters
+    ----------
+    batch : list of tuple
+        Samples from a windowed dataset (see above).
+    pad_value : float
+        Value used to pad the signal ``X`` channel rows (default ``0.0``).
+    pos_pad_value : float
+        Value used to pad the position ``ch_pos`` rows (default ``0.0``).
+
+    Returns
+    -------
+    X : torch.Tensor
+        Padded signals, shape ``(batch, max_ch, n_times)``.
+    y : torch.Tensor
+        Targets, collated with ``default_collate``.
+    crop_inds : list
+        Crop indices, collated with ``default_collate``.
+    ch_pos : torch.Tensor
+        Only when the samples include positions. Padded positions, shape
+        ``(batch, max_ch, 3)``.
+    ch_mask : torch.Tensor
+        Boolean mask, shape ``(batch, max_ch)``; ``True`` for real channels,
+        ``False`` for padding.
+    """
+    if len(batch) == 0:
+        raise ValueError("pad_channels_collate received an empty batch.")
+
+    has_pos = len(batch[0]) >= 4
+    Xs = [np.asarray(item[0]) for item in batch]
+
+    n_times = Xs[0].shape[1]
+    if any(x.shape[1] != n_times for x in Xs):
+        raise ValueError(
+            "pad_channels_collate only pads the channel axis; all windows must "
+            f"share the same number of time samples, got {sorted({x.shape[1] for x in Xs})}."
+        )
+
+    bsz = len(batch)
+    max_ch = max(x.shape[0] for x in Xs)
+
+    X_out = torch.full((bsz, max_ch, n_times), pad_value, dtype=torch.float32)
+    ch_mask = torch.zeros((bsz, max_ch), dtype=torch.bool)
+    pos_out = (
+        torch.full((bsz, max_ch, 3), pos_pad_value, dtype=torch.float32)
+        if has_pos
+        else None
+    )
+    for i, (item, x) in enumerate(zip(batch, Xs)):
+        c = x.shape[0]
+        X_out[i, :c] = torch.as_tensor(x, dtype=torch.float32)
+        ch_mask[i, :c] = True
+        if pos_out is not None:
+            pos_out[i, :c] = torch.as_tensor(np.asarray(item[3]), dtype=torch.float32)
+
+    # y and crop_inds carry no channel axis -> standard collation.
+    y = default_collate([item[1] for item in batch])
+    crop_inds = default_collate([item[2] for item in batch])
+
+    if pos_out is not None:
+        return X_out, y, crop_inds, pos_out, ch_mask
+    return X_out, y, crop_inds, ch_mask

{braindecode-1.6.1.dev1065 → braindecode-1.6.1.dev1079}/braindecode/eegneuralnet.py

@@ -134,7 +134,14 @@ class _EEGNeuralNet(NeuralNet, abc.ABC):
         i_window_in_trials = []
         i_window_stops = []
         window_ys = []
-        for X, y, i in self.get_iterator(dataset, drop_index=False):
+        for batch in self.get_iterator(dataset, drop_index=False):
+            if len(batch) > 3:
+                raise ValueError(
+                    "Cropped prediction does not support channel positions; "
+                    "disable return_ch_pos (set_return_ch_pos(False)) for cropped "
+                    "evaluation."
+                )
+            X, y, i = batch[0], batch[1], batch[2]
             i_window_in_trials.append(i[0].cpu().numpy())
             i_window_stops.append(i[2].cpu().numpy())
             with torch.no_grad():

{braindecode-1.6.1.dev1065 → braindecode-1.6.1.dev1079}/braindecode/functional/__init__.py

@@ -5,6 +5,7 @@ from .functions import (
     identity,
     plv_time,
     safe_log,
+    sinusoidal_positional_encoding,
     square,
 )
 from .initialization import glorot_weight_zero_bias, rescale_parameter
@@ -16,6 +17,7 @@ __all__ = [
     "identity",
     "plv_time",
     "safe_log",
+    "sinusoidal_positional_encoding",
     "square",
     "glorot_weight_zero_bias",
     "rescale_parameter",