Braindecode 1.5.0.dev179280875__tar.gz → 1.5.0.dev182195895__tar.gz

{braindecode-1.5.0.dev179280875/braindecode.egg-info → braindecode-1.5.0.dev182195895}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.5.0.dev179280875
+Version: 1.5.0.dev182195895
 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-1.5.0.dev179280875 → braindecode-1.5.0.dev182195895}/braindecode/models/__init__.py

@@ -4,11 +4,10 @@ from .atcnet import ATCNet
 from .attentionbasenet import AttentionBaseNet
 from .attn_sleep import AttnSleep
 from .base import EEGModuleMixin
-from .bendr import BENDR, InterpolatedBENDR
-from .biot import BIOT, InterpolatedBIOT
+from .bendr import BENDR
+from .biot import BIOT
 from .brainmodule import BrainModule
 from .cbramod import CBraMod
-from .codebrain import CodeBrain
 from .contrawr import ContraWR
 from .ctnet import CTNet
 from .deep4 import Deep4Net
@@ -30,8 +29,7 @@ from .fblightconvnet import FBLightConvNet
 from .fbmsnet import FBMSNet
 from .hybrid import HybridNet
 from .ifnet import IFNet
-from .interpolated import InterpolatedModel
-from .labram import InterpolatedLaBraM, Labram
+from .labram import Labram
 from .luna import LUNA
 from .medformer import MEDFormer
 from .msvtnet import MSVTNet
@@ -40,7 +38,6 @@ from .reve import REVE
 from .sccnet import SCCNet
 from .shallow_fbcsp import ShallowFBCSPNet
 from .signal_jepa import (
-    InterpolatedSignalJEPA,
     SignalJEPA,
     SignalJEPA_Contextual,
     SignalJEPA_PostLocal,
@@ -75,7 +72,6 @@ __all__ = [
     "BIOT",
     "BENDR",
     "CBraMod",
-    "CodeBrain",
     "ContraWR",
     "CTNet",
     "Deep4Net",
@@ -99,11 +95,6 @@ __all__ = [
     "FBMSNet",
     "HybridNet",
     "IFNet",
-    "InterpolatedBENDR",
-    "InterpolatedBIOT",
-    "InterpolatedLaBraM",
-    "InterpolatedModel",
-    "InterpolatedSignalJEPA",
     "Labram",
     "LUNA",
     "extract_channel_locations_from_chs_info",

{braindecode-1.5.0.dev179280875 → braindecode-1.5.0.dev182195895}/braindecode/models/bendr.py

@@ -1,60 +1,12 @@
 import copy
 
-import numpy as np
 import torch
 from einops.layers.torch import Rearrange
 from torch import nn
+from torch.nn.utils.parametrize import register_parametrization
 
 from braindecode.models.base import EEGModuleMixin
-
-# The 20 channels used to pre-train BENDR, in the order expected by the
-# `braindecode/braindecode-bendr` checkpoint. The first 19 entries are the
-# EEG channels taken verbatim from `dn3.transforms.instance.To1020.EEG_20_div`
-# (https://github.com/SPOClab-ca/dn3/blob/master/dn3/transforms/instance.py).
-# Their positions come from MNE's ``standard_1005`` montage (T5/T6 are
-# legacy names that share positions with P7/P8 there).
-#
-# The 20th entry is ``SCALE``, a relative-amplitude statistic (not an
-# electrode) appended by ``To1020(include_scale_ch=True)`` during
-# pre-training. Since it has no physical position, the ``loc`` below is
-# the centroid of the 19 EEG positions — purely a placeholder so that
-# :class:`~braindecode.modules.ChannelInterpolationLayer` (used by
-# :class:`InterpolatedBENDR`) can build a valid spline interpolation
-# matrix. It is NOT the SCALE the pre-training pipeline computes
-# (which is an RMS-like amplitude via ``dn3.MappingDeep1010``); users
-# who need a faithful SCALE must compute it themselves and feed 20
-# channels to :class:`BENDR` directly.
-_BENDR_TARGET_CHS_TUPLES: list[tuple[str, tuple[float, float, float]]] = [
-    ("FP1", (-0.0294367, +0.0839171, -0.0069900)),  # standard_1005
-    ("FP2", (+0.0298723, +0.0848959, -0.0070800)),  # standard_1005
-    ("F7", (-0.0702629, +0.0424743, -0.0114200)),  # standard_1005
-    ("F3", (-0.0502438, +0.0531112, +0.0421920)),  # standard_1005
-    ("FZ", (+0.0003122, +0.0585120, +0.0664620)),  # standard_1005
-    ("F4", (+0.0518362, +0.0543048, +0.0408140)),  # standard_1005
-    ("F8", (+0.0730431, +0.0444217, -0.0120000)),  # standard_1005
-    ("T7", (-0.0841611, -0.0160187, -0.0093460)),  # standard_1005
-    ("C3", (-0.0653581, -0.0116317, +0.0643580)),  # standard_1005
-    ("CZ", (+0.0004009, -0.0091670, +0.1002440)),  # standard_1005
-    ("C4", (+0.0671179, -0.0109003, +0.0635800)),  # standard_1005
-    ("T8", (+0.0850799, -0.0150203, -0.0094900)),  # standard_1005
-    ("T5", (-0.0724343, -0.0734527, -0.0024870)),  # standard_1005 (= P7)
-    ("P3", (-0.0530073, -0.0787878, +0.0559400)),  # standard_1005
-    ("PZ", (+0.0003247, -0.0811150, +0.0826150)),  # standard_1005
-    ("P4", (+0.0556667, -0.0785602, +0.0565610)),  # standard_1005
-    ("T6", (+0.0730557, -0.0730683, -0.0025400)),  # standard_1005 (= P8)
-    ("O1", (-0.0294134, -0.1124490, +0.0088390)),  # standard_1005
-    ("O2", (+0.0298426, -0.1121560, +0.0088000)),  # standard_1005
-    (
-        "SCALE",
-        (+0.0006439, -0.0131942, +0.0278448),
-    ),  # centroid of the 19 EEG positions (placeholder; see comment above)
-]
-
-_BENDR_TARGET_CHS_INFO: list[dict] = [
-    {"ch_name": ch, "kind": "eeg", "loc": np.asarray(loc, dtype=float)}
-    for ch, loc in _BENDR_TARGET_CHS_TUPLES
-]
-BENDR_CHANNEL_ORDER: list[str] = [ch for ch, _ in _BENDR_TARGET_CHS_TUPLES]
+from braindecode.modules.parametrization import MaxNormParametrize
 
 
 class BENDR(EEGModuleMixin, nn.Module):
@@ -243,6 +195,15 @@ class BENDR(EEGModuleMixin, nn.Module):
         The contextualizer is still created (to allow loading pretrained weights) but is not
         used in the forward pass. Requires input length of at least
         ``4 * product(enc_downsample)`` samples (384 with default downsampling of 96x).
+    n_chans_pretrained : int or None, default=None
+        Number of input channels the pretrained weights expect (20 for the official BENDR
+        checkpoint). When set and ``n_chans != n_chans_pretrained``, a 1x1 Conv1d with
+        max-norm constraint projects from ``n_chans`` to ``n_chans_pretrained`` before the
+        encoder. This allows fine-tuning pretrained BENDR on datasets with arbitrary channel
+        counts. When using ``from_pretrained``, pass ``strict=False`` since the checkpoint
+        will not contain ``channel_projection`` weights.
+    chan_proj_max_norm : float, default=1.0
+        Max-norm constraint value for the channel projection weights.
     """
 
     def __init__(
@@ -270,6 +231,8 @@ class BENDR(EEGModuleMixin, nn.Module):
         start_token=-5,  # Value for start token embedding
         final_layer=True,  # Whether to include the final linear layer
         encoder_only=False,  # If True, bypass contextualizer and use 4-chunk pooling
+        n_chans_pretrained=None,  # Expected input channels of pretrained weights
+        chan_proj_max_norm=1.0,  # Max-norm for channel projection weights
     ):
         super().__init__(
             n_outputs=n_outputs,
@@ -283,34 +246,25 @@ class BENDR(EEGModuleMixin, nn.Module):
         # Keep these parameters if needed later, otherwise they are captured by the mixin
         del n_outputs, n_chans, chs_info, n_times, input_window_seconds, sfreq
 
-        # If the user supplies chs_info, require it to match BENDR_CHANNEL_ORDER
-        # exactly (case-insensitive). Arbitrary channel sets should go through
-        # InterpolatedBENDR — same pattern as Labram / InterpolatedLaBraM.
-        # When chs_info is absent (the usual n_chans=20 path, incl.
-        # from_pretrained), no check is performed.
-        try:
-            _chs_info = self.chs_info
-        except ValueError:
-            _chs_info = None
-        if _chs_info is not None:
-            user_names = [ch["ch_name"] for ch in _chs_info]  # type: ignore[index]
-            canonical = BENDR_CHANNEL_ORDER
-            if [n.lower() for n in user_names] != [n.lower() for n in canonical]:
-                raise ValueError(
-                    f"BENDR requires chs_info to match BENDR_CHANNEL_ORDER exactly "
-                    f"({len(canonical)} channels, specific order; last is 'SCALE'). "
-                    f"Got {len(user_names)} channel(s). For arbitrary channel sets, "
-                    f"use InterpolatedBENDR "
-                    f"(from braindecode.models import InterpolatedBENDR)."
-                )
-
         self.encoder_h = encoder_h
         self.contextualizer_hidden = contextualizer_hidden
         self.include_final_layer = final_layer
         self.encoder_only = encoder_only
 
+        # Channel projection for pretrained weight compatibility
+        encoder_n_chans = self.n_chans
+        if n_chans_pretrained is not None and self.n_chans != n_chans_pretrained:
+            conv = nn.Conv1d(self.n_chans, n_chans_pretrained, 1, bias=False)
+            register_parametrization(
+                conv, "weight", MaxNormParametrize(chan_proj_max_norm)
+            )
+            self.channel_projection = conv
+            encoder_n_chans = n_chans_pretrained
+        else:
+            self.channel_projection = None
+
         self.encoder = _ConvEncoderBENDR(
-            in_features=self.n_chans,
+            in_features=encoder_n_chans,
             encoder_h=encoder_h,
             dropout=drop_prob,
             projection_head=projection_head,
@@ -354,6 +308,8 @@ class BENDR(EEGModuleMixin, nn.Module):
         self._build_head(n_outputs)
 
     def forward(self, x, return_features=False):
+        if self.channel_projection is not None:
+            x = self.channel_projection(x)
         encoded = self.encoder(x)
         # encoded: [batch_size, encoder_h, n_encoded_times]
 
@@ -596,23 +552,3 @@ class _BENDRContextualizer(nn.Module):
         # x: [batch_size, in_features, seq_len + 1]
 
         return x
-
-
-# -----------------------------------------------------------------------------
-# InterpolatedBENDR — experimental channel-interpolation variant of BENDR
-# -----------------------------------------------------------------------------
-# Wraps :class:`BENDR` with an MNE-backed channel-interpolation layer that
-# projects arbitrary user ``chs_info`` to the canonical 20-channel BENDR
-# input (:data:`_BENDR_TARGET_CHS_INFO` — the 19 pre-training EEG channels
-# plus a ``SCALE`` placeholder at the centroid of those 19 positions).
-# Frozen by default; set ``trainable=True`` to fine-tune the projection.
-#
-# NOTE: the ``SCALE`` target has no physical position, so the row of the
-# interpolation matrix that produces it is a spatial spline of the user's
-# EEG channels — *not* the dn3 ``MappingDeep1010`` RMS statistic the
-# checkpoint saw during pre-training. Expect degraded zero-shot transfer
-# from the SCALE channel; downstream fine-tuning should still work.
-
-from braindecode.models.interpolated import InterpolatedModel  # noqa: E402
-
-InterpolatedBENDR = InterpolatedModel(BENDR, _BENDR_TARGET_CHS_INFO)

{braindecode-1.5.0.dev179280875 → braindecode-1.5.0.dev182195895}/braindecode/models/biot.py

@@ -1,57 +1,12 @@
 import math
 from warnings import warn
 
-import numpy as np
 import torch
 import torch.nn as nn
 from linear_attention_transformer import LinearAttentionTransformer
 
 from braindecode.models.base import EEGModuleMixin
 
-# -----------------------------------------------------------------------------
-# Canonical channel order for InterpolatedBIOT — the 18-channel TCP bipolar
-# montage used by BIOT's shhs-prest and six-datasets pretrained checkpoints.
-# Source: https://github.com/ycq091044/BIOT (README + datasets/TUAB/process.py
-# + datasets/SHHS/process.py). Indices 0-15 are the TCP 16-channel bipolar
-# derivations; indices 16-17 are SHHS differential channels.
-#
-# The `loc` values are only used to build an MNE interpolation matrix for
-# InterpolatedBIOT. All entries are bipolar / differential derivations.
-# TODO: positions are stored as the midpoint of the two constituent
-# electrodes. This is a simplification — a bipolar signal V(A)-V(B) cannot
-# be faithfully recovered by spatial interpolation at the midpoint. Revisit
-# in a follow-up PR (e.g. a dedicated BipolarDerivationLayer).
-# -----------------------------------------------------------------------------
-
-# fmt: off
-_BIOT_TARGET_CHS_TUPLES: list[tuple[str, tuple[float, float, float]]] = [
-    ("FP1-F7", (-0.04984980, 0.06319570, -0.00920500)),
-    ("F7-T7", (-0.07721200, 0.01322780, -0.01038300)),
-    ("T7-P7", (-0.07829770, -0.04473570, -0.00591650)),
-    ("P7-O1", (-0.05092385, -0.09295085, 0.00317600)),
-    ("FP2-F8", (0.05145770, 0.06465880, -0.00954000)),
-    ("F8-T8", (0.07906150, 0.01470070, -0.01074500)),
-    ("T8-P8", (0.07906780, -0.04404430, -0.00601500)),
-    ("P8-O2", (0.05144915, -0.09261215, 0.00313000)),
-    ("FP1-F3", (-0.03984025, 0.06851415, 0.01760100)),
-    ("F3-C3", (-0.05780095, 0.02073975, 0.05327500)),
-    ("C3-P3", (-0.05918270, -0.04520975, 0.06014900)),
-    ("P3-O1", (-0.04121035, -0.09561840, 0.03238950)),
-    ("FP2-F4", (0.04085425, 0.06960035, 0.01686700)),
-    ("F4-C4", (0.05947705, 0.02170225, 0.05219700)),
-    ("C4-P4", (0.06139230, -0.04473025, 0.06007050)),
-    ("P4-O2", (0.04275465, -0.09535810, 0.03268050)),
-    ("C3-A2", (0.01021790, -0.01832050, -0.00183650)),
-    ("C4-A1", (-0.00947910, -0.01794500, -0.00220300)),
-]
-# fmt: on
-
-_BIOT_TARGET_CHS_INFO = [
-    {"ch_name": ch, "kind": "eeg", "loc": np.asarray(loc, dtype=float)}
-    for ch, loc in _BIOT_TARGET_CHS_TUPLES
-]
-BIOT_CHANNEL_ORDER = [ch for ch, _ in _BIOT_TARGET_CHS_TUPLES]
-
 
 class BIOT(EEGModuleMixin, nn.Module):
     r"""BIOT from Yang et al (2023) [Yang2023]_
@@ -484,9 +439,7 @@ class _BIOTEncoder(nn.Module):
         self.channel_tokens = nn.Embedding(
             num_embeddings=n_chans, embedding_dim=emb_size
         )
-        self.register_buffer(
-            "index", torch.arange(n_chans, dtype=torch.long), persistent=False
-        )
+        self.register_buffer("index", torch.arange(n_chans, dtype=torch.long))
 
     def stft(self, sample):
         """
@@ -600,16 +553,3 @@ class _BIOTEncoder(nn.Module):
         # (batch_size, emb)
         emb = self.transformer(emb).mean(dim=1)
         return emb
-
-
-# -----------------------------------------------------------------------------
-# InterpolatedBIOT — experimental channel-interpolation variant of BIOT
-# -----------------------------------------------------------------------------
-# Wraps :class:`BIOT` with an MNE-backed channel-interpolation layer that
-# projects arbitrary user ``chs_info`` to the canonical 18-channel BIOT
-# montage (:data:`_BIOT_TARGET_CHS_INFO`). Frozen by default; set
-# ``trainable=True`` to fine-tune the projection matrix.
-
-from braindecode.models.interpolated import InterpolatedModel  # noqa: E402
-
-InterpolatedBIOT = InterpolatedModel(BIOT, _BIOT_TARGET_CHS_INFO)

{braindecode-1.5.0.dev179280875 → braindecode-1.5.0.dev182195895}/braindecode/models/config.py

@@ -1,4 +1,3 @@
-# Authors: Sarthak Tayal <sarthaktayal2@gmail.com>
 from collections.abc import Callable
 from inspect import signature
 from types import UnionType
@@ -18,10 +17,10 @@ from braindecode.models.util import (
 
 try:
     from numpydantic import NDArray, Shape
-
-    _loc_type = NDArray[Shape["12"], np.float64]
 except ImportError:
-    _loc_type = np.ndarray  # type: ignore[misc]
+    # we can't use soft import for numpydantic because numpydantic does not define its version in __init__
+    NDArray = Any  # type: ignore
+    Shape = Any  # type: ignore
 
 
 class ChsInfoType(TypedDict, total=False, closed=True):  # type: ignore[call-arg]
@@ -30,7 +29,7 @@ class ChsInfoType(TypedDict, total=False, closed=True):  # type: ignore[call-arg
     coil_type: int
     coord_frame: int
     kind: str
-    loc: _loc_type  # type: ignore[valid-type,misc]
+    loc: NDArray[Shape["12"], np.float64]  # type: ignore[misc]
     logno: int
     range: float
     scanno: int