Braindecode 1.3.0.dev167809764__tar.gz → 1.3.0.dev168090315__tar.gz

{braindecode-1.3.0.dev167809764/braindecode.egg-info → braindecode-1.3.0.dev168090315}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.3.0.dev167809764
+Version: 1.3.0.dev168090315
 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>
@@ -22,17 +22,12 @@ Requires-Python: >=3.11
 Description-Content-Type: text/x-rst
 License-File: LICENSE.txt
 License-File: NOTICE.txt
+Requires-Dist: torch>=2.2
+Requires-Dist: torchaudio>=2.0
 Requires-Dist: mne>=1.11.0
 Requires-Dist: mne_bids>=0.16
-Requires-Dist: numpy
-Requires-Dist: pandas
-Requires-Dist: scipy
-Requires-Dist: matplotlib
 Requires-Dist: h5py
 Requires-Dist: skorch>=1.3.0
-Requires-Dist: torch>=2.0
-Requires-Dist: torchaudio>=2.0
-Requires-Dist: einops
 Requires-Dist: joblib
 Requires-Dist: torchinfo
 Requires-Dist: wfdb
@@ -40,7 +35,7 @@ Requires-Dist: linear_attention_transformer
 Requires-Dist: docstring_inheritance
 Requires-Dist: rotary_embedding_torch
 Provides-Extra: moabb
-Requires-Dist: moabb>=1.4.2; extra == "moabb"
+Requires-Dist: moabb>=1.4.3; extra == "moabb"
 Provides-Extra: eegprep
 Requires-Dist: eegprep[eeglabio]>=0.2.23; extra == "eegprep"
 Provides-Extra: hub
@@ -52,8 +47,9 @@ Requires-Dist: pytest-cov; extra == "tests"
 Requires-Dist: codecov; extra == "tests"
 Requires-Dist: pytest_cases; extra == "tests"
 Requires-Dist: mypy; extra == "tests"
+Requires-Dist: transformers>=4.57.0; extra == "tests"
 Provides-Extra: typing
-Requires-Dist: pydantic<3.0,>=2.0; extra == "typing"
+Requires-Dist: exca==0.4; extra == "typing"
 Requires-Dist: numpydantic>=1.7; extra == "typing"
 Provides-Extra: docs
 Requires-Dist: sphinx_gallery; extra == "docs"
@@ -75,6 +71,7 @@ Requires-Dist: openneuro-py; extra == "docs"
 Requires-Dist: plotly; extra == "docs"
 Requires-Dist: shap; extra == "docs"
 Requires-Dist: nbformat; extra == "docs"
+Requires-Dist: transformers; extra == "docs"
 Provides-Extra: all
 Requires-Dist: braindecode[moabb]; extra == "all"
 Requires-Dist: braindecode[tests]; extra == "all"

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/datautil/util.py

@@ -11,8 +11,7 @@ from skorch.helper import SliceDataset
 from skorch.utils import is_dataset
 
 from braindecode.datasets.base import BaseConcatDataset, WindowsDataset
-
-# from braindecode.models.util import SigArgName
+from braindecode.models.util import SigArgName
 
 log = logging.getLogger(__name__)
 
@@ -79,16 +78,16 @@ def infer_signal_properties(
     y=None,
     mode: Literal["classification", "regression"] = "classification",
     classes: list | None = None,
-) -> dict[str, Any]:  # TODO
+) -> dict[SigArgName, Any]:
     """Infers signal properties from the data.
 
     The extracted signal properties are:
 
-      * n_chans: number of channels
-      * n_times: number of time points
-      * n_outputs: number of outputs
-      * chs_info: channel information
-      * sfreq: sampling frequency
+    + n_chans: number of channels
+    + n_times: number of time points
+    + n_outputs: number of outputs
+    + chs_info: channel information
+    + sfreq: sampling frequency
 
     The returned dictionary can serve as kwargs for model initialization.
 
@@ -111,7 +110,7 @@ def infer_signal_properties(
         Dictionary with signal-properties. Can serve as kwargs for model
         initialization.
     """
-    signal_kwargs = dict()
+    signal_kwargs: dict[SigArgName, Any] = {}
     # Using shape to work both with torch.tensor and numpy.array:
     if (
         isinstance(X, mne.BaseEpochs)

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/__init__.py

@@ -32,6 +32,7 @@ from .luna import LUNA
 from .medformer import MEDFormer
 from .msvtnet import MSVTNet
 from .patchedtransformer import PBT
+from .reve import REVE
 from .sccnet import SCCNet
 from .shallow_fbcsp import ShallowFBCSPNet
 from .signal_jepa import (
@@ -93,6 +94,7 @@ __all__ = [
     "MEDFormer",
     "MSVTNet",
     "PBT",
+    "REVE",
     "SCCNet",
     "ShallowFBCSPNet",
     "SignalJEPA",

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/atcnet.py

@@ -15,7 +15,7 @@ from braindecode.modules import CausalConv1d, Ensure4d, MaxNormLinear
 class ATCNet(EEGModuleMixin, nn.Module):
     """ATCNet from Altaheri et al. (2022) [1]_.
 
-    :bdg-success:`Convolution` :bdg-secondary:`Recurrent` :bdg-info:`Small Attention`
+    :bdg-success:`Convolution` :bdg-secondary:`Recurrent` :bdg-info:`Attention/Transformer`
 
     .. figure:: https://user-images.githubusercontent.com/25565236/185449791-e8539453-d4fa-41e1-865a-2cf7e91f60ef.png
         :align: center

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/attentionbasenet.py

@@ -26,7 +26,7 @@ from braindecode.modules.attention import (
 class AttentionBaseNet(EEGModuleMixin, nn.Module):
     """AttentionBaseNet from Wimpff M et al. (2023) [Martin2023]_.
 
-    :bdg-success:`Convolution` :bdg-info:`Small Attention`
+    :bdg-success:`Convolution` :bdg-info:`Attention/Transformer`
 
     .. figure:: https://content.cld.iop.org/journals/1741-2552/21/3/036020/revision2/jnead48b9f2_hr.jpg
         :align: center

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/attn_sleep.py

@@ -18,7 +18,7 @@ from braindecode.modules import CausalConv1d
 class AttnSleep(EEGModuleMixin, nn.Module):
     """Sleep Staging Architecture from Eldele et al. (2021) [Eldele2021]_.
 
-    :bdg-success:`Convolution` :bdg-info:`Small Attention`
+    :bdg-success:`Convolution` :bdg-info:`Attention/Transformer`
 
     .. figure:: https://raw.githubusercontent.com/emadeldeen24/AttnSleep/refs/heads/main/imgs/AttnSleep.png
         :align: center

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/bendr.py

@@ -10,7 +10,7 @@ from braindecode.models.base import EEGModuleMixin
 class BENDR(EEGModuleMixin, nn.Module):
     """BENDR (BErt-inspired Neural Data Representations) from Kostas et al. (2021) [bendr]_.
 
-    :bdg-success:`Convolution` :bdg-danger:`Large Brain Model`
+    :bdg-success:`Convolution` :bdg-danger:`Foundation Model`
 
     .. figure:: https://www.frontiersin.org/files/Articles/653659/fnhum-15-653659-HTML/image_m/fnhum-15-653659-g001.jpg
         :align: center

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/biot.py

@@ -11,7 +11,7 @@ from braindecode.models.base import EEGModuleMixin
 class BIOT(EEGModuleMixin, nn.Module):
     """BIOT from Yang et al. (2023) [Yang2023]_
 
-    :bdg-danger:`Large Brain Model`
+    :bdg-danger:`Foundation Model`
 
     .. figure:: https://braindecode.org/dev/_static/model/biot.jpg
        :align: center
@@ -19,7 +19,7 @@ class BIOT(EEGModuleMixin, nn.Module):
 
     BIOT: Cross-data Biosignal Learning in the Wild.
 
-    BIOT is a large brain model for biosignal classification. It is
+    BIOT is a foundation model for biosignal classification. It is
     a wrapper around the `BIOTEncoder` and `ClassificationHead` modules.
 
     It is designed for N-dimensional biosignal data such as EEG, ECG, etc.

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/config.py

@@ -1,5 +1,3 @@
-import functools
-import operator
 from collections.abc import Callable
 from inspect import signature
 from types import UnionType
@@ -59,10 +57,25 @@ SIGNAL_ARGS_TYPES = {
 }
 
 
+class BaseBraindecodeModelConfig(pydantic.BaseModel):  # type: ignore
+    def create_instance(self) -> EEGModuleMixin:
+        model_cls = models_dict[self.model_name_]
+        kwargs = self.model_dump(mode="python", exclude={"model_name_"})
+        if kwargs.get("n_chans") is not None and kwargs.get("chs_info") is not None:
+            kwargs.pop("n_chans")
+        if (
+            kwargs.get("n_times") is not None
+            and kwargs.get("input_window_seconds") is not None
+            and kwargs.get("sfreq") is not None
+        ):
+            kwargs.pop("n_times")
+        return model_cls(**kwargs)
+
+
 def make_model_config(
     model_class: type[EEGModuleMixin],
     required: list[SigArgName],
-):
+) -> type[BaseBraindecodeModelConfig]:
     """Create a pydantic model config for a given model class.
 
     Parameters
@@ -84,18 +97,6 @@ def make_model_config(
         )
 
     # ironically, we need to ignore the type here to have the soft dependency.
-    class BaseBraindecodeModelConfig(pydantic.BaseModel):  # type: ignore
-        def create_instance(self) -> EEGModuleMixin:
-            kwargs = self.model_dump(mode="python", exclude={"model_name_"})
-            if kwargs.get("n_chans") is not None and kwargs.get("chs_info") is not None:
-                kwargs.pop("n_chans")
-            if (
-                kwargs.get("n_times") is not None
-                and kwargs.get("input_window_seconds") is not None
-                and kwargs.get("sfreq") is not None
-            ):
-                kwargs.pop("n_times")
-            return model_class(**kwargs)
 
     @pydantic.model_validator(mode="before")
     def validate_signal_params(cls, data: Any):
@@ -209,7 +210,7 @@ __all__ = ["make_model_config"]
 if not pydantic:
     pass
 else:
-    models_configs = []
+    models_configs: list[type[BaseBraindecodeModelConfig]] = []
     for model_name, req, _ in models_mandatory_parameters:
         model_cls = models_dict[model_name]
         model_cfg = make_model_config(model_cls, req)
@@ -218,8 +219,10 @@ else:
         models_configs.append(model_cfg)
 
     BraindecodeModelConfig = Annotated[  # type: ignore
-        functools.reduce(operator.or_, models_configs),
-        pydantic.Field(discriminator="model_name_"),
+        Union[tuple(models_configs)],
+        pydantic.Field(
+            discriminator="model_name_", description="Braindecode model configuration"
+        ),
     ]
 
 # # Example usage:

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/ctnet.py

@@ -27,7 +27,7 @@ from braindecode.modules import (
 class CTNet(EEGModuleMixin, nn.Module):
     """CTNet from Zhao, W et al (2024) [ctnet]_.
 
-    :bdg-success:`Convolution` :bdg-info:`Small Attention`
+    :bdg-success:`Convolution` :bdg-info:`Attention/Transformer`
 
      A Convolutional Transformer Network for EEG-Based Motor Imagery Classification
 

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/eegconformer.py

@@ -14,7 +14,7 @@ from braindecode.modules import FeedForwardBlock, MultiHeadAttention
 class EEGConformer(EEGModuleMixin, nn.Module):
     """EEG Conformer from Song et al. (2022) [song2022]_.
 
-    :bdg-success:`Convolution` :bdg-info:`Small Attention`
+    :bdg-success:`Convolution` :bdg-info:`Attention/Transformer`
 
     .. figure:: https://raw.githubusercontent.com/eeyhsong/EEG-Conformer/refs/heads/main/visualization/Fig1.png
         :align: center

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/labram.py

@@ -23,7 +23,7 @@ from braindecode.modules import MLP, DropPath
 class Labram(EEGModuleMixin, nn.Module):
     """Labram from Jiang, W B et al (2024) [Jiang2024]_.
 
-    :bdg-success:`Convolution` :bdg-danger:`Large Brain Model`
+    :bdg-success:`Convolution` :bdg-danger:`Foundation Model`
 
     .. figure:: https://arxiv.org/html/2405.18765v1/x1.png
         :align: center

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/luna.py

@@ -29,7 +29,7 @@ from braindecode.modules.layers import DropPath
 class LUNA(EEGModuleMixin, nn.Module):
     """LUNA from Döner et al. [LUNA]_.
 
-    :bdg-success:`Convolution` :bdg-danger:`Large Brain Model` :bdg-dark-line:`Channel`
+    :bdg-success:`Convolution` :bdg-danger:`Foundation Model` :bdg-dark-line:`Channel`
 
     .. figure:: https://arxiv.org/html/2510.22257v1/x1.png
         :align: center

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/medformer.py

@@ -20,7 +20,7 @@ from braindecode.models.base import EEGModuleMixin
 class MEDFormer(EEGModuleMixin, nn.Module):
     r"""Medformer from Wang et al. (2024) [Medformer2024]_.
 
-    :bdg-success:`Convolution` :bdg-danger:`Large Brain Model`
+    :bdg-success:`Convolution` :bdg-danger:`Foundation Model`
 
     .. figure:: https://raw.githubusercontent.com/DL4mHealth/Medformer/refs/heads/main/figs/medformer_architecture.png
         :align: center

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/msvtnet.py

@@ -13,7 +13,7 @@ from braindecode.models.base import EEGModuleMixin
 class MSVTNet(EEGModuleMixin, nn.Module):
     """MSVTNet model from Liu K et al (2024) from [msvt2024]_.
 
-    :bdg-success:`Convolution` :bdg-secondary:`Recurrent` :bdg-info:`Small Attention`
+    :bdg-success:`Convolution` :bdg-secondary:`Recurrent` :bdg-info:`Attention/Transformer`
 
     This model implements a multi-scale convolutional transformer network
     for EEG signal classification, as described in [msvt2024]_.

{braindecode-1.3.0.dev167809764 → braindecode-1.3.0.dev168090315}/braindecode/models/patchedtransformer.py

@@ -16,7 +16,7 @@ from braindecode.models.base import EEGModuleMixin
 class PBT(EEGModuleMixin, nn.Module):
     r"""Patched Brain Transformer (PBT) model from Klein et al. (2025) [pbt]_.
 
-    :bdg-danger:`Large Brain Model`
+    :bdg-danger:`Foundation Model`
 
     This implementation was based in https://github.com/timonkl/PatchedBrainTransformer/
 
@@ -136,7 +136,7 @@ class PBT(EEGModuleMixin, nn.Module):
 
     .. warning::
 
-        **Important:** As the other Large Brain Models in Braindecode, :class:`PBT` is
+        **Important:** As the other Foundation Models in Braindecode, :class:`PBT` is
         designed for large-scale pre-training and fine-tuning. Training from
         scratch on small datasets may lead to suboptimal results. Cross-Dataset
         pre-training and subsequent fine-tuning is recommended to leverage the