Braindecode 1.6.1.dev1037__tar.gz → 1.6.1.dev1041__tar.gz

{braindecode-1.6.1.dev1037/braindecode.egg-info → braindecode-1.6.1.dev1041}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.6.1.dev1037
+Version: 1.6.1.dev1041
 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>
@@ -46,7 +46,7 @@ Requires-Dist: zarr>=3.0; extra == "hub"
 Provides-Extra: viz
 Requires-Dist: captum>=0.7.0; extra == "viz"
 Provides-Extra: tests
-Requires-Dist: pytest<9.1; extra == "tests"
+Requires-Dist: pytest; extra == "tests"
 Requires-Dist: pytest-cov; extra == "tests"
 Requires-Dist: codecov; extra == "tests"
 Requires-Dist: pytest_cases; extra == "tests"

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode/datasets/moabb.py

@@ -15,6 +15,7 @@ from typing import Any
 
 import mne
 import pandas as pd
+from mne.utils import deprecated
 
 from braindecode.util import _update_moabb_docstring
 
@@ -207,3 +208,12 @@ class HGD(MOABBDataset):
 
     def __init__(self, subject_ids):
         super().__init__("Schirrmeister2017", subject_ids=subject_ids)
+
+
+@deprecated(
+    "`BNCI2014001` was renamed to `BNCI2014_001` in v1.13; this alias will be removed in v1.14."
+)
+class BNCI2014001(BNCI2014_001):
+    """Deprecated alias for BNCI2014001."""
+
+    pass

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode/models/__init__.py

@@ -15,12 +15,11 @@ from .deep4 import Deep4Net
 from .deepsleepnet import DeepSleepNet
 from .dgcnn import DGCNN
 from .eegconformer import EEGConformer
-from .eegdino import EEGDINO
 from .eeginception_erp import EEGInceptionERP
 from .eeginception_mi import EEGInceptionMI
 from .eegitnet import EEGITNet
 from .eegminer import EEGMiner
-from .eegnet import EEGNet
+from .eegnet import EEGNet, EEGNetv4
 from .eegnex import EEGNeX
 from .eegpt import EEGPT, InterpolatedEEGPT
 from .eegsimpleconv import EEGSimpleConv
@@ -85,7 +84,6 @@ __all__ = [
     "DeepSleepNet",
     "BrainModule",
     "EEGConformer",
-    "EEGDINO",
     "EEGPT",
     "InterpolatedEEGPT",
     "EEGInceptionERP",
@@ -93,6 +91,7 @@ __all__ = [
     "EEGITNet",
     "EEGMiner",
     "EEGNet",
+    "EEGNetv4",
     "EEGNeX",
     "EEGSym",
     "EEGSimpleConv",

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode/models/attn_sleep.py

@@ -8,6 +8,7 @@ from copy import deepcopy
 
 import torch
 import torch.nn.functional as F
+from mne.utils import deprecated
 from torch import nn
 
 from braindecode.models.base import EEGModuleMixin
@@ -537,3 +538,12 @@ class _PositionwiseFeedForward(nn.Module):
     def forward(self, x: torch.Tensor) -> torch.Tensor:
         """Implements FFN equation."""
         return self.w_2(self.dropout(self.activate(self.w_1(x))))
+
+
+@deprecated(
+    "`SleepStagerEldele2021` was renamed to `AttnSleep` in v1.12 to follow original author's name; this alias will be removed in v1.14."
+)
+class SleepStagerEldele2021(AttnSleep):
+    r"""Deprecated alias for SleepStagerEldele2021."""
+
+    pass

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode/models/eegnet.py

@@ -6,7 +6,7 @@ from __future__ import annotations
 from typing import Dict, Optional
 
 from einops.layers.torch import Rearrange
-from mne.utils import warn
+from mne.utils import deprecated, warn
 from torch import nn
 
 from braindecode.functional import glorot_weight_zero_bias
@@ -348,3 +348,12 @@ class EEGNet(EEGModuleMixin, nn.Sequential):
         self.add_module("final_layer", module)
 
         glorot_weight_zero_bias(self)
+
+
+@deprecated(
+    "`EEGNetv4` was renamed to `EEGNet` in v1.12; this alias will be removed in v1.14."
+)
+class EEGNetv4(EEGNet):
+    r"""Deprecated alias for EEGNet."""
+
+    pass

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode/models/summary.csv

@@ -56,4 +56,3 @@ InterpolatedBIOT,"Sleep Staging, Epilepsy",Classification,200,"chs_info, n_outpu
 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"
-EEGDINO,General,Classification,200,"n_chans, n_outputs, n_times",4539698,"EEGDINO(n_chans=19, n_outputs=4, n_times=1000)","Foundation Model,Attention/Transformer"

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode/models/tsinception.py

@@ -7,7 +7,7 @@ from __future__ import annotations
 import torch
 import torch.nn as nn
 from einops.layers.torch import Rearrange
-from mne.utils import warn
+from mne.utils import deprecated, warn
 
 from braindecode.models.base import EEGModuleMixin
 
@@ -283,3 +283,13 @@ class TSception(EEGModuleMixin, nn.Module):
             activation(),
             nn.AvgPool2d(kernel_size=(1, pool_size), stride=(1, pool_size)),
         )
+
+
+@deprecated(
+    "`TSceptionV1` was renamed to `TSception` in v1.12; "
+    "this alias will be removed in v1.14."
+)
+class TSceptionV1(TSception):
+    r"""Deprecated alias for TSception."""
+
+    pass

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode/models/util.py

@@ -189,6 +189,8 @@ def _init_models_dict():
             issubclass(m[1], models.base.EEGModuleMixin)
             and m[1] != models.base.EEGModuleMixin
         ):
+            if m[1].__name__ == "EEGNetv4":
+                continue
             models_dict[m[0]] = m[1]
 
 
@@ -432,7 +434,6 @@ models_mandatory_parameters: list[
         {"n_chans": 19, "n_times": 6000},
     ),
     ("DGCNN", ["n_chans", "n_outputs", "n_times", "chs_info"], None),
-    ("EEGDINO", ["n_chans", "n_outputs", "n_times"], None),
 ]
 
 ################################################################

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode/modules/__init__.py

@@ -14,7 +14,7 @@ from .attention import (
     MultiHeadAttention,
     SqueezeAndExcitation,
 )
-from .blocks import MLP, FeedForwardBlock, InceptionBlock, PatchTokenizer
+from .blocks import MLP, FeedForwardBlock, InceptionBlock
 from .convolution import (
     AvgPool2dWithConv,
     CausalConv1d,
@@ -68,7 +68,6 @@ __all__ = [
     "MLP",
     "FeedForwardBlock",
     "InceptionBlock",
-    "PatchTokenizer",
     "AvgPool2dWithConv",
     "CausalConv1d",
     "CombinedConv",

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode/modules/blocks.py

@@ -1,89 +1,7 @@
-from warnings import warn
-
 import torch
 from torch import nn
 
 
-class PatchTokenizer(nn.Module):
-    r"""Tokenize an EEG signal into non-overlapping temporal patches.
-
-    Transforms ``(batch, n_chans, n_times)`` into
-    ``(batch, n_chans, n_patches, patch_dim)`` by splitting the time axis into
-    non-overlapping patches of ``patch_size`` samples. This is the shared
-    patch / "tokenization" step used by transformer EEG foundation models
-    (e.g. LaBraM, CBraMod, EEG-DINO).
-
-    As in the filter-bank models (:class:`~braindecode.models.FBCNet`,
-    :class:`~braindecode.models.FBMSNet`), when ``n_times`` is not a multiple of
-    ``patch_size`` the input is right zero-padded (a warning is emitted at
-    construction); it is never an error.
-
-    Two modes:
-
-    - **non-learnable** (``learnable=False``, default): a pure reshape, so
-      ``patch_dim == patch_size`` and the raw samples of each patch are kept
-      (the patch embedding, if any, lives in the model).
-    - **learnable** (``learnable=True``): a strided ``Conv1d`` (kernel and
-      stride equal to ``patch_size``, applied per channel) maps each patch to
-      ``emb_dim`` features, so ``patch_dim == emb_dim``.
-
-    Parameters
-    ----------
-    patch_size : int
-        Number of time samples per patch.
-    n_times : int
-        Number of time samples of the input, used to set up the right-padding
-        when ``n_times`` is not a multiple of ``patch_size``.
-    emb_dim : int, optional
-        Output features per patch in learnable mode. Defaults to ``patch_size``.
-        Ignored when ``learnable=False``.
-    learnable : bool, default=False
-        Whether the tokenizer is a learned convolution or a fixed reshape.
-
-    Examples
-    --------
-    >>> import torch
-    >>> from braindecode.modules import PatchTokenizer
-    >>> tokenizer = PatchTokenizer(patch_size=200, n_times=1000)
-    >>> tokenizer(torch.randn(2, 19, 1000)).shape
-    torch.Size([2, 19, 5, 200])
-    """
-
-    def __init__(self, patch_size, n_times, emb_dim=None, learnable=False):
-        super().__init__()
-        self.patch_size = patch_size
-        self.learnable = learnable
-        self.emb_dim = (emb_dim or patch_size) if learnable else patch_size
-        if n_times % patch_size:
-            warn(
-                f"Time dimension ({n_times}) is not divisible by patch_size "
-                f"({patch_size}). Input will be padded.",
-                UserWarning,
-            )
-            self.padding_layer = nn.ConstantPad1d(
-                (0, patch_size - n_times % patch_size), 0.0
-            )
-        else:
-            self.padding_layer = nn.Identity()
-        # Defined unconditionally (Identity when not learnable) so the attribute
-        # always exists for torch.jit.script, which type-checks both branches.
-        if learnable:
-            self.patcher = nn.Conv1d(1, self.emb_dim, patch_size, stride=patch_size)
-        else:
-            self.patcher = nn.Identity()
-
-    def forward(self, x):
-        x = self.padding_layer(x)
-        batch_size, n_chans, _ = x.shape
-        if self.learnable:
-            x = x.flatten(0, 1).unsqueeze(1)  # (batch * chans, 1, time)
-            x = self.patcher(x)  # (batch * chans, emb, patches)
-            return x.reshape(batch_size, n_chans, x.shape[-2], x.shape[-1]).permute(
-                0, 1, 3, 2
-            )
-        return x.reshape(batch_size, n_chans, -1, self.patch_size)
-
-
 class InceptionBlock(nn.Module):
     """
     Inception block module.

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode/preprocessing/mne_preprocess.py

@@ -13,28 +13,6 @@ import mne.preprocessing
 from braindecode.preprocessing.preprocess import Preprocessor
 from braindecode.util import _clean_docstring_sections
 
-# Standalone MNE functions that are safe to wrap as a *callable* preprocessor.
-#
-# When ``fn`` is a callable and ``apply_on_array=False``, ``Preprocessor`` calls
-# ``fn(raw, **kwargs)`` and reassigns the dataset to whatever ``fn`` returns. That
-# is only correct for functions that return the modified ``Raw``/``Epochs``
-# instance. Many standalone MNE functions instead return auxiliary data
-# (annotations, a list of bad channels, a ``(inst, ...)`` tuple, ...), so passing
-# them as callables would silently replace the recording with that auxiliary
-# object. We therefore restrict the callable path to functions verified to return
-# the modified instance; every other standalone function keeps the existing
-# (string-name) behaviour. See :gh:`885`.
-_SAFE_STANDALONE_FUNCTIONS = frozenset(
-    {
-        # returns the Raw with the CSD-transformed data
-        mne.preprocessing.compute_current_source_density,
-        # returns the Raw with the new bipolar reference channel
-        mne.set_bipolar_reference,
-        # returns the Raw with the OTP-cleaned data
-        mne.preprocessing.oversampled_temporal_projection,
-    }
-)
-
 
 def _is_standalone_function(func):
     """
@@ -101,12 +79,7 @@ def _generate_init_method(func, force_copy_false=False):
             raise TypeError(
                 f"{func_name}() missing required arguments: {', '.join(mandatory)}"
             )
-        # For standalone functions verified to return the modified instance,
-        # pass the callable itself so it is actually applied. Every other
-        # function keeps the legacy string-name behaviour (see #885 and
-        # ``_SAFE_STANDALONE_FUNCTIONS`` above).
-        fn = func if func in _SAFE_STANDALONE_FUNCTIONS else func_name
-        Preprocessor.__init__(self, fn=fn, apply_on_array=False, **init_kwargs)
+        Preprocessor.__init__(self, fn=func_name, apply_on_array=False, **init_kwargs)
 
     init_method.__signature__ = inspect.signature(func)
     return init_method

braindecode-1.6.1.dev1041/braindecode/version.py

@@ -0,0 +1 @@
+__version__ = "1.6.1.dev1041"

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041/braindecode.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.6.1.dev1037
+Version: 1.6.1.dev1041
 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>
@@ -46,7 +46,7 @@ Requires-Dist: zarr>=3.0; extra == "hub"
 Provides-Extra: viz
 Requires-Dist: captum>=0.7.0; extra == "viz"
 Provides-Extra: tests
-Requires-Dist: pytest<9.1; extra == "tests"
+Requires-Dist: pytest; extra == "tests"
 Requires-Dist: pytest-cov; extra == "tests"
 Requires-Dist: codecov; extra == "tests"
 Requires-Dist: pytest_cases; extra == "tests"

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode.egg-info/SOURCES.txt

@@ -67,7 +67,6 @@ braindecode/models/deep4.py
 braindecode/models/deepsleepnet.py
 braindecode/models/dgcnn.py
 braindecode/models/eegconformer.py
-braindecode/models/eegdino.py
 braindecode/models/eeginception_erp.py
 braindecode/models/eeginception_mi.py
 braindecode/models/eegitnet.py

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/braindecode.egg-info/requires.txt

@@ -56,7 +56,7 @@ zarr>=3.0
 moabb>=1.4.3
 
 [tests]
-pytest<9.1
+pytest
 pytest-cov
 codecov
 pytest_cases

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/docs/api.rst

@@ -143,7 +143,6 @@ interface for all EEG models and can derive variable names when needed.
      Deep4Net
      DeepSleepNet
      EEGConformer
-     EEGDINO
      EEGInceptionERP
      EEGInceptionMI
      EEGITNet
@@ -256,7 +255,6 @@ perceptrons (MLPs) and inception blocks.
     MLP
     FeedForwardBlock
     InceptionBlock
-    PatchTokenizer
 
 Convolution
 ===========

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/docs/index.rst

@@ -293,14 +293,14 @@
                 <span class="code-step-num">02</span>
                 <span class="code-step-text">
                   <span class="code-step-title">Preprocess &amp; window</span>
-                  <span class="code-step-desc">Keep EEG sensors, bandpass-filter, then window the trials.</span>
+                  <span class="code-step-desc">Bandpass-filter, then cut motor-imagery trials.</span>
                 </span>
               </li>
               <li class="code-step">
                 <span class="code-step-num">03</span>
                 <span class="code-step-text">
                   <span class="code-step-title">Pick a model</span>
-                  <span class="code-step-desc">EEGNeX, sized from the data: 22 channels, 4 classes, 4 s @ 250 Hz.</span>
+                  <span class="code-step-desc">EEGNeX with 22 channels, 4 classes, 4.5 s @ 250 Hz.</span>
                 </span>
               </li>
               <li class="code-step">
@@ -321,8 +321,8 @@
               <div class="code-window-meta">PyTorch · CUDA</div>
             </div>
             <div class="code-window-body">
-              <div class="code-gutter"><div>1</div><div>2</div><div>3</div><div>4</div><div>5</div><div>6</div><div>7</div><div>8</div><div>9</div><div>10</div><div>11</div><div>12</div><div>13</div><div>14</div><div>15</div><div>16</div><div>17</div><div>18</div><div>19</div><div>20</div></div>
-              <div class="code-content"><div data-step="0"><span class="tok-com"># 1. Load BCI Competition IV-2a (subject 3) via MOABB</span></div><div data-step="0"><span class="tok-kw">from</span> <span class="tok-var">braindecode.datasets</span> <span class="tok-kw">import</span> <span class="tok-cls">MOABBDataset</span></div><div data-step="0"></div><div data-step="0"><span class="tok-var">dataset</span> = <span class="tok-fn">MOABBDataset</span>(<span class="tok-str">"BNCI2014_001"</span>, <span class="tok-attr">subject_ids</span>=[<span class="tok-num">3</span>])</div><div data-step="1"><span class="tok-com"># 2. Keep EEG channels, bandpass-filter, and window the trials</span></div><div data-step="1"><span class="tok-kw">from</span> <span class="tok-var">braindecode.preprocessing</span> <span class="tok-kw">import</span> (</div><div data-step="1">    <span class="tok-cls">Preprocessor</span>, <span class="tok-fn">preprocess</span>, <span class="tok-fn">create_windows_from_events</span>,</div><div data-step="1">)</div><div data-step="1"></div><div data-step="1"><span class="tok-fn">preprocess</span>(<span class="tok-var">dataset</span>, [</div><div data-step="1">    <span class="tok-fn">Preprocessor</span>(<span class="tok-str">"pick_types"</span>, <span class="tok-attr">eeg</span>=<span class="tok-kw">True</span>),</div><div data-step="1">    <span class="tok-fn">Preprocessor</span>(<span class="tok-str">"filter"</span>, <span class="tok-attr">l_freq</span>=<span class="tok-num">4.</span>, <span class="tok-attr">h_freq</span>=<span class="tok-num">38.</span>),</div><div data-step="1">])</div><div data-step="1"><span class="tok-var">windows</span> = <span class="tok-fn">create_windows_from_events</span>(<span class="tok-var">dataset</span>)</div><div data-step="2"><span class="tok-com"># 3. Pick a published architecture by name</span></div><div data-step="2"><span class="tok-kw">from</span> <span class="tok-var">braindecode</span> <span class="tok-kw">import</span> <span class="tok-cls">EEGClassifier</span></div><div data-step="2"></div><div data-step="2"><span class="tok-var">clf</span> = <span class="tok-fn">EEGClassifier</span>(<span class="tok-str">"EEGNeX"</span>, <span class="tok-attr">max_epochs</span>=<span class="tok-num">10</span>, <span class="tok-attr">train_split</span>=<span class="tok-kw">None</span>)</div><div data-step="3"><span class="tok-com"># 4. Train with sklearn-style fit()</span></div><div data-step="3"><span class="tok-var">clf</span>.<span class="tok-fn">fit</span>(<span class="tok-var">windows</span>, <span class="tok-attr">y</span>=<span class="tok-kw">None</span>)</div></div>
+              <div class="code-gutter"><div>1</div><div>2</div><div>3</div><div>4</div><div>5</div><div>6</div><div>7</div><div>8</div><div>9</div><div>10</div><div>11</div><div>12</div><div>13</div><div>14</div><div>15</div><div>16</div><div>17</div><div>18</div><div>19</div></div>
+              <div class="code-content"><div data-step="0"><span class="tok-com"># 1. Load BCI Competition IV-2a (subject 3) via MOABB</span></div><div data-step="0"><span class="tok-kw">from</span> <span class="tok-var">braindecode.datasets</span> <span class="tok-kw">import</span> <span class="tok-cls">MOABBDataset</span></div><div data-step="0"></div><div data-step="0"><span class="tok-var">dataset</span> = <span class="tok-fn">MOABBDataset</span>(<span class="tok-str">"BNCI2014_001"</span>, <span class="tok-attr">subject_ids</span>=[<span class="tok-num">3</span>])</div><div data-step="1"><span class="tok-com"># 2. Bandpass-filter and create event-aligned windows</span></div><div data-step="1"><span class="tok-kw">from</span> <span class="tok-var">braindecode.preprocessing</span> <span class="tok-kw">import</span> (</div><div data-step="1">    <span class="tok-cls">Preprocessor</span>, <span class="tok-fn">preprocess</span>, <span class="tok-fn">create_windows_from_events</span>,</div><div data-step="1">)</div><div data-step="1"></div><div data-step="1"><span class="tok-fn">preprocess</span>(<span class="tok-var">dataset</span>, [<span class="tok-fn">Preprocessor</span>(<span class="tok-str">"filter"</span>, <span class="tok-attr">l_freq</span>=<span class="tok-num">4.</span>, <span class="tok-attr">h_freq</span>=<span class="tok-num">38.</span>)])</div><div data-step="1"><span class="tok-var">windows</span> = <span class="tok-fn">create_windows_from_events</span>(<span class="tok-var">dataset</span>)</div><div data-step="2"><span class="tok-com"># 3. Instantiate a published architecture</span></div><div data-step="2"><span class="tok-kw">from</span> <span class="tok-var">braindecode.models</span> <span class="tok-kw">import</span> <span class="tok-cls">EEGNeX</span></div><div data-step="2"></div><div data-step="2"><span class="tok-var">model</span> = <span class="tok-fn">EEGNeX</span>(<span class="tok-attr">n_chans</span>=<span class="tok-num">22</span>, <span class="tok-attr">n_outputs</span>=<span class="tok-num">4</span>, <span class="tok-attr">n_times</span>=<span class="tok-num">1125</span>)</div><div data-step="3"><span class="tok-com"># 4. Train with the skorch-based EEGClassifier</span></div><div data-step="3"><span class="tok-kw">from</span> <span class="tok-var">braindecode</span> <span class="tok-kw">import</span> <span class="tok-cls">EEGClassifier</span></div><div data-step="3"></div><div data-step="3"><span class="tok-var">clf</span> = <span class="tok-fn">EEGClassifier</span>(<span class="tok-attr">module</span>=<span class="tok-var">model</span>, <span class="tok-attr">max_epochs</span>=<span class="tok-num">10</span>)</div><div data-step="3"><span class="tok-var">clf</span>.<span class="tok-fn">fit</span>(<span class="tok-var">windows</span>, <span class="tok-attr">y</span>=<span class="tok-kw">None</span>)</div></div>
             </div>
             <div class="code-output">
               <span class="ok"><svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.7" stroke-linecap="round" stroke-linejoin="round"><path d="M20 6 9 17l-5-5"/></svg> Trains on CPU or GPU</span>

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/docs/whats_new.rst

@@ -36,27 +36,16 @@ Enhancements
   variant of :class:`braindecode.models.EEGPT` built with
   :func:`~braindecode.models.interpolated.InterpolatedModel`.
   By `Pierre Guetschel`_.
-- Add :class:`braindecode.models.EEGDINO`, the EEG-DINO self-distillation
-  foundation model (Small/Medium/Large) with pretrained S/M weights. By `Bruno Aristimunha`_.
 
 API and behavior changes
 ========================
 
-- Removed the deprecated aliases that were scheduled for removal after their
-  deprecation in v1.2/v1.3: ``EEGNetv4`` (use
-  :class:`braindecode.models.EEGNet`), ``SleepStagerEldele2021`` (use
-  :class:`braindecode.models.AttnSleep`), ``TSceptionV1`` (use
-  :class:`braindecode.models.TSception`), and ``BNCI2014001`` (use
-  :class:`braindecode.datasets.BNCI2014_001`). (:gh:`1045` by `Bhargav Kowshik`_)
+- None yet
 
 Requirements
 ============
 
-- Cap the test dependency to ``pytest<9.1`` in the ``tests`` extra. ``pytest``
-  9.1.0 changed the ``IdMaker`` constructor signature, which breaks
-  ``pytest_cases`` 3.10.1 and makes the whole test suite crash at collection
-  time. The cap can be lifted once ``pytest_cases`` supports ``pytest>=9.1``.
-  By `Adam Mounir`_.
+- None yet
 
 Bug fixes
 ==========
@@ -70,24 +59,8 @@ Bug fixes
   use running statistics when ``batch_size == 1`` in train mode.
   By `Bruno Aristimunha`_.
 
-- Fix the auto-generated standalone-function preprocessors
-  (:class:`braindecode.preprocessing.ComputeCurrentSourceDensity`,
-  :class:`braindecode.preprocessing.SetBipolarReference`, and
-  :class:`braindecode.preprocessing.OversampledTemporalProjection`) passing the
-  function name as a string instead of the callable, so they failed to apply.
-  These functions return the modified instance and are now wrapped as callables.
-  Standalone functions that return auxiliary data (e.g. annotations or bad
-  channels) are intentionally left on the existing path for now. (:gh:`885` by
-  `Yiheng Li`_)
 - Fix incorrect import path in CONTRIBUTING.md by `Yiheng Li`_
 
-- Fix the broken EEGNeX quickstart snippet on the documentation landing page,
-  which kept non-EEG channels (including the STIM trigger), hardcoded a
-  mismatched ``n_times``, and failed at the default stratified validation split
-  with ``y=None``; it now restricts to EEG channels and lets
-  :class:`~braindecode.EEGClassifier` infer the signal dimensions from the data.
-  By `Bhargav Kowshik`_
-
 Code health
 ============
 
@@ -1270,4 +1243,3 @@ Authors
 .. _Léo Burgund: https://github.com/leob000
 .. _Adam Mounir: https://github.com/adammounir
 .. _Yiheng Li: https://github.com/YihengLi-1
-.. _Bhargav Kowshik: https://github.com/bkowshik

{braindecode-1.6.1.dev1037 → braindecode-1.6.1.dev1041}/pyproject.toml

@@ -80,7 +80,7 @@ eegprep = ["eegprep[eeglabio]>=0.2.23"]
 hub = ["huggingface_hub[torch]>=0.20.0", "zarr>=3.0"]
 viz = ["captum>=0.7.0"]
 tests = [
-    'pytest<9.1',  # pytest 9.1.0 changed IdMaker's signature, which breaks pytest_cases 3.10.1 (crash at collection time). Remove the cap once pytest_cases supports pytest >=9.1.
+    'pytest',
     'pytest-cov',
     'codecov',
     'pytest_cases',
@@ -162,9 +162,3 @@ testpaths = ["test"]
 python_files = ["test_*.py", "*_test.py"]
 # which functions inside them count as tests
 python_functions = ["test_*"]
-markers = [
-    "integration: integration tests",
-    "network: tests that require network access",
-    "huggingface: tests that access Hugging Face Hub",
-    "slow: slow tests",
-]