Braindecode 1.6.1.dev1045__tar.gz → 1.6.1.dev1047__tar.gz

{braindecode-1.6.1.dev1045/braindecode.egg-info → braindecode-1.6.1.dev1047}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.6.1.dev1045
+Version: 1.6.1.dev1047
 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.dev1045 → braindecode-1.6.1.dev1047}/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.dev1045 → braindecode-1.6.1.dev1047}/braindecode/models/__init__.py

@@ -19,7 +19,7 @@ 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
@@ -91,6 +91,7 @@ __all__ = [
     "EEGITNet",
     "EEGMiner",
     "EEGNet",
+    "EEGNetv4",
     "EEGNeX",
     "EEGSym",
     "EEGSimpleConv",

{braindecode-1.6.1.dev1045 → braindecode-1.6.1.dev1047}/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.dev1045 → braindecode-1.6.1.dev1047}/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.dev1045 → braindecode-1.6.1.dev1047}/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.dev1045 → braindecode-1.6.1.dev1047}/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]
 
 

braindecode-1.6.1.dev1047/braindecode/version.py

@@ -0,0 +1 @@
+__version__ = "1.6.1.dev1047"

{braindecode-1.6.1.dev1045 → braindecode-1.6.1.dev1047/braindecode.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.6.1.dev1045
+Version: 1.6.1.dev1047
 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.dev1045 → braindecode-1.6.1.dev1047}/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.dev1045 → braindecode-1.6.1.dev1047}/docs/whats_new.rst

@@ -40,12 +40,7 @@ Enhancements
 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
 ============
@@ -70,13 +65,6 @@ Bug fixes
 
 - 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
 ============
 
@@ -1259,4 +1247,3 @@ 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.dev1045/braindecode/version.py

@@ -1 +0,0 @@
-__version__ = "1.6.1.dev1045"