braindecode 1.2.0.dev168908090__py3-none-any.whl → 1.2.0.dev175267687__py3-none-any.whl

braindecode/models/deepsleepnet.py

@@ -8,14 +8,128 @@ from braindecode.models.base import EEGModuleMixin
 
 
 class DeepSleepNet(EEGModuleMixin, nn.Module):
-    """Sleep staging architecture from Supratak et al. (2017) [Supratak2017]_.
+    """DeepSleepNet from Supratak et al. (2017) [Supratak2017]_.
 
-     .. figure:: https://raw.githubusercontent.com/akaraspt/deepsleepnet/refs/heads/master/img/deepsleepnet.png
+    :bdg-success:`Convolution` :bdg-info:`Recurrent`
+
+    .. figure:: https://raw.githubusercontent.com/akaraspt/deepsleepnet/master/img/deepsleepnet.png
         :align: center
         :alt: DeepSleepNet Architecture
+        :width: 700px
+
+    .. rubric:: Architectural Overview
+
+    DeepSleepNet couples **dual-path convolution neural network representation learning** with
+    **sequence residual learning** via bidirectional LSTMs.
+
+    The network have:
+
+    - (i) learns complementary, time-frequency features from each
+      30-s epoch using **two parallel CNNs** (small vs. large first-layer filters), then
+    - (ii) models **temporal dependencies across epochs** using **two-layer BiLSTMs**
+      with a **residual shortcut** from the CNN features, and finally
+    - (iii) outputs per-epoch sleep stages. This design encodes both
+      epoch-local patterns and longer-range transition rules used by human scorers.
+
+    In term of implementation:
+
+    - (i) :class:`_RepresentationLearning` two CNNs extract epoch-wise features
+      (small-filter path for temporal precision; large-filter path for frequency precision);
+    - (ii) :class:`_SequenceResidualLearning` stacked BiLSTMs with peepholes + residual shortcut
+      inject temporal context while preserving CNN evidence;
+    - (iii) :class:`_Classifier` linear readout (softmax) for the five sleep stages.
+
+    .. rubric:: Macro Components
+
+    - :class:`_RepresentationLearning` **(dual-path CNN → epoch feature)**
+
+       - *Operations.*
+       - **Small-filter CNN** 4 times:
+       - :class:`~torch.nn.Conv1d`
+       - :class:`~torch.nn.BatchNorm1d`
+       - :class:`~torch.nn.ReLU`
+       - :class:`~torch.nn.MaxPool1d` after.
+       First conv uses **filter length ≈ Fs/2** and **stride ≈ Fs/16** to emphasize *timing* of graphoelements.
+    - **Large-filter CNN**:
+        - Same stack but first conv uses **filter length ≈ 4·Fs** and
+        - **stride ≈ Fs/2** to emphasize *frequency* content.
+    - Outputs from both paths are **concatenated** into the epoch embedding ``a_t``.
+
+    - *Rationale.*
+      Two first-layer scales provide a **learned, dual-scale filter bank** that trades
+      temporal vs. frequency precision without hand-crafted features.
+
+    - :class:`_SequenceResidualLearning` (:class:`~torch.nn.BiLSTM` **context + residual fusion)**
+
+        - *Operations.*
+        - **Two-layer BiLSTM** with **peephole connections** processes the sequence of epoch embeddings
+          ``{a_t}`` forward and backward; hidden states from both directions are **concatenated**.
+        - A **shortcut MLP** (fully connected + :class:`~torch.nn.BatchNorm1d` + :class:`~torch.nn.ReLU`) projects ``a_t`` to the BiLSTM output
+          dimension and is **added** (residual) to the :class:`~torch.nn.BiLSTM` output at each time step.
+        - *Role.* Encodes **stage-transition rules** and smooths predictions over time while preserving
+          salient CNN features via the residual path.
+
+    - :class:`_Classifier` **(epoch-wise prediction)**
+
+        - *Operations.*
+        - :class:`~torch.nn.Linear` to produce per-epoch class probabilities.
 
-    Convolutional neural network and bidirectional-Long Short-Term
-    for single channels sleep staging described in [Supratak2017]_.
+    Original training uses two-step optimization: CNN pretraining on class-balanced data,
+    then end-to-end fine-tuning with sequential batches.
+
+    .. rubric:: Convolutional Details
+
+    - **Temporal (where time-domain patterns are learned).**
+
+    Both CNN paths use **1-D temporal convolutions**. The *small-filter* path (first kernel ≈ Fs/2,
+    stride ≈ Fs/16) captures *when* characteristic transients occur; the *large-filter* path
+    (first kernel ≈ 4·Fs, stride ≈ Fs/2) captures *which* frequency components dominate over the
+    epoch. Deeper layers use **small kernels** to refine features with fewer parameters, interleaved
+    with **max pooling** for downsampling.
+
+    - **Spatial (how channels are processed).**
+    The original model operates on **single-channel** raw EEG; convolutions therefore mix only
+    along time (no spatial convolution across electrodes).
+
+    - **Spectral (how frequency information emerges).**
+    No explicit Fourier/wavelet transform is used. The **large-filter path** serves as a
+    *frequency-sensitive* analyzer, while the **small-filter path** remains *time-sensitive*,
+    together functioning as a **two-band learned filter bank** at the first layer.
+
+    .. rubric:: Attention / Sequential Modules
+
+    - **Type.** **Bidirectional LSTM** (two layers) with **peephole connections**; forward and
+      backward streams are independent and concatenated.
+    - **Shapes.** For a sequence of ``N`` epochs, the CNN produces ``{a_t} ∈ R^{D}``;
+      BiLSTM outputs ``h_t ∈ R^{2H}``; the shortcut MLP maps ``a_t → R^{2H}`` to enable
+      **element-wise residual addition**.
+    - **Role.** Models **long-range temporal dependencies** (e.g., persisting N2 without visible
+      K-complex/spindles), stabilizing per-epoch predictions.
+
+
+    .. rubric:: Additional Mechanisms
+
+    - **Residual shortcut over sequence encoder.** Adds projected CNN features to BiLSTM outputs,
+      improving gradient flow and retaining discriminative content from representation learning.
+    - **Two-step training.**
+        - (i) **Pretrain** the CNN paths with class-balanced sampling;
+        - (ii) **fine-tune** the full network with sequential batches, using **lower LR** for CNNs and **higher LR** for the
+        sequence encoder.
+    - **State handling.** BiLSTM states are **reinitialized per subject** so that temporal context
+      does not leak across recordings.
+
+
+    .. rubric:: Usage and Configuration
+
+    - **Epoch pipeline.** Use **two parallel CNNs** with the first conv sized to **Fs/2** (small path)
+      and **4·Fs** (large path), with strides **Fs/16** and **Fs/2**, respectively; stack three more
+      conv blocks with small kernels, plus **max pooling** in each path. Concatenate path outputs
+      to form epoch embeddings.
+    - **Sequence encoder.** Apply **two-layer BiLSTM (peepholes)** over the sequence of embeddings;
+      add a **projection MLP** on the CNN features and **sum** with BiLSTM outputs (residual).
+      Finish with :class:`~torch.nn.Linear` per epoch.
+    - **Reference implementation.** See the official repository for a faithful implementation and
+      training scripts.
 
     Parameters
     ----------
@@ -32,7 +146,6 @@ class DeepSleepNet(EEGModuleMixin, nn.Module):
     drop_prob : float, default=0.5
         The dropout rate for regularization. Values should be between 0 and 1.
 
-
     References
     ----------
     .. [Supratak2017] Supratak, A., Dong, H., Wu, C., & Guo, Y. (2017).

braindecode/models/eegconformer.py

@@ -27,22 +27,25 @@ class EEGConformer(EEGModuleMixin, nn.Module):
     EEG-Conformer is a *convolution-first* model augmented with a *lightweight transformer
     encoder*. The end-to-end flow is:
 
-    - (i) :class:`_PatchEmbedding` converts the continuous EEG into a compact sequence of tokens via a :class:`ShallowFBCSPNet` temporal–spatial conv stem and temporal pooling;
-    - (ii) :class:`_TransformerEncoder applies small multi-head self-attention to integrate longer-range temporal context across tokens;
+    - (i) :class:`_PatchEmbedding` converts the continuous EEG into a compact sequence of tokens via a
+      :class:`ShallowFBCSPNet` temporal–spatial conv stem and temporal pooling;
+    - (ii) :class:`_TransformerEncoder` applies small multi-head self-attention to integrate
+      longer-range temporal context across tokens;
     - (iii) :class:`_ClassificationHead` aggregates the sequence and performs a linear readout.
-        This preserves the strong inductive biases of shallow CNN filter banks while adding
-        just enough attention to capture dependencies beyond the pooling horizon [song2022]_.
+      This preserves the strong inductive biases of shallow CNN filter banks while adding
+      just enough attention to capture dependencies beyond the pooling horizon [song2022]_.
 
     .. rubric:: Macro Components
 
     - :class:`_PatchEmbedding` **(Shallow conv stem → tokens)**
 
-    - *Operations.*
-        - A temporal convolution (`:class:`torch.nn.Conv2d`) ``(1 x L_t)`` forms a data-driven "filter bank";
-        - A spatial convolution (`:class:`torch.nn.Conv2d`) (n_chans x 1)`` projects across electrodes, collapsing the channel axis into a virtual channel.
-        - **Normalization function** `:class:torch.nn.BatchNorm`
-        - **Activation function** `:class:torch.nn.ELU`
-        - **Average Pooling** `:class:torch.nn.AvgPool` along time (kernel ``(1, P)`` with stride ``(1, S)``)
+        - *Operations.*
+        - A temporal convolution (`:class:torch.nn.Conv2d`) ``(1 x L_t)`` forms a data-driven "filter bank";
+        - A spatial convolution (`:class:torch.nn.Conv2d`) (n_chans x 1)`` projects across electrodes,
+          collapsing the channel axis into a virtual channel.
+        - **Normalization function** :class:`torch.nn.BatchNorm`
+        - **Activation function** :class:`torch.nn.ELU`
+        - **Average Pooling** :class:`torch.nn.AvgPool` along time (kernel ``(1, P)`` with stride ``(1, S)``)
         -  final ``1x1`` :class:`torch.nn.Linear` projection.
 
     The result is rearranged to a token sequence ``(B, S_tokens, D)``, where ``D = n_filters_time``.
@@ -53,7 +56,7 @@ class EEGConformer(EEGModuleMixin, nn.Module):
 
     - :class:`_TransformerEncoder` **(context over temporal tokens)**
 
-    - *Operations.*
+        - *Operations.*
         - A stack of ``att_depth`` encoder blocks. :class:`_TransformerEncoderBlock`
         - Each block applies LayerNorm :class:`torch.nn.LayerNorm`
         - Multi-Head Self-Attention (``att_heads``) with dropout + residual :class:`MultiHeadAttention` (:class:`torch.nn.Dropout`)
@@ -67,7 +70,7 @@ class EEGConformer(EEGModuleMixin, nn.Module):
 
     - :class:`ClassificationHead` **(aggregation + readout)**
 
-    - *Operations*.
+        - *Operations*.
         - Flatten, :class:`torch.nn.Flatten` the sequence ``(B, S_tokens·D)`` -
         - MLP (:class:`torch.nn.Linear` → activation (default: :class:`torch.nn.ELU`) → :class:`torch.nn.Dropout` → :class:`torch.nn.Linear`)
         - final Linear to classes.

braindecode/models/eeginception_erp.py

@@ -15,12 +15,84 @@ from braindecode.modules import DepthwiseConv2d, Ensure4d, InceptionBlock
 class EEGInceptionERP(EEGModuleMixin, nn.Sequential):
     """EEG Inception for ERP-based from Santamaria-Vazquez et al (2020) [santamaria2020]_.
 
+    :bdg-success:`Convolution`
+
     .. figure:: https://braindecode.org/dev/_static/model/eeginceptionerp.jpg
         :align: center
         :alt: EEGInceptionERP Architecture
 
-    The code for the paper and this model is also available at [santamaria2020]_
-    and an adaptation for PyTorch [2]_.
+        Figure: Overview of EEG-Inception architecture. 2D convolution blocks and depthwise 2D convolution blocks include batch normalization, activation and dropout regularization. The kernel size is displayed for convolutional and average pooling layers.
+
+    .. rubric:: Architectural Overview
+
+    A two-stage, multi-scale CNN tailored to ERP detection from short (0-1000 ms) single-trial epochs. Signals are mapped through
+    * (i) :class:`_InceptionModule1` multi-scale temporal feature extraction plus per-branch spatial mixing;
+    * (ii) :class:`_InceptionModule2` deeper multi-scale refinement at a reduced temporal resolution; and
+    * (iii) :class:`_OutputModule` compact aggregation and linear readout.
+
+    .. rubric:: Macro Components
+
+    - :class:`_InceptionModule1` **(multi-scale temporal + spatial mixing)**
+
+        - *Operations.*
+        - `EEGInceptionERP.c1`: :class:`torch.nn.Conv2d` ``k=(64,1)``, stride ``(1,1)``, *same* pad on input reshaped to ``(B,1,128,8)`` → BN → activation → dropout.
+        - `EEGInceptionERP.d1`: :class:`torch.nn.Conv2d` (depthwise) ``k=(1,8)``, *valid* pad over channels → BN → activation → dropout.
+        - `EEGInceptionERP.c2`: :class:`torch.nn.Conv2d` ``k=(32,1)`` → BN → activation → dropout; then `EEGInceptionERP.d2` depthwise ``k=(1,8)`` → BN → activation → dropout.
+        - `EEGInceptionERP.c3`: :class:`torch.nn.Conv2d` ``k=(16,1)`` → BN → activation → dropout; then `EEGInceptionERP.d3` depthwise ``k=(1,8)`` → BN → activation → dropout.
+        - `EEGInceptionERP.n1`: :class:`torch.nn.Concat` over branch features.
+        - `EEGInceptionERP.a1`: :class:`torch.nn.AvgPool2d` ``pool=(4,1)``, stride ``(4,1)`` for temporal downsampling.
+
+    *Interpretability/robustness.* Depthwise `1 x n_chans` layers act as learnable montage-wide spatial filters per temporal scale; pooling stabilizes against jitter.
+
+    - :class:`_InceptionModule2` **(refinement at coarser timebase)**
+
+        - *Operations.*
+        - `EEGInceptionERP.c4`: :class:`torch.nn.Conv2d` ``k=(16,1)`` → BN → activation → dropout.
+        - `EEGInceptionERP.c5`: :class:`torch.nn.Conv2d` ``k=(8,1)`` → BN → activation → dropout.
+        - `EEGInceptionERP.c6`: :class:`torch.nn.Conv2d` ``k=(4,1)`` → BN → activation → dropout.
+        - `EEGInceptionERP.n2`: :class:`torch.nn.Concat` (merge C4-C6 outputs).
+        - `EEGInceptionERP.a2`: :class:`torch.nn.AvgPool2d` ``pool=(2,1)``, stride ``(2,1)``.
+        - `EEGInceptionERP.c7`: :class:`torch.nn.Conv2d` ``k=(8,1)`` → BN → activation → dropout; then `EEGInceptionERP.a3`: :class:`torch.nn.AvgPool2d` ``pool=(2,1)``.
+        - `EEGInceptionERP.c8`: :class:`torch.nn.Conv2d` ``k=(4,1)`` → BN → activation → dropout; then `EEGInceptionERP.a4`: :class:`torch.nn.AvgPool2d` ``pool=(2,1)``.
+
+    *Role.* Adds higher-level, shorter-window evidence while progressively compressing temporal dimension.
+
+    - :class:`_OutputModule` **(aggregation + readout)**
+
+        - *Operations.*
+        - :class:`torch.nn.Flatten`
+        - :class:`torch.nn.Linear` ``(features → 2)``
+
+    .. rubric:: Convolutional Details
+
+    - **Temporal (where time-domain patterns are learned).**
+    First module uses 1D temporal kernels along the 128-sample axis: ``64``, ``32``, ``16``
+    (≈500, 250, 125 ms at 128 Hz). After ``pool=(4,1)``, the second module applies ``16``,
+    ``8``, ``4`` (≈125, 62.5, 31.25 ms at the pooled rate). All strides are ``1`` in convs;
+    temporal resolution changes only via average pooling.
+
+    - **Spatial (how electrodes are processed).**
+    Depthwise convs with ``k=(1,8)`` span all channels and are applied **per temporal branch**,
+    yielding scale-specific channel projections (no cross-branch mixing until concatenation).
+    There is no full 2D mixing kernel; spatial mixing is factorized and lightweight.
+
+    - **Spectral (how frequency information is captured).**
+    No explicit transform; multiple temporal kernels form a *learned filter bank* over
+    ERP-relevant bands. Successive pooling acts as low-pass integration to emphasize sustained
+    post-stimulus components.
+
+    .. rubric:: Additional Mechanisms
+
+    - Every conv/depthwise block includes **BatchNorm**, nonlinearity (paper used grid-searched activation), and **dropout**.
+    - Two Inception stages followed by short convs and pooling keep parameters small (≈15k reported) while preserving multi-scale evidence.
+    - Expected input: epochs of shape ``(B,1,128,8)`` (time x channels as a 2D map) or reshaped from ``(B,8,128)`` with an added singleton feature dimension.
+
+    .. rubric:: Usage and Configuration
+
+    - **Key knobs.** Number of filters per branch; kernel lengths in both Inception modules; depthwise kernel over channels (typically ``n_chans``); pooling lengths/strides; dropout rate; choice of activation.
+    - **Training tips.** Use 0-1000 ms windows at 128 Hz with CAR; tune activation and dropout (they strongly affect performance); early-stop on validation loss when overfitting emerges.
+
+    .. rubric:: Implementation Details
 
     The model is strongly based on the original InceptionNet for an image. The main goal is
     to extract features in parallel with different scales. The authors extracted three scales
@@ -33,12 +105,9 @@ class EEGInceptionERP(EEGModuleMixin, nn.Sequential):
     The winners of BEETL Competition/NeurIps 2021 used parts of the
     model [beetl]_.
 
-    The model is fully described in [santamaria2020]_.
+    The code for the paper and this model is also available at [santamaria2020]_
+    and an adaptation for PyTorch [2]_.
 
-    Notes
-    -----
-    This implementation is not guaranteed to be correct, has not been checked
-    by original authors, only reimplemented from the paper based on [2]_.
 
     Parameters
     ----------

braindecode/models/eeginception_mi.py

@@ -13,6 +13,8 @@ from braindecode.modules import Ensure4d
 class EEGInceptionMI(EEGModuleMixin, nn.Module):
     """EEG Inception for Motor Imagery, as proposed in Zhang et al. (2021) [1]_
 
+    :bdg-success:`Convolution`
+
     .. figure:: https://content.cld.iop.org/journals/1741-2552/18/4/046014/revision3/jneabed81f1_hr.jpg
         :align: center
         :alt: EEGInceptionMI Architecture

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
@@ -19,23 +19,21 @@ from braindecode.modules import (
 )
 
 
-class EEGNetv4(EEGModuleMixin, nn.Sequential):
-    """EEGNet v4 model from Lawhern et al. (2018) [Lawhern2018]_.
-
-    :bdg-success:`Convolution` :bdg-secondary:`Depthwise–Separable`
+class EEGNet(EEGModuleMixin, nn.Sequential):
+    """EEGNet model from Lawhern et al. (2018) [Lawhern2018]_.
 
+    :bdg-success:`Convolution`
     .. figure:: https://content.cld.iop.org/journals/1741-2552/15/5/056013/revision2/jneaace8cf01_hr.jpg
        :align: center
-       :alt: EEGNetv4 Architecture
+       :alt: EEGNet Architecture
        :width: 600px
 
     .. rubric:: Architectural Overview
 
-    EEGNetv4 is a compact convolutional network designed for EEG decoding with a
-    pipeline that mirrors classical EEG processing:
+    EEGNet is a compact convolutional network designed for EEG decoding with a pipeline that mirrors classical EEG processing:
     - (i) learn temporal frequency-selective filters,
     - (ii) learn spatial filters for those frequencies, and
-    - (iii) condense features with depthwise–separable convolutions before a lightweight classifier.
+    - (iii) condense features with depthwise-separable convolutions before a lightweight classifier.
 
     The architecture is deliberately small (temporal convolutional and spatial patterns) [Lawhern2018]_.
 
@@ -46,9 +44,9 @@ class EEGNetv4(EEGModuleMixin, nn.Sequential):
     - **Depthwise Spatial Filtering.**
       Depthwise convolution spanning the channel dimension with ``groups = F1``,
       yielding ``D`` spatial filters for each temporal filter (no cross-filter mixing).
-    - **Norm–Nonlinearity–Pooling (+ dropout).**
+    - **Norm-Nonlinearity-Pooling (+ dropout).**
       Batch normalization → ELU → temporal pooling, with dropout.
-    - **Depthwise–Separable Convolution Block.**
+    - **Depthwise-Separable Convolution Block.**
       (a) depthwise temporal conv to refine temporal structure;
       (b) pointwise 1x1 conv to mix feature maps into ``F2`` combinations.
     - **Classifier Head.**
@@ -56,16 +54,16 @@ class EEGNetv4(EEGModuleMixin, nn.Sequential):
 
     .. rubric:: Convolutional Details
 
-    **Temporal.** The initial temporal convs serve as a *learned filter bank*:
-    long 1-D kernels (implemented as 2-D with singleton spatial extent) emphasize oscillatory bands and transients.
-    Because this stage is linear prior to BN/ELU, kernels can be analyzed as FIR filters to reveal each feature’s spectrum [Lawhern2018]_.
+    - **Temporal.** The initial temporal convs serve as a *learned filter bank*:
+      long 1-D kernels (implemented as 2-D with singleton spatial extent) emphasize oscillatory bands and transients.
+      Because this stage is linear prior to BN/ELU, kernels can be analyzed as FIR filters to reveal each feature’s spectrum [Lawhern2018]_.
 
-    **Spatial.** The depthwise spatial conv spans the full channel axis (kernel height = #electrodes; temporal size = 1).
-    With ``groups = F1``, each temporal filter learns its own set of ``D`` spatial projections—akin to CSP, learned end-to-end and
-    typically regularized with max-norm.
+    - **Spatial.** The depthwise spatial conv spans the full channel axis (kernel height = #electrodes; temporal size = 1).
+      With ``groups = F1``, each temporal filter learns its own set of ``D`` spatial projections—akin to CSP, learned end-to-end and
+      typically regularized with max-norm.
 
-    **Spectral.** No explicit Fourier/wavelet transform is used. Frequency structure
-    is captured implicitly by the temporal filter bank; later depthwise temporal kernels act as short-time integrators/refiners.
+    - **Spectral.** No explicit Fourier/wavelet transform is used. Frequency structure
+      is captured implicitly by the temporal filter bank; later depthwise temporal kernels act as short-time integrators/refiners.
 
     .. rubric:: Additional Comments
 
@@ -74,6 +72,8 @@ class EEGNetv4(EEGModuleMixin, nn.Sequential):
     - **Depthwise & separable convs:** Parameter-efficient decomposition (depthwise + pointwise) retains power while limiting overfitting
       [Chollet2017]_ and keeps temporal vs. mixing steps interpretable.
     - **Regularization:** Batch norm, dropout, pooling, and optional max-norm on spatial kernels aid stability on small EEG datasets.
+    - The v4 means the version 4 at the arxiv paper [Lawhern2018]_.
+
 
     Parameters
     ----------
@@ -349,174 +349,10 @@ class EEGNetv4(EEGModuleMixin, nn.Sequential):
         glorot_weight_zero_bias(self)
 
 
-class EEGNetv1(EEGModuleMixin, nn.Sequential):
-    """EEGNet model from Lawhern et al. 2016 from [EEGNet]_.
-
-    See details in [EEGNet]_.
-
-    Parameters
-    ----------
-    in_chans :
-        Alias for n_chans.
-    n_classes:
-        Alias for n_outputs.
-    input_window_samples :
-        Alias for n_times.
-    activation: nn.Module, default=nn.ELU
-        Activation function class to apply. Should be a PyTorch activation
-        module class like ``nn.ReLU`` or ``nn.ELU``. Default is ``nn.ELU``.
-
-    Notes
-    -----
-    This implementation is not guaranteed to be correct, has not been checked
-    by original authors, only reimplemented from the paper description.
-
-    References
-    ----------
-    .. [EEGNet] Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon,
-       S. M., Hung, C. P., & Lance, B. J. (2016).
-       EEGNet: A Compact Convolutional Network for EEG-based
-       Brain-Computer Interfaces.
-       arXiv preprint arXiv:1611.08024.
-    """
-
-    def __init__(
-        self,
-        n_chans=None,
-        n_outputs=None,
-        n_times=None,
-        final_conv_length="auto",
-        pool_mode="max",
-        second_kernel_size=(2, 32),
-        third_kernel_size=(8, 4),
-        drop_prob=0.25,
-        activation: nn.Module = nn.ELU,
-        chs_info=None,
-        input_window_seconds=None,
-        sfreq=None,
-    ):
-        super().__init__(
-            n_outputs=n_outputs,
-            n_chans=n_chans,
-            chs_info=chs_info,
-            n_times=n_times,
-            input_window_seconds=input_window_seconds,
-            sfreq=sfreq,
-        )
-        del n_outputs, n_chans, chs_info, n_times, input_window_seconds, sfreq
-        warn(
-            "The class EEGNetv1 is deprecated and will be removed in the "
-            "release 1.0 of braindecode. Please use "
-            "braindecode.models.EEGNetv4 instead in the future.",
-            DeprecationWarning,
-        )
-        if final_conv_length == "auto":
-            assert self.n_times is not None
-        self.final_conv_length = final_conv_length
-        self.pool_mode = pool_mode
-        self.second_kernel_size = second_kernel_size
-        self.third_kernel_size = third_kernel_size
-        self.drop_prob = drop_prob
-        # For the load_state_dict
-        # When padronize all layers,
-        # add the old's parameters here
-        self.mapping = {
-            "conv_classifier.weight": "final_layer.conv_classifier.weight",
-            "conv_classifier.bias": "final_layer.conv_classifier.bias",
-        }
-
-        pool_class = dict(max=nn.MaxPool2d, mean=nn.AvgPool2d)[self.pool_mode]
-        self.add_module("ensuredims", Ensure4d())
-        n_filters_1 = 16
-        self.add_module(
-            "conv_1",
-            nn.Conv2d(self.n_chans, n_filters_1, (1, 1), stride=1, bias=True),
-        )
-        self.add_module(
-            "bnorm_1",
-            nn.BatchNorm2d(n_filters_1, momentum=0.01, affine=True, eps=1e-3),
-        )
-        self.add_module("elu_1", activation())
-        # transpose to examples x 1 x (virtual, not EEG) channels x time
-        self.add_module("permute_1", Rearrange("batch x y z -> batch z x y"))
-
-        self.add_module("drop_1", nn.Dropout(p=self.drop_prob))
-
-        n_filters_2 = 4
-        # keras pads unequal padding more in front, so padding
-        # too large should be ok.
-        # Not padding in time so that cropped training makes sense
-        # https://stackoverflow.com/questions/43994604/padding-with-even-kernel-size-in-a-convolutional-layer-in-keras-theano
-
-        self.add_module(
-            "conv_2",
-            nn.Conv2d(
-                1,
-                n_filters_2,
-                self.second_kernel_size,
-                stride=1,
-                padding=(self.second_kernel_size[0] // 2, 0),
-                bias=True,
-            ),
-        )
-        self.add_module(
-            "bnorm_2",
-            nn.BatchNorm2d(n_filters_2, momentum=0.01, affine=True, eps=1e-3),
-        )
-        self.add_module("elu_2", activation())
-        self.add_module("pool_2", pool_class(kernel_size=(2, 4), stride=(2, 4)))
-        self.add_module("drop_2", nn.Dropout(p=self.drop_prob))
-
-        n_filters_3 = 4
-        self.add_module(
-            "conv_3",
-            nn.Conv2d(
-                n_filters_2,
-                n_filters_3,
-                self.third_kernel_size,
-                stride=1,
-                padding=(self.third_kernel_size[0] // 2, 0),
-                bias=True,
-            ),
-        )
-        self.add_module(
-            "bnorm_3",
-            nn.BatchNorm2d(n_filters_3, momentum=0.01, affine=True, eps=1e-3),
-        )
-        self.add_module("elu_3", activation())
-        self.add_module("pool_3", pool_class(kernel_size=(2, 4), stride=(2, 4)))
-        self.add_module("drop_3", nn.Dropout(p=self.drop_prob))
-
-        output_shape = self.get_output_shape()
-        n_out_virtual_chans = output_shape[2]
-
-        if self.final_conv_length == "auto":
-            n_out_time = output_shape[3]
-            self.final_conv_length = n_out_time
-
-        # Incorporating classification module and subsequent ones in one final layer
-        module = nn.Sequential()
-
-        module.add_module(
-            "conv_classifier",
-            nn.Conv2d(
-                n_filters_3,
-                self.n_outputs,
-                (n_out_virtual_chans, self.final_conv_length),
-                bias=True,
-            ),
-        )
-
-        # Transpose back to the logic of braindecode,
-
-        # so time in third dimension (axis=2)
-        module.add_module(
-            "permute_2",
-            Rearrange("batch x y z -> batch x z y"),
-        )
-
-        module.add_module("squeeze", SqueezeFinalOutput())
-
-        self.add_module("final_layer", module)
+@deprecated(
+    "`EEGNetv4` was renamed to `EEGNet` in v1.12; this alias will be removed in v1.14."
+)
+class EEGNetv4(EEGNet):
+    """Deprecated alias for EEGNet."""
 
-        glorot_weight_zero_bias(self)
+    pass