Add architecture-only model card

README.md

@@ -0,0 +1,269 @@
+---
+license: bsd-3-clause
+library_name: braindecode
+pipeline_tag: feature-extraction
+tags:
+  - eeg
+  - biosignal
+  - pytorch
+  - neuroscience
+  - braindecode
+  - convolutional
+  - transformer
+---
+
+# SCCNet
+
+SCCNet from Wei, C S (2019) .
+
+> **Architecture-only repository.** This repo documents the
+> `braindecode.models.SCCNet` class. **No pretrained weights are
+> distributed here** — instantiate the model and train it on your own
+> data, or fine-tune from a published foundation-model checkpoint
+> separately.
+
+## Quick start
+
+```bash
+pip install braindecode
+```
+
+```python
+from braindecode.models import SCCNet
+
+model = SCCNet(
+    n_chans=22,
+    sfreq=250,
+    input_window_seconds=4.0,
+    n_outputs=4,
+)
+```
+
+The signal-shape arguments above are example defaults — adjust them
+to match your recording.
+
+## Documentation
+
+- Full API reference (parameters, references, architecture figure):
+  <https://braindecode.org/stable/generated/braindecode.models.SCCNet.html>
+- Interactive browser with live instantiation:
+  <https://huggingface.co/spaces/braindecode/model-explorer>
+- Source on GitHub: <https://github.com/braindecode/braindecode/blob/master/braindecode/models/sccnet.py#L17>
+
+## Architecture description
+
+The block below is the rendered class docstring (parameters,
+references, architecture figure where available).
+
+<div class='bd-doc'><main>
+<p>SCCNet from Wei, C S (2019) [sccnet]_.</p>
+<span style="display:inline-block;padding:2px 8px;border-radius:4px;background:#5cb85c;color:white;font-size:11px;font-weight:600;margin-right:4px;">Convolution</span>
+
+
+
+ Spatial component-wise convolutional network (SCCNet) for motor-imagery EEG
+ classification.
+
+ .. figure:: https://dt5vp8kor0orz.cloudfront.net/6e3ec5d729cd51fe8acc5a978db27d02a5df9e05/2-Figure1-1.png
+    :align: center
+    :alt:  Spatial component-wise convolutional network
+    :width: 680px
+
+ .. rubric:: Architectural Overview
+
+ SCCNet is a spatial-first convolutional layer that fixes temporal kernels in seconds
+ to make its filters correspond to neurophysiologically aligned windows. The model
+ comprises four stages:
+
+ 1. **Spatial Component Analysis**: Performs convolution spatial filtering
+     across all EEG channels to extract spatial components, effectively
+     reducing the channel dimension.
+ 2. **Spatio-Temporal Filtering**: Applies convolution across the spatial
+     components and temporal domain to capture spatio-temporal patterns.
+ 3. **Temporal Smoothing (Pooling)**: Uses average pooling over time to smooth the
+    features and reduce the temporal dimension, focusing on longer-term patterns.
+ 4. **Classification**: Flattens the features and applies a fully connected
+    layer.
+
+ .. rubric:: Macro Components
+
+ - `SCCNet.spatial_conv` **(spatial component analysis)**
+
+     - *Operations.*
+     - :class:`~torch.nn.Conv2d` with kernel `(n_chans, N_t)` and stride `(1, 1)` on an input reshaped to `(B, 1, n_chans, T)`; typical choice `N_t=1` yields a pure across-channel projection (montage-wide linear spatial filter).
+     - Zero padding to preserve time, :class:`~torch.nn.BatchNorm2d`; output has `N_u` component signals shaped `(B, 1, N_u, T)` after a permute step.
+
+ *Interpretability/robustness.* Mimics CSP-like spatial filtering: each learned filter is a channel-weighted component, easing inspection and reducing channel noise.
+
+ - `SCCNet.spatial_filt_conv` **(spatio-temporal filtering)**
+
+     - *Operations.*
+     - :class:`~torch.nn.Conv2d` with kernel `(N_u, 12)` over components and time (12 samples ~ 0.1 s at 125 Hz),
+     - :class:`~torch.nn.BatchNorm2d`;
+     - Nonlinearity is **power-like**: the original paper uses **square** like :class:`~braindecode.models.ShallowFBCSPNet` with the class :class:`~braindecode.modules.LogActivation` as default.
+     - :class:`~torch.nn.Dropout` with rate `p=0.5`.
+
+ - *Role.* Learns frequency-selective energy features and inter-component interactions within a 0.1 s context (beta/alpha cycle scale).
+
+ - `SCCNet.temporal_smoothing` **(aggregation + readout)**
+
+     - *Operations.*
+     - :class:`~torch.nn.AvgPool2d` with size `(1, 62)` (~ 0.5 s) for temporal smoothing and downsampling
+     - :class:`~torch.nn.Flatten`
+     - :class:`~torch.nn.Linear` to `n_outputs`.
+
+
+ .. rubric:: Convolutional Details
+
+ * **Temporal (where time-domain patterns are learned).**
+     The second block's kernel length is fixed to 12 samples (≈ 100 ms) and slides with
+     stride 1; average pooling `(1, 62)` (≈ 500 ms) integrates power over longer spans.
+     These choices bake in short-cycle detection followed by half-second trend smoothing.
+
+ * **Spatial (how electrodes are processed).**
+     The first block's kernel spans **all electrodes** `(n_chans, N_t)`. With `N_t=1`,
+     it reduces to a montage-wide linear projection, mapping channels → `N_u` components.
+     The second block mixes **across components** via kernel height `N_u`.
+
+ * **Spectral (how frequency information is captured).**
+     No explicit transform is used; learned **temporal kernels** serve as bandpass-like
+     filters, and the **square/log power** nonlinearity plus 0.5 s averaging approximate
+     band-power estimation (ERD/ERS-style features).
+
+ .. rubric:: Attention / Sequential Modules
+
+ This model contains **no attention** and **no recurrent units**.
+
+ .. rubric:: Additional Mechanisms
+
+ - :class:`~torch.nn.BatchNorm2d` and zero-padding are applied to both convolutions;
+   L2 weight decay was used in the original paper; dropout `p=0.5` combats overfitting.
+ - Contrasting with other compact neural network, in EEGNet performs a temporal depthwise conv
+   followed by a **depthwise spatial** conv (separable), learning temporal filters first.
+   SCCNet inverts this order: it performs a **full spatial projection first** (CSP-like),
+   then a short **spatio-temporal** conv with an explicit 0.1 s kernel, followed by
+   **power-like** nonlinearity and longer temporal averaging. EEGNet's ELU and
+   separable design favor parameter efficiency; SCCNet's second-scale kernels and
+   square/log emphasize interpretable **band-power** features.
+
+ - Reference implementation: see [sccnetcode]_.
+
+ .. rubric:: Usage and Configuration
+
+ * **Training from the original authors.**
+
+ * Match window length so that `T` is comfortably larger than pooling length
+     (e.g., > 1.5-2 s for MI).
+ * Start with standard MI augmentations (channel dropout/shuffle, time reverse)
+     and tune `n_spatial_filters` before deeper changes.
+
+ Parameters
+ ----------
+ n_spatial_filters : int, optional
+     Number of spatial filters in the first convolutional layer, variable `N_u` from the
+     original paper. Default is 22.
+ n_spatial_filters_smooth : int, optional
+     Number of spatial filters used as filter in the second convolutional
+     layer. Default is 20.
+ drop_prob : float, optional
+     Dropout probability. Default is 0.5.
+ activation : nn.Module, optional
+     Activation function after the second convolutional layer. Default is
+     logarithm activation.
+
+ References
+ ----------
+ .. [sccnet] Wei, C. S., Koike-Akino, T., & Wang, Y. (2019, March). Spatial
+     component-wise convolutional network (SCCNet) for motor-imagery EEG
+     classification. In 2019 9th International IEEE/EMBS Conference on
+     Neural Engineering (NER) (pp. 328-331). IEEE.
+ .. [sccnetcode] Hsieh, C. Y., Chou, J. L., Chang, Y. H., & Wei, C. S.
+     XBrainLab: An Open-Source Software for Explainable Artificial
+     Intelligence-Based EEG Analysis. In NeurIPS 2023 AI for
+     Science Workshop.
+
+ .. rubric:: Hugging Face Hub integration
+
+ When the optional ``huggingface_hub`` package is installed, all models
+ automatically gain the ability to be pushed to and loaded from the
+ Hugging Face Hub. Install with::
+
+     pip install braindecode[hub]
+
+ **Pushing a model to the Hub:**
+
+ .. code::
+     from braindecode.models import SCCNet
+
+     # Train your model
+     model = SCCNet(n_chans=22, n_outputs=4, n_times=1000)
+     # ... training code ...
+
+     # Push to the Hub
+     model.push_to_hub(
+         repo_id="username/my-sccnet-model",
+         commit_message="Initial model upload",
+     )
+
+ **Loading a model from the Hub:**
+
+ .. code::
+     from braindecode.models import SCCNet
+
+     # Load pretrained model
+     model = SCCNet.from_pretrained("username/my-sccnet-model")
+
+     # Load with a different number of outputs (head is rebuilt automatically)
+     model = SCCNet.from_pretrained("username/my-sccnet-model", n_outputs=4)
+
+ **Extracting features and replacing the head:**
+
+ .. code::
+     import torch
+
+     x = torch.randn(1, model.n_chans, model.n_times)
+     # Extract encoder features (consistent dict across all models)
+     out = model(x, return_features=True)
+     features = out["features"]
+
+     # Replace the classification head
+     model.reset_head(n_outputs=10)
+
+ **Saving and restoring full configuration:**
+
+ .. code::
+     import json
+
+     config = model.get_config()            # all __init__ params
+     with open("config.json", "w") as f:
+         json.dump(config, f)
+
+     model2 = SCCNet.from_config(config)    # reconstruct (no weights)
+
+ All model parameters (both EEG-specific and model-specific such as
+ dropout rates, activation functions, number of filters) are automatically
+ saved to the Hub and restored when loading.
+
+ See :ref:`load-pretrained-models` for a complete tutorial.</main>
+</div>
+
+## Citation
+
+Please cite both the original paper for this architecture (see the
+*References* section above) and braindecode:
+
+```bibtex
+@article{aristimunha2025braindecode,
+  title   = {Braindecode: a deep learning library for raw electrophysiological data},
+  author  = {Aristimunha, Bruno and others},
+  journal = {Zenodo},
+  year    = {2025},
+  doi     = {10.5281/zenodo.17699192},
+}
+```
+
+## License
+
+BSD-3-Clause for the model code (matching braindecode).
+Pretraining-derived weights, if you fine-tune from a checkpoint,
+inherit the licence of that checkpoint and its training corpus.