Add architecture-only model card

README.md

@@ -0,0 +1,243 @@
+---
+license: bsd-3-clause
+library_name: braindecode
+pipeline_tag: feature-extraction
+tags:
+  - eeg
+  - biosignal
+  - pytorch
+  - neuroscience
+  - braindecode
+  - foundation-model
+  - transformer
+  - sleep-staging
+---
+
+# InterpolatedBIOT
+
+Channel-interpolating wrapper around :class:`BIOT`.
+
+> **Architecture-only repository.** This repo documents the
+> `braindecode.models.InterpolatedBIOT` 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 InterpolatedBIOT
+
+model = InterpolatedBIOT(
+    n_chans=16,
+    sfreq=200,
+    input_window_seconds=10.0,
+    n_outputs=2,
+)
+```
+
+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.InterpolatedBIOT.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/interpolated.py#L1>
+
+## Architecture description
+
+The block below is the rendered class docstring (parameters,
+references, architecture figure where available).
+
+<div class='bd-doc'><main>
+<p>Channel-interpolating wrapper around :class:`BIOT`.</p>
+<p>:bdg-dark-line:`Channel`</p>
+<p>Accepts arbitrary user <span class="docutils literal">chs_info</span> and projects them to the
+backbone's canonical channel set via
+:class:`~braindecode.modules.ChannelInterpolationLayer`.</p>
+<p>For all other parameters and behavior see the backbone
+documentation reproduced below.</p>
+<p>BIOT from Yang et al (2023) [Yang2023]_</p>
+<span style="display:inline-block;padding:2px 8px;border-radius:4px;background:#d9534f;color:white;font-size:11px;font-weight:600;margin-right:4px;">Foundation Model</span>
+
+
+
+ .. figure:: https://braindecode.org/dev/_static/model/biot.jpg
+    :align: center
+    :alt: BioT
+
+ BIOT: Cross-data Biosignal Learning in the Wild.
+
+ 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.
+ The method was proposed by Yang et al. [Yang2023]_ and the code is
+ available at [Code2023]_
+
+ The model is trained with a contrastive loss on large EEG datasets
+ TUH Abnormal EEG Corpus with 400K samples and Sleep Heart Health Study
+ 5M. Here, we only provide the model architecture, not the pre-trained
+ weights or contrastive loss training.
+
+ The architecture is based on the `LinearAttentionTransformer` and
+ `PatchFrequencyEmbedding` modules.
+ The `BIOTEncoder` is a transformer that takes the input data and outputs
+ a fixed-size representation of the input data. More details are
+ present in the `BIOTEncoder` class.
+
+ The `ClassificationHead` is an ELU activation layer, followed by a simple
+ linear layer that takes the output of the `BIOTEncoder` and outputs
+ the classification probabilities.
+
+ .. important::
+    **Pre-trained Weights Available**
+
+    This model has pre-trained weights available on the Hugging Face Hub.
+    You can load them using:
+
+    .. code:: python
+        from braindecode.models import BIOT
+
+        # Load the original pre-trained model from Hugging Face Hub
+        # For 16-channel models:
+        model = BIOT.from_pretrained("braindecode/biot-pretrained-prest-16chs")
+
+        # For 18-channel models:
+        model = BIOT.from_pretrained("braindecode/biot-pretrained-shhs-prest-18chs")
+        model = BIOT.from_pretrained("braindecode/biot-pretrained-six-datasets-18chs")
+
+    To push your own trained model to the Hub:
+
+    .. code:: python
+        # After training your model
+        model.push_to_hub(
+            repo_id="username/my-biot-model", commit_message="Upload trained BIOT model"
+        )
+
+    Requires installing ``braindecode[hug]`` for Hub integration.
+
+ .. versionadded:: 0.9
+
+ Parameters
+ ----------
+ embed_dim : int, optional
+     The size of the embedding layer, by default 256
+ num_heads : int, optional
+     The number of attention heads, by default 8
+ num_layers : int, optional
+     The number of transformer layers, by default 4
+ 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``.
+ return_feature: bool, optional
+     Changing the output for the neural network. Default is single tensor
+     when return_feature is True, return embedding space too.
+     Default is False.
+ hop_length: int, optional
+     The hop length for the torch.stft transformation in the
+     encoder. The default is 100.
+ sfreq: int, optional
+     The sfreq parameter for the encoder. The default is 200
+
+ References
+ ----------
+ .. [Yang2023] Yang, C., Westover, M.B. and Sun, J., 2023, November. BIOT:
+    Biosignal Transformer for Cross-data Learning in the Wild. In Thirty-seventh
+    Conference on Neural Information Processing Systems, NeurIPS.
+ .. [Code2023] Yang, C., Westover, M.B. and Sun, J., 2023. BIOT
+    Biosignal Transformer for Cross-data Learning in the Wild.
+    GitHub https://github.com/ycq091044/BIOT (accessed 2024-02-13)
+
+ .. 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 BIOT
+
+     # Train your model
+     model = BIOT(n_chans=22, n_outputs=4, n_times=1000)
+     # ... training code ...
+
+     # Push to the Hub
+     model.push_to_hub(
+         repo_id="username/my-biot-model",
+         commit_message="Initial model upload",
+     )
+
+ **Loading a model from the Hub:**
+
+ .. code::
+     from braindecode.models import BIOT
+
+     # Load pretrained model
+     model = BIOT.from_pretrained("username/my-biot-model")
+
+     # Load with a different number of outputs (head is rebuilt automatically)
+     model = BIOT.from_pretrained("username/my-biot-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 = BIOT.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.