| --- |
| library_name: braindecode |
| license: other |
| license_name: usc-academic-non-commercial |
| license_link: https://github.com/ShanechiLab/BaRISTA/blob/83b27375eba60e9eba9da4e7dd8fb283baace376/LICENSE.md |
| pipeline_tag: feature-extraction |
| tags: |
| - braindecode |
| - BaRISTA |
| - ieeg |
| - seeg |
| - foundation-model |
| - pytorch_model_hub_mixin |
| --- |
| |
| # BaRISTA, parcels scale |
|
|
| The released BaRISTA encoder of [Oganesian, Hashemi and Shanechi |
| (2025)](https://arxiv.org/abs/2512.12135) for the **parcels** spatial scale, |
| converted to |
| [`braindecode.models.BaRISTA`](https://braindecode.org/stable/generated/braindecode.models.BaRISTA.html). |
|
|
| Source: `pretrained_models/parcels_chans.ckpt` at revision |
| [`83b27375eba60e9eba9da4e7dd8fb283baace376`](https://github.com/ShanechiLab/BaRISTA/tree/83b27375eba60e9eba9da4e7dd8fb283baace376), |
| sha256 `6c234517d286a8e710b09716dc88c713618670df523cfffb89e4c9073f2657c1`. Conversion renames tensors and fuses the released gated |
| projections into the single projection this port uses; `convert_barista_weights.py` |
| in this repository reproduces it. Encoder tokens match the released forward |
| equations to 3.6e-06 in float32 on CPU. |
|
|
| ## Usage |
|
|
| Supply the montage of each batch as `spatial_indices`, an ``(n_chans,)`` tensor of Destrieux parcels in ``[0, 121)``: |
|
|
| ```python |
| import torch |
| from braindecode.models import BaRISTA |
| |
| model = BaRISTA.from_pretrained("braindecode/BaRISTA-parcels", n_chans=64, n_outputs=2) |
| logits = model(torch.randn(8, 64, 6144), spatial_indices=torch.randint(0, 121, (64,))) |
| ``` |
|
|
| The saved geometry is 64 channels and 6144 samples at 2048 Hz, the |
| pretraining window. Mean pooling makes the encoder independent of both, so pass |
| your own `n_chans`, `n_times` and `n_outputs` when loading. |
|
|
| ## Limitations |
|
|
| These files hold the encoder only, as does the release. Braindecode |
| initializes the classification head on load, so it needs fine-tuning, as does |
| the learned read-out of the paper's protocol (`pooling="learned"`), which was |
| never released. The check |
| above covers float32 CPU encoder tokens, not downstream accuracy, GPU kernels or |
| mixed precision. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @inproceedings{oganesian2025barista, |
| title={BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity}, |
| author={Oganesian, Lucine L. and Hashemi, Saba and Shanechi, Maryam M.}, |
| booktitle={Advances in Neural Information Processing Systems}, |
| year={2025} |
| } |
| ``` |
|
|
| ## License |
|
|
| Copyright (c) 2025 University of Southern California. Educational, research and |
| non-profit use only; commercial use requires an agreement with the USC Stevens |
| Center for Innovation. See `NOTICE.txt` and the [original licence](https://github.com/ShanechiLab/BaRISTA/blob/83b27375eba60e9eba9da4e7dd8fb283baace376/LICENSE.md). |
|
|
