|
Download README.md from Jay1208/SAMBA: direct link, hf CLI and curl.
- Browser
- Download file 3.43 kB
-
https://huggingface.co/Jay1208/SAMBA/resolve/main/README.md
- Command line
-
hf download hf://Jay1208/SAMBA/README.md
-
curl -L -o README.md https://huggingface.co/Jay1208/SAMBA/resolve/main/README.md
3.43 kB
| library_name: samba-eeg | |
| pipeline_tag: feature-extraction | |
| tags: | |
| - eeg | |
| - brain-computer-interface | |
| - self-supervised-learning | |
| - mamba | |
| - pytorch | |
| # SAMBA | |
| EEG representation models. [Project website](https://samba.dcode.ai/) · [Code](https://github.com/Jiazhen-Hong/SAMBA) · [Paper](https://arxiv.org/abs/2511.18571) | |
| SAMBA was developed during my 2025 internship at Emotiv. The original checkpoints are no longer available, so we retrained both models. SAMBA-100s follows the original training method with a rebuilt TUAB pipeline and validation split. SAMBA-2s adds HBN, Muse, and DICE to the Emotiv data for greater electrode-layout diversity. | |
| ## Checkpoints | |
| Both models use 128 Hz EEG. The names indicate the pretraining window; the encoders support other input lengths and channel layouts. | |
| | | [SAMBA-2s](SAMBA-2s) | [SAMBA-100s](SAMBA-100s) | | |
| |---|---|---| | |
| | Window | 2 s, 256 samples | 100 s, 12,800 samples | | |
| | Data | Emotiv¹, HBN, Muse, DICE | TUAB | | |
| | Pretraining channels | 4, 14, 19, 129 | 16 bipolar | | |
| | Parameters | 1.06M | 1.06M | | |
| ¹ Alpha, Attention, Crowdsource, DriverDistraction, and STEW. | |
| ## Learned EEG spatial weights | |
| SAMBA uses electrode coordinates to learn how to combine EEG channels. These maps show how the spatial weights change during training. | |
| | Eyes open vs. closed | Driver distraction | Motor imagery | | |
| |:---:|:---:|:---:| | |
| | <img src="https://raw.githubusercontent.com/Jiazhen-Hong/SAMBA/main/Figures/Topo_gif/EyesState_GIF.gif" width="250" alt="Eyes open vs. closed"> | <img src="https://raw.githubusercontent.com/Jiazhen-Hong/SAMBA/main/Figures/Topo_gif/DriverDistraction_GIF.gif" width="250" alt="Driver distraction"> | <img src="https://raw.githubusercontent.com/Jiazhen-Hong/SAMBA/main/Figures/Topo_gif/MI_GIF.gif" width="250" alt="Motor imagery"> | | |
| ## Usage | |
| Requires a compatible CUDA system. | |
| ```bash | |
| git clone https://github.com/Jiazhen-Hong/SAMBA.git | |
| cd SAMBA | |
| pip install -e '.[mamba,hub]' | |
| ``` | |
| ```python | |
| from pathlib import Path | |
| import torch | |
| from huggingface_hub import snapshot_download | |
| from samba_eeg import SambaModel | |
| variant = "SAMBA-2s" # or "SAMBA-100s" | |
| folder = snapshot_download( | |
| "Jay1208/SAMBA", | |
| allow_patterns=[f"{variant}/*"], | |
| ) | |
| model = SambaModel.from_pretrained(Path(folder) / variant).cuda().eval() | |
| ``` | |
| Prepare EEG at 128 Hz: | |
| - `signals`: `[batch, channels, samples]`. | |
| - `positions`: `[channels, 3]` or `[batch, channels, 3]`, matching the channel order and the coordinate units and frame in `config.json`. | |
| - Normalize each channel in each window by its absolute 95th percentile. TUAB pretraining uses a 0.5–45 Hz bandpass. | |
| ```python | |
| signals = signals.to(device="cuda", dtype=torch.float32) | |
| positions = positions.to(device="cuda", dtype=torch.float32) | |
| # Skip if already normalized. | |
| scale = torch.quantile(signals.abs(), 0.95, dim=-1, keepdim=True) | |
| signals = signals / scale.clamp_min(1e-8) | |
| with torch.inference_mode(): | |
| features = model.encode(signals, positions) | |
| pooled_features = features.mean(dim=1) | |
| ``` | |
| `features` has shape `[batch, floor(samples / 8), 128]`. Use the pooled features for linear probing, or fine-tune the encoder. | |
| ## Citation | |
| ```bibtex | |
| @article{hong2026samba, | |
| title={SAMBA: Toward an EEG Foundation Model via Differential Mamba and Coordinate-Driven Spatial Embedding}, | |
| author={Hong, Jiazhen and Mackellar, Geoffrey and Ghane, Soheila}, | |
| journal={arXiv preprint arXiv:2511.18571}, | |
| year={2026} | |
| } | |
| ``` |