Metadata-Version: 2.4
Name: neuroencoder
Version: 1.0.0
Summary: EEG model embeddings - distilled EPI-250k
Author-email: Neuroencoder <contact@neuroencoder.com>
License: Apache-2.0
Project-URL: Homepage, https://neuroencoder.com
Project-URL: Documentation, https://docs.neuroencoder.com
Project-URL: Repository, https://github.com/avocardio/neuroencoder
Project-URL: HuggingFace, https://huggingface.co/Neuroencoder/epi-embedding
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Healthcare Industry
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: torch>=2.1
Requires-Dist: numpy
Requires-Dist: scipy
Requires-Dist: timm
Requires-Dist: huggingface_hub>=0.24
Requires-Dist: pandas
Requires-Dist: scikit-learn
Requires-Dist: umap-learn
Requires-Dist: matplotlib
Requires-Dist: embedding-atlas>=0.13
Requires-Dist: anywidget
Requires-Dist: mne>=1.5
Provides-Extra: dev
Requires-Dist: pytest>=7; extra == "dev"
Requires-Dist: pytest-cov; extra == "dev"

# neuroencoder

EEG foundation model embeddings for Python.

```bash
pip install neuroencoder
```

```python
import neuroencoder as ne
from neuroencoder import MRL

images = ne.preprocess(eeg, sfreq=256, channel_names=ch_names)

model = MRL.from_pretrained()
embeddings = model.predict(images, dim=192)

ne.explore(embeddings)   # interactive Apple Embedding Atlas
ne.plot(embeddings)      # static matplotlib UMAP
```

## Model access

The MRL model is gated on HuggingFace. [Request access](https://huggingface.co/Neuroencoder/epi-embedding), then authenticate once:

```bash
huggingface-cli login
```

or export `HF_TOKEN=hf_...` before running.

## Documentation

Full docs at [docs.neuroencoder.com](https://docs.neuroencoder.com).

- [Introduction](https://docs.neuroencoder.com/introduction) — what this is
- [Quickstart](https://docs.neuroencoder.com/quickstart) — your first embedding
- [Embeddings](https://docs.neuroencoder.com/embeddings) — the MRL model end-to-end
- [Visualization](https://docs.neuroencoder.com/visualization) — Apple Embedding Atlas
- [Benchmarks](https://docs.neuroencoder.com/benchmarks) — performance on 20 clinical EEG tasks
- [API reference](https://docs.neuroencoder.com/api)

## Links

- Source: [github.com/avocardio/neuroencoder](https://github.com/avocardio/neuroencoder)
- Model weights: [huggingface.co/Neuroencoder/epi-embedding](https://huggingface.co/Neuroencoder/epi-embedding)
- Website: [neuroencoder.com](https://neuroencoder.com)
