---
license: openrail
library_name: openmhc
tags:
- openmhc
- wearables
- time-series
- imputation
---

# OpenMHC DLinear

Reference checkpoint for [OpenMHC](https://github.com/AshleyLab/myheartcounts-dataset).
Window: daily (1440 minute), 19 sensor channels.

Wrapper around a [PyPOTS](https://github.com/WenjieDu/PyPOTS)-backed imputer trained on the OpenMHC imputation training split. Reconstructs masked sensor windows across 19 channels.

## Usage

```python
from openmhc.imputers import DLinearImputer
import openmhc

imp = DLinearImputer.from_release("hf://MyHeartCounts/openmhc-dlinear-imp")
results = openmhc.evaluate_imputation(imp, version="xs")
print(results.summary())
```

Requires the matching optional extras: `pip install 'openmhc[pypots,hf]'`.

Pin a specific revision with the `@` suffix:

```python
DLinearImputer.from_release("hf://MyHeartCounts/openmhc-dlinear-imp@v1.0")
```

## Provenance

- Origin: W&B artifact `MHC_Dataset/mhc-pypots-dlinear/dlinear:v49`
- Validation: **val MAE 0.1335 (epoch 2)**
- Architecture hyperparameters are pinned in `openmhc_manifest.json`.

## License

Released under the OpenRAIL license. See the OpenMHC repository for use
restrictions tied to the underlying data agreement.

## Citation

```bibtex
@misc{openmhc,
  title  = {OpenMHC: Accelerating the Science of Wearable Foundation Models},
  author = {OpenMHC team},
  url    = {https://github.com/AshleyLab/myheartcounts-dataset}
}
```