Metadata-Version: 2.4
Name: quantem-core
Version: 0.1.0
Summary: Inference and lightweight adaptation for the QuantEM and OmniEM electron-microscopy organelle segmentation models
Author: Arrojo e Drigo Lab, Vanderbilt University
License-Expression: BSD-3-Clause
Keywords: electron microscopy,segmentation,vision transformer,organelle
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Classifier: Operating System :: OS Independent
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=2.2
Requires-Dist: timm>=1.0.20
Requires-Dist: numpy>=1.24
Requires-Dist: scipy>=1.10
Requires-Dist: scikit-image>=0.22
Requires-Dist: safetensors>=0.4
Requires-Dist: huggingface-hub>=0.24
Provides-Extra: test
Requires-Dist: pytest>=7; extra == "test"
Requires-Dist: pytest-cov; extra == "test"
Provides-Extra: dev
Requires-Dist: ruff>=0.6; extra == "dev"
Dynamic: license-file

# quantem-core

Inference and lightweight adaptation for the QuantEM and OmniEM electron-microscopy organelle
segmentation models. This is the core engine under
both [`napari-quantem`](../napari-quantem). 

Contains eight released models — {mitochondria, endoplasmic reticulum, nucleus, lipid droplets} ×
{QuantEM ViT-B, OmniEM ViT-L} — with the inference procedure: resample to the model's training resolution, EM-corpus normalisation, 512 px sliding
windows at 25 % overlap with Hann blending, threshold, connected components.

## Development

```bash
pip install -e ".[test]"
pytest
```

Tests that need the original pretraining checkpoint skip unless `QUANTEM_REF_CKPT` points at it.

## Licence

BSD-3-Clause — see [`LICENSE`](LICENSE).
