Metadata-Version: 2.4
Name: linkinpy-stardist
Version: 0.0.1
Summary: LinkinPy-compatible high-level StarDist training and inference workflows.
Author-email: "Bruno M. Saraiva" <bruno.msaraiva2@gmail.com>
License-Expression: MIT
Requires-Python: >=3.10
Requires-Dist: llvmlite>=0.42
Requires-Dist: numba>=0.59
Requires-Dist: numpy>=1.26
Requires-Dist: stardist>=0.9.2
Requires-Dist: tensorboard>=2.15
Requires-Dist: tensorflow>=2.15
Requires-Dist: tifffile>=2024.8.10
Description-Content-Type: text/markdown

# LinkinPy-StarDist

LinkinPy-compatible Python package for StarDist 2D workflows.

It provides three high-level functions:

- `train_2d_with_qc`: train a custom StarDist 2D model with optional augmentation and quality control
- `predict_2d_custom_model`: run inference with a trained model directory
- `predict_2d_pretrained_model`: run inference with a StarDist pretrained model

Training expects paired raw images and instance-label masks. File names are matched by stem, so `images/cell01.tif` pairs with `masks/cell01.tif`.

When quality control is enabled, the data is split into train, validation, and test sets. The held-out test split is used only for QC metrics after training.
