Metadata-Version: 2.4
Name: viscy-transforms
Version: 0.1.0a0
Summary: Image transforms for virtual staining microscopy
Project-URL: Homepage, https://github.com/mehta-lab/VisCy
Project-URL: Issues, https://github.com/mehta-lab/VisCy/issues
Project-URL: Repository, https://github.com/mehta-lab/VisCy
Author-email: Biohub <compmicro@czbiohub.org>
License-Expression: BSD-3-Clause
Keywords: deep learning,image transforms,microscopy,pytorch,virtual staining
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: BSD License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Processing
Requires-Python: >=3.12
Requires-Dist: kornia>=0.8.2
Requires-Dist: monai>=1.5.2
Requires-Dist: numpy>=2.4.1
Requires-Dist: torch>=2.10
Provides-Extra: notebook
Requires-Dist: cmap>=0.7; extra == 'notebook'
Requires-Dist: jupyterlab>=4.5.3; extra == 'notebook'
Requires-Dist: matplotlib>=3.10.8; extra == 'notebook'
Requires-Dist: pooch>=1.9; extra == 'notebook'
Requires-Dist: scikit-image>=0.26; extra == 'notebook'
Description-Content-Type: text/markdown

# viscy-transforms

Image transforms for virtual staining microscopy.

Part of the [VisCy](https://github.com/mehta-lab/VisCy) project.

## Installation

### From PyPI (when published)

```bash
pip install viscy-transforms
```

### For development (from monorepo root)

```bash
# Using uv (recommended)
uv pip install -e packages/viscy-transforms

# Or via workspace sync
uv sync --package viscy-transforms
```

## Usage

```python
from viscy_transforms import NormalizeSampled, BatchedRandAffined

# Transforms follow MONAI dictionary transform pattern
# See documentation for full API reference
```

## Features

- PyTorch-based image transforms optimized for microscopy data
- MONAI Dictionary transform compatibility for DataLoader pipelines
- Kornia-accelerated augmentations (affine, noise, blur)
- Specialized transforms for virtual staining workflows

## Examples

To run the example notebook, install with the `notebook` extra:

```bash
pip install viscy-transforms[notebook]
```

See the [batched transforms benchmark notebook](docs/examples/batched_transforms.ipynb) for a comparison of batched GPU transforms vs standard MONAI transforms.

## Dependencies

- `torch>=2.4.1`
- `kornia`
- `monai>=1.4`
- `numpy`

## Documentation

In the works!

## License

BSD-3-Clause - see [LICENSE](../../LICENSE) in repository root.
