Image transforms for virtual staining microscopy.
Part of the VisCy project.
pip install viscy-transforms# Using uv (recommended)
uv pip install -e packages/viscy-transforms
# Or via workspace sync
uv sync --package viscy-transformsfrom viscy_transforms import NormalizeSampled, BatchedRandAffined
# Transforms follow MONAI dictionary transform pattern
# See documentation for full API reference- 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
To run the example notebook, install with the notebook extra:
pip install viscy-transforms[notebook]See the batched transforms benchmark notebook for a comparison of batched GPU transforms vs standard MONAI transforms.
torch>=2.4.1korniamonai>=1.4numpy
In the works!
BSD-3-Clause - see LICENSE in repository root.