Viscy

> [!WARNING]
> This is a release candidate for testing.

What's Changed
* Script to use ConvNeXt v1 Tiny as a feature extractor by ziw-liu in https://github.com/mehta-lab/VisCy/pull/228
* Fix dice score by ziw-liu in https://github.com/mehta-lab/VisCy/pull/230
* Evaluate existing segmentation by ziw-liu in https://github.com/mehta-lab/VisCy/pull/213
* Check if the sliding window size is valid by ziw-liu in https://github.com/mehta-lab/VisCy/pull/229
* Memory-mapped caching for image translation training by ziw-liu in https://github.com/mehta-lab/VisCy/pull/218
* Update license metadata by ziw-liu in https://github.com/mehta-lab/VisCy/pull/233


**Full Changelog**: https://github.com/mehta-lab/VisCy/compare/v0.3.0rc2...v0.3.0rc3

> [!WARNING]
> This is a release candidate for testing.

What's Changed
* Explicit target shape argument in the HCS data module by ziw-liu in https://github.com/mehta-lab/VisCy/pull/212
* Rank nearest neighbors in embedding space by ziw-liu in https://github.com/mehta-lab/VisCy/pull/211
* Gradio example by edyoshikun in https://github.com/mehta-lab/VisCy/pull/158
* Adding NTXENT loss by edyoshikun in https://github.com/mehta-lab/VisCy/pull/204
* Fix the wrong import name for pairwise_distance_matrix() by edyoshikun in https://github.com/mehta-lab/VisCy/pull/215
* Fixing the TripletDataModule() after changes to HCSDataModule by edyoshikun in https://github.com/mehta-lab/VisCy/pull/216
* Sharded distributed sampler for cached dataloading in DDP by ziw-liu in https://github.com/mehta-lab/VisCy/pull/195
* Tweak README by ziw-liu in https://github.com/mehta-lab/VisCy/pull/206
* Expose the option to not return negative samples in the triplet data module by edyoshikun in https://github.com/mehta-lab/VisCy/pull/225


**Full Changelog**: https://github.com/mehta-lab/VisCy/compare/v0.3.0rc1...v0.3.0rc2

> [!WARNING]
> This is a release candidate for testing.

VisCy 0.3.0 incorporates the representation learning task as a core feature.

Breaking change

The top-level CLI now supports both image translation and representation learning tasks. This required changes to configuration files. Concretely, `data` and `model` fields now require import paths to be specified. See the updated [examples](https://github.com/mehta-lab/VisCy/tree/v0.3.0rc0/examples/configs) for reference on migrating existing virtual staining configs.


What's Changed
* Add script to visualize effective receptive field by ziw-liu in https://github.com/mehta-lab/VisCy/pull/144
* adding VS hugginface demo by edyoshikun in https://github.com/mehta-lab/VisCy/pull/172
* Single-cell representation learning by ziw-liu in https://github.com/mehta-lab/VisCy/pull/153
* Vendor pad shape function by ziw-liu in https://github.com/mehta-lab/VisCy/pull/189
* Fix module name spelling by ziw-liu in https://github.com/mehta-lab/VisCy/pull/190
* Add new author to citation by ziw-liu in https://github.com/mehta-lab/VisCy/pull/188
* Add links to hosted files and napari-iohub wiki by ziw-liu in https://github.com/mehta-lab/VisCy/pull/192
* Bump MONAI to unpin NumPy by ziw-liu in https://github.com/mehta-lab/VisCy/pull/194
* Add badges to readme by ziw-liu in https://github.com/mehta-lab/VisCy/pull/197
* Simplify development installation by ziw-liu in https://github.com/mehta-lab/VisCy/pull/198
* Fix validation loss aggregation in VSUNet by ziw-liu in https://github.com/mehta-lab/VisCy/pull/202
* Expose prefetch_factor and persistent_worker for the HCS datamodule by edyoshikun in https://github.com/mehta-lab/VisCy/pull/203


**Full Changelog**: https://github.com/mehta-lab/VisCy/compare/v0.2.1...v0.3.0rc1

> [!WARNING]
> This is a release candidate for testing.

VisCy 0.3.0 incorporates the representation learning task as a core feature.

Breaking change

The top-level CLI now supports both image translation and representation learning tasks. This required changes to configuration files. Concretely, `data` and `model` fields now require import paths to be specified. See the updated [examples](https://github.com/mehta-lab/VisCy/tree/v0.3.0rc0/examples/configs) for reference on migrating existing virtual staining configs.

What's Changed
* Add script to visualize effective receptive field by ziw-liu in https://github.com/mehta-lab/VisCy/pull/144
* adding VS hugginface demo by edyoshikun in https://github.com/mehta-lab/VisCy/pull/172
* Single-cell representation learning by ziw-liu in https://github.com/mehta-lab/VisCy/pull/153
* Vendor pad shape function by ziw-liu in https://github.com/mehta-lab/VisCy/pull/189
* Fix module name spelling by ziw-liu in https://github.com/mehta-lab/VisCy/pull/190
* Add new author to citation by ziw-liu in https://github.com/mehta-lab/VisCy/pull/188
* Add links to hosted files and napari-iohub wiki by ziw-liu in https://github.com/mehta-lab/VisCy/pull/192


**Full Changelog**: https://github.com/mehta-lab/VisCy/compare/v0.2.1...v0.3.0rc0

Patch release to update README and example notebooks.

What's Changed

* version lighting CLI example by mattersoflight in https://github.com/mehta-lab/VisCy/pull/128
* Updated code (contrastive learning) by alishbaimran in https://github.com/mehta-lab/VisCy/pull/130
* Configurable drop path rate in contrastive models by ziw-liu in https://github.com/mehta-lab/VisCy/pull/131
* Config-based prediction with Xarray-based output format by ziw-liu in https://github.com/mehta-lab/VisCy/pull/132
* Plot tracks in latent space and real space by mattersoflight in https://github.com/mehta-lab/VisCy/pull/135
* Fix deprecated custom forward method by ziw-liu in https://github.com/mehta-lab/VisCy/pull/151
* updating the notebook after running it at DLMBL2024 by edyoshikun in https://github.com/mehta-lab/VisCy/pull/149


**Full Changelog**: https://github.com/mehta-lab/VisCy/compare/v0.2.0...v0.2.1

- Application scripts for single-cell infection classification through semantic segmentation
- Tutorial notebook that demonstrates the virtual staining pipeline
- Test time augmentations in the virtual staining prediction writer

This release maintains compatibility with the virtual staining model weights from the v0.1.0 release ([download link](https://github.com/mehta-lab/VisCy/releases/download/v0.1.0/VisCy-0.1.0-VS-models.zip)).

What's Changed
* Update dataset URL for demos by ziw-liu in https://github.com/mehta-lab/VisCy/pull/103
* Bump lightning and matplotlib by ziw-liu in https://github.com/mehta-lab/VisCy/pull/105
* Cellular infection phenotyping using annotated viral sensor data & label-free images by Soorya19Pradeep in https://github.com/mehta-lab/VisCy/pull/70
* Pin numpy due to MONAI bug by ziw-liu in https://github.com/mehta-lab/VisCy/pull/111
* Updating demo notebook for training by edyoshikun in https://github.com/mehta-lab/VisCy/pull/100
* Test time augmentations by edyoshikun in https://github.com/mehta-lab/VisCy/pull/91

New Contributors
* Soorya19Pradeep made their first contribution in https://github.com/mehta-lab/VisCy/pull/70

**Full Changelog**: https://github.com/mehta-lab/VisCy/compare/v0.1.1...v0.2.0rc0