0.4.0

What's Changed

• DynaCLR_V2 Submission by @edyoshikun in #240
• Update README.md to point to NMI 2025 by @mattersoflight in #265
• Update the DLMBL Notebook by @edyoshikun in #278
• Fix deprecated numpy call by @ziw-liu in #281
• Expose Final Z cropping in TripletDataModule by @ziw-liu in #270
• Batched dataloading for contrastive learning by @ziw-liu in #276
• add readthedocs config by @mattersoflight in #289
• Fix preprocessing with zarr-python 3 by @ziw-liu in #294
• Batched transforms by @ziw-liu in #282
• Adding annotation typings by @edyoshikun in #300
• Example for Shearing transform by @edyoshikun in #305
• Patch ModelSummary with BatchTransforms by @edyoshikun in #307
• Remove typo in PC by @edyoshikun in #308
• Strip the slash on fov_name for valid anchors on the triplet by @edyoshikun in #313
• Fix typo in readme by @ziw-liu in #309
• Catch hyperparameter incompatibility in checkpoints by @ziw-liu in #319
• Fix the pseudotrack creation by @edyoshikun in #312
• Zoom map transform by @ziw-liu in #314
• Pin xarray by @ziw-liu in #325
• Use new API from zarr-python 3 by @ziw-liu in #320
• Adding support for pyramids by @edyoshikun in #129
• fix prefetch in cached omezarr data module by @alxndrkalinin in #326
• add 5th and 95th percentile by @ritvikvasan in #317
• 3D ResNet for contrastive learning by @ziw-liu in #285
• Test preprocessing sharded arrays by @ziw-liu in #316
• Write Annotations to AnnData by @srivarra in #303
• Added pre-commit by @srivarra in #330
• Pre-commit on all files by @edyoshikun in #331
• Log the similarity between anchor and negatives by @edyoshikun in #332
• Implementation of Beta VAE for benchmarking by @edyoshikun in #273
• Add precommit to dev dependencies by @alxndrkalinin in #334
• Fix examples by @alxndrkalinin in #336
• Expose loading the ckpt to the contrastive model by @edyoshikun in #340
• Removing duplicate call for random seed for PHATE by @edyoshikun in #341
• Add quickstart for the VCP by @edyoshikun in #343
• VCP Dynaclr Extra updates by @srivarra in #344
• Move and fix annotations for AnnData by @edyoshikun in #347
• compute normalization per timepoint by @ritvikvasan in #345
• Add import statement for FullyConvolutionalMAE in VCP Quickstart by @melissawm in #350
• patching a bug when we added the normalize by time transforms. by @edyoshikun in #360
• cli for linear classifier by @edyoshikun in #355
• Predict volume by @ieivanov in #280
• Test Zarr v2 and v3 for our dataloaders and models by @edyoshikun in #372
• This adds the initial configurable QC metrics by @edyoshikun in #364
• Depend on waveorder>=3.0 by @ieivanov in #395

New Contributors

• @ieivanov made their first contribution in #280

Full Changelog: v0.3.2...v0.4.0

VisCy 0.3.4

This a maintenance patch to avoid an upstream breaking change. No code change from 0.3.3.

What's Changed

• Pin lightning for 0.3 by @ziw-liu in #310

Full Changelog: v0.3.3...v0.3.4

VisCy 0.3.4rc0

Warning

This is a release candidate for testing.

What's Changed

• Pin lightning for 0.3 by @ziw-liu in #310

Full Changelog: v0.3.3...v0.3.4rc0

VisCy 0.3.3

Maintenance patch for resolving dependencies. No code change from v0.3.2.

What's Changed

• Pin iohub by @ziw-liu in #298

Full Changelog: v0.3.2...v0.3.3

VisCy 0.3.3rc0

Warning

This is a release candidate for testing.

What's Changed

• Pin iohub by @ziw-liu in #298

Full Changelog: v0.3.2...v0.3.3rc0

VisCy 0.3.2

Note

Our paper Robust virtual staining of landmark organelles with Cytoland is now published in Nature Machine Intelligence!
This version of VisCy is compatible with the models and demos described in the paper.

This release includes maintenance patches and documentation improvements.

What's Changed

• Fix swapped colormap in the neuromast tutorial by @ziw-liu in #256
• Document AugmentedPredictionVSUNet by @ziw-liu in #261
• Update HF demo links by @ziw-liu in #264
• Replace black with ruff by @ziw-liu in #262

Full Changelog: v0.3.1...v0.3.2

VisCy 0.3.2rc0

Warning

This is a release candidate for testing.

What's Changed

• Fix swapped colormap in the neuromast tutorial by @ziw-liu in #256
• Document AugmentedPredictionVSUNet by @ziw-liu in #261
• Update HF demo links by @ziw-liu in #264
• Replace black with ruff by @ziw-liu in #262

Full Changelog: v0.3.1...v0.3.2rc0

VisCy 0.3.1

This release includes maintenance patches and documentation improvements.

What's Changed

• Add CLI tutorials for VCP by @ziw-liu in #239
• Update README.md to align with the title of the cytoland paper by @mattersoflight in #243
• Update VCP tutorials by @ziw-liu in #244
• Delay cellpose import by @ziw-liu in #245
• Add contact information by @melissawm in #248
• Add neuromast notebook by @ziw-liu in #249
• Skip broken test with pycocotools on python 3.13 by @ziw-liu in #252
• Fix DLMBL excercise setup script by @ziw-liu in #253
• Tweak VCP tutorials by @ziw-liu in #251
• Readme updates by @ziw-liu in #246

New Contributors

• @melissawm made their first contribution in #248

Full Changelog: v0.3.0...v0.3.1

VisCy 0.3.1rc0

Warning

This is a release candidate for testing.

What's Changed

• Add CLI tutorials for VCP by @ziw-liu in #239
• Update README.md to align with the title of the cytoland paper by @mattersoflight in #243
• Update VCP tutorials by @ziw-liu in #244
• Delay cellpose import by @ziw-liu in #245
• Add contact information by @melissawm in #248
• Add neuromast notebook by @ziw-liu in #249
• Skip broken test with pycocotools on python 3.13 by @ziw-liu in #252
• Fix DLMBL excercise setup script by @ziw-liu in #253
• Tweak VCP tutorials by @ziw-liu in #251
• Readme updates by @ziw-liu in #246

New Contributors

• @melissawm made their first contribution in #248

Full Changelog: v0.3.0...v0.3.1rc0

VisCy 0.3.0

VisCy 0.3.0 brings performance improvements to the image translation task, especially for very large datasets in distributed training. It also 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 for reference on migrating existing virtual staining configs.

What's Changed

• Add script to visualize effective receptive field by @ziw-liu in #144
• adding VS hugginface demo by @edyoshikun in #172
• Single-cell representation learning by @ziw-liu in #153
• Vendor pad shape function by @ziw-liu in #189
• Fix module name spelling by @ziw-liu in #190
• Add new author to citation by @ziw-liu in #188
• Add links to hosted files and napari-iohub wiki by @ziw-liu in #192
• Bump MONAI to unpin NumPy by @ziw-liu in #194
• Add badges to readme by @ziw-liu in #197
• Simplify development installation by @ziw-liu in #198
• Fix validation loss aggregation in VSUNet by @ziw-liu in #202
• Expose prefetch_factor and persistent_worker for the HCS datamodule by @edyoshikun in #203
• Explicit target shape argument in the HCS data module by @ziw-liu in #212
• Rank nearest neighbors in embedding space by @ziw-liu in #211
• Gradio example by @edyoshikun in #158
• Adding NTXENT loss by @edyoshikun in #204
• Fix the wrong import name for pairwise_distance_matrix() by @edyoshikun in #215
• Fixing the TripletDataModule() after changes to HCSDataModule by @edyoshikun in #216
• Sharded distributed sampler for cached dataloading in DDP by @ziw-liu in #195
• Tweak README by @ziw-liu in #206
• Expose the option to not return negative samples in the triplet data module by @edyoshikun in #225
• Script to use ConvNeXt v1 Tiny as a feature extractor by @ziw-liu in #228
• Fix dice score by @ziw-liu in #230
• Evaluate existing segmentation by @ziw-liu in #213
• Check if the sliding window size is valid by @ziw-liu in #229
• Memory-mapped caching for image translation training by @ziw-liu in #218
• Update license metadata by @ziw-liu in #233
• Update supported python version range by @ziw-liu in #200
• Add DOI badge by @ziw-liu in #235
• Bump iohub by @ziw-liu in #236
• VCP tutorials by @ziw-liu in #227
• Remove outdated docs by @ziw-liu in #238

Full Changelog: v0.2.1...v0.3.0