# Release Overview **New in version 1.8.14** Fix prompt clearing with napari 0.9.1 to prevent crashes when toggling labels after commit. Preserve point labels and track IDs when clearing individual slices. **New in version 1.8.13** Fix pip installations that used a stale Segment Anything release with an incorrect PyTorch image resize. Pip now installs `segment-anything-py>=1.0.1`. **New in version 1.8.12** Support napari 0.9, pin `napari<0.10`, and fix the tracking annotator when prompt layers already exist and when selecting box prompts. **New in version 1.8.11** Fix stale embeddings and add AIS tests for the BioImage.IO/BioEngine model export. **New in version 1.8.10** Support automatic instance segmentation in the bioimage.io model export and add a code of conduct and contributing guide. **New in version 1.8.9** Pin `napari<0.9` and minor updates to joint training. **New in version 1.8.8** Fix the bioimage.io model export for bioimageio.spec >=0.5.11. **New in version 1.8.7** Fixing minor issues with 1.8.6 related to clearing custom weights / checkpoint paths in the annotator and training widgets. **New in version 1.8.6** Support napari 0.8 (which requires Python >=3.11) and switch the PyPI Qt backend to PyQt6. **New in version 1.8.5** Add tracking model and solver options, clarify CLI arguments, and fix compatibility with recent bioimage-cpp versions. **New in version 1.8.3 - 1.8.4** Switch the Qt backend to PyQt6 and require napari >=0.7. **New in version 1.8.2** Fix the napari plugin manifest for the renamed `micro_sam` package and expand the FAQ with segmentation and fine-tuning advice. **New in version 1.8.1** Rename the package to `micro_sam` on PyPI (now installable via `pip install micro_sam`). **New in version 1.8.0** `micro_sam` is now available on PyPI, alongside minor documentation updates. **New in version 1.7.7** Fixes for tiled NMS and MPS inference, plus a new example for instance segmentation-only finetuning. **New in version 1.7.6** Minor fixes for automatic tracking pipeline using trackastra. **New in version 1.7.3 - 1.7.5** Minor extensions and improvements to several functions' input arguments. **New in version 1.7.2** Handful patch fixes to minor issues. **New in version 1.7.1** Fixing minor issues in 1.7.0 (related to trackastra, automatic segmentation and training functions) and adding new section in documentation for our new automatic segmentation pipeline, APG. **New in version 1.7.0** Updates to the automatic instance segmentation pipeline (introduces APG - automatic prompt generation). **New in version 1.6.2** Publish improved version of the medical imaging model and minor fixes to image series annotator. **New in version 1.6.1** Minor updates to training functionality and some other tiny updates. **New in version 1.6.0** Publish improved versions of the light microscopy (v4) and electron microscopy (v3) models. **New in version 1.5.0** - Preliminary version of object classification tool. - Enabling support for napari v6, zarr v3 and numpy v2. - Add support for training models for automatic instance segmentation-only. **New in version 1.4.0** This release includes three main changes: - Preliminary support for automatic tracking via [Trackastra](https://github.com/weigertlab/trackastra) integration. - Changes in the GUI to make the model names more informative. - Much easier installation on Windows. **New in version 1.3.1** Fixing minor issues with 1.3.0 and adding new section in documentation for our data submission initiative. **New in version 1.3.0** This release introduces a new light microscopy model that was trained on a larger dataset and clearly improves automatic segmentation. **New in version 1.2.2** Fixing minor issues with 1.2.1 for making automatic segmentation CLI more flexible. **New in version 1.2.1** This version introduces several changes that are part of three of our recent publications that are built on top of micro_sam: - [medico-sam](https://github.com/computational-cell-analytics/medico-sam), which improves SAM for medical images. - [peft-sam](https://github.com/computational-cell-analytics/peft-sam), which investigates parameter efficient finetuning for SAM. - [patho-sam](https://github.com/computational-cell-analytics/patho-sam), which improves SAM for histopathology. **New in version 1.2.0** The main changes in this version are: - Installation using only conda-forge dependencies and simplified installation instructions (on Linux and Mac OS). - Fix annotation in napari widgets with scale factors. - Support for several parameter-efficient training methods. **New in version 1.1.1** Fixing minor issues with 1.1.0 and enabling pytorch 2.5 support. **New in version 1.1.0** This version introduces several improvements: - Bugfixes and several minor improvements. - Compatibility with napari >=0.5. - Automatic instance segmentation CLI. - Initial support for parameter efficient fine-tuning and automatic semantic segmentation in 2d and 3d (not available in napari plugin, part of the python library). **New in version 1.0.1** Use stable URL for model downloads and fix issues in state precomputation for automatic segmentation. **New in version 1.0.0** This release mainly fixes issues with the previous release and marks the napari user interface as stable. **New in version 0.5.0** This version includes a lot of new functionality and improvements. The most important changes are: - Re-implementation of the annotation tools. The tools are now implemented as napari plugin. - Using our improved functionality for automatic instance segmentation in the annotation tools, including automatic segmentation for 3D data. - New widgets to use the finetuning and image series annotation functionality from napari. - Improved finetuned models for light microscopy and electron microscopy data that are available via bioimage.io. **New in version 0.4.1** - Bugfix for the image series annotator. Before the automatic segmentation did not work correctly. **New in version 0.4.0** - Significantly improved model finetuning. - Update the finetuned models for microscopy, see [details in the doc](https://computational-cell-analytics.github.io/micro-sam/micro_sam.html#finetuned-models). - Training decoder for direct instance segmentation (not available via the GUI yet). - Refactored model download functionality using [pooch](https://pypi.org/project/pooch/). **New in version 0.3.0** - Support for ellipse and polygon prompts. - Support for automatic segmentation in 3d. - Training refactoring and speed-up of fine-tuning. **New in version 0.2.1 and 0.2.2** - Several bugfixes for the newly introduced functionality in 0.2.0. **New in version 0.2.0** - Functionality for training / finetuning and evaluation of Segment Anything Models. - Full support for our finetuned segment anything models. - Improvements of the automated instance segmentation functionality in the 2d annotator. - And several other small improvements. **New in version 0.1.1** - Fine-tuned segment anything models for microscopy (experimental). - Simplified instance segmentation menu. - Menu for clearing annotations. **New in version 0.1.0** - We support tiling in all annotators to enable processing large images. - Implement new automatic instance segmentation functionality: - That is faster. - Enables interactive update of parameters. - And also works for large images by making use of tiled embeddings. - Implement the `image_series_annotator` for processing many images in a row. - Use the data hash in pre-computed embeddings to warn if the input data changes. - Create a simple GUI to select which annotator to start. - And made many other small improvements and fixed bugs. **New in version 0.0.2** - We have added support for bounding box prompts, which provide better segmentation results than points in many cases. - Interactive tracking now uses a better heuristic to propagate masks across time, leading to better automatic tracking results. - And have fixed several small bugs.