v0.1.4

What's Changed

• Intensity and radius bug by @BBQuercus in #141
• TrackMate output file changes by @BBQuercus in #144
• Prepare for release 0.1.4 by @BBQuercus in #145

Full Changelog: v0.1.3...v0.1.4

---

Authors

• @BBQuercus
• @zhanyinx

v0.1.3

Overview

This release contains some of the following QOL improvements and the deepblink visualize submodule:

• CLI submodule visualize in #134
• Scale pixel size in deepblink create in #135
• Scale pixel size in deepblink predict in #136
• Conda Python 3.8 support and bugfix in #139

Full Changelog: v0.1.2...v0.1.3

---

Authors

• @BBQuercus
• @zhanyinx

v0.1.2

Overview

This release contains some of the following minor QOL improvements:

• Account for new Trackmate output files

• Remove python version requirements

• Fix spots close to edges error in 3d_prediction

• Add pretraining option in CLI

• Add example notebooks

• NAR release

• KNIME node release

---

Authors

• @BBQuercus
• @zhanyinx

deepBlink v0.1.1

Overview

This release contains some of the following minor QOL improvements:

• https://deepblink.readthedocs.io/en/latest/ finally works again
• Output optional probabilities in the csv file
• Add timeout information in deepblink download
• Add different ways of calculating deepblink.inference.get_intensities

---

Authors

• @BBQuercus
• @zhanyinx

deepBlink v0.1.0

Overview

This pre-release contains some of the following updates:

• New model names
• YouTube video in README
• Brought readthedocs back to life

---

Authors

• @BBQuercus
• @zhanyinx

Minor bug patch before 0.1.0

Overview

This pre-release contains some of the following updates:

• Wandb training bug fixed
• Single network with more optionality
• Conda package creation on tag publication
• Gaussian localisation benchmark
• Raw configuration file option

---

Authors

• @BBQuercus
• @zhanyinx

Getting ready for 0.1.0

Overview

This pre-release contains some of the following updates:

• A completely overhauled CLI
• More succinct models
• Finalized benchmarking scripts
• Various bug fixes and improved documentation

---

Authors

• @BBQuercus
• @zhanyinx

deepBlink v.0.0.6

Overview

This release mainly focussed on the addition of benchmarking and some bug fixes.

• Benchmarking scripts for TrackMate, SpotLearn, DetNet, and deepBlink
• According changes in pink.metrics
• Intensity calculation as option in CLI

Note: Changelog was not updated for the release. Updates will be added in the next commit.

---

Authors

• @BBQuercus
• @zhanyinx

deepBlink v.0.0.5x

We're on zenodo!

This is a intermediate release without many feature changes to link zenodo and get a DOI for this repository.

deepBlink v.0.0.5

Overview

“It works fine on MY computer”

Those days are over as it's testing time. While the test-suite is not fully complete it gives us some more confidence over our commits.
Additional changes in this release include:

• Change from prediction matrix to coordinate list as default dataset component. Accompanying changes include the use of cell_size in the dataset class and a dynamic Resnet architecture.
• Scipy requirement for a new deepblink.metrics.f1_cutoff_score way of calculating the F1 score directly from coordinates.
• Depreciation of deepblink.metrics.compute_score and deepblink.metrics.weighted_f1_coordinates.
• Addition of deepblink.optimizers.amsgrad function.
• Movement of functions:
  • train_valid_split to util
  • load_image to io

The next release will include benchmarking scripts and is most likely the last release before the first minor 0.1.0 and non-pre-release.

---

Authors

• @BBQuercus
• @zhanyinx