Apoc

Latest version: v0.12.0

Safety actively analyzes 723144 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 3 of 4

0.6.2

Bug fixes
* Pixel classifier result images were of type float32 instead of uint32

Improvements
* Test and code coverage improved

0.6.1

Bugfix
* object classifier couldn't be created in case the file didn't exist

0.6.0

New features
* The classifiers can now be applied in Fiji using the corresponding Fiji plugin: https://github.com/clij/clijx-accelerated-pixel-and-object-classification

Bug fixes
* ObjectSegmenter.cl files were misleadingly saved in the "PixelClassifier" format.
* ObjectClassification features were saved comma-separated, pixel-classification feastures were saved space-separated. Starting with this release, all features are saved space-separated (similar to other function in CLIJ). This change is backwards-compatible. The old format is still accepted.

Backwards compatibility breaking changes:
* In case, in future versions of APOC, these old classifiers can't be loaded anymore, consider editing the `.cl` file by replacing `classifier_class_name = PixelClassifier` with `classifier_class_name = ObjectSegmenter`. If this doesn't help, [please get in touch](https://github.com/haesleinhuepf/apoc/issues).

0.5.9

This is a maintenance release for making tests work and improving code coverage

0.5.7

New features
* `ProbabilityMapper` for producing probability maps for specific classes

0.5.6

Bugfix
* Fixed deprecation warning from scikit-learn

Page 3 of 4

© 2025 Safety CLI Cybersecurity Inc. All Rights Reserved.