An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
Initial implementation of dataclasses for model inputs and outputs, meant to collect feedback (DO NOT MERGE).
Adds ImageBatch and VideoBatch dataclasses and base classes.
collate_fn had to be updated to allow collating the dataclasses as batches.
Backward compatibility is achieved by defining the __getitem__ and __setitem__ methods in the BatchItem base class and by adding prorties for renamed attributes (e.g. mask -> gt_mask).
β¨ Changes
Select what type of change your PR is:
[ ] π Bug fix (non-breaking change which fixes an issue)
[x] π¨ Refactor (non-breaking change which refactors the code base)
[ ] π New feature (non-breaking change which adds functionality)
[ ] π₯ Breaking change (fix or feature that would cause existing functionality to not work as expected)
[ ] π Documentation update
[ ] π Security update
β Checklist
Before you submit your pull request, please make sure you have completed the following steps:
[ ] π I have summarized my changes in the CHANGELOG and followed the guidelines for my type of change (skip for minor changes, documentation updates, and test enhancements).
[ ] π I have made the necessary updates to the documentation (if applicable).
[ ] π§ͺ I have written tests that support my changes and prove that my fix is effective or my feature works (if applicable).
π Description
ImageBatch
andVideoBatch
dataclasses and base classes.collate_fn
had to be updated to allow collating the dataclasses as batches.__getitem__
and__setitem__
methods in theBatchItem
base class and by adding prorties for renamed attributes (e.g.mask
->gt_mask
).β¨ Changes
Select what type of change your PR is:
β Checklist
Before you submit your pull request, please make sure you have completed the following steps:
For more information about code review checklists, see the Code Review Checklist.