- Fix lightning implementation of batch size finder not working properly when the initial batch size is bigger than the dataset length, now also the code checks that the last iteration works properly.
2.1.6
Updated
- Remove poetry dependencies from quadra toml - Update readme to explain how to use poetry properly
2.1.5
Fixed
- Fix classification val_dataloader shuffling data when it shouldn't
2.1.4
Updated
- Remove black from pre-commit hooks - Use ruff as the main formatter and linting tool - Upgrade mypy version - Upgrade mlflow version - Apply new pre-commits to all tests - Update most of typing to py310 style
2.1.3
Updated
- Update anomalib to v0.7.0+obx.1.3.2
2.1.2
Updated
- Update anomalib to v0.7.0+obx.1.3.1 - The optimal anomaly threshold is now computed as the average between the max good and min bad score when the F1 is 1