7 Commits (bf90288a95a0e6498f5c844ed76d78cd1dcf9642)

Author	SHA1	Message	Date
laynholt	bf90288a95	fix: correct auto split sampling, fix non-TIF memory leak, update README ... **Bug fix** 1. Fixed an error in dataset sampling during automatic splitting. 2. Fixed a memory leak when loading images in formats other than `.tif`. **Changes:** 1. `shuffle` can now be used with both `pre-split` and `split` methods. 2. `offsets` can be specified as floating-point values for dynamic computation. 3. `size` and `offsets` now support mixed formats (i.e., both `int` and `float`). 4. F1 and mAP metrics are now computed by default in `micro`, `macro`, and `per_class` variations. 5. Classes `BoundaryExclusion` and `IntensityDiversification` have been renamed to follow the MONAI naming style. 6. Minor updates to the README for clarity and consistency.	4 weeks ago
laynholt	b0e7b21a21	refactor: migrate all type annotations from Python 3.9 to 3.10 syntax ... Replaced typing module generics like List, Dict, Tuple with built-in alternatives (list, dict, tuple). Updated code to use new union syntax (X | Y) instead of Union[X, Y].	6 months ago
laynholt	28f978956c	Added the creation of error masks for each class; ... Added arguments for creating only prediction masks, as well as refusing to save the output; Added execution time display; The pretrained_weight parameter has been moved to common; Parameters related to ensembles have been removed.	6 months ago
laynholt	b201367596	Fixed bugs that prevented the project from running. Mediar Former values for the F1 metric were achieved.	6 months ago
laynholt	c1ef9d20d5	Fixed bugs that prevented the project from running. Mediar Former values for the F1 metric were achieved.	6 months ago
laynholt	8885950b9e	renamed img->image; label->mask	7 months ago
laynholt	78f97a72a2	simple project restruct, added transforms	7 months ago