Open Ertz012 opened 7 months ago
added a feature that trains and tests on negative data this should reduce false positive segmentations on background
TODO: split negative data in training and test
Todo: make superclass dataset with params (e g. Size) and collate_fn. Thus, it's defined on every dataset, not just ListDataset
Proposed changes
added a feature that trains and tests on negative data this should reduce false positive segmentations on background
Related issues
Necessary checks