Loss functions seem to use one of classes or ignore_index or even both. We should support both options for all loss functions. This generates confusion when using multiple loss functions (see https://github.com/microsoft/torchgeo/issues/1896) This involves updating the following:
isaaccorley
commented
8 months ago
Loss functions seem to use one of
classesorignore_indexor even both. We should support both options for all loss functions. This generates confusion when using multiple loss functions (see https://github.com/microsoft/torchgeo/issues/1896) This involves updating the following:JaccardLossFocalLossDiceLoss(this uses bothclassesandignore_indexTverskyLoss(this is just a subclass ofDiceLoss)