skada
skada copied to clipboard
scikit-adaptation
Domain adaptation toolbox compatible with scikit-learn and pytorch
I like the one of braindecode (https://github.com/braindecode/braindecode/blob/master/CONTRIBUTING.md) Having one can help people contribute. I see a lot of people struggling with pre-commit, for example.
Paper: https://arxiv.org/pdf/1901.00976 Mostly eq 3-4-5 + paragraph 3.4 ### New Features: * **CAN and CANLoss Implementation:** * Added `CANLoss` class to `skada/deep/_divergence.py` to implement the contrastive domain discrepancy (CDD) loss....
The `predict_proba` of deep method was choosing the nonlin attributes by looking at `criterion` attribute of the solvers. The `DomainAwareNet` has a `DomainAwareCriterion` as criterion. We should choose the nonlin...
`skada.deep` does not support binary classification because `DomainAwareNet` inherits from `skorch.classifier.NeuralNetClassifier`. To do classification with skorch, it should inherits from `skorch.classifier.NeuralNetBinaryClassifier`. See: https://skorch.readthedocs.io/en/latest/classifier.html
#### Description When using the `CircularValidation` scorer with deep models, a `ValueError` is raised during the inverse transformation of predicted source labels. This error occurs because the predicted labels (`y_pred_source`)...
`_check_y_masking` is used in some functions such as CircularValidation but not everywhere. Some adapters can be used with `y_target` not masked.
`DomainAwareDataset` is not exposed in the doc api
Metadata
Owner
Metadata
Domain adaptation toolbox compatible with scikit-learn and pytorch