skada
skada copied to clipboard
scikit-adaptation
Domain adaptation toolbox compatible with scikit-learn and pytorch
See details in #184
Add optional argument if the user knows what they are doing (similar to `allow_source`). This would likely break many tests + documentation.
Instead, introduce a required flag for `pack` with `mask_target_labels = True | False`.
https://scikit-adaptation.github.io/dev/quickstart.html Unclear to a novel user. Probably needs trimming and more structure.
Right now we assume that features (e.g. `features_s`, `features_t`) are 2-dimentional tensors. This might not always be the case. Should be either stated in the documentation clearly, or we can...
In the DeepCoral method, the class `DeepCoralLoss` computes first the covariance matrices and then calls the `deep_coral_loss` function with cov as arguments. I would like to have to covariance estimation...
After fitting a `DomainAwareNet`, it's not possible to deep copy it. Strangely it works before the fitting. Error raised: `AttributeError: Can't pickle local object '_get_intermediate_layers..hook'` It's necessary to be able...
This PR is a WIP implementation of [Geodesic Flow Kernel](https://projet.liris.cnrs.fr/imagine/pub/proceedings/CVPR2012/data/papers/261_O2D-03.pdf). This method requires the [Generalized SVD](https://en.wikipedia.org/wiki/Generalized_singular_value_decomposition), and it is not implemented either in numpy or Scipy. The `transferlearning` library uses...
Metadata
Owner
Metadata
Domain adaptation toolbox compatible with scikit-learn and pytorch