skada.OTMappingAdapter
- skada.OTMappingAdapter(metric='sqeuclidean', norm=None, max_iter=100000)[source]
Domain Adaptation Using Optimal Transport.
See [6] for details.
- Parameters:
- metricstr, optional (default="sqeuclidean")
The ground metric for the Wasserstein problem
- norm{'median', 'max', 'log', 'loglog'} (default=None)
If given, normalize the ground metric to avoid numerical errors that can occur with large metric values.
- max_iterint, optional (default=100_000)
The maximum number of iterations before stopping OT algorithm if it has not converged.
- Attributes:
- ot_transport_object
The OT object based on Earth Mover's distance fitted on the source and target data.
References
[6]N. Courty, R. Flamary, D. Tuia and A. Rakotomamonjy, Optimal Transport for Domain Adaptation, in IEEE Transactions on Pattern Analysis and Machine Intelligence
