adapt.metrics.domain_classifier
- adapt.metrics.domain_classifier(Xs, Xt, classifier=None, **fit_params)[source]
Return 1 minus the mean square error of a classifer disciminating between Xs and Xt.
\[\Delta = 1 - \min_{h \in H} || h(X_S) - 1 ||^2 + || h(X_T) ||^2\]Where:
\(H\) is a class of classifier.
- Parameters
- Xsarray
Source array
- Xtarray
Target array
- classifiersklearn estimator or tensorflow Model instance
Classifier
- fit_paramskey, value arguments
Parameters for the fit method of the classifier.
- Returns
- scorefloat
See also
reverse_validationDANN
References
- 1
[1] Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, and V. Lempitsky. “Domain-adversarial training of neural networks”. In JMLR, 2016.