skada.deep.DeepCoral
- skada.deep.DeepCoral(module, layer_name, reg=1, assume_centered=False, base_criterion=None, **kwargs)[source]
DeepCORAL domain adaptation method.
From [12].
- Parameters:
- moduletorch module (class or instance)
A PyTorch
Module.- layer_namestr
The name of the module's layer whose outputs are collected during the training for the adaptation.
- regfloat, optional (default=1)
Regularization parameter for DA loss.
- assume_centered: bool, default=False
If True, data are not centered before computation.
- base_criteriontorch criterion (class)
The base criterion used to compute the loss with source labels. If None, the default is torch.nn.CrossEntropyLoss.
References
[12]Baochen Sun and Kate Saenko. Deep coral: Correlation alignment for deep domain adaptation. In ECCV Workshops, 2016.
