GenericAttention#

class txv.exp.GenericAttention(model)#

Link to Paper: Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers

__init__(model)#
Parameters:

model (torch.nn.Module) – A model from txv.vit

Tip

Use the model with lrp=False as LRP models have higher memory footprint.

explain(input: Tensor, index: int | None = None, layer: int = 1, abm: bool = True, **kwargs) → Tensor#
Parameters:

  • input (torch.Tensor) – Input tensor

  • index (int, optional) – Index of the class to explain, by default the predicted class is explained

  • layer (int, optional) – Layer number to start the computation of attention weights, by default 1

  • abm (bool, optional) – Architecture based modification, by default True