Open enkeejunior1 opened 7 months ago
Hi, and thank you for your awesome repository!
I recently tried using this library to validate some attribution methods, specifically by utilizing evaluator.evaluate.
However, I discovered that it only uses an attribution map from a single sample. link
attrA = self.gt_feature_importances.detach().numpy().reshape(1, -1) attrB = self.explanation_x_f.detach().numpy().reshape(1, -1)
Is this behavior expected? The comment mentions evaluator.evaluate using n x m samples, so I am confused.
evaluator.evaluate
Hi, and thank you for your awesome repository!
I recently tried using this library to validate some attribution methods, specifically by utilizing evaluator.evaluate.
However, I discovered that it only uses an attribution map from a single sample. link
Is this behavior expected? The comment mentions
evaluator.evaluate
using n x m samples, so I am confused.