Closed szubing closed 2 years ago
Hi @szubing thanks for your interest!
If I understand your question correctly, this is used for the full LRP baseline where the relevance is propagated all the way back to the input. Our method only requires propagation of relevance to the attention layers.
I hope this helps, but if not do let me know and I’ll do my best to clarify.
Hi @szubing thanks for your interest!
If I understand your question correctly, this is used for the full LRP baseline where the relevance is propagated all the way back to the input image. Our method only requires propagation of relevance to the attention layers.
I hope this helps, but if not do let me know and I’ll do my best to clarify.
Hi, Hila, thank you very much!
Hi, Hila, I have a question about relprop in BertModel class in BERT.py: def relprop(self, cam, kwargs): cam = self.pooler.relprop(cam, kwargs)
print("111111111111",cam.sum())
Why we do not need to reprop the embedding module by self.embeddings.relprop(cam, **Kwargs) here before returning cam?