Gradients in Grad Rollout

[ilovecv]

Hi,
For the gradients list in this fuction: https://github.com/jacobgil/vit-explain/blob/main/vit_grad_rollout.py#L9
do we need to reverse the gradients? Since the attention is accumulated in the forward path, while gradient is accumulated in the backward path. To multiply attention with gradient, we need to reverse the gradient: gradients = gradients[::-1].

What do you think? Thanks

[ymp5078]

I agree with @ilovecv

I check the address of the module using the following code and found that the order is reversed. Please let me know if you have any thoughts.

`def get_attention(self, module, input, output):
print('f',id(module))
self.attentions.append(output.cpu())

def get_attention_gradient(self, module, grad_input, grad_output):
    print('b',id(module))
    self.attention_gradients.append(grad_input[0].cpu())`

and found that
f 140200126500192
f 140200126548912
f 140200126499136
f 140200206491504
f 140200000463632
f 140200000464592
f 140200000465552
f 140200000466512
f 140200000172624
f 140200000173584
f 140200000174544
b 140200000174544
b 140200000173584
b 140200000172624
b 140200000466512
b 140200000465552
b 140200000464592
b 140200000463632
b 140200206491504
b 140200126499136
b 140200126548912
b 140200126500192
b 140200126500144