Error with Grad CAM during lesson 18

Part 1 (2020)
1

Hello,

I am sure this is a trivial problem :sweat_smile:. I am trying to get the activation map on the final conv layer for an image in validation set while following lesson 18 for grad CAM. Here is the error;

1

w = grad[0].mean(dim=(1,2), keepdim=True)

2

gradcam_map = (w * act[0]).sum(0).detach().cpu()

---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
<ipython-input-79-76f83767f6d3> in <module>
----> 1 w = grad[0].mean(dim=(1,2), keepdim=True)
      2 gradcam_map = (w * act[0]).sum(0).detach().cpu()

IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

For info i have 8 classes so, my grad[0]:


grad[0]

tensor([0., 1., 0., 0., 0., 0., 0., 0.], device='cuda:0')

So what should I set my dim to? I set it to dim=(8,9) which is what I had expected it to be but it didn’t work.

Thanks!