Pedro Herruzo
Pedro Herruzo
Dear @1Konny, Thanks for your implementation! I have detected that line 168 in `gradcam.py`: `alpha_denom = gradients.pow(2).mul(2) + \ activations.mul(gradients.pow(3)).view(b, k, u*v).sum(-1, keepdim=True).view(b, k, 1, 1)` should be: `global_sum =...
changes in `gradcam.py`: fixed wrong denominator of Eq.19 (second term: `Sum_{a,b} A^{k}_{a,b}`) in the paper. changes in `example.ipynb`: added a flag to automatically detect if Cuda can be used, otherwise,...
Dear @adityac94 , @tataiani If I understand correctly, you use the following assumption to go from eq.7 to eq.8, and from eq.8 to eq.9: $\frac{\partial^2 Y^C}{\partial A^k_{ab} \partial A^k_{ij}} =...