You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The nature biotech paper describes importance scores using GRAM in extended figure 9 and the methods. I can't find how to compute them in the GitHub repo. Can you point me in the right direction? Thanks!
The text was updated successfully, but these errors were encountered:
Hi @thomas-reimonn yes unfortunately the GRAM calculation is not included here because it didn't work as well as attention scores from our experiments. If you want to calculate it, the mechanism is very similar to grad-cam. Here is an implementation for CV models and should be easy to adapt to C.Origami: https://github.com/tanjimin/grad-cam-pytorch-light
Hi!
The nature biotech paper describes importance scores using GRAM in extended figure 9 and the methods. I can't find how to compute them in the GitHub repo. Can you point me in the right direction? Thanks!
The text was updated successfully, but these errors were encountered: