Closed meet10may closed 3 years ago
Hi @meet10may,
can you verify whether the background areas contain only zero-valued inputs when fed into the network (after preprocessing the inputs)? If already gradient computation leads to non-zero attribution in the background area, I would expect some neurons (ie inputs) firing in these locations. It would be interesting to see the lowest layers outputs corresponding to in these areas.
I'm closing this issue due to inactivity. Feel free to reopen if the problem still exists.
I am using the
innvestigate
package to visualize my deep learning model and I have encountered a strange situation, where the innvestigate methods compute values that are outside the image! I have tried withdeep_taylor
,integrated gradients
,gradient
, and all seem to compute values that lie outside the image. There is no signal outside the image(the brain)!However, if I compute the Shapley values from
shap
package, the values are reasonable, and they are all inside the brain(which makes sense).The model is created using
tensorflow1.12
. I have attached the screenshots. The input training data is task-based fMRI data of size9032x91x109x91x1
. Additionally, there is no issue with the trained model as it performs the task as expected!Here is a piece of code:
Could you please provide your thoughts on it and where I am doing wrong?
Thank you so much!
Result using Innvestigate Result using Shap