Closed schdief06 closed 3 years ago
Hi @schdief06 , thank you for reporting the error.
I believe it's a bug that involve the normalize_gradient
option of activation_maximization function.
Could you please try to add normalize_gradient=False
option to calling activation_maximization function.
[Note!]
We are going to remove the normalize_gradient
option at next version.
So I'm sorry to bother you, but please remove the code (normalize_gradient=False
) when updating tf-keras-vis to next version in your environment.
The next version will be released in this year.
Regards.
Hi @keisen,
when disabling normalize_gradient it is working! Thank you!
For now, I disabled the option in ActivationMaximization and GradCAM in version 0.5.4.
Thanks!
Hi,
I want to generate the activation maximization for all the neurons of my output layer (128). But when generating more than 4 at once, I get the following error:
Here is my code:
For values of neurons <= 4 it seems to work just fine. Thanks for helping