2
$\begingroup$

I'm building CNN network of Image to Image.

After training, I have some bad results in part of the Image.

I would like to find the neurons that most influenced those pixels and do retraining only for them.

I have seen some previous works about visualizing networks, like here:

https://github.com/utkuozbulak/pytorch-cnn-visualizations

But they are only finding activations maps or visualizing with softmax in the output layer.

How can I do that for Image to Image?

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.