search

experiencor / deep-viz-keras

Implementations of some popular Saliency Maps in Keras
https://experiencor.github.io/cnn_visual.html
164 stars 31 forks source link

get_gradients loss is the output of the NN #6

Open sulantha2006 opened 6 years ago

sulantha2006 commented 6 years ago

This may be a more of a theoretical question. But, when calculating the saliency maps and the guided back prop, when calculating the loss to get the gradients, the output is used (of the class). Is it how the loss needs to be calculated for saliency and guided back prop? Thank you.

Max-ChenFei commented 5 years ago

I have the same questions. I see some implementations of saliency map use loss while here just use the output of the model. Thank you!