Finding the strongest activation map in a layer

[abhigoku10]

• [x] Check that you are up-to-date with the master branch of keras-vis. You can update with: pip install git+git://github.com/raghakot/keras-vis.git --upgrade --no-deps

• [x] If running on TensorFlow, check that you are up-to-date with the latest version. The installation instructions can be found here.

• [x] If running on Theano, check that you are up-to-date with the master branch of Theano. You can update with: pip install git+git://github.com/Theano/Theano.git --upgrade --no-deps

• [x] Provide a link to a GitHub Gist of a Python script that can reproduce your issue (or just copy the script here if it is short).

@keisen @bradykieffer @fredrikluo @ahmedhosny Hi thanks for the code just wanted know , in a given layer for number of filters how to extract / visualize the filter which has the maximum magnitude or strongest activation map in the given filter layer . Can you pls point at code level too

[keisen]

Do you mean you need to find and visualize the filter outputing max values from all layers?

[raghakot]

you will need to forward the image through the network and get raw filter values yourself using K.function. once you know which filter you want, use ActivationMax visualization to see what that filter is looking for.

Does that help?

[abhigoku10]

@keisen Not entirely from all the layer Ex: if with the first layer i am having 64 filters , i need to have maximum output for the first layer from 64 filters

@raghakot will check this method once