AttributeError: Layer output has multiple inbound nodes

[pau557]

• [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

• [ ] 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).

I am trying to do activation maximization in my Keras neural network.

My network is very simple.

• input layer (240-long vector)
• dense layer (1740 units, Relu)
• dense layer (3240 units, Linear, name='output')

I would like to do activation-maximization to visualize what inputs activate a particular neuron in the output layer. With layer_idx=-1 and filter_indices=neuron_index :

max_input = visualize_activation(model, layer_idx, filter_indices,input_range = (0., 1.))

returns me

AttributeError: Layer output has multiple inbound nodes, hence the notion of "layer output" is ill-defined. Use `get_output_at(node_index)` instead.

Thank you.

[raghakot]

That's interesting. Do you have some code for me to reproduce this? Could be a keras compatibility thing. Are you using latest keras?