How to turn entire keras model into theano function

Question

I want to turn my keras model into a theano function so that I can compute the gradients on the inputs. I thought this might be cool for visualizing the network. I want to

Answer 1

Following the FAQ, try:

from keras import backend as K
get_last_layer_output = K.function([model.layers[0].input],
                                   [model.layers[-1].output])

For the most recent version of Keras (1.0), use

from keras import backend as K
get_last_layer_output = K.function([model.layers[0].input],
                                   [model.layers[-1].get_output(train=False)])

Answer 2

For "old" keras(0.3.x for example):

I don't use this version but examples like this one should work.

For "new" keras(1.0+):

Since you use Dropout layer, you will need to add another input K.learning_phase() and give it the value 0 (0 for testing, 1 for training.)

code:

from keras import backend as K
K.function([model.layers[0].input, K.learning_phase()], [model.layers[-1].output])

Reference: keras FAQ