How to turn the entire keras model into anano function

Question

I want to turn my keras model into anano function so that I can calculate gradients on inputs. I thought it could be cool to visualize the network. I want to use these gradients to improve the functions of the original image based on what, according to the neural network, is. I do not understand what I am doing wrong with the following code.

model = Sequential() model.add(InputLayer((3, H, W))) model.add(GaussianNoise(0.03)) model.add(Flatten()) model.add(Dense(512, activation = 'relu', name = 'dense')) model.add(Dropout(0.2)) model.add(Dense(20, activation = 'relu')) model.add(Dense(C, activation = 'softmax', W_regularizer = l2())) ... f = theano.function([model.input], model.output) 

I get the following exception.

 theano.gof.fg.MissingInputError: A variable that is an input to the graph was neither provided as an input to the function nor given a value. A chain of variables leading from this input to an output is [keras_learning_phase, DimShuffle{x,x}.0, Elemwise{switch,no_inplace}.0, dot.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Elemwise{mul,no_inplace}.0, dot.0, Elemwise{add,no_inplace}.0, Softmax.0]. This chain may not be unique Backtrace when the variable is created: File "<frozen importlib._bootstrap>", line 222, in _call_with_frames_removed File "/usr/local/lib/python3.5/dist-packages/keras/backend/__init__.py", line 51, in <module> from .theano_backend import * File "<frozen importlib._bootstrap>", line 969, in _find_and_load File "<frozen importlib._bootstrap>", line 958, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 673, in _load_unlocked File "<frozen importlib._bootstrap_external>", line 662, in exec_module File "<frozen importlib._bootstrap>", line 222, in _call_with_frames_removed File "/usr/local/lib/python3.5/dist-packages/keras/backend/theano_backend.py", line 13, in <module> _LEARNING_PHASE = T.scalar(dtype='uint8', name='keras_learning_phase') # 0 = test, 1 = train 

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 latest 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 (for example, 0.3.x):

I do not use this version, but examples like this should work.

For the "new" keras (1.0 +):

Since you are using the Dropout layer, you will need to add another K.learning_phase() input and give it a value of 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]) 

Link: keras FAQ