1

I have a Keras functional model defined as:

    # Construct DNN
    spec_input = keras.layers.Input(shape=(1, ctx, fft), name='spec')
    x = keras.layers.Flatten(data_format)(spec_input)

    for layer in range(len(args.dnn_struct)):
        x = Dense(args.dnn_struct[layer])(x)
        x = BatchNormalization()(x)
        x = keras.layers.ReLU()(x)

    out = Dense(fft, activation="sigmoid", name=f'spp')(x)
    model = Model(inputs=spec_input, outputs=out)

I would like to get the output of each layer in the model for a given input and the answers given in Keras, How to get the output of each layer? do not work for a functional model. I am currently using Tensorflow 1.14

When I try using 

from keras import backend as K

inp = model.input                                           # input placeholder
outputs = [layer.output for layer in model.layers]          # all layer outputs
functor = K.function([inp, K.learning_phase()], outputs )   # evaluation function

# Testing
test = np.random.random(input_shape)[np.newaxis,...]
layer_outs = functor([test, 1.])
print(layer_outs)

I get the error

Traceback (most recent call last):
  File "/home/xyz/anaconda3/envs/tf/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1446, in __init__
    session._session, options_ptr)
tensorflow.python.framework.errors_impl.InvalidArgumentError: spec:0 is both fed and fetched.
OverLordGoldDragon
  • 1
  • 9
  • 53
  • 101
DVK
  • 475
  • 2
  • 6
  • 27

1 Answers1

1

UPDATE: You cannot fetch outputs of all layers, because "all layers" includes Input - and the error message is self-explanatory. Use:

outputs = get_all_outputs(model, input_data, 1)

Below should work for any model, Model or Sequential: 
def get_all_outputs(model, input_data, learning_phase=1):
    outputs = [layer.output for layer in model.layers[1:]] # exclude Input
    layers_fn = K.function([model.input, K.learning_phase()], outputs)
    return layers_fn([input_data, learning_phase])

Layer-level solutions:

def get_layer_outputs(model, layer_name, input_data, learning_phase=1):
    outputs   = [layer.output for layer in model.layers if layer_name in layer.name]
    layers_fn = K.function([model.input, K.learning_phase()], outputs)
    return layers_fn([input_data, learning_phase])

# or, for passing in a layer directly
def get_layer_outputs(model, layer, input_data, learning_phase=1):
    layer_fn = K.function([model.input, K.learning_phase()], layer.output)
    return layer_fn([input_data, learning_phase])
OverLordGoldDragon
  • 1
  • 9
  • 53
  • 101