重用一组Keras图层

Question

I know that you can reuse Keras layers. For eg I declare two layers for a decoder network:

decoder_layer_1 = Dense(intermediate_dim,activation='relu',name='decoder_layer_1')
decoder_layer_2 = Dense(intermediate_dim,activation='relu',name='decoder_layer_2')

Use in first model:

decoded = decoder_layer_1(z)
decoded = decoder_layer_2(decoded)

Use in second model:

_decoded = decoder_layer_1(decoder_input)
_decoded = decoder_layer_2(_decoded)

The above method is ok if I need to reuse only a couple of layers, cumbersome if I want to reuse a large number of layers (for eg. a decoder network with 10 layers). Is there a more efficient means to do it other than explicitly declaring each layer. Is there a means to implement it as shown below:

decoder_layers = group_of_layers() 

Reuse in the first model:

decoded = group_of_layers(z)

Reuse in the second model:

_decoded = group_of_layers(decoder_input)

Answer 1

I struggled with this problem too. What works for me is to wrap shared parts in a model, with its own input definition:

def group_of_layers(intermediate_dim):
    shared_model_input = keras.layers.Input(shape=...)
    shared_internal_layer = keras.layers.Dense(intermediate_dim, activation='relu', name='shared_internal_layer')(shared_model_input)
    shared_model_output = keras.layers.Dense(intermediate_dim, activation='relu', name='shared_model_output')(shared_internal_layer)
    return keras.models.Model(shared_model_input, shared_model_output)

In Functional API, you can use the shared model in the same way a single layer as long as the model's input layer matches shape of layers you apply to it:

group = group_of_layers(intermediate_dim)
result1 = group(previous_layer)
result2 = group(different_previous_layer)

The weights are going to be shared then.

This is nicely described in the documentation, see Shared vision model .

Answer 2

You can try:

def group_of_layers(x, intermediate_dim):
    x = Dense(intermediate_dim,activation='relu',name='decoder_layer_1')(x)
    x = Dense(intermediate_dim,activation='relu',name='decoder_layer_2')(x)
    return x

And then:

decoded = group_of_layers(z, intermediate_dim)
_decoded = group_of_layers(decoder_input, intermediate_dim)

You must declare input and outputs of the model afterwards though, eg for second model:

model = Model(inputs = decoder_input, outputs = _decoded)

You could also append a final layer like:

final_layer = Dense(...)(_decoded)
model = Model(inputs = decoder_input, outputs = final_layer)