Shared layers

Advanced Deep Learning with Keras

Zach Deane Mayer

Data Scientist

Shared layers

Require the functional API
Very flexible

Shared layers

input_tensor_1 = Input((1,))
input_tensor_2 = Input((1,))

Shared layers

shared_layer = Dense(1)
output_tensor_1 = shared_layer(input_tensor_1)
output_tensor_2 = shared_layer(input_tensor_2)

Sharing multiple layers as a model

input_tensor = Input(shape=(1,))
n_teams = 10887
embed_layer = Embedding(input_dim=n_teams,
                        input_length=1,
                        output_dim=1,
                        name='Team-Strength-Lookup')
embed_tensor = embed_layer(input_tensor)
flatten_tensor = Flatten()(embed_tensor)
model = Model(input_tensor, flatten_tensor)

input_tensor_1 = Input((1,))
input_tensor_2 = Input((1,))
output_tensor_1 = model(input_tensor_1)
output_tensor_2 = model(input_tensor_2)

Sharing multiple layers as a model

Let's practice!

Advanced Deep Learning with Keras