How to use keras layers in custom keras layer

Question

I am trying to write my own keras layer. In this layer, I want to use some other keras layers. Is there any way to do something like this:

class MyDenseLayer(tf.         


        

Answer 1

In the TF2 custom layer Guide, they "recommend creating such sublayers in the __init__ method (since the sublayers will typically have a build method, they will be built when the outer layer gets built)." So just move the creation of self.fc into __init__ will give what you want.

class MyDenseLayer(tf.keras.layers.Layer):
  def __init__(self, num_outputs):
    super(MyDenseLayer, self).__init__()
    self.num_outputs = num_outputs
    self.fc = tf.keras.layers.Dense(self.num_outputs)

  def build(self, input_shape):
    self.built = True

  def call(self, input):
    return self.fc(input)

input = tf.keras.layers.Input(shape = (16,))
output = MyDenseLayer(10)(input)
model = tf.keras.Model(inputs = [input], outputs = [output])
model.summary()

Output:

Model: "model_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_2 (InputLayer)         [(None, 16)]              0         
_________________________________________________________________
my_dense_layer_2 (MyDenseLay (None, 10)                170       
=================================================================
Total params: 170
Trainable params: 170
Non-trainable params: 0