How do I add keras dropout layers?

Question

How do I add Keras dropout layer? Unfortunately, I don't know where exactly I would have to add this layer. I looked at 2 links:

• https://keras.io/api/layers/regularization_layers/dropout/
• https://machinelearningmastery.com/dropout-regularization-deep-learning-models-keras/

For example, I've seen this

model.add(Dense(60, input_dim=60, activation='relu', kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
model.add(Dense(30, activation='relu', kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
model.add(Dense(1, activation='sigmoid'))

The dense layers are created with a loop as I understand it so I'm not sure how to add this.

def get_Model(...):
   
    # build dense layer for model
    for i in range(1, len(dense_layers)):
       
        layer = Dense(dense_layers[i],
                      activity_regularizer=l2(reg_layers[i]),
                      activation='relu',
                      name='layer%d' % i)
        mlp_vector = layer(mlp_vector)

    predict_layer = Concatenate()([mf_cat_latent, mlp_vector])
    result = Dense(1, activation='sigmoid',
                   kernel_initializer='lecun_uniform', name='result')

    model = Model(inputs=[input_user, input_item], outputs=result(predict_layer))

    return model

Answer 1

Try this:

for i in range(1, len(dense_layers)):
   
    layer = Dense(dense_layers[i],
                  activity_regularizer=l2(reg_layers[i]),
                  activation='relu',
                  name='layer%d' % i)
    mlp_vector = layer(mlp_vector)
    mlp_vector = Dropout(0.2)(mlp_vector)

Have a look on Functional API here https://keras.io/guides/functional_api/