zdmc23 / oneshot-audio

Experiment with "one-shot learning" techniques to recognize a voice signature

oneshot-audio's Issues

object() takes no parameters

Hi, I use the original code but I got error like this:

TypeError Traceback (most recent call last)
in
14 return base_network, model
15
---> 16 base_network, model = get_model()

in get_model(weights)
8 input_b = Input(shape=input_shape)
9
---> 10 processed_a = create_base_network(input_shape)(input_a)
11 processed_b = create_base_network(input_shape)(input_b)
12 distance = Lambda(euclidean_distance, output_shape=eucl_dist_output_shape)([processed_a, processed_b])

in create_base_network(input_shape)
22 x = Dropout(0.1)(x)
23 x = Dense(128, activation='relu')(x)
---> 24 return Model(a, x)
25
26 def compute_accuracy(y_true, y_pred):

TypeError: object() takes no parameters

You have any idea ?