Labinot Jakupi

Tuning hidden layers

6

model = tf.keras.Sequential() # dense layer model.add(tf.keras.layers.Dense( {{choice([32, 64, 128])}}, input_dim=1530, kernel_initializer={{choice(['glorot_uniform', 'random_uniform'])}}, kernel_regularizer=tf.keras.regularizers.l2({{choice([0.01, 0.05, 0.1])}}) )) model.add(tf.keras.layers.Activation('relu')) # dropout model.add(tf.keras.layers.Dropout({{uniform(0, 1)}})) # if 'three' chosen, add an additional layer...

Is it possible to use a created and compiled network in another file within `create_model()` method? Doing this gives me the error below: `Traceback (most recent call last): .. in...