hypermodel-tl.py

def model_builder_tl(hp):
  
  # Flatten the output layer to 1 dimension
  x = layers.Flatten()(last_output)

  # Add a fully connected layer with  hidden units and ReLU activation
  # Tune the number of units in the  Dense layer
  # Choose an optimal value between 32-512
  hp_units = hp.Int('units', min_value = 32, max_value = 512, step = 32,)
  # Tune the activation function for Dense layer
  # Choose an optimal value from relu, tanh, sigmoid
  hp_activation_dense = hp.Choice( "dense_activation", values=["relu", "tanh", "sigmoid"], default="relu" )
  x = layers.Dense(units = hp_units, activation = hp_activation_dense)(x)

  # Add a dropout rate 
  # Tune the Dropout
  # Choose an optimal value between 0.1-0.5
  hp_dropout = hp.Float("dropout_1", min_value=0.1, max_value=0.5, default=0.25, step=0.05)
  x = layers.Dropout(rate=hp_dropout)(x)                  
  # Add a final softmax layer for classification
  x = layers.Dense  (3, activation='softmax')(x)           

  model = Model( pre_trained_model.input, x)

  # Tune the learning rate for the optimizer 
  # Choose an optimal value from 0.01, 0.001, or 0.0001
  hp_learning_rate = hp.Choice('learning_rate', values = [1e-2, 1e-3, 1e-4]) 
  
  model.compile(optimizer = keras.optimizers.Adam(learning_rate = hp_learning_rate),
                loss = keras.losses.CategoricalCrossentropy(from_logits = True), 
                metrics = ['accuracy'])
  
  
  return model