hypermodel.py

def model_builder(hp):
  model = keras.Sequential()
 
  model.add(keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(150, 150, 3)))
  model.add(keras.layers.MaxPooling2D(2, 2))

  # Tune the number of filters for the second Conv2D 
  # Choose an optimal value from 64-128
  hp_filters = hp.Choice('num_filters', values=[64, 128], default=64,)
  model.add(keras.layers.Conv2D(filters=hp_filters, kernel_size=3, activation='relu'))
  model.add(keras.layers.MaxPooling2D(2, 2))

  model.add(keras.layers.Flatten())

  # 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)
  model.add(keras.layers.Dropout(rate=hp_dropout))

  # 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" )
  model.add(keras.layers.Dense(units = hp_units, activation = hp_activation_dense))
  model.add(keras.layers.Dense(3, activation='softmax'))

  # 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