hypermodel_Hparams.py

def model_builder_HPARAMS(hparams):
  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
  model.add(keras.layers.Conv2D(hparams[HP_NUM_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
  model.add(keras.layers.Dropout(hparams[HP_DROPOUT]))

  # Tune the number of units in the  Dense layer
  # Tune the activation function for Dense layer
  # Choose an optimal value from relu, tanh, sigmoid

  model.add(keras.layers.Dense(units = hparams[HP_NUM_UNITS], activation = hparams[HP_ACTIVATION]))
  model.add(keras.layers.Dense(3, activation='softmax'))

  # Choose ideal optimizer function
  model.compile(optimizer = hparams[HP_OPTIMIZER],
                loss = keras.losses.CategoricalCrossentropy(from_logits = True), 
                metrics = ['accuracy'])
  

  model.fit(train_generator,
            validation_data=validation_generator,
            epochs=5)
  _, accuracy = model.evaluate(validation_generator)
  return accuracy