Байская оптимизация гиперпараметров глубокой нейронной сети / ошибка gp_minimize

Question

Я пытаюсь оптимизировать гиперпараметры для глубокой нейронной сети, ее структуру (количество скрытых слоев и количество нейронов в каждом) в дополнение к скорости обучения и функции активации.

Как видите У меня есть основная функция, которую нужно оптимизировать (приспособленность), моя проблема в том, что функция оптимизации не принимает набор параметров по умолчанию для стратирования.

Это дает мне следующий результат:

Fitness () не хватает 3 обязательных позиционных аргумента: 'num_dense_layers', 'num_dense_nodes' и 'activate'

, что означает, что он не берет более одного параметра из списка по умолчанию one

Я чувствую, что это действительно банальная ошибка

обратите внимание, что Create_model и фитнес-функции работают правильно

любые предложения ???

def create_model(learning_rate,num_dense_layers,
                 num_dense_nodes, activation):
    """
    Hyper-parameters:
    learning_rate:     Learning-rate for the optimizer.
    num_dense_layers:  Number of dense layers.
    num_dense_nodes:   Number of nodes in each dense layer.
    activation:        Activation function for all layers.
    """
    
    # Start construction of a Keras Sequential model.
    model = Sequential()
    
    # Add an input layer which is similar to a feed_dict in TensorFlow.
    # Note that the input-shape must be a tuple containing the image-size.
    model.add(InputLayer(input_shape=(4,)))

    # Add fully-connected / dense layers.
    # The number of layers is a hyper-parameter we want to optimize.
    for i in range(num_dense_layers):
        # Name of the layer. This is not really necessary
        # because Keras should give them unique names.
        name = 'layer_dense_{0}'.format(i+1)

        # Add the dense / fully-connected layer to the model.
        # This has two hyper-parameters we want to optimize:
        # The number of nodes and the activation function.
        model.add(Dense(num_dense_nodes,
                        activation=activation,
                        name=name))

    # Last fully-connected / dense layer with softmax-activation
    # for use in classification.
    model.add(Dense(1, activation='linear'))
    
    # Use the Adam method for training the network.
    # We want to find the best learning-rate for the Adam method.
    optimizer = Adam(lr=learning_rate)
    #sgd = SGD(lr=learning_rate, momentum=0.9, decay=1e-6, nesterov=True)
    # In Keras we need to compile the model so it can be trained.
    model.compile(optimizer= optimizer ,
                  loss='mse',
                  metrics=['mse'])
    
    return model


from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=1)

x_train, x_val, y_train, y_val = train_test_split(x_train, y_train, test_size=0.25, random_state=1) # 0.25 x 0.8 = 0.2
print (x_train.shape, y_train.shape)
print (x_test.shape, y_test.shape)
print (x_val.shape, y_val.shape)

#evaluating the model 

path_best_model = '19_best_model.h5'
best_mse = 0.0

def fitness(learning_rate, num_dense_layers,
            num_dense_nodes, activation):
    """
    Hyper-parameters:
    learning_rate:     Learning-rate for the optimizer.
    num_dense_layers:  Number of dense layers.
    num_dense_nodes:   Number of nodes in each dense layer.
    activation:        Activation function for all layers.
    """

    # Print the hyper-parameters.
    print('learning rate: {0:.1e}'.format(learning_rate))
    print('num_dense_layers:', num_dense_layers)
    print('num_dense_nodes:', num_dense_nodes)
    print('activation:', activation)
    print()
    
    # Create the neural network with these hyper-parameters.
    model = create_model(learning_rate=learning_rate,
                         num_dense_layers=num_dense_layers,
                         num_dense_nodes=num_dense_nodes,
                         activation=activation)
    '''
    # Dir-name for the TensorBoard log-files.
    log_dir = log_dir_name(learning_rate, num_dense_layers,
                           num_dense_nodes, activation)
    
    # Create a callback-function for Keras which will be
    # run after each epoch has ended during training.
    # This saves the log-files for TensorBoard.
    # Note that there are complications when histogram_freq=1.
    # It might give strange errors and it also does not properly
    # support Keras data-generators for the validation-set.
    callback_log = TensorBoard(
        log_dir=log_dir,
        histogram_freq=0,
        write_graph=True,
        write_grads=False,
        write_images=False)
    we have a callback peoblem 
    ProfilerNotRunningError: Cannot stop profiling. No profiler is running.
    
    the solution is somewho discussed on 
    tensorflow website
    '''
   
    # Use Keras to train the model.
    history = model.fit(x_train,
                        y_train,
                        epochs=200,
                        batch_size=1,
                        validation_data= (x_val,y_val))

    # Get the classification accuracy on the validation-set
    # after the last training-epoch.
    mse = history.history['val_mse'][-1]

    # Print the classification accuracy.
    print()
    print("MSE: {0:.2%}".format(mse))
    print()

    K.clear_session()
    tensorflow.reset_default_graph()
    return mse


# Define the Hyperparameters ranges:
dim_learning_rate = Real(low=1e-6, high=1e-2, prior='log-uniform', name='learning_rate')
dim_num_dense_layers = Integer(low=1, high=15, name='num_dense_layers')
dim_num_dense_nodes = Integer(low=5, high=512, name='num_dense_nodes')
dim_activation = Categorical(categories=['relu', 'sigmoid','tanh','softmax'],name='activation')



HPs = [dim_learning_rate,dim_num_dense_layers,dim_num_dense_nodes,dim_activation]
 
default_parameters = [1e-5, 1, 16, 'relu']  


search_result = gp_minimize(func=fitness,
                            dimensions=HPs,
                            acq_func='EI', # Expected Improvement.
                            n_calls=40,
                            x0=default_parameters)