Учебное пособие Theano: прогнозирование с использованием обученной модели

Я новичок в Theano. И когда я запускаю код логистической регрессии (http://deeplearning.net/tutorial/code/logistic_sgd.py),i есть проблема, в конце кода есть функция прогнозирования:

def predict():
    """
    An example of how to load a trained model and use it
    to predict labels.
    """

    # load the saved model
    classifier = pickle.load(open('best_model.pkl'))

    # compile a predictor function
    predict_model = theano.function(
        inputs=[classifier.input],
        outputs=classifier.y_pred)

    # We can test it on some examples from test test
    dataset='mnist.pkl.gz'
    datasets = load_data(dataset)
    test_set_x, test_set_y = datasets[2]
    test_set_x = test_set_x.get_value()

    predicted_values = predict_model(test_set_x[:10])
    print("Predicted values for the first 10 examples in test set:")
    print(predicted_values)

Он может перезагружать модель и прогнозировать метки новых данных. Но я не могу получить результат прогноза. Мои результаты выглядят так, когда я запускаю весь код

/usr/bin/python2.7 /home/daiy/PycharmProjects/MNISTdigitclassification/logistic-regression-code.py
... loading data
... building the model
... training the model
epoch 1, minibatch 83/83, validation error 12.458333 %
epoch 2, minibatch 83/83, validation error 11.010417 % 
.
.
.   
epoch 73, minibatch 83/83, validation error 7.500000 %
Optimization complete with best validation score of 7.500000 %,
The code run for 74 epochs, with 3.189913 epochs/sec
The code for file logistic-regression-code.py ran for 23.2s

    Process finished with exit code 0

Я отлаживаю его в pycharm, он не показывает ошибок, а когда я создаю новый файл py.file, код вроде этого:

import pickle,numpy
import theano
import six.moves.cPickle as pickle
import gzip
import os
import theano.tensor as T

def load_data(dataset):
    ''' Loads the dataset

    :type dataset: string
    :param dataset: the path to the dataset (here MNIST)
    '''

    #############
    # LOAD DATA #
    #############

    # Download the MNIST dataset if it is not present
    data_dir, data_file = os.path.split(dataset)
    if data_dir == "" and not os.path.isfile(dataset):
        # Check if dataset is in the data directory.
        new_path = os.path.join(
            os.path.split(__file__)[0],
            "..",
            "data",
            dataset
        )
        if os.path.isfile(new_path) or data_file == 'mnist.pkl.gz':
            dataset = new_path



    print('... loading data')

    with gzip.open(dataset, 'rb') as f:
        try:
            train_set, valid_set, test_set = pickle.load(f, encoding='latin1')
        except:
            train_set, valid_set, test_set = pickle.load(f)

    def shared_dataset(data_xy, borrow=True):
        """ Function that loads the dataset into shared variables

        The reason we store our dataset in shared variables is to allow
        Theano to copy it into the GPU memory (when code is run on GPU).
        Since copying data into the GPU is slow, copying a minibatch everytime
        is needed (the default behaviour if the data is not in a shared
        variable) would lead to a large decrease in performance.
        """
        data_x, data_y = data_xy
        shared_x = theano.shared(numpy.asarray(data_x,
                                               dtype=theano.config.floatX),
                                 borrow=borrow)
        shared_y = theano.shared(numpy.asarray(data_y,
                                               dtype=theano.config.floatX),
                                 borrow=borrow)
        # When storing data on the GPU it has to be stored as floats
        # therefore we will store the labels as ``floatX`` as well
        # (``shared_y`` does exactly that). But during our computations
        # we need them as ints (we use labels as index, and if they are
        # floats it doesn't make sense) therefore instead of returning
        # ``shared_y`` we will have to cast it to int. This little hack
        # lets ous get around this issue
        return shared_x, T.cast(shared_y, 'int32')

    test_set_x, test_set_y = shared_dataset(test_set)
    valid_set_x, valid_set_y = shared_dataset(valid_set)
    train_set_x, train_set_y = shared_dataset(train_set)


    rval = [(train_set_x, train_set_y), (valid_set_x, valid_set_y),
            (test_set_x, test_set_y)]
    return rval

dataset = 'mnist.pkl.gz'
datasets = load_data(dataset)
train_set_x, train_set_y = datasets[0]
valid_set_x, valid_set_y = datasets[1]
test_set_x, test_set_y = datasets[2]

def predict():
    '''

    :return:
    '''

    classifier = pickle.load(open('best_model.pkl','rb'))

    predict_model = theano.function(inputs=[classifier.input],outputs=classifier.y_pred)

    dataset = 'mnist.pkl.gz'
    datasets = load_data(dataset)
    test_set_x ,test_set_y = datasets[2]
    test_set_x = test_set_x.get_value()

    predicted_values = predict_model(test_set_x[:10])
    print('predicted values for the first 10 examples in test data:')
    print predicted_values

вывод:

/usr/bin/python2.7 /home/daiy/PycharmProjects/MNISTdigitclassification/yuce.py
... loading data

Process finished with exit code0

по-прежнему нет прогнозного вывода. но когда я отлаживаю это, это:

/usr/bin/python2.7 /raid/pycharm-community-2016.2.3/helpers/pydev/pydevd.py --multiproc --qt-support --client 127.0.0.1 --port 43960 --file /home/daiy/PycharmProjects/MNISTdigitclassification/yuce.py
warning: Debugger speedups using cython not found. Run '"/usr/bin/python2.7" "/raid/pycharm-community-2016.2.3/helpers/pydev/setup_cython.py" build_ext --inplace' to build.
pydev debugger: process 4506 is connecting

Connected to pydev debugger (build 162.1967.10)
... loading data
Exception TypeError: TypeError("'NoneType' object is not callable",) in <function _remove at 0x7fe6444f1668> ignored

Process finished with exit code 0

Думаю, это простой вопрос, но я не могу найти ответа. и я использую python2.7 в ubuntun14.04.1.