UnboundLocalError Tensorflow

Question

我正在尝试使用tensorflow和python 3.7运行用于训练神经网络的代码，但是出现此错误。我是tensorflow的新手，有人可以提示我如何解决吗？

这是我的错误：UnboundLocalError：分配前引用了本地变量'train_diretorio'

这是代码的一部分，如果有人可以帮助，我是python和tensorflow的新手

..Imports

def train():
model_config = configuration.ModelConfig()
model_config.input_file_pattern = input_file_pattern
model_config.inception_checkpoint_file = inception_checkpoint_file
training_config = configuration.TrainingConfig()

# Create training directory.
train_diretorio = train_diretorio
if not tf.gfile.IsDirectory(train_diretorio):
    tf.logging.info("Creating training directory: %s", train_diretorio)
    tf.gfile.MakeDirs(train_diretorio)

# Build the TensorFlow graph.
g = tf.Graph()
with g.as_default():
    # Build the model.
    model = show_and_tell_model.ShowAndTellModel(
            model_config, mode="train", train_inception=train_inception)
    model.build()

    # Set up the learning rate.
    learning_rate_decay_fn = None
    if train_inception:
        learning_rate = tf.constant(training_config.train_inception_learning_rate)
    else:
        learning_rate = tf.constant(training_config.initial_learning_rate)
        if training_config.learning_rate_decay_factor > 0:
            num_batches_per_epoch = (training_config.num_examples_per_epoch /
                             model_config.batch_size)
            decay_steps = int(num_batches_per_epoch *
                      training_config.num_epochs_per_decay)

            def _learning_rate_decay_fn(learning_rate, global_step):
                return tf.train.exponential_decay(
                                  learning_rate,
                                  global_step,
                                  decay_steps=decay_steps,
                                  decay_rate=training_config.learning_rate_decay_factor,
                                  staircase=True)

            learning_rate_decay_fn = _learning_rate_decay_fn

    # Set up the training ops.
    train_op = tf.contrib.layers.optimize_loss(
                                    loss=model.total_loss,
                                    global_step=model.global_step,
                                    learning_rate=learning_rate,
                                    optimizer=training_config.optimizer,
                                    clip_gradients=training_config.clip_gradients,
                                    learning_rate_decay_fn=learning_rate_decay_fn)

    # Set up the Saver for saving and restoring model checkpoints.
    saver = tf.train.Saver(max_to_keep=training_config.max_checkpoints_to_keep)

# Run training.
tf.contrib.slim.learning.train(
                            train_op,
                            train_diretorio,
                            log_every_n_steps=log_every_n_steps,
                            graph=g,
                            global_step=model.global_step,
                            number_of_steps=number_of_steps,
                            init_fn=model.init_fn,
                            saver=saver)


input_file_pattern = 'im2txt/data/mscoco/train-?????-of-00256'


inception_checkpoint_file = 'im2txt/data/inception_v3.ckpt'
train_diretorio = 'im2txt/model'


train_inception = False
number_of_steps = 1000000
log_every_n_steps = 1

train()


train_inception = False
number_of_steps = 1000000
log_every_n_steps = 1

train()